CN110532832A - A kind of bar code high-precision recognition methods based on computer vision - Google Patents
A kind of bar code high-precision recognition methods based on computer vision Download PDFInfo
- Publication number
- CN110532832A CN110532832A CN201810534749.2A CN201810534749A CN110532832A CN 110532832 A CN110532832 A CN 110532832A CN 201810534749 A CN201810534749 A CN 201810534749A CN 110532832 A CN110532832 A CN 110532832A
- Authority
- CN
- China
- Prior art keywords
- image
- bar code
- computer vision
- recognition methods
- methods based
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/146—Methods for optical code recognition the method including quality enhancement steps
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of bar code high-precision recognition methods based on computer vision, comprising the following steps: A, is taken pictures using high-precision camera to article and pre-processes the image of shooting；B, the bar code image signal on article is carried out feature extraction and is sent to processor to handle；C, to treated, bar code image signal is sent to background terminal, and the recognition methods accuracy of identification that the present invention uses is high, and recognition efficiency is high, improves work efficiency.
Description
Technical field
The present invention relates to technical field of computer vision, specially a kind of bar code high-precision based on computer vision is identified
Method.
Background technique
Computer vision is is studied the science for how making machine " seeing ", further, exactly refers to photography
Machine and computer replace human eye the machine vision such as to be identified, tracked and measured to target, and further do graphics process, make computer
It is treated as the image for being more suitable for eye-observation or sending instrument detection to.As a branch of science, computer vision research
Relevant theory and technology, it is intended to establish the artificial intelligence system that ' information ' can be obtained from image or multidimensional data.This
In signified information refer to what Shannon was defined, can be used to help to make the information of one " decision ".Because perception can be regarded as
Information is extracted from sensory signal, so computer vision also can be regarded as how research makes manual system from image or multidimensional
The science of " perception " in data.
Two dimensional code is also known as two-dimensional bar code, it is the black and white being distributed in the plane according to certain rules with specific geometric figure
Alternate figure is a key of all information datas；Bar code identification recognition efficiency on current product is low, and precision is low.
Summary of the invention
It is above-mentioned to solve the purpose of the present invention is to provide a kind of bar code high-precision recognition methods based on computer vision
The problem of being proposed in background technique.
To achieve the above object, the invention provides the following technical scheme: a kind of bar code high-precision based on computer vision
Recognition methods, comprising the following steps:
A, it is taken pictures using high-precision camera to article and is pre-processed the image of shooting；
B, the bar code image signal on article is carried out feature extraction and is sent to processor to handle；
C, to treated, bar code image signal is sent to background terminal.
Preferably, in the step A image pre-processing method the following steps are included:
A, image gray processing becomes color image the gray level image of single-channel data, is obtained according to weighted average method
Gray level image；
B, image enhancement removes unwanted texture in image to contour feature in the prominent image of original image transformation data
Feature；
C, image filtering handles image with Sequential filter, then carries out fusion treatment, specific formula is as follows:
T (x, y)=max (ga(x, y), gb(x, y), gc(x, y), gd(x, y))
Wherein, t (x, y) is gray value of the fused image at coordinate points (x, y), ga(x, y), gb(x, y), gc(x,
y)、gd(x, y) be respectively it is horizontal, 45 degree, vertically, gray scale of the Sequential filter result figure in 135 degree of directions at coordinate points (x, y)
Value；
D, image binaryzation is chosen the gray level image of 256 brightness degrees by threshold value and obtains reflection image entirety
With the binary image of local feature, bianry image is obtained using based on the adaptive threshold fuzziness of histogram.
Preferably, in the step B feature extracting method the following steps are included:
A, image to be extracted is pressed into class Haar method texture feature extraction histogram；
B, the central point pixel of extraction image to be detected and its upper and lower, left and right and four angular vertexs are compared acquisition texture
Feature histogram；
C, cascade image to be detected step a and step b, to obtain bar code image textural characteristics.
Preferably, processor processing method is as follows in the step B:
A, picture signal is input to SRD Gauss narrow pulse generating circuit and forms narrow pulse signal, then by narrow pulse signal
By second-order differential Gaussian particle filter circuit output subnanosecond grade, second-order differential Gaussian pulse signal；
B, output subnanosecond grade, second-order differential Gaussian pulse signal in step a are calculated using computing device, according to
The picture signal characteristics of feedback calculate transmission characteristic；
C, according to the picture signal characteristics fed back in step b, step a and b are repeated；Picture signal is exported.
Compared with prior art, the beneficial effects of the present invention are: the recognition methods accuracy of identification height that the present invention uses, identification
It is high-efficient, it improves work efficiency；Wherein, the image pre-processing method treatment effeciency that the present invention uses is high, treated image
It is high-quality, it is identified convenient for subsequent high-precision；The feature extracting method of use greatly reduces characteristic dimension, improves detection
Rate；In addition, the processor processing method that the present invention uses can enhance picture signal, further increase to picture signal
Detection effect.
Detailed description of the invention
Fig. 1 is flow chart of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, the present invention provides a kind of technical solution: a kind of bar code high-precision based on computer vision identification side
Method, comprising the following steps:
A, it is taken pictures using high-precision camera to article and is pre-processed the image of shooting；
B, the bar code image signal on article is carried out feature extraction and is sent to processor to handle；
C, to treated, bar code image signal is sent to background terminal.
In the present invention, image pre-processing method in step A the following steps are included:
A, image gray processing becomes color image the gray level image of single-channel data, is obtained according to weighted average method
Gray level image；
B, image enhancement removes unwanted texture in image to contour feature in the prominent image of original image transformation data
Feature；
C, image filtering handles image with Sequential filter, then carries out fusion treatment, specific formula is as follows:
T (x, y)=max (ga(x, y), gb(x, y), gc(x, y), gd(x, y))
Wherein, t (x, y) is gray value of the fused image at coordinate points (x, y), ga(x, y), gb(x, y), gc(x,
y)、gd(x, y) be respectively it is horizontal, 45 degree, vertically, gray scale of the Sequential filter result figure in 135 degree of directions at coordinate points (x, y)
Value；
D, image binaryzation is chosen the gray level image of 256 brightness degrees by threshold value and obtains reflection image entirety
With the binary image of local feature, bianry image is obtained using based on the adaptive threshold fuzziness of histogram.
In the present invention, feature extracting method in step B the following steps are included:
A, image to be extracted is pressed into class Haar method texture feature extraction histogram；
B, the central point pixel of extraction image to be detected and its upper and lower, left and right and four angular vertexs are compared acquisition texture
Feature histogram；
C, cascade image to be detected step a and step b, to obtain bar code image textural characteristics.
In addition, processor processing method is as follows in step B in the present invention:
A, picture signal is input to SRD Gauss narrow pulse generating circuit and forms narrow pulse signal, then by narrow pulse signal
By second-order differential Gaussian particle filter circuit output subnanosecond grade, second-order differential Gaussian pulse signal；
B, output subnanosecond grade, second-order differential Gaussian pulse signal in step a are calculated using computing device, according to
The picture signal characteristics of feedback calculate transmission characteristic；
C, according to the picture signal characteristics fed back in step b, step a and b are repeated；Picture signal is exported.
In conclusion the recognition methods accuracy of identification that the present invention uses is high, recognition efficiency is high, improves work efficiency；Its
In, the image pre-processing method treatment effeciency that the present invention uses is high, and picture quality that treated is good, knows convenient for subsequent high-precision
Not；The feature extracting method of use greatly reduces characteristic dimension, improves verification and measurement ratio；In addition, the processor that the present invention uses
Processing method can enhance picture signal, further increase the detection effect to picture signal.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (4)
1. a kind of bar code high-precision recognition methods based on computer vision, it is characterised in that: the following steps are included:
A, it is taken pictures using high-precision camera to article and is pre-processed the image of shooting；
B, the bar code image signal on article is carried out feature extraction and is sent to processor to handle；
C, to treated, bar code image signal is sent to background terminal.
2. a kind of bar code high-precision recognition methods based on computer vision according to claim 1, it is characterised in that: institute
State image pre-processing method in step A the following steps are included:
A, image gray processing, becomes color image the gray level image of single-channel data, obtains gray scale according to weighted average method
Image；
B, image enhancement removes unwanted textural characteristics in image to contour feature in the prominent image of original image transformation data；
C, image filtering handles image with Sequential filter, then carries out fusion treatment, specific formula is as follows:
T (x, y)=max (ga(x, y), gb(x, y), gc(x, y), gd(x, y))
Wherein, t (x, y) is gray value of the fused image at coordinate points (x, y), ga(x, y), gb(x, y), gc(x, y), gd
(x, y) be respectively it is horizontal, 45 degree, vertically, gray value of the Sequential filter result figure in 135 degree of directions at coordinate points (x, y)；
D, image binaryzation is chosen the gray level image of 256 brightness degrees by threshold value and obtains reflection image entirety drawn game
The binary image of portion's feature obtains bianry image using based on the adaptive threshold fuzziness of histogram.
3. a kind of bar code high-precision recognition methods based on computer vision according to claim 1, it is characterised in that: institute
State feature extracting method in step B the following steps are included:
A, image to be extracted is pressed into class Haar method texture feature extraction histogram；
B, the central point pixel of extraction image to be detected and its upper and lower, left and right and four angular vertexs are compared acquisition textural characteristics
Histogram；
C, cascade image to be detected step a and step b, to obtain bar code image textural characteristics.
4. a kind of bar code high-precision recognition methods based on computer vision according to claim 1, it is characterised in that: institute
It is as follows to state processor processing method in step B:
A, picture signal is input to SRD Gauss narrow pulse generating circuit and forms narrow pulse signal, then narrow pulse signal is passed through
Second-order differential Gaussian particle filter circuit output subnanosecond grade, second-order differential Gaussian pulse signal；
B, output subnanosecond grade, second-order differential Gaussian pulse signal in step a are calculated using computing device, according to feedback
Picture signal characteristics calculate transmission characteristic；
C, according to the picture signal characteristics fed back in step b, step a and b are repeated；Picture signal is exported.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810534749.2A CN110532832A (en) | 2018-05-24 | 2018-05-24 | A kind of bar code high-precision recognition methods based on computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810534749.2A CN110532832A (en) | 2018-05-24 | 2018-05-24 | A kind of bar code high-precision recognition methods based on computer vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110532832A true CN110532832A (en) | 2019-12-03 |
Family
ID=68657840
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810534749.2A Withdrawn CN110532832A (en) | 2018-05-24 | 2018-05-24 | A kind of bar code high-precision recognition methods based on computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110532832A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105681623A (en) * | 2016-02-24 | 2016-06-15 | 无锡南理工科技发展有限公司 | Image signal enhancement processing method |
| CN105701495A (en) * | 2016-01-05 | 2016-06-22 | 贵州大学 | Image texture feature extraction method |
| CN106056020A (en) * | 2016-06-01 | 2016-10-26 | 东莞理工学院 | Bar code detection and recognition method and system based on machine vision system |
| CN107403124A (en) * | 2017-07-31 | 2017-11-28 | 苏州经贸职业技术学院 | A kind of barcode detection recognition methods of view-based access control model image |
| CN107941808A (en) * | 2017-11-10 | 2018-04-20 | 中国计量大学 | 3D printing Forming Quality detecting system and method based on machine vision |
-
2018
- 2018-05-24 CN CN201810534749.2A patent/CN110532832A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701495A (en) * | 2016-01-05 | 2016-06-22 | 贵州大学 | Image texture feature extraction method |
| CN105681623A (en) * | 2016-02-24 | 2016-06-15 | 无锡南理工科技发展有限公司 | Image signal enhancement processing method |
| CN106056020A (en) * | 2016-06-01 | 2016-10-26 | 东莞理工学院 | Bar code detection and recognition method and system based on machine vision system |
| CN107403124A (en) * | 2017-07-31 | 2017-11-28 | 苏州经贸职业技术学院 | A kind of barcode detection recognition methods of view-based access control model image |
| CN107941808A (en) * | 2017-11-10 | 2018-04-20 | 中国计量大学 | 3D printing Forming Quality detecting system and method based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| 黄婷婷等: "用图象处理来识别二维条形码", 《电脑知识与技术》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Semantic-supervised infrared and visible image fusion via a dual-discriminator generative adversarial network | |
| US11830230B2 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
| CN108875935B (en) | Natural image target material visual characteristic mapping method based on generation countermeasure network | |
| CN107844795B (en) | Convolutional neural network feature extraction method based on principal component analysis | |
| CN106228528B (en) | A kind of multi-focus image fusing method based on decision diagram and rarefaction representation | |
| CN108921942B (en) | Method and device for 2D (two-dimensional) conversion of image into 3D (three-dimensional) | |
| CN110084773A (en) | A kind of image interfusion method based on depth convolution autoencoder network | |
| CN112561879B (en) | Ambiguity evaluation model training method, image ambiguity evaluation method and image ambiguity evaluation device | |
| CN112767279A (en) | Underwater image enhancement method for generating countermeasure network based on discrete wavelet integration | |
| CN111080670A (en) | Image extraction method, device, equipment and storage medium | |
| CN110136075A (en) | It is a kind of to recycle the remote sensing image defogging method for generating confrontation network based on edge sharpening | |
| CN114820471A (en) | Visual inspection method for surface defects of intelligent manufacturing microscopic structure | |
| Tung et al. | Elliptical density shape model for hand gesture recognition | |
| CN109165551B (en) | Expression recognition method for adaptively weighting and fusing significance structure tensor and LBP characteristics | |
| Avinash et al. | Color hand gesture segmentation for images with complex background | |
| CN114783020B (en) | Dynamic face recognition method based on novel countermeasure learning deblurring theory | |
| CN110532832A (en) | A kind of bar code high-precision recognition methods based on computer vision | |
| CN104102911A (en) | Image processing for AOI (automated optical inspection)-based bullet appearance defect detection system | |
| CN116740498B (en) | Model pre-training method, model training method, object processing method and device | |
| Guo et al. | Progressive domain translation defogging network for real-world fog images | |
| Chen et al. | Illumination processing in face recognition | |
| CN108491820B (en) | Method, device and equipment for identifying limb representation information in image and storage medium | |
| CN112906508B (en) | Face living body detection method based on convolutional neural network | |
| Wang et al. | A new method of speeded up robust features image registration based on image preprocessing | |
| CN115273184A (en) | Face living body detection model training method and device |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191203 |