Image Recognition (Computer Vision)

Pengenalan Pola buku diharapkan dapat mempermudah dalam mengidentifikasi dan menginventarisasi buku.
Penelitian ini mencoba menggunakan teknik pengolahan citra dan algoritma Learning Vector Quantization
(LVQ) untuk pengenalan buku. Algoritma LVQ digunakan untuk proses pelatihan dan pengujian/pengenalan,
sementara pengolahan citra dibutuhkan pada setiap proses tersebut.
Citra yang digunakan untuk untuk pengenalan pola adalah sampul buku. Tahap-tahap pengolahan citra sebagai
berikut: Tipe File Citra JPEG dikonversi menjadi Bitmap untuk memudahkan mengakses tiap pixel citra,
mengubah citra RGB menjadi B/W agar memudahkan proses binerisasi, normalisasi dengan mengubah ukuran
citra menjadi 300X300 pixel sehingga ukuran pixel lebih kecil dan seragam, terakhir adalah proses binerisasi
yaitu mengkonversi setiap pixel citra sampul buku menjadi data biner 0 dan 1. Data biner kemudian digunakan
pada proses pelatihan dan pengujian/pengenalan LVQ.
Uji coba aplikasi menggunakan 12 buku, yang terdiri dari 2 judul buku. 2 untuk w1 dan w2, 4 untuk data
pelatihan dan 6 untuk pengujian/pengenalan. Inisialisasi LVQ menggunakan MaxEpoch=10, eps=0.001 dan
α=0.05. Hasilnya, aplikasi dapat mengenali semua buku yang diujikan.
Kata kunci : Pengolahan Citra, LVQ, Pengenalan Pola, Buku.

In the article there are presented the results of recognition of seven emotional states (neutral, joy, sadness, surprise, anger, fear, disgust) based on facial expressions. Coefficients describing elements of facial expressions, registered for six subjects, were used as features. The features have been calculated for three-dimensional face model. The classification of features were performed using k-NN classifier and MLP neural network.

The problem of recursively approximating motion resulting from the Optical Flow (OF) in video thru Total Least Squares (TLS) techniques is addressed. TLS method solves an inconsistent system Gu=z , with G and z in error due to temporal/spatial derivatives, and nonlinearity, while the Ordinary Least Squares (OLS) model has noise only in z. Sources of difficulty involve the non-stationarity of the field, the ill-posedness, and the existence of noise in the data. Three ways of applying the TLS with different noise conjectures to the end problem are observed. First, the classical TLS (cTLS) is introduced, where the entries of the error matrices of each row of the augmented matrix [G;z] have zero mean and the same standard deviation. Next, the Generalized Total Least Squares (GTLS) is defined to provide a more stable solution, but it still has some problems. The Generalized Scaled TLS (GSTLS) has G and z tainted by different sources of additive zero-mean Gaussian noise and scaling [G;z] by nonsingular D and E, that is, D[G;z]E makes the errors iid with zero mean and a diagonal covariance matrix. The scaling is computed from some knowledge on the error distribution to improve the GTLS estimate. For moderate levels of additive noise, GSTLS outperforms the OLS, and the GTLS approaches. Although any TLS variant requires more computations than the OLS, it is still applicable with proper scaling of the data matrix.

Efficient and accurate object detection has been an important topic in the advancement of computer vision systems. With the advent of machine learning and deep learning techniques, the accuracy for object detection has increased drastically. The project aims to incorporate state-of-the-art technique for object detection with the goal of achieving high accuracy with a real-time performance. In this project, we use a completely machine learning with opencv and deep learning based approach to solve the problem of object detection in an end-to-end fashion. The network is trained on the most challenging publicly available dataset, on which a object detection challenge is conducted annually. The resulting system is fast and accurate, thus aiding those applications which require object detection.

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 novelties: (i) unlike all previous work on aerial image registration, we approach the problem using a set-based paradigm; (ii) we show how 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. 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.

This study analyzes a low-cost reliable real-time optimal monitoring platform for fused filament fabrication-based open source 3-D printing. An algorithm for reconstructing 3-D images from overlapping 2-D intensity measurements with relaxed camera positioning requirements is compared with a single camera solution for single side 3-D printing monitoring. The algorithms are tested for different 3-D object geometry and filament colors. The results showed that both of the algorithms with a single and double camera system were effective at detecting a clogged nozzle, incomplete project, or loss of filament for a wide range of 3-D object geometries and filament colors. The combined approach was the most effective and achieves 100 percent detection rate for failures. The combined method analyzed here has a better detection rate and a lower cost compared to previous methods. In addition, this method is generalizable to a wide range of 3-D printer geometries, which enables further deployment of desktop 3-D printing as wasted print time and filament are reduced, thereby improving the economic advantages of distributed manufacturing.

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.

Augmented reality have undergone considerable improvement in past years. Many special techniques and hardware devices were developed, but the crucial breakthrough came with the spread of intelligent mobile phones. This enabled mass spread of augmented reality applications. However mobile devices have limited hardware capabilities, which narrows down the methods usable for scene analysis. In this article we propose an augmented reality application which is using cloud computing to enable using of more complex computational methods such as neural networks. Our goal is to create an affordable augmented reality application suitable which will help car designers in by ’virtualizing’ car modifications.

Convolutional neural network (CNN) is one of the most prominent architectures and algorithm in Deep Learning. It shows a remarkable improvement in the recognition and classification of objects. This method has also been proven to be very effective in a variety of computer vision and machine learning. As in other deep learning, however, training this approach is interesting yet challenging. Recently, some metaheuristic algorithms have been used to optimize CNN using Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing and Harmony Search. In this paper, another type of metaheuristic algorithms with different strategy has been proposed, i.e. Microcanonical Annealing to optimize Convolutional Neural Network. The performance of the proposed method is tested using the MNIST and CIFAR-10 datasets. Although experiment results of MNIST dataset indicate the increase in computation time (1.02x-1.38x), nevertheless this proposed method can considerably enhance the performance of the original CNN (up to 4.60%). On the CIFAR10 dataset, currently, state of the art is 96.53% using fractional pooling, while this proposed method achieves 99.14%.

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.

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.

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 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%).

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.

Illumination and pose invariance are the most challenging aspects of face recognition. In this paper we describe a fully automatic face recognition system that uses video information to achieve illumination and pose robustness. In the proposed method, highly nonlinear manifolds of face motion are approximated using three Gaussian pose clusters. Pose robustness is achieved by comparing the corresponding pose clusters and probabilistically combining the results to derive a measure of similarity between two manifolds. Illumination is normalized on a per-pose basis. Region-based gamma intensity correction is used to correct for coarse illumination changes, while further refinement is achieved by combining a learnt linear manifold of illumination variation with constraints on face pattern distribution, derived from video. Comparative experimental evaluation is presented and the proposed method is shown to greatly outperform state-of-the-art algorithms. Consistent recognition rates of 94-100% are achieved across dramatic changes in illumination.

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.

Logistic Regression (Preloaded Dataset) scikit-learn comes with a few small datasets that do not require to download any file from some external website. The digits dataset we will use is one of these small standard datasets. These datasets are useful to quickly illustrate the behavior of the various algorithms implemented in the scikit. They are however often too small to be representative of real world machine learning tasks. After learning the basics of logisitic regression, we will use the MNIST Handwritten digit database Each datapoint is a 8x8 image of a digit.

youtube video: https://www.youtube.com/watch?v=71iXeuKFcQM
Logistic Regression Jupyter Notebook (Digits Dataset): https://github.com/mGalarnyk/Python_Tutorials/blob/master/Sklearn/Logistic_Regression/LogisticRegression_toy_digits.ipynb
Logistic Regression Jupyter Notebook (MNIST Dataset): https://github.com/mGalarnyk/Python_Tutorials/blob/master/Sklearn/Logistic_Regression/LogisticRegression_MNIST.ipynb

The aim of this paper is to automatically identify a Roman Imperial denarius from a single query photograph of its obverse and reverse. Such functionality has the potential to contribute greatly to various national schemes which encourage laymen to report their finds to local museums. Our work introduces a series of novelties: (i) this is the first paper which describes a method for extracting the legend of an ancient coin from a photograph; (ii) we are also the first to suggest the idea and propose a method for identifying a coin using a series of carefully engineered retrievals, each harnessed for further information using visual or meta-data processing; (iii) we show how in addition to a unique standard reference number for a query coin, the proposed system can be used to extract salient coin information (issuing authority, obverse and reverse descriptions, mint date) and retrieve images of other coins of the same type.

—The paper presents an automated system for classification of fruits. A dataset containing five different fruits was constructed using an ordinary camera. All the fruits were analyzed on the basis of their color (RGB space), shape and texture and then classified using different classifiers to find the classifier that gives the best accuracy. Gray Level Co-occurance Matrix(GLCM) is used to calculate texture features .Best accuracy was achieved by support vector machine (svm). All the processing was carried out in Matlab.

Achieving illumination invariance in the presence of large pose changes remains one of the most challenging aspects of automatic face recognition from low resolution imagery. In this paper, we propose a novel recognition methodology for their robust and efficient matching. The framework is based on outputs of simple image processing filters that compete with unprocessed greyscale input to yield a single matching score between two individuals. Specifically, we show how the discrepancy of the illumination conditions between query input and training (gallery) data set can be estimated implicitly and used to weight the contributions of the two competing representations. The weighting parameters are representation-specific (i.e. filter-specific), but not gallery-specific. Thus, the computationally demanding, learning stage of our algorithm is offline-based and needs to be performed only once, making the added online overhead minimal. Finally, we describe an extensive empirical evaluation of the proposed method in both a video and still image-based setup performed on five databases, totalling 333 individuals, over 1660 video sequences and 650 still images, containing extreme variation in illumination, pose and head motion. 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 97% of the individuals.

This work is motivated by two important trends in consumer computing: (i) the growing pervasiveness of mobile computing devices, and (ii) the users' desire for increasingly complex but readily acquired and manipulated information content. Specifically, we develop and describe a system for 3D model creation of an object, using only a standard mobile device such as a smart phone. Our approach applies the structured light projection methodology and exploits multiple image input such as frames from a video sequence. In comparison with previous work, a significant further challenge addressed here is that of lower quality input data and limited hardware (processing power and memory, camera and projector quality). Novelties include: (i) a comparison of projection pattern detection approaches in the context of a mobile environment - a robust method combining colour detection and a phase congruency descriptor is proposed, (ii) a model for single view reconstruction which exploits epipolar, coplanarity and topological constraints, (iii) the use of mobile device sensor data in the iterative closest point algorithm used to register multiple partial 3D reconstructions, and (iv) two heuristics for determining the order in which buffered single view based reconstructions are merged. Our experiments demonstrate that visually appealing results are obtained in a speedy manner which does not require specialist knowledge or expertise from the user.

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.

In part one of the Critique of Judgment, Immanuel Kant wrote that "the judgment of taste . . . is not a cognitive judgment, and so not logical, but is aesthetic [1]." While the condition of aesthetic discernment has long been the subject of philosophical discourse, the role of the arbiters of that judgment has more often been assumed than
questioned. The art historian, critic, connoisseur, and curator have long held the esteemed position of the aesthetic judge, their training, instinct, and eye part of the inimitable subjective processes that Kant described as occurring upon artistic evaluation. Although the concept of intangible knowledge in regard to aesthetic theory has been much explored, little discussion has arisen in response to the development of new types of artificial intelligence as a challenge to the seemingly ineffable abilities of the human observer. This paper examines the developments in the field of computer vision analysis of paintings from canonical movements within the history of Western art and the reaction of art historians to the application of this technology in the field. Through an investigation of the ethical consequences of this innovative technology, the unquestioned authority of the art expert is challenged and the subjective nature of aesthetic judgment is brought to philosophical scrutiny once again.

In this paper we consider face recognition from sets of face images and, in particular, recognition invariance to illumination. The main contribution is an algorithm based on the novel concept of Maximally Probable Mutual Modes (MMPM). Specifically: (i) we discuss and derive a local manifold illumination invariant and (ii) show how the invariant naturally leads to a formulation of "common modes" of two face appearance distributions. Recognition is then performed by finding the most probable mode, which is shown to be an eigenvalue problem. The effectiveness of the proposed method is demonstrated empirically on a challenging database containing the total of 700 video sequences of 100 individuals.

In this paper we address the problem of matching sets of vectors embedded in the same input space. We propose an approach which is motivated by canonical correlation analysis (CCA), a statistical technique which has proven successful in a wide variety of pattern recognition problems. Like CCA when applied to the matching of sets, our extended canonical correlation analysis (E-CCA) aims to extract the most similar modes of variability within two sets. Our first major contribution is the formulation of a principled framework for robust inference of such modes from data in the presence of uncertainty associated with noise and sampling randomness. E-CCA retains the efficiency and closed form computability of CCA, but unlike it, does not possess free parameters which cannot be inferred directly from data (inherent data dimensionality, and the number of canonical correlations used for set similarity computation). Our second major contribution is to show that in contrast to CCA, E-CCA is readily adapted to match sets in a discriminative learning scheme which we call discriminative extended canonical correlation analysis (DE-CCA). Theoretical contributions of this paper are followed by an empirical evaluation of its premises on the task of face recognition from sets of rasterized appearance images. The results demonstrate that our approach, E-CCA, already outperforms both CCA and its quasi-discriminative counterpart constrained CCA (C-CCA), for all values of their free parameters. An even greater improvement is achieved with the discriminative variant, DE-CCA.

The paper explains the development of a classification program which is to be integrated to a robot that will autonomously play chess. The problem is to perform a classification on a 12 class data set of chess pieces which works on a real-time video feed. Various approaches have been discussed for the problem; finally Convolutional Neural
Network was chosen to develop the solution.

The paper develops two different approaches to solve the problem. One approach uses a single Convolutional Neural Network for classification. The other divides the problem into two classification task, classifying of the chess piece color and classifying the chess piece based on shape. The models developed from both the approaches are compared based on accuracy and computational time.

Cross validation was used to ensure the classification accuracy results are repeatable. To understand the accuracy in classifying each class, a confusion matrix was generated and the important features were visualized to understand the learnt features. The computation time for all the function calls on the program were measured and the average was calculated. Finally, the robustness of the 1-Step model to the change in object size was experimentally determined.

The thesis concentrates on computational methods pertaining to ancient ostraca - ink on clay inscriptions, written in Hebrew. These texts originate from the biblical kingdoms of Israel and Judah, and dated to the late First Temple period (8th – early 6th centuries BCE). The ostraca are almost the sole remaining epigraphic evidence from the First Temple period and are therefore important for archaeological, historical, linguistic, and religious studies of this era. This “noisy” material offers a fertile ground for the development of various “robust” image analysis, image processing, computer vision and machine learning methods, dealing with the challenging domain of ancient documents’ analysis. The common procedures of modern epigraphers involve manual and labor-intensive steps, facing the risk of unintentionally mixing documentation with interpretation. Therefore, the main goal of this study is establishing a computerized paleographic framework for handling First Temple period epigraphic material. The major research questions, addressed in this thesis are: quality evaluation of manual facsimiles; quality evaluation of ostraca images; automatic binarization of the documents and its subsequent refinement; quality evaluation of binarizations on global and local levels; identification of different writers between inscriptions (two distinct methods are proposed); image segmentation (with improvements over the classical Chan-Vese algorithm); and letters’ shape prior estimation. The developed methods were tested on real-world archaeological and modern data and their results are found to be favorable.

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.

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).

Diabetes affects a lot of people everywhere, and has associated complications such as vision loss, heart failure and stroke. Among a group of 100 patients with diabetes, 10 people would likely have diabetes-related eye problems. An ophthalmologist (eye doctor) would have to check the eyes of all 100 patients periodically to find out who had problems. The proposed system tend to analysis the retina fundus images for early detect of any sign related to eyes problems due to diabetic. The image analysis system is broken down into a number of modules which sequentially process the input image to extract information at different levels. These modules included detection the exudates and hemorrhage, blood vessel touristy measure, blood vessel diameter, and each of these modules may need another steps for analyzing of image. The results were highly promised and the percentage of early detection for normal and abnormal retina was 100%.

Our aim in this paper is to robustly match frontal faces in the presence of extreme illumination changes, using only a single training image per person and a single probe image. In the illumination conditions we consider, which include those with the dominant light source placed behind and to the side of the user, directly above and pointing downwards or indeed below and pointing upwards, this is a most challenging problem. The presence of sharp cast shadows, large poorly illuminated regions of the face, quantum and quantization noise and other nuisance effects, makes it difficult to extract a sufficiently discriminative yet robust representation. We introduce a representation which is based on image gradient directions near robust edges which correspond to characteristic facial features. Robust edges are extracted using a cascade of processing steps, each of which seeks to harness further discriminative information or normalize for a particular source of extra-personal appearance variability. The proposed representation was evaluated on the extremely difficult YaleB data set. Unlike most of the previous work we include all available illuminations, perform training using a single image per person and match these also to a single probe image. In this challenging evaluation setup, the proposed gradient edge map achieved 0.8% error rate, demonstrating a nearly perfect receiver-operator characteristic curve behaviour. This is by far the best performance achieved in this setup reported in the literature, the best performing methods previously proposed attaining error rates of approximately 6-7%.

This paper proposes COCOCLUST, a contour-based color clustering method which robustly segments and binarizes colored text from complex images. Rather than operating on the entire image, a ‘small’ representative set of color pixels is first identified using the contour information. The method involves the following steps: (i) identification of prototype colors (ii) a one-pass algorithm to identify color clusters that serve as seeds for the refining step using k-means clustering (iii) assignment of pixels in the original image to the nearest color cluster (iv) identification of potential candidate text regions in individual color layer and (v) adaptive binarization. We propose a robust binarization technique to threshold the identified text regions, taking into account the presence of inverse texts, such that the output image always has black text on a white background. Experiments on several complex images having large variations in font, size, color, orientation and script illustrate the robustness of the method.

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.