Good Recognition Rate Research Articles

Dense ResNet Based Human Action Recognition using Novel Trajectory Maps on 3D Skeletal Data

The machine learning research community is presently working on human action/activity recognition issue in real-time videos, and facing several hundreds of confronts. In this scenario, deep convolutional neural networks have initiated their powerful role in strengthen the numerous vision-based HAR systems. In recent years there has been impressive performance and great potential for imaging tasks with introducing residual connections along with a traditional CNN model in a single architecture known as the Residual Network (ResNet). In this paper we propose to use skeletal trajectory maps for the detection of human actions. A new ResNet based algorithm named dense ResNet has been proposed to perform the classification task. The trajectories of 3D joint locations are converted into color coded RGB images. These trajectory plotted images are able to capture the spatio-temporal evolutions of 3D motions from skeleton sequences and can be efficiently learned by deep learning algorithms. We then train the proposed dense ResNet to learn the features from these color coded RGB trajectory information of the human body 3D joint locations. The novelty of the proposed method is evaluated on MSR Action 3D, UTKinect-Action3D, G3D and NTU RGB-D datasets. Experimental results shows that the proposed architecture attains good recognition rates with less computation resource.

Adaptive hybrid technique for face recognition

One of the most important biometric features for personal identification is the face. In current paper, a new method of face verification upon on singular value decomposition (SVD) and standard deviation (SD) would be described. Due to many variations in real-life such as pose, illumination, or facial expression, there would be difficulty of face recognition. It should be mentioned that there are many approaches for face recognition, however, there is no one could be considered as the most suitable for many situations. One of the methods used is Singular value vector for an image detecting, but the drawback of this approach is the low rate of recognition, where one scale singular value vector is used for face acknowledgment. There an algorithm has been developed to expand the rate of the recognition. In this paper, an approach has been proposed to associate two feature sets obtained from SVD and SD method. It has noticed a good recognition rate could be obtained from the experimental results, where approximately more that 97.5% recognition rate has obtained on the ORL data base. The results from current proposed method have matched with some techniques and it has shown that this method is better than the existing approaches. An extensive experiment has demonstrated not only better performance, but it offers a great likely to achieve equivalent performance to other categories of state-of-the-art methods.

Efficient Unconstrained Iris Recognition System Based on CCT-Like Mask Filter Bank

In this paper, a new personal identification method based on unconstrained iris recognition is presented. We apply a nontraditional step for feature extraction where a new circular contourlet filter bank is used to capture the iris characteristics. This idea is based on a new geometrical image transform called the circular contourlet transform (CCT). An efficient multilevel and multidirectional contourlet decomposition method is needed to form a reduced-length quantized feature vector with improved performance. The CCT transform provides both multiscale and multioriented analysis of iris features. Circular contourlet-like mask filters can be used with shapes just like the 2D circular-support regions in different scales and directions. A reduced recognition system is realized using a single branch of the whole decomposition bank, highlighting a system realization with lower complexity and fewer computations. In the proposed recognition system, only five out of seven elements of the gray level cooccurrence matrix are required in the creation of the feature vector, which leads to a further reduction in computations. In addition, the highly discriminative frequency regions due to the use of circular-support decompositions can result in highly accurate feature vectors, reflecting good recognition rates for the proposed system. It is shown that the proposed system has encouraging performance in terms of high recognition rates and a reduced number of elements of the feature vector. This reflects reliable and rapid recognition properties. In addition, some promising characteristics of the system are apparent since it can efficiently be realized with lower computation complexity.

A reliable sense maintenance scheme by sense holes recognised and self-healing in sensor networks of internet of things

Sense holes recognised and self-healing in sensor networks have important significance for sense performance. Most of the existing researches assumed that the coordinates are known. A distributed reliable sense maintenance scheme by sense holes recognised and self-healing was presented. Firstly, it reduced the required nodes density limit to maintain reliable sense by mathematical analysis. Then, a sense holes recognised algorithm based on the Hamiltonian graph and computation geometry was proposed. It could identify triangular holes and realise a good recognition rate without nodes accurate position. Based on virtual forces strategy, a sense holes self-healing algorithm was presented. Simulation results showed the algorithm was superior to others in energy-balancing. The sense holes recognised algorithm could efficiently and quickly detect sense holes in sensor networks as shown in simulations.

Skeleton based gait recognition for long and baggy clothes

Human gait is a significant biometric feature used for the identification of people by their style of walking. Gait offers recognition from a distance at low resolution while requiring no user interaction. On the other hand, other biometrics are likely to require a certain level of interaction. In this paper, a human gait recognition method is presented to identify people who are wearing long baggy clothes like Thobe and Abaya. Microsoft Kinect sensor is used as a tool to establish a skeleton based gait database. The skeleton joint positions are obtained and used to create five different datasets. Each dataset contained different combination of joints to explore their effectiveness. An evaluation experiment was carried out with 20 walking subjects, each having 25 walking sequences in total. The results achieved good recognition rates up to 97%.

Performance Evaluation of Completed Local Ternary Pattern (CLTP) for Face Image Recognition

Feature extraction is the most important step that affects the recognition accuracy of face recognition. One of these features are the texture descriptors that are playing an important role as local features descriptor in many of the face recognition systems. Recently, many types of texture descriptors had been proposed and used for face recognition task. The Completed Local Ternary Pattern (CLTP) is one of the texture descriptors that has been proposed for texture image classification and had been tested for different image classification tasks. It proposed to overcome the Local Binary Pattern (LBP) drawbacks where the CLTP is more robust to noise as well as shown a good discriminative property than others. In this paper, a comprehensive study on the performance of the CLTP for face recognition task has been done. The aim of this study is to investigate and evaluate the CLTP performance using eight different face datasets and compared with the previous texture descriptors. In the experimental results, the CLTP had been shown good recognition rates and outperformed the other texture descriptors for this task. Several face datasets are used in this paper, such as Georgia Tech Face, Collection Facial Images, Caltech Pedestrian Faces, JAFFE, FEI, YALE, ORL, UMIST datasets.

Acoustic-Based Fault Diagnosis of Commutator Motor

In the paper, the author presents acoustic-based fault diagnosis of a commutator motor (CM). Five states of the commutator motor were considered: healthy commutator motor, commutator motor with broken rotor coil, commutator motor with shorted stator coils, commutator motor with broken tooth on sprocket, commutator motor with damaged gear train. A method of feature extraction MSAF-15-MULTIEXPANDED-8-GROUPS (Method of Selection of Amplitudes of Frequency Multiexpanded 8 Groups) was described and implemented. Classification methods, such as nearest neighbour (NN), nearest mean (NM), self-organizing map (SOM), backpropagation neural network (BNN) were used for acoustic analysis of the commutator motor. The paper provides results of acoustic analysis of the commutator motor. The results had a good recognition rate. The results of acoustic analysis were in the range of 88.4–94.6%. The NM classifier and the MSAF-15-MULTIEXPANDED-8-GROUPS provided TERCM = 94.6%.

Swallowing Sound Recognition at Home Using GMM

BackgroundAiming for autonomous living for the people after a stroke is the challenge these days especially for swallowing disorders or dysphagia. The most common cause of dysphagia is stroke. In France, stroke occurs every 4 minutes, which implies 13000 hospitalizations per year. Currently, continuous medical home monitoring of patients is not available. The patient must be hospitalized or visit the medical community for possible follow-up. It is in this context that E-SwallHome (Swallowing & Breathing: Modelling and e-Health at Home) project proposes to develop tools, from hospital care until the patient returns home, which are able to monitor in real time the process of swallowing. MethodThis paper presents a relevant health problem affecting patient recovering from stroke. We propose a frequency acoustical analysis for automatic detection of swallowing process and a non-invasive acoustic based method to differentiate between swallowing sounds and other sounds in normal ambient environment during food intake. ResultThe proposal algorithm for events detection gives a global rate of good detection of 87.31%. Classification of sounds of swallowing and other sounds based on Gaussian Mixture Models (GMM), using the leave-one-out approach according to the small amount of data in our database, gives a good recognition rate of swallowing sounds of 84.57%. ConclusionThe proposal method has great potential to assist in the clinical evaluation using only swallowing sounds, which is a non-invasive technic for swallowing studies.

EOG angle recognition based on mixed LPC and DTW

In this thesis, EOG model is divided into four groups according to different scanning Angle, which is L1, L2, R1 and R2. Feature extraction adopts mixed LPC coefficient with the EOG waveform feature. This thesis adopts DTW, SVM and BP neural network on the EOG Angle recognition, each algorithm can achieve good recognition rate, but DTW is better. This thesis also designs an application that controls cartoon character movement through eye glancing to different Angles in different directions. That app can identify the eye movement type of the current data based on the template already stored and DTW algorithm.

Sparsity Based Locality-Sensitive Discriminative Dictionary Learning for Video Semantic Analysis

Dictionary learning (DL) and sparse representation (SR) based classifiers have greatly impacted the classification performance and have had good recognition rate on image data. In video semantic analysis (VSA), the local structure of video data contains more vital discriminative information needed for classification. However, this has not been fully exploited by the current DL based approaches. Besides, similar coding findings are not being realized from video features with the same video category. Based on the issues stated afore, a novel learning algorithm, called sparsity based locality-sensitive discriminative dictionary learning (SLSDDL) for VSA is proposed in this paper. In the proposed algorithm, a discriminant loss function for the category based on sparse coding of the sparse coefficients is introduced into structure of locality-sensitive dictionary learning (LSDL) algorithm. Finally, the sparse coefficients for the testing video feature sample are solved by the optimized method of SLSDDL and the classification result for video semantic is obtained by minimizing the error between the original and reconstructed samples. The experiment results show that the proposed SLSDDL significantly improves the performance of video semantic detection compared with the comparative state-of-the-art approaches. Moreover, the robustness to various diverse environments in video is also demonstrated, which proves the universality of the novel approach.

Protein subnuclear localization based on a new effective representation and intelligent kernel linear discriminant analysis by dichotomous greedy genetic algorithm.

A wide variety of methods have been proposed in protein subnuclear localization to improve the prediction accuracy. However, one important trend of these means is to treat fusion representation by fusing multiple feature representations, of which, the fusion process takes a lot of time. In view of this, this paper novelly proposed a method by combining a new single feature representation and a new algorithm to obtain good recognition rate. Specifically, based on the position-specific scoring matrix (PSSM), we proposed a new expression, correlation position-specific scoring matrix (CoPSSM) as the protein feature representation. Based on the classic nonlinear dimension reduction algorithm, kernel linear discriminant analysis (KLDA), we added a new discriminant criterion and proposed a dichotomous greedy genetic algorithm (DGGA) to intelligently select its kernel bandwidth parameter. Two public datasets with Jackknife test and KNN classifier were used for the numerical experiments. The results showed that the overall success rate (OSR) with single representation CoPSSM is larger than that with many relevant representations. The OSR of the proposed method can reach as high as 87.444% and 90.3361% for these two datasets, respectively, outperforming many current methods. To show the generalization of the proposed algorithm, two extra standard datasets of protein subcellular were chosen to conduct the expending experiment, and the prediction accuracy by Jackknife test and Independent test is still considerable.

Neural Network based Handwritten Character Recognition system

Handwritten character recognition has been one of the active and challenging research areas in the field of image processing and pattern recognition. It has numerous applications which include, reading aid for blind, bank cheques and conversion of any hand written document into structural text form. In this paper an attempt is made to recognize handwritten characters for English alphabets without feature extraction using multilayer Feed Forward neural network. Each character data set contains 26 alphabets. Fifty different character data sets are used for training the neural network. The trained network is used for classification and recognition. In the proposed system, each character is resized into 30x20 pixels, which is directly subjected to training. That is, each resized character has 600 pixels and these pixels are taken as features for training the neural network. The results show that the proposed system yields good recognition rates which are comparable to that of feature extraction based schemes for handwritten character recognition

FEATURE EXTRACTION TECHNIQUES FOR HANDWRITTEN CHARACTER RECOGNITION

In this era of growing automation, automatic character recognition has become need of the hour. Optical character recognition (OCR) techniques allow computers to recognize handwritten characters and change them in digital format or other formats which are understandable by computers. This automatic recognition requires feature extraction from character images. Feature extraction is a very important phase of character recognition. This paper discusses features based on shapes, skeletons, image moments, image transforms, critical points, etc. This paper also investigates different types of features used in literature works. A good feature set results in good recognition rates. Thus, it is important to have knowledge of different types of features and their properties. This paper benefits its readers by providing them insight of different types of features and helps them in identifying the appropriate feature set according to their application.

Malytics: A Malware Detection Scheme

An important problem of cyber-security is malware analysis. Besides good precision and recognition rate, a malware detection scheme needs to be able to generalize well for novel malware families (a.k.a zero-day attacks). It is important that the system does not require excessive computation particularly for deployment on the mobile devices. In this paper, we propose a novel scheme to detect malware which we call Malytics. It is not dependent on any particular tool or operating system. It extracts static features of any given binary file to distinguish malware from benign. Malytics consists of three stages: feature extraction, similarity measurement and classification. The three phases are implemented by a neural network with two hidden layers and an output layer. We show feature extraction, which is performed by tf -simhashing, is equivalent to the first layer of a particular neural network. We evaluate Malytics performance on both Android and Windows platforms. Malytics outperforms a wide range of learning-based techniques and also individual state-of-the-art models on both platforms. We also show Malytics is resilient and robust in addressing zero-day malware samples. The F1-score of Malytics is 97.21% and 99.45% on Android dex file and Windows PE files respectively, in the applied datasets. The speed and efficiency of Malytics are also evaluated.

Face Recognition with Occlusion using a wireframe model and Support Vector Machine

This paper proposes a face recognition system with the capacity of achieving high recognition rates, even if the face image presents significant occlusion, using a wireframe model and a Facefit tool that acquires a coordinate system with fiducial points that characterize the facial parts. Thereby, the occlusions are emulated by the selection of points that represent four cases of partial blockage of the face such as: occlusion in eyes area, occlusion in the area of mouth and occlusion in left and right part of face in a separately way. Computer simulations show that the proposed system provides recognition rates higher than 95% in each case, providing also stability to the identification system. Thus, the wireframe model presents a robust coordinate system that even in complex cases, as data loss, is able to obtain a fairly good recognition rate.

A REVIEW ON RECOGNITION OF HANDWRITTEN URDU CHARACTERS USING NEURAL NETWORKS

Character recognition being one of the most interesting and attractive areas of pattern recognition and artificial intelligence has got additional consideration during last decade due to its wide range of applications. It contributes immensely to the computerization process and enhancing the man-machine interaction in many applications. It is an art of detecting and recognizing the characters from input image and converting them into ASCII or other corresponding machine editable form. There are four main phases of Character Recognition – Data acquisition and Preprocessing, Segmentation, Feature extraction and Classification. Several research studies have been carried out for recognition of scripts like Chinese, Japanese, English, Devanagari, etc. but the research regarding Urdu Script is still immature due to cursive, variable and overlapping nature of Urdu characters and different writing styles. Research studies on printed Urdu characters have shown good recognition rate but the Handwritten Urdu Script Recognition is still an open and challenging area for researchers. This paper presents a review of Urdu handwritten character recognition methods with special reference to neural networks and includes information regarding the various operations that may be performed on the image for the recognition of Urdu characters. In literature, it has been found that B-Spline curves are not yet applied in combination with Neural Networks for Urdu script recognition. The current research work intends to use B-Splines curves for feature extraction with Feed Forward Neural Network as classifier and focuses on isolated characters in offline domain.

Multi-objective optimization for hand posture recognition

Hand gestures are an intuitive way for humans to interact with computers. They are becoming increasingly popular in several applications, such as smart houses, games, vehicle infotainment systems, kitchens and operating theaters. An effective human–computer interaction system should aim at both good recognition accuracy and speed. This paper proposes a new approach for static hand gesture recognition. A benchmark database with 36 gestures is used, containing variations in scale, illumination and rotation. Several common image descriptors, such as Fourier, Zernike moments, pseudo-Zernike moments, Hu moments, complex moments and Gabor features are comprehensively compared in terms of their respective accuracy and speed. Gesture recognition is undertaken by a multilayer perceptron which has a flexible structure and fast recognition. In order to achieve improved accuracy and minimize computational cost, both the feature vector and the neural network are tuned by a multi-objective evolutionary algorithm based on the Nondominated Sorting Genetic Algorithm II (NSGA-II). The proposed method is compared with state-of-the-art methods. A real-time gesture recognition system based on the proposed descriptor is constructed and evaluated. Experimental results show a good recognition rate, using a descriptor with low computational cost and reduced size.

Deep Learning Approach for Devanagari Script Recognition

In this paper, we have proposed a new technique for recognition of handwritten Devanagari Script using deep learning architecture. In any OCR or classification system extracting discriminating feature is most important and crucial step for its success. Accuracy of such system often depends on the good feature representation. Deciding upon the appropriate features for classification system is highly subjective and requires lot of experience to decide proper set of features for a given classification system. For handwritten Devanagari characters it is very difficult to decide on optimal set of good feature to get good recognition rate. These methods use raw pixel values as features. Deep Learning architectures learn hierarchies of features. In this work, first image is preprocessed to remove noise, converted to binary image, resized to fixed size of 30[Formula: see text][Formula: see text][Formula: see text]40 and then convert to gray scale image using mask operation, it blurs the edges of the images. Then we learn features using an unsupervised stacked Restricted Boltzmann Machines (RBM) and use it with the deep belief network for recognition. Finally network weight parameters are fine tuned by supervised back propagation learning to improve the overall recognition performance. The proposed method has been tested on large set of handwritten numerical, character, vowel modifiers and compound characters and experimental results reveals that unsupervised method yields very good accuracy of (83.44%) and upon fine tuning of network parameters with supervised learning yields accuracy of (91.81%) which is the best results reported so far for handwritten Devanagari characters.

Remote monitoring, distress detection by slightest invasive systems: Sound recognition based on hierarchical i-vectors.

Europe has a growing aging population, leading to the need for adapted healthcare services. Our work aims at proposing a solution for falls detection of elderly people using sound recognition based on a hierarchical i-vectors system. The system presented in this paper improves significantly the accuracy of sound recognition compared to the state of the art methods. The latter provides a good recognition rate of 81.98% on noiseless sounds. This system needs to be tested in a noisy environment and this can be improved by using new sound descriptors.

Efficient Weighted Histogram Features for Single-Shot Person Re-Identification

In video surveillance, person re-identification is an important task of recognizing individuals in diverse locations over different non-overlapping camera views under the condition of large illumination variations. In order to deal with these challenges, two different and efficient color-based-methods are proposed for single-shot person re-identification in this article, which uses the Gaussian mixture model to combine with color histograms (low-level feature) and the dense salient patches (mid-level feature) as the color features. Both the two proposed systems are three-stage processes. The first stage is the image enhancement by illumination normalization, and it used to deal the intensity variations. The second stage includes pedestrian segmentation and human region partition, which separates the background (BG) and foreground (FG) and locates the body segments to improve the accuracy of feature extracting and matching. The third stage is to perform feature extracting and matching. A Gaussian mixture model is used in the first system, GMMWCH, to generate the weighted color histogram as the color features, which has a low computation time and a good recognition rate. For the second system, SaliGMMWCH, the dense correspondence is used to link the color histogram weighted by the Gaussian mixture model to find salient regions. Even though that takes more time for computation, the SaliGMMWCH retains a better recognition rate than GMMWCH. In addition, the correct match can be chosen by matching the similarity scores of different feature with an appropriate weight selection. Both the proposed methods have been tested on the benchmark, VIPeR and PRID 2011, for evaluation. The experimental results demonstrate superior recognition rate and execution performance by using the proposed methods compared to other representative methods.