Lbp

Automatic facial expression recognition has become a progressive research area since it plays a major role in human computer interaction. The facial expression recognition finds its major application in areas like social interaction and social intelligence. However it is not an easy task because the facial image, facial occlusion, face color/shape etc. is not easy to deal with. In this paper, various techniques for feature extraction like Gabor filters, Principal Component Analysis (PCA), Local Binary Patterns (LBP), Linear Discriminant Analysis (LDA), DCT, with different classifiers like Support Vector Machine (SVM) and Neural Networks, which are used to recognize human expression in various conditions on different databases are being examined.

Fruit disease cause a calamitous problem and results in economic and agricultural industry loss. Earlier detection of infected fruit had done manually but now with the advancement in technology image processing techniques was developed. There are two phases; first is for training and the other is for testing. In training phases, all the data related to the infected and non-infected fruit is stored and in testing phase, it is analyzed that whether the fruit is infected or not and if yes then by which disease. In this paper, the different existing techniques used to detect the infected fruit are discussed. These techniques are proved to be beneficial for the farmers as they help in detection of fruit disease in early stages.

Automatic facial expression recognition is still a hard research area with several challenges to meet. Efficient facial expression recognition system is developed to recognize the facial expressions even when the face is slightly tilted. Applications of facial expression recognition system include border security systems, forensics, virtual reality, computer games, robotics, machine vision, video conferencing, user profiling for customer satisfaction, broadcasting and web services. Initially the face localization is done using the viola jones face detector. The facial components are extracted if the facial components are properly detected and the features are extracted from the whole face if the facial components are not detected. The extracted facial features are represented by three features vectors: the Zernike moments, LBP features and DCT transform components. In order to reduce the dimensionality, a subset feature selection algorithm is used prior to training process. The paper presents a comparison between the PCA based method and Normalized mutual information selection method for reducing the dimensionality. The feature vectors are combined and reduced and then applied to SVM classifier for training process. Experiment results shows that the proposed methodology affirms a good performance in facial expression recognition.

In this paper we develop a novel MRF formulation for calculating sparse features correspondence in image pairs. Our MRF terms can include cliques of variable sizes, and solve these using Loopy Belief Propagation. To calculate our MRF topology we develop a variant of the K-means algorithm which we call the KN-means algorithm (where each mean has a specified number of neighbours). The method is compared to other state of the art sparse feature correspondence algorithms and shown to compare well, es-pecially for less dense feature sets. Outliers are handled naturally within this paradigm.

Buildings are termed as important components for various applications. Building extraction is defined as a sub-problem of Object Recognition. Though, numerous building extraction techniques have been proposed in the literature. But still they often exhibit limited success in the real scenarios. The main purpose of this research is to develop an algorithm which is able to detect and extract buildings from satellite images. In the proposed approach feature-based extraction process is used to extract buildings from satellite images. The overall system is tested and high performance detection is achieved which shows the effectiveness of proposed approach. Index Terms-building extraction, artificial neural networks, Hough Transform, LBP.

Glaucoma is an unending eye ailment which prompts vision misfortune(loss). It is a quiet theft of sight.currently manual evaluation of optic disk and cup is a standard procedure which has its own drawbacks for mass screening Early discovery of glaucoma can possibly lessen the danger of visual deficiency. Nonetheless numerous patients are ignorant of the ailment, since it advances gradually without effortlessly detectable indications. In late studies, there is no viable technique for minimal effort populace based glaucoma recognition or screening. In this work, the propose strategy is cup to disk proportion (CDR) evaluation, utilizing 2-D retinal fundus pictures. In the first place, the picture is pre-prepared by changing over the picture into HSI and applying the channel. Taken after by, the optic plate is initially divided and reproduced utilizing a novel scanty uniqueness obliged coding (SDC) approach. Considers both the difference imperative and the sparsity requirement from an arrangement of reference circle with known CDRs. In this way, the reproduction coefficients from the SDC are used to register the CDR for the testing circle.

This paper presents a novel approach for real time face detection using heterogeneous computing. The algorithm uses local binary pattern (LBP) as feature vector for face detection. OpenCL is used to accelerate the code using GPU[1]. Illuminance invariance is achieved using gamma correction and Difference of Gaussian(DOG) to make the algorithm robust against varying lighting conditions. This implementation is compared with previous parallel implementation and is found to perform faster.

Estimating the age into different categories i.e. 1. Childhood (0-12 years) 2. Young Age (13-25years) 3. Middle age (26-40years) 4. Senior age (40-60years) 5.Senior Citizens(more than 60 years) using fuzzy model is a challenging task for researchers .There are many classifiers to classify the data into different age groups. In our proposed method age is classified into different age groups based on the transition count of Local Binary Patterns for Left angular pattern and Right angular pattern. Age Estimation is essential in many applications like where there is no entry for the people whose age is less than particular age, biometrics, crime detection and so on

This work focuses on the obstacle detection and face detection which helps for blind person in day-today activities. Raspberry pi is used for interface powered by MATLAB. It helps in recognizing usual objects around the person. Addition to that, it also helps in finding the known person approaching the user. Portable power supply keeps the hardware running throughout the day and the power bank can be recharged. Hence the power consumption is low. I. INTRODUCTION Over 37 million people across the globe are visually impaired, among which one in three of them is an Indian, visually impaired people feel difficult to identify objects and reduces their activities in several fields like, while working in office difficult to identify things. The main aim of the project is to detect obstacles and recognize faces which would help them to do their daily work easier and smoother without any disturbances. The rest of the paper is organized as follows: Section II discusses the components used for face detection and obstacle detection. The Literature review is discussed in Section III. Section IV contains proposed system. Section V includes Testing, Results and future work.

Face recognition is for recognizing human faces from single images out of a large database. The task is difficult because of image variation in terms of position, size, expression, and pose and it is important because this uses in different areas such as surveillance at airports, border crossings, security systems etc. There are two underlying motivations for us to write this survey paper: the first is to provide an up-to-date review of the existing literature, and the second is to offer some insights into the studies of machine recognition of faces. There are many methods exist to perform face detection, on this, Some use flesh tones, some use contours, and other are even more complex involving templates, neural networks, or filters. This all methods generally utilize 2D images for feature extraction and matching. Nowadays some of the algorithms make use of 3D images for the same. It will give more accurate and higher resilience towards covariates, such as expression, illumination and pose variations. But it is challenging because of the high cost of 3D sensors. RGB-D face recognition is introduced to reduce this problem of high cost of 3D sensors, which makes use of the features of both original image and depth image for the face recognition. This survey focuses on different 2D or 3D or combination of both face recognition techniques under different covariates, such as illuminations, expressions, noise, disguised conditions and different pose variations.

Pedestrian Detection is of interest in many computer vision applications such as intelligent transportation systems and human-robot interaction; among the existing methods, the combination of shape feature (i.e. Histogram of Oriented Gradients (HOG)) and texture features (i.e. Local Binary Pattern (LBP)) has shown promising results in detection accuracy, but it is limited due to computation cost. In this paper, we introduce a new pedestrian detection algorithm with fast computation of these features on GPU. We propose a robust and rapid pedestrian detector by combining the HOG with LBP, as the feature set and corresponding Support Vector Machine (SVM) classifiers. Also, we use the integral image method and an efficient parallel implementation to reduce detection time. We can achieve a more than 10× speed up, and 7% increase in detection rate.

In this work, we define a new method for indexing and retrieving non-geotagged video sequences based on the visual content only by using the Local Binary Pattern (LBP) and Singular Value Decomposition (SVD) techniques. The main question of our system, Is it possible to determine the geographic location of a video film on the GIS-map from just its pixels of frames?. The proposed system is introduced to answer the questions like that. The GIS database was constructed by storing the reference images on the intersection between segment roads in the map. The Local Binary Pattern (LBP) is used to extract the features form images. The Singular Value Decomposition (SVD) technique is used for compress the length of features and indexing the images in the database. The input to the system is a video taken from the camera puts on a vehicle as forward facing camera. The output of the proposed system is the geo-location of keyframes of video which correspond the geo-tagged images retrieved from the GIS database.

In this work, we define a new method for indexing and retrieving non-geotagged video sequences based on the visual content only by using the Local Binary Pattern (LBP) and Singular Value Decomposition (SVD) techniques. The main question of our system, Is it possible to determine the geographic location of a video film on the GIS-map from just its pixels of frames?. The proposed system is introduced to answer the questions like that. The GIS database was constructed by storing the reference images on the intersection between segment roads in the map. The Local Binary Pattern (LBP) is used to extract the features form images. The Singular Value Decomposition (SVD) technique is used for compress the length of features and indexing the images in the database. The input to the system is a video taken from the camera puts on a vehicle as forward facing camera. The output of the proposed system is the geo-location of keyframes of video which correspond the geo-tagged images retrieved from the GIS database.

In the proposed work, classification of diseased and undiseased arecanut have been determined using texture features of Local Binary Pattern (LBP), Haar Wavelets, GLCM and Gabor. This work has been carried out in two stages. In the first stage, LBP have been applied on each color component of HSI and YCbCr color models and histogram of LBP is generated. The statistical method correlation is used to measure the distance between histogram of training set and query sample and obtained a success rate of 92.00%. We have not achieved better results in the first stage. In the second stage, texture features of Haar wavelets, GLCM and Gabor have been used. In this stage, RGB input arecanut image is transformed to HSI and YCbCr color models and texture features are extracted from each color component. Subset of texture features with high degree of discrimination power has been identified empirically based on combination of texture features. The kNN classifier gave a success rate of 100% for d...

— In this paper, an efficient approach for glaucomatous image classification system using fundus images is proposed. The main aim of this study is to detect glaucoma accurately in order to reduce the visual loss and impairment. The proposed system uses two important texture features; Gray Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP) in an efficient manner. These texture features are extracted not only from the fundus image but also the optical density image obtained from the fundus image. Before extracting features, region of interest is obtained from the Green channel of the fundus image as it has high contrast than other two colour components. Support Vector Machine (SVM) classifier is used for the classification of fundus image into normal or abnormal based on the extracted features. Results show that the proposed system provides promising results with 100% sensitivity and 99% specificity.

Eyebrow is one of the most salient features. It has a lot of potential application in face recognition, non verbal communication and revelation of emotions. This paper presents an human eyebrow recognition system based on fast template matching and fourier spectrum distance (FSD). Normalized Cross Correlation (NCC) is used for matching similarity in fast template matching. The features are extracted by using the Local Binary Pattern(LBP). Various distance measures like manhattan distance, Euclidean distance, mahalanobis distance were used and Euclidean distance performed the best by recognizing human eyebrows with an accuracy of 92%.

This paper presents a real-time face recognition system using kinect sensor. The algorithm is implemented on GPU using opencl and significant speed improvements are observed. We use kinect depth image to increase the robustness and reduce computational cost of conventional LBP based face recognition. The main objective of this paper was to perform robust, high speed fusion based face recognition and tracking. The algorithm is mainly composed of three steps. First step is to detect all faces in the video using viola jones algorithm. The second step is online database generation using a tracking window on the face. A modified LBP feature vector is calculated using fusion information from depth and greyscale image on GPU. This feature vector is used to train a svm classifier. Third step involves recognition of multiple faces based on our modified feature vector.

The system is designed to determine the visage expressions such as vigor and grain skin and to apply feature extraction methods for feeling recognition. All the three dimensional input images are converted into vigor and grain images to represent in two dimensional image like structure that helps to easily perform manipulation on the images. The texture features helps to retrieve the color components from a texture coordinates such as RGB components and that helps to generate the texture images for a three dimensional image. In the texture images, the facial regions are identified through Viola Jones technique. The dif erent region of interest is eye, nose and mouth. The coarse region of interest is extracted to reduce the time complexity for finding the entire region of interest as well as the false detection rate, and they are called as salient facial patches and they are located based on the position of facial landmarks. The active facial patches are positioned below the eyes, in between eye brows, around the nose and mouth corners. Feature extraction is done by Local Binary Pattern (LBP) algorithm. Principal Component Analysis (PCA) is a feature selection technique which is used to select the relevant features from the vigor and range images and then they are classified by Multi class Support Vector Machine (SVM) algorithm

Leukemia is a group of cancers that usually begins in the marrow and results in high numbers of abnormal white blood cells. The bone marrow produces the cellular elements of the blood, including platelets, red blood cells and white blood cells. The differences between these groups lie on the texture, color, size and morphology of nucleus and cytoplasm. These white blood cells are not fully developed and are called blasts or leukemia cells. Image processing technique involved five basic components which are image acquisition, image pre-processing, image segmentation, feature extraction and classification. The proposed system firstly individuates in the blood image the leucocytes from the others blood cells, then it selects the lymphocyte cells, it evaluates morphological indexes from those cells and finally it classifies the presence of the leukemia. Discriminative Robust LBP is used for feature extraction. They alleviate the intensity reversal problem of object and background. Our proposed feature is tested on ALL IDB dataset and obtained 89 % accuracy.