Pattern recognition (Engineering)

The hierarchical nature of bone makes it a difficult material to fully comprehend. The equine third metacarpal (MC3) bone experiences nonuniform surface strains, which are a measure of displacement induced by loads. This paper investigates the use of an artificial neural network expert system to quantify MC3 bone loading. Previous studies focused on determining the response of bone using load, bone geometry, mechanical properties, and constraints as input parameters. This is referred to as a forward problem and is generally solved using numerical techniques such as finite element analysis (FEA). Conversely, an inverse problem has to be solved to quantify load from the measurements of strain and displacement. Commercially available FEA packages, without manipulating their underlying algebraic formulae, are incapable of completing a solution to the inverse problem. In this study, an artificial neural network (ANN) was employed to quantify the load required to produce the MC3 displacement and surface strains determined experimentally. Nine hydrated MC3 bones from thoroughbred horses were loaded in compression in an MTS machine. Ex-vivo experiments measured strain readings from one three-gauge rosette and three distinct single-element gauges at different locations on the MC3 midshaft, associated displacement, and load exposure time. Horse age and bone side (left or right limb) were also recorded for each MC3 bone. This information was used to construct input variables for the ANN model. The ability of this expert system to predict the MC3 loading was investigated. The ANN prediction offered excellent reliability for the prediction of load in the MC3 bones investigated, i.e. R2 ≥ 0.98.

Illumination invariance remains the most researched, yet the most challenging aspect of automatic face recognition. In this paper we investigate the discriminative power of colour-based invariants in the presence of large illumination changes between training and test data, when appearance changes due to cast shadows and non-Lambertian effects are significant. Specifically, there are three main contributions: (i) we employ a more sophisticated photometric model of the camera and show how its parameters can be estimated, (ii) we derive several novel colour-based face invariants, and (iii) on a large database of video sequences we examine and evaluate the largest number of colour-based representations in the literature. Our results suggest that colour invariants do have a substantial discriminative power which may increase the robustness and accuracy of recognition from low resolution images.

Dynamically changing background ("dynamic background") still presents a great challenge to many motion-based video surveillance systems. In the context of event detection, it is a major source of false alarms. There is a strong need from the security industry either to detect and suppress these false alarms, or dampen the effects of background changes, so as to increase the sensitivity to meaningful events of interest. In this paper, we restrict our focus to one of the most common causes of dynamic background changes: that of swaying tree branches and their shadows under windy conditions. Considering the ultimate goal in a video analytics pipeline, we formulate a new dynamic background detection problem as a signal processing alternative to the previously described but unreliable computer vision-based approaches. Within this new framework, we directly reduce the number of false alarms by testing if the detected events are due to characteristic background motions. In addition, we introduce a new dataset suitable for the evaluation of dynamic background detection. It consists of real-world events detected by a commercial surveillance system from two static surveillance cameras. The research question we address is whether dynamic background can be detected reliably and efficiently using simple motion features and in the presence of similar but meaningful events such as loitering. Inspired by the tree aerodynamics theory, we propose a novel method named local variation persistence (LVP), that captures the key characteristics of swaying motions. The method is posed as a convex optimization problem whose variable is the local variation. We derive a computationally efficient algorithm for solving the optimization problem, the solution of which is then used to form a powerful detection statistic. On our newly collected dataset, we demonstrate that the proposed LVP achieves excellent detection results and outperforms the best alternative adapted from existing art in the dynamic background literature.

The k-means algorithm is a partitional clustering method. Over 60 years old, it has been successfully used for a variety of problems. The popularity of k-means is in large part a consequence of its simplicity and efficiency. In this paper we are inspired by these appealing properties of k-means in the development of a clustering algorithm which accepts the notion of "positively" and "negatively" labelled data. The goal is to discover the cluster structure of both positive and negative data in a manner which allows for the discrimination between the two sets. The usefulness of this idea is demonstrated practically on the problem of face recognition, where the task of learning the scope of a person's appearance should be done in a manner which allows this face to be differentiated from others.

Biometric systems provide automatic identification of the people base on their own characteristic features. Unlike the other biometric systems such as face, voice, vein, fingerprint recognitions, iris has randomly scattered features. Iris recognition is considered as the one of the most reliable and accurate biometric identification system. It consists of four stages such as; image acquisition, image preprocessing, image feature extraction, and image matching process. In this work, we are proposing a new feature extraction method and new matching metric in order to find an effective threshold value to separate the intra and inter class distribution of the iris images of different people by using eight-level quantization. Instead of using whole iris region, we have used statistically pre-selected iris regions. This selection had reduced the computational time and decreased the storage capacity. Our suggested metrics is rotation invariant and compares two vectors' selected rows calculated by the Fourier Transform. We have suggested eight level quantization of the phase information in order to create iris feature extraction. Finally, we have shown ROC Curves to check the accuracy of our proposed metric. The accuracy of our work is 99.0%, proposed threshold value is 0.746 where FAR is 0.07%, FRR is 39.32% and AUC is 97.4%. Using the CASIA Iris Database, we have compared our proposed matching metric with Hamming Distance metric and we report better performance in terms of matching time.

International Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI) is an open access peer-reviewed journal that provides an excellent international forum for sharing knowledge and results in theory, methodology and applications of Artificial Intelligence, Soft Computing. The Journal looks for significant contributions to all major fields of the Artificial Intelligence, Soft Computing in theoretical and practical aspects. The aim of the Journal is to provide a platform to the researchers and practitioners from both academia as well as industry to meet and share cutting-edge development in the field.

The self-quotient image is a biologically inspired representation which has been proposed as an illumination invariant feature for automatic face recognition. Owing to the lack of strong domain specific assumptions underlying this representation, it can be readily extracted from raw images irrespective of the persons's pose, facial expression etc. What makes the self-quotient image additionally attractive is that it can be computed quickly and in a closed form using simple low-level image operations. However, it is generally accepted that the self-quotient is insufficiently robust to large illumination changes which is why it is mainly used in applications in which low precision is an acceptable compromise for high recall (e.g. retrieval systems). Yet, in this paper we demonstrate that the performance of this representation in challenging illuminations has been greatly underestimated. We show that its error rate can be reduced by over an order of magnitude, without any changes to the representation itself. Rather, we focus on the manner in which the dissimilarity between two self-quotient images is computed. By modelling the dominant sources of noise affecting the representation, we propose and evaluate a series of different dissimilarity measures, the best of which reduces the initial error rate of 63.0% down to only 5.7% on the notoriously challenging YaleB data set.

In this paper we study the performance of Spiking Neural Networks (SNN)and Support Vector Machine (SVM) by using a GPU, model GeForce 6400M. Respect to applications of SNN, the methodology may be used for clustering, classification of databases, odor, speech and image recognition..In case of methodology SVM, is typically applied for clustering, regression and progression. According to particular characteristics of these methodologies,theycan be parallelizedin several grades. However, level of parallelism is limited to architecture of hardware. So, is very sure to get better results using other hardware with more computational resources. The different approaches are evaluated by the training speed and performance. On the other hand, some authors have coded algorithms SVM light, but nobody has programming QP SVM in a GPU. Algorithms were coded by authors in the hardware, like Nvidia card, FPGA or sequential circuits that depends on methodology used, to compare learning timewith between GPU and CPU. Also, in the survey we introduce a brief description of the types of ANN and its techniques of execution to be related with results of researching.

This paper addresses the task of time-separated aerial image registration. The ability to solve this problem accurately and reliably is important for a variety of subsequent image understanding applications. The principal challenge lies in the extent and nature of transient appearance variation that a land area can undergo, such as that caused by the change in illumination conditions, seasonal variations, or the occlusion by non-persistent objects (people, cars). Our work introduces several major novelties: (i) unlike previous work on aerial image registration, we approach the problem using a set-based paradigm; (ii) we show how image space local, pair-wise constraints can be used to enforce a globally good registration using a constraints graph structure; (iii) we show how a simple holistic representation derived from raw aerial images can be used as a basic building block of the constraints graph in a manner which achieves both high registration accuracy and speed; (iv) lastly, we introduce a new and, to the best of our knowledge, the only data corpus suitable for the evaluation of set-based aerial image registration algorithms. Using this data set, we demonstrate: (i) that the proposed method outperforms the state-of-the-art for pair-wise registration already, achieving greater accuracy and reliability, while at the same time reducing the computational cost of the task; and (ii) that the increase in the number of available images in a set consistently reduces the average registration error, with a major difference already for a single additional image.

The analysis of human crowds has widespread uses from law enforcement to urban engineering and traffic management. All of these require a crowd to first be detected, which is the problem addressed in this paper. Given an image, the algorithm we propose segments it into crowd and non-crowd regions. The main idea is to capture two key properties of crowds: (i) on a narrow scale, its basic element should look like a human (only weakly so, due to low resolution, occlusion, clothing variation etc.), while (ii) on a larger scale, a crowd inherently contains repetitive appearance elements. Our method exploits this by building a pyramid of sliding windows and quantifying how "crowd-like" each level of the pyramid is using an underlying statistical model based on quantized SIFT features. The two aforementioned crowd properties are captured by the resulting feature vector of window responses, describing the degree of crowd-like appearance around an image location as the surrounding spatial extent is increased.

The problem of object recognition is of immense practical importance and potential, and the last decade has witnessed a number of breakthroughs in the state of the art. Most of the past object recognition work focuses on textured objects and local appearance descriptors extracted around salient points in an image. These methods fail in the matching of smooth, untextured objects for which salient point detection does not produce robust results. The recently proposed bag of boundaries (BoB) method is the first to directly address this problem. Since the texture of smooth objects is largely uninformative, BoB focuses on describing and matching objects based on their post-segmentation boundaries. Herein we address three major weaknesses of this work. The first of these is the uniform treatment of all boundary segments. Instead, we describe a method for detecting the locations and scales of salient boundary segments. Secondly, while the BoB method uses an image based elementary descriptor (HoGs + occupancy matrix), we propose a more compact descriptor based on the local profile of boundary normals' directions. Lastly, we conduct a far more systematic evaluation, both of the bag of boundaries method and the method proposed here. Using a large public database, we demonstrate that our method exhibits greater robustness while at the same time achieving a major computational saving -- object representation is extracted from an image in only 6%  of the time needed to extract a bag of boundaries, and the storage requirement is similarly reduced to less than 8%.

Content-Based Image Retrieval (CBIR) locates, retrieves and displays images alike to one given as a query, using a set of features. It demands accessible data in medical archives and from medical equipment, to infer meaning after some processing. A problem similar in some sense to the target image can aid clinicians. CBIR complements text-based retrieval and improves evidence-based diagnosis, administration, teaching, and research in healthcare. It facilitates visual/automatic diagnosis and decision-making in real-time remote consultation/screening, store-and-forward tests, home care assistance and overall patient surveillance. Metrics help comparing visual data and improve diagnostic. Specially designed architectures can benefit from the application scenario. CBIR use calls for file storage standardization, querying procedures, efficient image transmission, realistic databases, global availability, access simplicity, and Internet-based structures. This chapter recommends important and complex aspects required to handle visual content in healthcare.

Asymmetric classification problems are characterized by class imbalance or unequal costs for different types of misclassifications. One of the main cited weaknesses of AdaBoost is its perceived inability to handle asymmetric problems. As a result, a multitude of asymmetric versions of AdaBoost have been proposed, mainly as heuristic modifications to the original algorithm. In this paper we challenge this approach and propose instead handling asymmetric tasks by properly calibrating the scores of the original AdaBoost so that they correspond to probability estimates. We then account for the asymmetry using classic decision theoretic approaches. Empirical comparisons of this approach against the most representative asymmetric Adaboost variants show that it compares favorably. Moreover, it retains the theoretical guarantees of the original AdaBoost and it can easily be adjusted to account for changes in class imbalance or costs without need for retraining.

Illumination invariance remains the most researched, yet the most challenging aspect of automatic face recognition. In this paper we propose a novel, general recognition framework for efficient matching of individual face images, sets or sequences. The framework is based on simple image processing filters that compete with unprocessed greyscale input to yield a single matching score between individuals. It is shown how the discrepancy between illumination conditions between novel input and the training data set can be estimated and used to weigh the contribution of two competing representations. We describe an extensive empirical evaluation of the proposed method on 171 individuals and over 1300 video sequences with extreme illumination, pose and head motion variation. On this challenging data set our algorithm consistently demonstrated a dramatic performance improvement over traditional filtering approaches. We demonstrate a reduction of 50-75% in recognition error rates, the best performing method-filter combination correctly recognizing 96% of the individuals.

Over the course of the last decade, infrared (IR) and particularly thermal IR imaging based face recognition has emerged as a promising complement to conventional, visible spectrum based approaches which continue to struggle when applied in the real world. While inherently insensitive to visible spectrum illumination changes, IR images introduce specific challenges of their own, most notably sensitivity to factors which affect facial heat emission patterns, e.g.\ emotional state, ambient temperature, and alcohol intake. In addition, facial expression and pose changes are more difficult to correct in IR images because they are less rich in high frequency detail which is an important cue for fitting any deformable model. In this paper we describe a novel method which addresses these major challenges. Specifically, to normalize for pose and facial expression changes we generate a synthetic frontal image of a face in a canonical, neutral facial expression from an image of the face in an arbitrary pose and facial expression. This is achieved by piecewise affine warping which follows active appearance model (AAM) fitting. This is the first publication which explores the use of an AAM on thermal IR images; we propose a pre-processing step which enhances detail in thermal images, making AAM convergence faster and more accurate. To overcome the problem of thermal IR image sensitivity to the exact pattern of facial temperature emissions we describe a representation based on reliable anatomical features. In contrast to previous approaches, our representation is not binary; rather, our method accounts for the reliability of the extracted features. This makes the proposed representation much more robust both to pose and scale changes. The effectiveness of the proposed approach is demonstrated on the largest public database of thermal IR images of faces on which it achieved 100% identification rate, significantly outperforming previously described methods.

This paper addresses the problem of tracking moving objects of variable appearance in challenging scenes rich with features and texture. Reliable tracking is of pivotal importance in surveillance applications. It is made particularly difficult by the nature of objects encountered in such scenes: these too change in appearance and scale, and are often articulated (e.g. humans). We propose a method which uses fast motion detection and segmentation as a constraint for both building appearance models and their robust propagation (matching) in time. The appearance model is based on sets of local appearances automatically clustered using spatio-kinetic similarity, and is updated with each new appearance seen. This integration of all seen appearances of a tracked object makes it extremely resilient to errors caused by occlusion and the lack of permanence of due to low data quality, appearance change or background clutter. These theoretical strengths of our algorithm are empirically demonstrated on two hour long video footage of a busy city marketplace.

The application of data mining (DM) in healthcare is increasing. Healthcare organizations generate and collect large voluminous and heterogeneous information daily and DM helps to uncover some interesting patterns, which leads to the manual tasks elimination, easy data extraction directly from records, to save lives, to reduce the cost of medical services and to enable early detection of diseases. These patterns can help healthcare specialists to make forecasts, put diagnoses, and set treatments for patients in health facilities. This work overviews DM methods and main issues. Three case studies illustrate DM in healthcare applications: (i) In-Vitro Fertilization; (ii) Content-Based Image Retrieval (CBIR); and (iii) Organ transplantation.

In contrast to most scientific disciplines, sports science research has been characterized by comparatively little effort investment in the development of relevant phenomenological models. Scarcer yet is the application of said models in the practical domain. The present paper presents a framework which allows resistance training practitioners (coaches or athletes themselves) to employ a recently proposed model of neuromuscular engagement and adaptation in actual training program design. The first novelty concerns the monitoring aspect of coaching. A method for extracting training performance characteristics from loosely constrained video sequences, effortlessly and with minimal human input, using computer vision is described. The extracted data is subsequently used to infer the value of the parameters of the underlying neuromuscular model. This is achieved by using known differential equations describing the motion of the resistance during a particular exercise, in what is usually termed the inverse dynamics problem. Lastly, a computer simulation of hypothetical training bouts, using athlete specific capability parameters, is used to predict the effected adaptation and with it the changes in performance. The software developed and for the first time described here allows the practitioner to manipulate hypothetical training parameters and immediately see their effect on predicted adaptation for a specific athlete. Thus, this work presents a holistic view of the monitoring-assessment-adjustment loop. By bridging the gap between the theoretical and applied aspects of sports science, the present contribution serves to strongly encourage a further research focus on the development of more general, comprehensive models in this field.

The objective of this work is to recognize all the frontal faces of a character in the closed world of a movie or situation comedy, given a small number of query faces. This is challenging because faces in a feature-length film are relatively uncontrolled with a wide variability of scale, pose, illumination, and expressions, and also may be partially occluded. We develop a recognition method based on a cascade of processing steps that normalize for the effects of the changing imaging environment. In particular there are three areas of novelty: (i) we suppress the background surrounding the face, enabling the maximum area of the face to be retained for recognition rather than a subset; (ii) we include a pose refinement step to optimize the registration between the test image and face exemplar; and (iii) we use robust distance to a sub-space to allow for partial occlusion and expression change. The method is applied and evaluated on several feature length films. It is demonstrated that high recall rates (over 92%) can be achieved whilst maintaining good precision (over 93%).

Classification of coins is an important but laborious aspect of numismatics - the field that studies coins and currency. It is particularly challenging in the case of ancient coins. Due to the way they were manufactured, as well as wear from use and exposure to chemicals in the soil, the same ancient coin type can exhibit great variability in appearance. We demonstrate that geometry-free models of appearance do not perform better than chance on this task and that only a small improvement is gained by previously proposed models of combined appearance and geometry. Thus, our first major contribution is a new type of feature which is efficient in terms of computational time and storage requirements, and which effectively captures geometric configurations between descriptors corresponding to local features. Our second contribution is a description of a fully automatic system based on the proposed features, which robustly localizes, segments out and classifies coins from cluttered images. We also describe a large database of ancient coins that we collected and which will be made publicly available. Finally, we report the results of empirical comparison of different coin matching techniques. The features proposed in this paper are found to greatly outperform existing methods.

本論文では，顔画像認識などで有効性が知られている相互部分空間法に混合類似度法の考えを組み込んだ混合相互部分空間法を提案する．提案法は混合類似度法において重要な役割を果たす” 差分ベクトル” を部分空間の差異を表す” 差分部分空間” に置き換えている点で，混合類似度法の自然な一般化になっている．相互部分空間法では比較すべき２つのパターン分布をそれぞれ部分空間で表し，両者のなす正準角度に基づいて識別を行うことで、パターン変形に対する高い吸収能力を実現している．しかし各クラス部分空間は各パターンを近似する点では最適になっているが，識別の観点からは必ずしも最良とは言えず，識別性能に関しては改善の余地が多分にあった．混合相互部分空間法は相互部分空間法のこの欠点を改善する方法となっている．同様の目的で提案されている制約相互部分空間法や直交相互部分空間法に比べて，誤認識し易い特定の類似パターン分布同士に対して，ピンポイントで誤識別を改善できる利点がある．提案法の有効性を公開顔画像データベースを用いて検証する．

6th International Conference on Signal Processing and Pattern Recognition (SIPR 2020) is a
forum for presenting new advances and research results in the fields of Digital Processing and
Pattern Recognition. The conference will bring together leading researchers, engineers and
scientists in the domain of interest from around the world. Authors are solicited to contribute to
the conference by submitting articles that illustrate research results, projects, surveying works
and industrial experiences

Image restoration keeping sharp edges is achieved by bilateral filter. In this paper, an approach to improve edges for the filter is presented. The proposed algorithm relies on clustering by Expectation Maximization that produced clusters of intensive values. A stage is followed where standard deviation of Gaussian filters for scales of the spatial and intensity are adjusted by features of the clusters. This makes the filters have adaptive levels of smoothing for specific clusters and helps to preserve edges while remove noise. Experiments and evaluation by PSNR metrics indicated the restoration quality enhanced and the efficacy of the proposed adaptive bilateral filter algorithm.

Notwithstanding recent work which has demonstrated the potential of using Twitter messages for content-specific data mining and analysis, the depth of such analysis is inherently limited by the scarcity of data imposed by the 140 character tweet limit. In this paper we describe a novel approach for targeted knowledge exploration which uses tweet content analysis as a preliminary step. This step is used to bootstrap more sophisticated data collection from directly related but much richer content sources. In particular we demonstrate that valuable information can be collected by following URLs included in tweets. We automatically extract content from the corresponding web pages and treating each web page as a document linked to the original tweet show how a temporal topic model based on a hierarchical Dirichlet process can be used to track the evolution of a complex topic structure of a Twitter community. Using autism-related tweets we demonstrate that our method is capable of capturing a much more meaningful picture of information exchange than user-chosen hashtags.

The hierarchical nature of bone makes it a difficult material to fully comprehend. The equine third metacarpal (MC3) bone experiences nonuniform surface strains, which are a measure of displacement induced by loads. This paper investigates the use of an artificial neural network expert system to quantify MC3 bone loading. Previous studies focused on determining the response of bone using load, bone geometry, mechanical properties, and constraints as input parameters. This is referred to as a forward problem and is generally solved using numerical techniques such as finite element analysis (FEA). Conversely, an inverse problem has to be solved to quantify load from the measurements of strain and displacement. Commercially available FEA packages, without manipulating their underlying algebraic formulae, are incapable of completing a solution to the inverse problem. In this study, an artificial neural network (ANN) was employed to quantify the load required to produce the MC3 displacement and surface strains determined experimentally. Nine hydrated MC3 bones from thoroughbred horses were loaded in compression in an MTS machine. Ex-vivo experiments measured strain readings from one three-gauge rosette and three distinct single-element gauges at different locations on the MC3 midshaft, associated displacement, and load exposure time. Horse age and bone side (left or right limb) were also recorded for each MC3 bone. This information was used to construct input variables for the ANN model. The ability of this expert system to predict the MC3 loading was investigated. The ANN prediction offered excellent reliability for the prediction of load in the MC3 bones investigated, i.e. R 2 � 0.98.

We have developed a system for automatic facial expression recognition running on Google Glass, delivering real-time social cues to children with Autism Spectrum Disorder (ASD). The system includes multiple mechanisms to engage children and their parents, who administer this technology within the home. We completed an at-home design trial with 14 families that used the learning aid over a 3-month period. We found that children with ASD generally respond well to wearing the system at home and opt for the most expressive feedback choice. We further evaluated app usage, facial engagement, and model accuracy. We found that the device can act as a powerful training aid when used periodically in the home, that interactive video content from wearable therapy sessions should be augmented with sufficient context about the content to produce long-term engagement, and that the design of wearable systems for children with ASD should be heavily dependent on the functioning level of the child. We contribute general design implications for developing wearable aids used by children with ASD and other behavioral disorders as well as their parents during at-home parent-administered therapy sessions.

In this paper we introduce two novel methods for object recognition from video. Our major contributions are (i) the use of dense, overlapping local descriptors as means of accurately capturing the appearance of generic, even untextured objects, (ii) a framework for employing such sets for recognition using video, (iii) a detailed empirical examination of different aspects of the proposed model and (iv) a comparative performance evaluation on a large object database. We describe and compare two bag-of-visual-words (BoVW)-based representations of an object’s appearance in a video sequence, one using a per-sequence bag-of-words and one using a set of per-frame bag-of-words. Empirical results demonstrate the effectiveness of both representations with a somewhat favourable performance of the former.

In spite of over two decades of intense research, illumination and pose invariance remain prohibitively challenging aspects of face recognition for most practical applications. The objective of this work is to recognize faces using video sequences both for training and recognition input, in a realistic, unconstrained setup in which lighting, pose and user motion pattern have a wide variability and face images are of low resolution. The central contribution is an illumination invariant, which we show to be suitable for recognition from video of loosely constrained head motion. In particular there are three contributions: (i) we show how a photometric model of image formation can be combined with a statistical model of generic face appearance variation to exploit the proposed invariant and generalize in the presence of extreme illumination changes; (ii) we introduce a video sequence "re-illumination" algorithm to achieve fine alignment of two video sequences; and (iii) we use the smoothness of geodesically local appearance manifold structure and a robust same-identity likelihood to achieve robustness to unseen head poses. We describe a fully automatic recognition system based on the proposed method and an extensive evaluation on 323 individuals and 1474 video sequences with extreme illumination, pose and head motion variation. Our system consistently achieved a nearly perfect recognition rate (over 99.7% on all four databases).

In this paper we are interested in analyzing behaviour in crowded public places at the level of holistic motion. Our aim is to learn, without user input, strong scene priors or labelled data, the scope of "normal behaviour" for a particular scene and thus alert to novelty in unseen footage. The first contribution is a low-level motion model based on what we term tracklet primitives, which are scene-specific elementary motions. We propose a clustering-based algorithm for tracklet estimation from local approximations to tracks of appearance features. This is followed by two methods for motion novelty inference from tracklet primitives: (a) an approach based on a non-hierarchial ensemble of Markov chains as a means of capturing behavioural characteristics at different scales, and (b) a more flexible alternative which exhibits a higher generalizing power by accounting for constraints introduced by intentionality and goal-oriented planning of human motion in a particular scene. Evaluated on a 2h long video of a busy city marketplace, both algorithms are shown to be successful at inferring unusual behaviour, the latter model achieving better performance for novelties at a larger spatial scale.

Linear subspace representations of appearance variation are pervasive in computer vision. This paper addresses the problem of robustly matching such subspaces (computing the similarity between them) when they are used to describe the scope of variations within sets of images of different (possibly greatly so) scales. A naive solution of projecting the low-scale subspace into the high-scale image space is described first and subsequently shown to be inadequate, especially at large scale discrepancies. A successful approach is proposed instead. It consists of (i) an interpolated projection of the low-scale subspace into the high-scale space, which is followed by (ii) a rotation of this initial estimate within the bounds of the imposed "downsampling constraint". The optimal rotation is found in the closed-form which best aligns the high-scale reconstruction of the low-scale subspace with the reference it is compared to. The method is evaluated on the problem of matching sets of (i) face appearances under varying illumination and (ii) object appearances under varying viewpoint, using two large data sets. In comparison to the naive matching, the proposed algorithm is shown to greatly increase the separation of between-class and within-class similarities, as well as produce far more meaningful modes of common appearance on which the match score is based.

Pattern Recognition and Classification is considered one of the most promising applications in the scientific field of Artificial Neural Networks (ANN). However, regardless of the vast scientific advances in almost every aspect of the technology and mathematics, neural networks still need to be fairly large and complex (i.e., deep), in order to provide robust results. In this article, we propose a novel ANN architecture approach that aims to combine two fairly small Neural Networks based on an introduced probability term of correct classification. Additionally, we present a second ANN, used to reclassify the potentially incorrect results by using the most probable error-free results as additional training data with the predicted labels. The proposed method achieves a rapid decrease in the mean square error compared to other large and complex ANN architectures with a similar execution time. Our approach demonstrates increased effectiveness when applied to various databases, related t...

Along time, humans organized several entities of the real world into categories, as a means to summarize and abstract their properties while avoiding an explosion of labels that would be otherwise needed to identify every possible individual entity. The task of assigning categories to given entities, often represented in terms of a set of selected features, is called pattern recognition. This work discusses the interesting relationship between feature extraction/selection and respective assignment of categories (classification), especially regarding the type of mappings required for transforming entities into feature vectors, and then mapping these vectors into categories. The current work also focuses on the implications of the fact that supervised classification relies on pre-definition of the reference categories (e.g. prototypes) obtained by previous unsupervised pattern recognition, possibly involving different sets of features that are no longer accessible.

In this paper, the detection of delaminations in carbon-fiber-reinforced-plastic (CFRP) laminate plates induced by low-velocity impacts (LVI) is investigated by means of Auto-Regressive (AR) models obtained from the time histories of the acquired responses of the composite specimens. A couple of piezoelectric patches for actuation and sensing purposes are employed. The proposed structural health monitoring (SHM) routine begins with the selection of the suitable locations of the piezoelectric transducers via the numerical analysis of the curvature mode shapes of the CFRP plates. The normalized data recorded for the undamaged plate configuration are then analyzed to obtain the most suitable AR model using five techniques based on the Akaike Information Criterion (AIC), the Akaike Final Prediction Error (FPE), the Partial Autocorrelation Function (PAF), the Root Mean Squared (RMS) of the AR residuals for different order p, and the Singular Value Decomposition (SVD). Linear Discriminant Analysis (LDA) is then applied on the AR model parameters to enhance the performance of the proposed delamination identification routine. Results show the effectiveness of the developed procedure when a reduced number of sensors is available.

Our aim is to estimate the perspective-effected geometric distortion of a scene from a video feed. In contrast to all previous work we wish to achieve this using from low-level, spatio-temporally local motion features used in commercial semi-automatic surveillance systems. We: (i) describe a dense algorithm which uses motion features to estimate the perspective distortion at each image locus and then polls all such local estimates to arrive at the globally best estimate, (ii) present an alternative coarse algorithm which subdivides the image frame into blocks, and uses motion features to derive block-specific motion characteristics and constrain the relationships between these characteristics, with the perspective estimate emerging as a result of a global optimization scheme, and (iii) report the results of an evaluation using nine large sets acquired using existing close-circuit television (CCTV) cameras. Our findings demonstrate that both of the proposed methods are successful, their accuracy matching that of human labelling using complete visual data.

This paper presents the results of a decipher historical inscriptions approach to demonstrate the application of different similarity metrics, classification and algorithm acceleration methods. Deciphering historical inscriptions is difficult in the most cases because the survived inscriptions typically contain calligraphic glyphs, grapheme errors or incomplete words. The basis of the presented methods are the geometric-topological features, which form feature vectors for each glyphs and undeciphered symbols that describes the shape of them with the numerical data. The elaborated method calculates the similarity distances of the inscriptions by the matching accuracies of the recognized graphemes through their topological feature vectors and determines the meaning of the inscription using an external dictionary of historical words. The actual version of the deciphering software is restricted for the one-word-long inscriptions. The article presents experimental results, which were pro...

The objective of this work is to authenticate individuals based on the appearance of their faces. This is a difficult pattern recognition problem because facial appearance is generally greatly affected by the changes in the way a face is illuminated, by the camera viewpoint and partial occlusions, for example due to eye-wear. We describe a fully automatic algorithm that systematically addresses each of these challenges. The main novelty is an algorithm for decision-level fusion of two types of imagery: one acquired in the visual and one acquired in infrared electromagnetic spectrum. Specifically: we examine (i) the effects of preprocessing of data in each domain, (ii) the fusion of holistic and local facial appearance, and (iii) propose an algorithm for combining the similarity scores in visual and thermal spectra in the presence of prescription glasses and significant pose variations, using a small number of training images (5-7). Our system achieved a high correct identification rate of 97% on a freely available dataset containing extreme illumination changes.

Face recognition from a single image remains an important task in many practical applications and a significant research challenge. Some of the challenges are inherent to the problem, for example due to changing lighting conditions. Others, no less significant, are of a practical nature -- face recognition algorithms cannot be assumed to operate on perfect data, but rather often on data that has already been subject to pre-processing errors (e.g. localization and registration errors). This paper introduces a novel method for face recognition that is both trained and queried using only a single image per subject. The key concept, motivated by abundant prior work on face appearance manifolds, is that of face part manifolds - it is shown that the appearance seen through a sliding window overlaid over an image of a face, traces a trajectory over a 2D manifold embedded in the image space. We present a theoretical argument for the use of this representation and demonstrate how it can be effectively exploited in the single image based recognition. It is shown that while inheriting the advantages of local feature methods, it also implicitly captures the geometric relationship between discriminative facial features and is naturally robust to face localization errors. Our theoretical arguments are verified in an experimental evaluation on the Yale Face Database.

In this paper we address the problem of matching patterns in the so-called verification setting in which a novel, query pattern is verified against a single training pattern: the decision sought is whether the two match (i.e. belong to the same class) or not. Unlike previous work which has universally focused on the development of more discriminative distance functions between patterns, here we consider the equally important and pervasive task of selecting a distance threshold which fits a particular operational requirement - specifically, the target false positive rate (FPR). First, we argue on theoretical grounds that a data-driven approach is inherently ill-conditioned when the desired FPR is low, because by the very nature of the challenge only a small portion of training data affects or is affected by the desired threshold. This leads us to propose a general, statistical model-based method instead. Our approach is based on the interpretation of an inter-pattern distance as implicitly defining a pattern embedding which approximately distributes patterns according to an isotropic multi-variate normal distribution in some space. This interpretation is then used to show that the distribution of training inter-pattern distances is the non-central chi-square distribution, differently parameterized for each class. Thus, to make the class-specific threshold choice we propose a novel analysis-by-synthesis iterative algorithm which estimates the three free parameters of the model (for each class) using task-specific constraints. The validity of the premises of our work and the effectiveness of the proposed method are demonstrated by applying the method to the task of set-based face verification on a large database of pseudo-random head motion videos.

This paper presents the results of a decipher historical inscriptions approach to demonstrate the application of different similarity metrics, classification and algorithm acceleration methods. Deciphering historical inscriptions is difficult in the most cases because the survived inscriptions typically contain calligraphic glyphs, grapheme errors or incomplete words. The basis of the presented methods are the geometric-topological features, which form feature vectors for each glyphs and undeciphered symbols that describes the shape of them with the numerical data. The elaborated method calculates the similarity distances of the inscriptions by the matching accuracies of the recognized graphemes through their topological feature vectors and determines the meaning of the inscription using an external dictionary of historical words. The actual version of the deciphering software is restricted for the one-word-long inscriptions. The article presents experimental results, which were processed on a real inscription. It demonstrates the efficiency of the methods. The deciphering software could be used for a paleographical research, especially in deciphering ancient hard to read inscriptions.

As a consequence of its close relationship with human cognition and intelligence, pattern recognition has motivated great interest in science and technology. Though emphasis is typically placed on feature selection and classification methods, the patterns to be categorized need to be generated first. In this work we discuss how better understanding about how the patterns to be recognized were originally generated can provide valuable insights about both feature selection and pattern classification. Indeed, the relationship between pattern generation and pattern recognition indicates that the latter is intrinsically related to scientific modeling, i.e. understanding how data is produced.

Deep learning consists of using typically large neuronal networks to effectively solve many classification and clustering problems. Its impressive performance derives from using many layers with many neurons, as well as considering large databases. In this text, we briefly describe and discuss in introductory fashion the principles of deep learning as well as some of the principal models. A companion tutorial in Python has been prepared in order to complement the presentation.

In this chapter we are interested in accurately recognizing human faces in the presence of
large and unpredictable illumination changes. Our aim is to do this in a setup realistic for
most practical applications, that is, without overly constraining the conditions in which image
data is acquired. Specifically, this means that people’s motion and head poses are largely
uncontrolled, the amount of available training data is limited to a single short sequence per
person, and image quality is low.
In conditions such as these, invariance to changing lighting is perhaps the most significant practical challenge for face recognition algorithms. The illumination setup in which
recognition is performed is in most cases impractical to control, its physics difficult to accurately model and face appearance differences due to changing illumination are often larger
than those differences between individuals [1]. Additionally, the nature of most real-world
applications is such that prompt, often real-time system response is needed, demanding appropriately efficient as well as robust matching algorithms.
In this chapter we describe a novel framework for rapid recognition under varying illumination, based on simple image filtering techniques. The framework is very general and we
demonstrate that it offers a dramatic performance improvement when used with a wide range
of filters and different baseline matching algorithms, without sacrificing their computational
efficiency.

Linear subspace representations of appearance variation are pervasive in computer vision. In this paper we address the problem of robustly matching them (computing the similarity between them) when they correspond to sets of images of different (possibly greatly so) scales. We show that the naïve solution of projecting the low-scale subspace into the high-scale image space is inadequate, especially at large scale discrepancies. A successful approach is proposed instead. It consists of (i) an interpolated projection of the low-scale subspace into the high-scale space, which is followed by (ii) a rotation of this initial estimate within the bounds of the imposed “downsampling constraint”. The optimal rotation is found in the closed-form which best aligns the high-scale reconstruction of the low-scale subspace with the reference it is compared to. The proposed method is evaluated on the problem of matching sets of face appearances under varying illumination. In comparison to the naïve matching, our algorithm is shown to greatly increase the separation of between-class and within-class similarities, as well as produce far more meaningful modes of common appearance on which the match score is based.