CN109033949A - Face identification method and system based on optical coherence tomography - Google Patents
Face identification method and system based on optical coherence tomography Download PDFInfo
- Publication number
- CN109033949A CN109033949A CN201810596262.7A CN201810596262A CN109033949A CN 109033949 A CN109033949 A CN 109033949A CN 201810596262 A CN201810596262 A CN 201810596262A CN 109033949 A CN109033949 A CN 109033949A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- blood flow
- target user
- subsystem
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000012014 optical coherence tomography Methods 0.000 title claims abstract description 56
- 230000017531 blood circulation Effects 0.000 claims description 114
- 238000012545 processing Methods 0.000 claims description 53
- 238000009826 distribution Methods 0.000 claims description 49
- 238000001228 spectrum Methods 0.000 claims description 46
- 239000013307 optical fiber Substances 0.000 claims description 32
- 210000004204 blood vessel Anatomy 0.000 claims description 23
- 238000005457 optimization Methods 0.000 claims description 12
- 239000006185 dispersion Substances 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 8
- 238000002583 angiography Methods 0.000 claims description 6
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000003672 processing method Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 20
- 238000012937 correction Methods 0.000 description 17
- 239000000835 fiber Substances 0.000 description 10
- 230000000694 effects Effects 0.000 description 8
- 238000003384 imaging method Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 238000002601 radiography Methods 0.000 description 5
- 230000003595 spectral effect Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000001678 irradiating effect Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005305 interferometry Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003325 tomography Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/145—Illumination specially adapted for pattern recognition, e.g. using gratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
Face identification method and system provided by the invention based on optical coherence tomography, is related to technical field of face recognition, firstly, face information acquisition subsystem is scanned face, obtains and stores human face structure image and three-dimensional flow distributed image；Secondly, human face structure image is compared structural images recognition subsystem with the target user's structural images prestored, judge whether target is target user, if not, authentification failure and identification is terminated, if so, then authenticating success；Three-dimensional flow distributed image is compared blood-stream image recognition subsystem with the target user's blood-stream image prestored, continues to judge whether target is target user, if not, authentification failure and identification is terminated, if so, then authenticating success.The technical solution alleviates the low technical problem of identification accuracy of the existing technology, realizes and compares the recognition of face compared with three-dimensional flow distributed image based on human face structure image, improves the accuracy of recognition of face.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to a face recognition method and system based on optical coherence tomography.
Background
The human face recognition is an automatic processing technology which can be used for identifying identity by analyzing a human face image by a computer tool, extracting effective human face features by adopting different feature representation methods and then comparing the extracted features with features in a pre-stored feature library. With the continuous development of computer technology, image processing and other technologies, face recognition is widely applied to various fields of production and life.
At present, the face recognition technology mainly compares local features, global features and mixed features of a face with features in a pre-stored feature library. However, in recent years, in the development process of the face recognition technology, human face deception behaviors occur, such as printing a face image on paper, or displaying the face image on a screen by using a projection device, a liquid crystal display screen and other playing devices, even performing 3D modeling by using the modeling technology, controlling a model to make blinking, mouth opening, head shaking and other actions, placing the model in front of an acquisition device of the face recognition system to obtain various face images, wherein the face images have great similarity with real face images and become unsafe factors in the face recognition system. For example, patent document CN201610042384.2 discloses a face recognition system and a face recognition method, which take images at multiple positions with a single lens, determine whether the images are the target user by distance calculation and feature comparison, and prevent interference of face images, projection, and liquid crystal display. However, this system cannot eliminate interference of a physical face model created by 3D modeling. Therefore, the existing face recognition technology has the technical problem of low recognition accuracy.
Disclosure of Invention
In view of the above, the present invention provides a face recognition method and system based on optical coherence tomography to alleviate the technical problem of low recognition accuracy in the existing face recognition technology.
In a first aspect, an embodiment of the present invention provides a face recognition method based on optical coherence tomography, including the following steps:
a face information acquisition step: scanning a human face, and acquiring and storing a human face image, wherein the human face image is a human face structure image and/or a three-dimensional blood flow distribution image;
when the face image only contains the face structure image, the face information acquisition step further comprises a structure image identification step: comparing the face structure image with a prestored target user structure image, judging whether the target is a target user, if not, failing authentication and terminating identification, and if so, successfully authenticating;
when the face image only contains the three-dimensional blood flow distribution image, the step of identifying the blood flow image is also included after the step of acquiring the face information: comparing the three-dimensional blood flow distribution image with a prestored target user blood flow image, judging whether the target is a target user, if not, failing authentication and terminating identification, and if so, successfully authenticating;
and when the face image comprises a face structure image and a three-dimensional blood flow distribution image, sequentially executing a structure image identification step and a blood flow image identification step after the face information acquisition step.
Further, in the method for identifying a face based on optical coherence tomography provided in the embodiment of the present invention, the step of acquiring face information specifically includes: the human face is scanned through the human face information acquisition subsystem, the scanning light becomes measuring light after scanning, the measuring light interferes with the reference light to form interference light, the interference light is acquired by the spectrum acquisition device and is transmitted to the signal processor after being converted, a human face image is generated after processing, and the human face image is stored.
Further, in the method for identifying a face based on optical coherence tomography provided in the embodiment of the present invention, a face image is generated after processing, and the method specifically includes:
processing the analog signal by adopting any image processing method of an interpolation method, a dispersion compensation method or a Fourier transform method to obtain a face structure image;
and processing the analog signal by adopting an OCT micro-angiography algorithm to obtain a three-dimensional blood flow distribution image.
Further, in the face recognition method based on optical coherence tomography provided in the embodiment of the present invention, the three-dimensional blood flow distribution image is compared with a pre-stored blood flow image of the target user, specifically: and quantitatively evaluating the blood vessel density, the blood vessel complexity and the blood vessel diameter according to the three-dimensional blood flow distribution image, and comparing the quantized result data with prestored blood flow data corresponding to the prestored blood flow image of the target user.
Further, in the method for identifying a face based on optical coherence tomography provided in the embodiment of the present invention, the step of acquiring face information further includes:
an image optimization step: and performing re-registration processing and motion compensation processing on the acquired image.
Further, in the face recognition method based on optical coherence tomography provided in the embodiment of the present invention, the re-registration processing is performed on the acquired image, specifically: and carrying out image preprocessing on the collected image, processing the reflected bright stripes to carry out denoising, carrying out upper edge contour extraction on the image of each frame, and carrying out re-registration on the image by adopting a motion estimation algorithm.
Further, in the face recognition method based on optical coherence tomography provided in the embodiment of the present invention, the motion compensation processing is performed on the collected image, specifically: and performing motion estimation on the whole situation based on the relation of adjacent frames, simultaneously performing image movement detection on the whole situation by adopting the correlation of adjacent frame baselines of the scanned images, then making a sliding window by utilizing a cross-correlation algorithm to perform sliding pixel error estimation on each frame of image, and recovering the obtained motion estimation displacement by adopting a compensation method so as to achieve template matching.
In a second aspect, an embodiment of the present invention provides a face recognition system based on optical coherence tomography, including: the system comprises a face information acquisition subsystem and an image recognition subsystem;
the face information acquisition subsystem comprises: the device comprises a light source, an optical fiber beam splitter, a reference arm, a scanning device, a spectrum acquisition device and a signal processor; the face information acquisition subsystem is used for scanning a face to acquire and store a face image;
the image recognition subsystem includes a structural image recognition subsystem and/or a blood flow image recognition subsystem.
Further, in the face recognition system based on optical coherence tomography provided in the embodiment of the present invention, the optical fiber splitter includes a circulator and/or an optical fiber coupler;
the reference arm comprises a first optical fiber collimator, a first lens and a reflector which are connected in sequence;
the scanning device includes: the scanning galvanometer, the objective lens and the second lens are arranged in the optical fiber collimator;
the spectrum collection device comprises: the third optical fiber collimator, the beam expander, the grating, the third lens and the photoelectric sensor CCD;
the signal processor is provided with a memory in which a signal processing subsystem for performing signal processing is stored.
Further, in the face recognition system based on optical coherence tomography provided in the embodiment of the present invention, the signal processing subsystem includes:
the blood flow image generation device comprises an image optimization module, and a structural image generation module and a blood flow image generation module which are respectively connected with the image optimization module.
Further, in the face recognition system based on optical coherence tomography provided in the embodiment of the present invention, the image optimization module includes an image preprocessing unit, an image contour extraction unit, a sliding matching unit, and a displacement compensation unit, which are connected in sequence.
Further, in the face recognition system based on optical coherence tomography provided in the embodiment of the present invention, the structural image recognition subsystem includes:
the structure image processing unit compares the face structure image with a target user structure image prestored in the target user structure image storage unit, judges whether the target is a target user or not, if not, the authentication fails and the identification is terminated, and if so, the authentication succeeds.
Further, in the face recognition system based on optical coherence tomography provided in the embodiment of the present invention, the blood flow image recognition subsystem includes:
the blood flow image processing unit compares the three-dimensional blood flow distribution image with a target user blood flow image prestored in the target user blood flow image storage unit, continuously judges whether the target is the target user, if not, the authentication fails and the identification is terminated, and if so, the authentication succeeds.
The embodiment of the invention has the following beneficial effects: according to the face recognition method and system based on optical coherence tomography provided by the embodiment of the invention, a face information acquisition subsystem scans a face to acquire and store a face image, wherein the face image is a face structure image and/or a three-dimensional blood flow distribution image; when the face image only contains the face structure image, the structure image recognition subsystem compares the face structure image with a prestored target user structure image to judge whether the target is a target user, if not, the authentication fails and the recognition is terminated, and if so, the authentication is successful; when the face image only contains the three-dimensional blood flow distribution image, the blood flow image recognition subsystem compares the three-dimensional blood flow distribution image with a prestored blood flow image of a target user and judges whether the target is the target user, if not, the authentication fails and the recognition is terminated, and if so, the authentication succeeds; and when the face image comprises a face structure image and a three-dimensional blood flow distribution image, sequentially executing a structure image identification step and a blood flow image identification step after the face information acquisition step. According to the technical scheme, the purpose of forming blood flow radiography imaging by scanning the bottom layer skin structure and further extracting the characteristic information of the target bottom layer skin is achieved by adopting the optical coherence tomography technology, so that the face recognition based on face structure image comparison and three-dimensional blood flow distribution image comparison is realized, the accuracy of the face recognition is improved, the condition that a forged three-dimensional face model is difficult to distinguish during face recognition is improved, the accuracy of identity authentication is further improved, and the technical problem that the recognition accuracy is low in the existing face recognition technology is solved.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a face recognition method based on optical coherence tomography according to an embodiment of the present invention;
fig. 2 is a flowchart of a face information acquisition step in the face recognition method based on optical coherence tomography according to the embodiment of the present invention;
fig. 3 is a schematic structural diagram of a face recognition system based on optical coherence tomography according to an embodiment of the present invention.
Icon:
100-a face information acquisition subsystem; 110-a light source; 120-a circulator; 130-a fiber coupler; 140-a reference arm; 141-a first fiber collimator; 142-a first lens; 143-mirror; 150-a scanning device; 151-a second fiber collimator; 152-scanning galvanometer; 153-objective lens; 154-a second lens; 160-a spectrum acquisition device; 161-a third fiber collimator; 162-a beam expander; 163-a grating; 164-a third lens; 165-photosensor CCD; 170-a signal processor; 200-a structural image recognition subsystem; 300-blood flow image recognition subsystem.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, in the development process of a face recognition technology, a face deception behavior occurs, and a forged face image has great similarity with a real face image and becomes an unsafe factor in a face recognition system.
The first embodiment is as follows:
referring to fig. 1, a flowchart of a face recognition method based on optical coherence tomography according to an embodiment of the present invention is provided. The embodiment of the invention provides a face recognition method based on optical coherence tomography, which comprises the following steps:
firstly, executing a human face information acquisition step: the face information acquisition subsystem scans the face by adopting an optical coherence tomography technology to acquire a face image corresponding to the recognition target face, wherein the face image is a face structure image and/or a three-dimensional blood flow distribution image, and the face structure image and the three-dimensional blood flow distribution image are stored. The face information acquisition subsystem comprises: the device comprises a light source, an optical fiber beam splitter, a reference arm, a scanning device, a spectrum acquisition device and a signal processor; the face information acquisition subsystem is used for scanning the face, imaging and acquiring and storing a face image. The reference arm comprises a first optical fiber collimator, a first lens and a reflector which are connected in sequence; the scanning device includes: the scanning galvanometer, the objective lens and the second lens are arranged in the optical fiber collimator; the spectrum collection device comprises: the third optical fiber collimator, the beam expander, the grating, the third lens and the photoelectric sensor CCD; the signal processor is provided with a memory, and a signal processing subsystem for executing signal processing is stored in the memory; the signal processing subsystem is connected with the image identification subsystem. The imaging technology based on optical coherence tomography is a mesoscopic scale observation imaging method, based on the principle of low coherence interferometry, a nondestructive detection tomography image reflecting the fine structure and the function of a human face can be obtained, and a three-dimensional blood flow distribution map of the human face can also be obtained.
Referring to fig. 2, a flowchart of a face information acquisition step in the face recognition method based on optical coherence tomography according to the embodiment of the present invention is shown. Further, in the face recognition method based on optical coherence tomography provided in the embodiment of the present invention, the scanning of the face by the face information acquisition subsystem in the face information acquisition step by using the optical coherence tomography specifically includes: the human face is scanned through the human face information acquisition subsystem, the scanning light becomes measuring light after scanning, the measuring light interferes with the reference light to form interference light, the interference light is acquired by the spectrum acquisition device and is transmitted to the signal processor after being converted, a human face image is generated after processing, and the human face image is stored. Specifically, infrared light emitted by a light source of the face information acquisition subsystem forms two beams of infrared light after passing through an optical fiber beam splitter, the optical fiber beam splitter comprises a circulator and/or an optical fiber coupler, one beam of infrared light enters a first optical fiber collimator and a first lens of a reference arm, is reflected by a reflector in the reference arm and then returns to be reference light according to an original light path, the other beam of infrared light is scanning light, the scanning light scans a face through a scanning device, namely, the scanning light enters a second lens and a second optical fiber collimator of the scanning device, is emitted to a scanning galvanometer after being emitted by the second optical fiber collimator, the light emitted by the scanning galvanometer is further irradiated at different positions of the face through an objective lens, the scanning light is reflected or scattered at different positions of the face to be measuring light, and the measuring light returns along the original light path, namely returns to sequentially pass through the objective lens and the scanning galvanometer, And the returned measuring light and the reference light interfere in the optical fiber coupler to form interference light. After the face information acquisition subsystem scans a face, interference light is acquired by the spectrum acquisition device and then converted into an analog signal, the analog signal is transmitted to the signal processor, a face image is sequentially generated after processing, the face image is stored, and the face image is a face structure image and/or a three-dimensional blood flow distribution image. The central wavelength of the light source is 1310nm, the full width at half maximum is 60nm, the emission power is 25mW, and the power of the light source irradiating on the human face is 20 mW.
Further, in the method for identifying a face based on optical coherence tomography provided in the embodiment of the present invention, the interference light in the step of acquiring face information is acquired and converted into an analog signal after passing through the circulator, and specifically: interference light emitted by the optical fiber coupler passes through the circulator, then is collimated by the third optical fiber collimator of the spectrum acquisition device, and then enters the beam expander, light rays are irradiated to the grating after being expanded, wherein the beam expander is used for expanding the diameter of a collimated light spot, so that the area of the light spot irradiated on the grating is increased, the number of irradiated stripes is increased, the light passing through the grating is separately emitted to the lens at different angles, the lens focuses transmitted light with different wavelengths to the photoelectric sensor CCD, and the photoelectric sensor CCD converts optical signals into analog signals and sends the analog signals to the signal processing subsystem.
Further, in the method for identifying a face based on optical coherence tomography provided in the embodiment of the present invention, the step of acquiring face information is processed to generate a face image, specifically:
and a structural image generation module in a signal processor of the face information acquisition subsystem processes the analog signal by adopting any image processing method of an interpolation method, a dispersion compensation method or a Fourier transform method to obtain a face structural image. Other analog signal processing methods can be adopted by those skilled in the art to obtain the face structure image. The dispersion compensation method can be attributed to the deformation of the correction spectrum, and the deformation of the correction spectrum adopts a method of fitting the spectrum coordinate for a high-order coefficient, namely the wavelength corresponding to each pixel on the photoelectric sensor CCDλ(n) Expressed in the following form:
wherein,c kis composed ofkThe correction coefficient of the order spectral coordinates,Nthe number of the pixel points is,c 0indicating a shift in the starting offset of the spectrum, its effect being to causeλ(n) Translation is generated without affecting the waveform. The similarity coefficient of the calibrated reference light spectrum and the light source standard spectrum is maximized, and the optimal reference light spectrum and the optimal light source standard spectrum can be found in a certain numerical value interval through programming according to practical problemsc 0。c 1Indicating the resolution of the spectrometer, which changes will result in spectral broadening or compression,c 2…c k and the spectrum coordinate correction coefficient of more than second order is expressed, the plane reflector is used as the interference spectrum of the sample, and the peak position obtained by calibrating the spectrum is consistent with the actual optical path difference.
The correction coefficient above the second order is mainly the nonlinear deformation of the correction spectrum, is the main parameter for eliminating the influence of dispersion on the resolution, and the optimal coefficient above the second order can be found out by applying a method of cyclic difference in a certain numerical value interval. However, the second-order coefficient has a significant effect on dispersion compensation, while the third-order coefficient has a small effect, so that the algorithm only discusses the second-order coefficient in the present application. Therefore, the wavelength corresponding to each pixel on the CCD is expressed as follows:
neglecting the correction coefficient above the third order, solving the required condition for the correction above the second order and solvingc 1The conditions were the same. Knowing the standard spectrum of the light source, the spectrum of the original reference light and the interference spectrum of the sample with the plane mirror, the spectrum of the original reference light can be obtainedc 1，c 2，c 0The correction coefficients of the respective orders are obtained one by one.
A blood flow image generation module in a signal processor of the face information acquisition subsystem processes the analog signals by adopting an OCT micro-angiography algorithm to obtain three-dimensional blood flow distribution images, and a person skilled in the art can also realize the acquisition of the three-dimensional blood flow distribution images by adopting other analog signal processing algorithms. The basic principle of the OCT micro-angiography algorithm is as follows: other tissue parts in the human body are static, and blood flows in blood vessels, so that moving blood flow information can be obtained by means of subtraction according to the difference between adjacent frames. In the application, the blood flow radiography algorithm acquires 5 frames or more than 5 frames of image data at the same position through the face information acquisition subsystem, and each frame of image data comprises an amplitude component A and a phase component omega. And (3) calculating blood flow information by adopting a method based on the amplitude component difference delta A or a mode of combining two differences based on the amplitude and the phase. The method for calculating the blood flow distribution information only by adopting the amplitude component difference does not require the stability of the phase, has relatively low requirement on an acquisition device, and is relatively simple in processing complexity; the method for obtaining blood flow distribution information based on amplitude and phase difference can obtain better effect on imaging details and vessel connectivity, but the processing time is relatively long, and any one of the methods can be selected and used according to actual needs.
Further, in the method for identifying a face based on optical coherence tomography provided in the embodiment of the present invention, the step of acquiring face information further includes:
an image optimization step: and performing re-registration processing and motion compensation processing on the acquired image. The re-registration processing of the acquired image specifically comprises: and carrying out image preprocessing on the collected image, processing the reflected bright stripes to carry out denoising, carrying out upper edge contour extraction on the image of each frame, and carrying out re-registration on the image by adopting a motion estimation algorithm. The motion compensation processing of the collected image specifically comprises the following steps: and performing motion estimation on the whole situation based on the relation of adjacent frames, simultaneously performing image movement detection on the whole situation by adopting the correlation of adjacent frame baselines of the scanned images, then making a sliding window by utilizing a cross-correlation algorithm to perform sliding pixel error estimation on each frame of image, and performing image restoration by adopting a compensation method aiming at the solved motion estimation displacement so as to achieve template matching. The compensation method comprises the steps of averaging all interference spectrum signals acquired in one-time scanning of the system to obtain direct-current components, carrying out double zero filling on interference signals in a wave number domain, and then carrying out Fourier transformation to obtain a structural image of a space domain sample, wherein the zero filling technology reduces the distance between two pixels in the depth direction of the image to be half of an original image, and then carrying out registration on a local structural image by using an image registration method based on a cross-correlation algorithm.
When the face image only contains the face structure image, the structural image recognition step of the face recognition method based on the optical coherence tomography provided by the embodiment of the invention is executed after the face information acquisition step: and comparing the face structure image with the target user structure image stored in the target user structure image storage unit, judging whether the target is the target user, if not, failing the authentication and terminating the identification, and if so, successfully authenticating. Further, the feature difference calculation is carried out on the face structure image by adopting any distance calculation mode of cosine distance, Euclidean distance and Mahalanobis distance.
When the face image only contains a three-dimensional blood flow distribution image, the blood flow image recognition step of the face recognition method based on the optical coherence tomography provided by the embodiment of the invention is executed after the face information acquisition step: and comparing the three-dimensional blood flow distribution image with the target user blood flow image stored in the target user blood flow image storage unit, continuously judging whether the target is the target user, if not, failing the authentication and terminating the identification, and if so, successfully authenticating.
And when the face image comprises a face structure image and a three-dimensional blood flow distribution image, sequentially executing a structure image identification step and a blood flow image identification step after the face information acquisition step. And when the results of the structural image identification step and the blood flow image identification step are both successful in authentication, the face identification authentication is considered to be successful, and if the authentication result of any one of the structural image identification step and the blood flow image identification step is authentication failure and the identification is terminated, the face identification authentication is considered to be failed.
Further, in the face recognition method based on optical coherence tomography provided in the embodiment of the present invention, the comparing step of the blood flow image recognition step compares the three-dimensional blood flow distribution image with the pre-stored blood flow image of the target user, specifically: and quantitatively evaluating the blood vessel density, the blood vessel complexity and the blood vessel diameter according to the three-dimensional blood flow distribution image, and comparing the quantized result data with prestored blood flow data corresponding to the prestored blood flow image of the target user. The blood vessel density represents the blood vessel area rho in different unit areas, the blood vessel area in the unit area is calculated by adopting an integration method, the blood vessel density distribution rho in different areas is different, and the blood vessel density distribution rho is taken as a variable; vessel complexity refers to the ratio of the area to the length of the vessel in a unit area: s/H, wherein s is the area of the blood vessel in the unit area, and H is the length of the blood vessel in the unit area; the diameter of the blood vessel refers to the diameter of the blood vessel at different positions, and the diameter size of the blood vessel is extracted by adopting a multi-scale method. The person skilled in the art can also set other quantitative parameters of the three-dimensional blood flow distribution image according to actual needs. The invention is based on the optical coherence tomography scanning technology, can collect the structural features of the human face and simultaneously collect partial feature blood vessel information, and compares the partial feature blood vessel information with the features in the pre-stored feature library, thereby avoiding the deception of the human face and improving the accuracy of the human face recognition.
According to the face recognition method and system based on optical coherence tomography provided by the embodiment of the invention, a face information acquisition subsystem scans a face to acquire and store a face image, wherein the face image is a face structure image and/or a three-dimensional blood flow distribution image; when the face image only contains the face structure image, the structure image recognition subsystem compares the face structure image with a prestored target user structure image to judge whether the target is a target user, if not, the authentication fails and the recognition is terminated, and if so, the authentication is successful; when the face image only contains the three-dimensional blood flow distribution image, the blood flow image recognition subsystem compares the three-dimensional blood flow distribution image with a prestored blood flow image of a target user and judges whether the target is the target user, if not, the authentication fails and the recognition is terminated, and if so, the authentication succeeds; and when the face image comprises a face structure image and a three-dimensional blood flow distribution image, sequentially executing a structure image identification step and a blood flow image identification step after the face information acquisition step. According to the technical scheme, the purpose of forming blood flow radiography imaging by scanning the bottom layer skin structure and further extracting the characteristic information of the target bottom layer skin is achieved by adopting the optical coherence tomography technology, so that the face recognition based on face structure image comparison and three-dimensional blood flow distribution image comparison is realized, the accuracy of the face recognition is improved, the condition that a forged three-dimensional face model is difficult to distinguish during face recognition is improved, the accuracy of identity authentication is further improved, and the technical problem that the recognition accuracy is low in the existing face recognition technology is solved.
Example two:
referring to fig. 3, a schematic structural diagram of a face recognition system based on optical coherence tomography according to an embodiment of the present invention is provided. The embodiment of the invention provides a face recognition system based on optical coherence tomography, which comprises: the system comprises a face information acquisition subsystem 100 and an image recognition subsystem, wherein the image recognition subsystem comprises a structural image recognition subsystem 200 and a blood flow image recognition subsystem 300. The face information acquisition subsystem 100, the structural image recognition subsystem 200 and the blood flow image recognition subsystem 300 are connected in sequence.
The face information acquisition subsystem 100 includes: a light source 110, a fiber optic beam splitter, a reference arm 140, a scanning device 150, a spectrum acquisition device 160, and a signal processor 170; the face information acquisition subsystem 100 is used for scanning a face, and acquiring and storing a face image. The fiber splitter includes a circulator 120 and/or a fiber coupler 130, and the reference arm 140 includes a first fiber collimator 141, a first lens 142, and a mirror 143 connected in sequence. The scanning device 150 includes: a second fiber collimator 151, a scanning galvanometer 152, an objective 153, and a second lens 154. The spectrum collection device 160 includes: a third fiber collimator 161, a beam expander 162, a grating 163, a third lens 164, and a photosensor CCD 165. The signal processor 170 is provided with a memory in which a signal processing subsystem for performing signal processing is stored, and the signal processing subsystem is connected with the structural image recognition subsystem and the blood flow image recognition subsystem, respectively. The infrared light emitted from the light source 110 passes through the optical fiber beam splitter to form two beams of infrared light, wherein one beam of infrared light enters the first optical fiber collimator 141 and the first lens 142 of the reference arm 140, is reflected by the reflector 143 in the reference arm 140 and then returns to the reference light according to the original optical path, the other beam of infrared light is scanning light, the scanning light scans the face through the scanning device 150, i.e., the scanning light enters the second lens 154 and the second optical fiber collimator 151 of the scanning device 150, is emitted to the scanning galvanometer 152 after being emitted through the second optical fiber collimator 151, the light emitted through the scanning galvanometer 152 is irradiated on different positions of the face through the objective lens 153, the scanning light is reflected or scattered through different positions of the face to form measuring light, the measuring light returns along the original optical path, i.e., returns to pass through the objective lens 153, the scanning galvanometer 152, the second optical fiber collimator 151 and the second lens 154 in sequence, the returned measuring light interferes with the reference light in the optical fiber coupler 130 to form interference light, the interference light is collected by the spectrum collection device 160 via the circulator and then converted into an analog signal, the analog signal is transmitted to the signal processor 170, a face structure image and a three-dimensional blood flow distribution image are sequentially generated after processing, and the face structure image and the three-dimensional blood flow distribution image are stored. The central wavelength of the light source is 1310nm, the full width at half maximum is 60nm, the emission power is 25mW, and the power of the light source irradiating on the human face is 20 mW.
Further, in the face recognition system based on optical coherence tomography provided in the embodiment of the present invention, the signal processing subsystem includes: the blood flow image generation device comprises an image optimization module, a structural image generation module and a blood flow image generation module, wherein the image optimization module, the structural image identification module and the blood flow image identification module are sequentially connected. The image optimization module comprises an image preprocessing unit, an image contour extraction unit, a sliding matching unit and a displacement compensation unit which are sequentially connected.
And a structural image generation module in a signal processor of the face information acquisition subsystem processes the analog signal by adopting any image processing method of an interpolation method, a dispersion compensation method or a Fourier transform method to obtain a face structural image. The dispersion compensation method can be attributed to the distortion of the correction spectrum, which is most effectively fitted with high-order coefficients to the spectral coordinates, i.e., the wavelengths corresponding to the pixels on the photoelectric sensor CCDλ(n) Expressed in the following form:
wherein,c kis composed ofkThe order of the spectral coordinate correction function,Nis the number of pixels.c 0Indicating a shift in the starting offset of the spectrum, its effect being to causeλ(n) Translation is generated without affecting the waveform. The similarity coefficient of the calibrated reference light spectrum and the light source standard spectrum is maximized, and the optimal reference light spectrum and the optimal light source standard spectrum can be found in a certain numerical value interval through programming according to practical problemsc 0。c 1Indicating the resolution of the spectrometer, which changes will result in spectral broadening or compression,c 2…c k and the spectrum coordinate correction coefficient of more than second order is expressed, the plane reflector is used as the interference spectrum of the sample, and the peak position obtained by calibrating the spectrum is consistent with the actual optical path difference.
The correction coefficient above the second order is mainly the nonlinear deformation of the correction spectrum, is the main parameter for eliminating the influence of dispersion on the resolution, and the optimal coefficient above the second order can be found out by applying a method of cyclic difference in a certain numerical value interval. However, the second-order coefficient has a significant effect on dispersion compensation, while the third-order coefficient has a small effect, so that the algorithm only discusses the second-order coefficient in the present application. Therefore, the wavelengths corresponding to the individual pixels on the CCD are represented as follows:
the correction coefficients above the third order are ignored. Solving the conditions required for correction of more than second order and solvingc 1The conditions were the same. Knowing the standard spectrum of the light source, the spectrum of the original reference light and an interference spectrum using the plane mirror as a sample, the method can be based onc 1，c 2，c 0The correction coefficients of the respective orders are obtained one by one.
A blood flow image generation module in a signal processor of the face information acquisition subsystem processes the analog signal by adopting an OCT (optical coherence tomography) micro-angiography algorithm to obtain a three-dimensional blood flow distribution image, wherein the basic principle of the OCT micro-angiography algorithm is as follows: other tissue parts in the human body are static, and blood flows in blood vessels, so that moving blood flow information can be obtained by means of subtraction according to the difference between adjacent frames. The specific method for processing the blood flow radiography algorithm comprises the following steps: the OCT system acquisition device acquires 5 frames or more than 5 frames of image data at the same position, and each frame of image data comprises an amplitude component A and a phase component omega. The blood flow information may be obtained by a method Δ a based on the amplitude component difference alone, or may be obtained by combining the amplitude and phase differences. The method for calculating the blood flow distribution information only by using the amplitude difference does not require the stability of the phase, has relatively low requirement on an acquisition device, and is relatively simple in processing complexity; the method for obtaining blood flow distribution information based on amplitude and phase difference can obtain better effect on imaging details and vessel connectivity, but the processing time is relatively long, and any one of the methods can be selected and used according to actual needs.
Further, in the face recognition system based on optical coherence tomography provided in the embodiment of the present invention, the structural image recognition subsystem 200 includes: the structural image processing unit compares the face structural image with a target user structural image prestored in the target user structural image storage unit, judges whether the target is a target user or not, if not, the authentication fails and the identification is terminated, and if so, the blood flow image identification subsystem is started.
Further, in the face recognition system based on optical coherence tomography provided in the embodiment of the present invention, the blood flow image recognition subsystem 300 includes: the blood flow image processing unit compares the three-dimensional blood flow distribution image with a target user blood flow image prestored in the target user blood flow image storage unit, continuously judges whether the target is the target user, if not, the authentication fails and the identification is terminated, and if so, the authentication succeeds.
The embodiment of the invention provides a face recognition system based on optical coherence tomography, which comprises: the face information acquisition subsystem and the image recognition subsystem, wherein, the face information acquisition subsystem includes: the device comprises a light source, an optical fiber beam splitter, a reference arm, a scanning device, a spectrum acquisition device and a signal processor; the face information acquisition subsystem is used for scanning a face to acquire and store a face image; the image recognition subsystem includes a structural image recognition subsystem and/or a blood flow image recognition subsystem. According to the technical scheme, the purpose of forming blood flow radiography imaging by scanning the bottom layer skin structure and further extracting the characteristic information of the target bottom layer skin is achieved by adopting the optical coherence tomography technology, so that the face recognition based on face structure image comparison and three-dimensional blood flow distribution image comparison is realized, the accuracy of the face recognition is improved, the condition that a forged three-dimensional face model is difficult to distinguish during face recognition is improved, the accuracy of identity authentication is further improved, and the technical problem that the recognition accuracy is low in the existing face recognition technology is solved.
In the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and specific meanings of the terms in the invention may be understood in specific instances by those skilled in the art. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (13)
1. A face recognition method based on optical coherence tomography is characterized by comprising the following steps:
a face information acquisition step: scanning a human face to acquire and store a human face image, wherein the human face image is a human face structure image and/or a three-dimensional blood flow distribution image;
when the face image only contains a face structure image, the face information acquisition step further comprises a structure image identification step after the face information acquisition step: comparing the face structure image with a pre-stored target user structure image, judging whether a target is a target user, if not, failing authentication and terminating identification, and if so, successfully authenticating;
when the face image only contains a three-dimensional blood flow distribution image, the face information acquisition step further comprises a blood flow image recognition step after the face information acquisition step: comparing the three-dimensional blood flow distribution image with a prestored target user blood flow image, judging whether the target is a target user, if not, failing authentication and terminating identification, and if so, successfully authenticating;
and when the face image comprises a face structure image and a three-dimensional blood flow distribution image, sequentially executing the structure image identification step and the blood flow image identification step after the face information acquisition step.
2. The method according to claim 1, wherein the face information acquisition step specifically comprises: the human face is scanned through the human face information acquisition subsystem, the reference light and the scanned measurement light are interfered to form interference light, the interference light is acquired and converted by the spectrum acquisition device and then transmitted to the signal processor, a human face image is generated after processing, and the human face image is stored.
3. The method according to claim 2, wherein the processing generates a face image, specifically:
processing the analog signal by adopting any image processing method of an interpolation method, a dispersion compensation method or a Fourier transform method to obtain a face structure image;
and processing the analog signal by adopting an OCT micro-angiography algorithm to obtain a three-dimensional blood flow distribution image.
4. The method according to claim 1, wherein the comparing the three-dimensional blood flow distribution image with a pre-stored target user blood flow image comprises: and quantitatively evaluating the blood vessel density, the blood vessel complexity and the blood vessel diameter according to the three-dimensional blood flow distribution image, and comparing the quantized result data with prestored blood flow data corresponding to the prestored blood flow image of the target user.
5. The method of claim 1, wherein the face information collecting step further comprises:
an image optimization step: and performing re-registration processing and motion compensation processing on the acquired image.
6. The method according to claim 5, characterized in that the re-registration of the acquired images is performed, in particular: and carrying out image preprocessing on the collected image, processing the reflected bright stripes to carry out denoising, carrying out upper edge contour extraction on the image of each frame, and carrying out re-registration on the image by adopting a motion estimation algorithm.
7. The method according to claim 5, wherein the motion compensation processing is performed on the captured image, specifically: and performing motion estimation on the whole situation based on the relation of adjacent frames, simultaneously performing image movement detection on the whole situation by adopting the correlation of adjacent frame baselines of the scanned images, then making a sliding window by utilizing a cross-correlation algorithm to perform sliding pixel error estimation on each frame of image, and recovering the obtained motion estimation displacement by adopting a compensation method so as to achieve template matching.
8. A face recognition system based on optical coherence tomography, comprising: the system comprises a face information acquisition subsystem and an image recognition subsystem;
the face information acquisition subsystem comprises: the device comprises a light source, an optical fiber beam splitter, a reference arm, a scanning device, a spectrum acquisition device and a signal processor; the face information acquisition subsystem is used for scanning a face to acquire and store a face image;
the image identification subsystem comprises a structural image identification subsystem and/or a blood flow image identification subsystem.
9. The system of claim 8,
the optical fiber beam splitter comprises a circulator and/or an optical fiber coupler;
the reference arm comprises a first optical fiber collimator, a first lens and a reflector which are connected in sequence;
the scanning device includes: the scanning galvanometer, the objective lens and the second lens are arranged in the optical fiber collimator;
the spectrum collection device comprises: the third optical fiber collimator, the beam expander, the grating, the third lens and the photoelectric sensor CCD;
the signal processor is provided with a memory in which a signal processing subsystem for performing signal processing is stored.
10. The system of claim 9, wherein the signal processing subsystem comprises:
the blood flow monitoring system comprises an image optimization module, and a structural image generation module and a blood flow image generation module which are respectively connected with the image optimization module.
11. The system according to claim 10, wherein the image optimization module comprises an image preprocessing unit, an image contour extraction unit, a sliding matching unit and a displacement compensation unit connected in sequence.
12. The system of claim 8, wherein the structural image recognition subsystem comprises:
the structure image processing unit compares the face structure image with a target user structure image prestored in the target user structure image storage unit, judges whether the target is a target user or not, if not, the authentication fails and the identification is terminated, and if so, the authentication succeeds.
13. The system of claim 8, wherein the blood flow image recognition subsystem comprises:
the blood flow image processing unit compares the three-dimensional blood flow distribution image with a target user blood flow image prestored in the target user blood flow image storage unit, continuously judges whether the target is the target user, if not, the authentication fails and the identification is terminated, and if so, the authentication succeeds.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810596262.7A CN109033949A (en) | 2018-06-11 | 2018-06-11 | Face identification method and system based on optical coherence tomography |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810596262.7A CN109033949A (en) | 2018-06-11 | 2018-06-11 | Face identification method and system based on optical coherence tomography |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109033949A true CN109033949A (en) | 2018-12-18 |
Family
ID=64612729
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810596262.7A Pending CN109033949A (en) | 2018-06-11 | 2018-06-11 | Face identification method and system based on optical coherence tomography |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109033949A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110292359A (en) * | 2019-07-09 | 2019-10-01 | 浙江大学 | A kind of method and apparatus of unmarked full optical neuron regulation and imaging |
| CN111493930A (en) * | 2020-04-24 | 2020-08-07 | 天津恒宇医疗科技有限公司 | Novel endoscopic blood flow imaging and blood flow parameter quantification method and system |
| CN111493853A (en) * | 2020-04-24 | 2020-08-07 | 天津恒宇医疗科技有限公司 | Blood vessel parameter evaluation method and system for angiodermic diseases |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101770613A (en) * | 2010-01-19 | 2010-07-07 | 北京智慧眼科技发展有限公司 | Social insurance identity authentication method based on face recognition and living body detection |
| CN105342568A (en) * | 2015-11-26 | 2016-02-24 | 上海交通大学 | Optical coherence tomography method and system combining phase and amplitude |
| CN106073788A (en) * | 2016-07-19 | 2016-11-09 | 杭州捷诺飞生物科技有限公司 | In-situ three-dimensional based on OCT prints skin repair equipment and its implementation |
| CN106491078A (en) * | 2015-09-07 | 2017-03-15 | 南京理工大学 | Remove the method and device of ordered dither noise in blood-stream image |
| CN107307848A (en) * | 2017-05-27 | 2017-11-03 | 天津海仁医疗技术有限公司 | A kind of recognition of face and skin detection system based on the micro- contrast imaging of high speed large area scanning optics |
| US20170347872A1 (en) * | 2016-06-03 | 2017-12-07 | Nidek Co., Ltd. | Ophthalmic apparatus |
| CN108042125A (en) * | 2017-05-27 | 2018-05-18 | 天津海仁医疗技术有限公司 | A kind of high speed endoscopic optical coherent flow imaging system |
-
2018
- 2018-06-11 CN CN201810596262.7A patent/CN109033949A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101770613A (en) * | 2010-01-19 | 2010-07-07 | 北京智慧眼科技发展有限公司 | Social insurance identity authentication method based on face recognition and living body detection |
| CN106491078A (en) * | 2015-09-07 | 2017-03-15 | 南京理工大学 | Remove the method and device of ordered dither noise in blood-stream image |
| CN105342568A (en) * | 2015-11-26 | 2016-02-24 | 上海交通大学 | Optical coherence tomography method and system combining phase and amplitude |
| US20170347872A1 (en) * | 2016-06-03 | 2017-12-07 | Nidek Co., Ltd. | Ophthalmic apparatus |
| CN106073788A (en) * | 2016-07-19 | 2016-11-09 | 杭州捷诺飞生物科技有限公司 | In-situ three-dimensional based on OCT prints skin repair equipment and its implementation |
| CN107307848A (en) * | 2017-05-27 | 2017-11-03 | 天津海仁医疗技术有限公司 | A kind of recognition of face and skin detection system based on the micro- contrast imaging of high speed large area scanning optics |
| CN108042125A (en) * | 2017-05-27 | 2018-05-18 | 天津海仁医疗技术有限公司 | A kind of high speed endoscopic optical coherent flow imaging system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110292359A (en) * | 2019-07-09 | 2019-10-01 | 浙江大学 | A kind of method and apparatus of unmarked full optical neuron regulation and imaging |
| CN110292359B (en) * | 2019-07-09 | 2021-01-08 | 浙江大学 | Method and device for label-free all-optical nerve regulation and imaging |
| CN111493930A (en) * | 2020-04-24 | 2020-08-07 | 天津恒宇医疗科技有限公司 | Novel endoscopic blood flow imaging and blood flow parameter quantification method and system |
| CN111493853A (en) * | 2020-04-24 | 2020-08-07 | 天津恒宇医疗科技有限公司 | Blood vessel parameter evaluation method and system for angiodermic diseases |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10278584B2 (en) | Method and system for three-dimensional imaging | |
| US9269144B2 (en) | Method and apparatus for motion correction and image enhancement for optical coherence tomography | |
| CN103502770B (en) | Improved imaging with real-time tracking using optical coherence tomography | |
| CN103356162B (en) | Image processing equipment and image processing method | |
| CN106073700B (en) | Image generating method and video generation device | |
| US20070263906A1 (en) | Personal Identification Method by Subcutaneous Bloodstream Measurement and Personal Identification Device | |
| US8787623B2 (en) | Methods, systems and computer program products for diagnosing conditions using unique codes generated from a multidimensional image of a sample | |
| US10206580B2 (en) | Full-field OCT system using wavelength-tunable laser and three-dimensional image correction method | |
| JP5924955B2 (en) | Image processing apparatus, image processing apparatus control method, ophthalmic apparatus, and program | |
| US20110026783A1 (en) | Personal authentication method using subcutaneous bloodstream measurement and personal authentication device | |
| WO2010062883A1 (en) | Methods, systems and computer program products for biometric identification by tissue imaging using optical coherence tomography (oct) | |
| CN103251379A (en) | Image processing apparatus, image processing method, and program | |
| JP6436442B2 (en) | Photoacoustic apparatus and image processing method | |
| CN109033949A (en) | Face identification method and system based on optical coherence tomography | |
| WO2013125707A1 (en) | Cycloduction measurement device, cycloduction measurement method, and cycloduction measurement program | |
| US10470653B2 (en) | Image processing apparatus, image processing method, and storage medium that generate a motion contrast enface image | |
| Sekulska-Nalewajko et al. | The detection of internal fingerprint image using optical coherence tomography | |
| US10916012B2 (en) | Image processing apparatus and image processing method | |
| EP2693397B1 (en) | Method and apparatus for noise reduction in an imaging system | |
| CN113706567B (en) | Blood flow imaging quantification processing method and device combined with blood vessel morphological characteristics | |
| US20240302274A1 (en) | Method for three-dimensional (3d) image calibration for a spectral domain optical coherence tomography (oct) system | |
| WO2011066366A1 (en) | Methods, systems and computer program products for diagnosing conditions using unique codes generated from a multidimensional image of a sample | |
| JP6598963B2 (en) | Image processing apparatus, image processing method, and program | |
| CN117942041A (en) | Vascular imaging method, device, equipment and storage medium | |
| CN115294027A (en) | Heart rate detection method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |