Dinesh Kumar Vishwakarma

Hybrid classifier based human activity recognition using the silhouette and cells

A new approach for the recognition of human activity using silhouette is proposed.The effectiveness of the proposed approach is measured using various classifiers.A new hybrid classification model is proposed to boost the recognition accuracy.The minimum classification error is achieved through a hybrid classification model. The aim of this paper is to present a new approach for human activity recognition in a video sequence by exploiting the key poses of the human silhouettes, and constructing a new classification model. The spatio-temporal shape variations of the human silhouettes are represented by dividing the key poses of the silhouettes into a fixed number of grids and cells, which leads to a noise free depiction. The computation of parameters of grids and cells leads to modeling of feature vectors. This computation of parameters of grids and cells is further arranged in such a manner so as to preserve the time sequence of the silhouettes. To classify, these feature vectors, a hybrid classification model is proposed based upon the comparative study of Linear Discriminant Analysis (LDA), K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM) classifier. The proposed hybrid classification model is a combination of SVM and 1-NN model and termed as SVM-NN. The effectiveness of the proposed approach of activity representation and classification model is tested over three public data sets i.e. Weizmann, KTH, and Ballet Movement. The comparative analysis shows that the proposed method is superior in terms of recognition accuracy to similar state-of-the-art methods.

Human Activity Recognition Based on Spatial Distribution of Gradients at Sublevels of Average Energy Silhouette Images

The aim of this paper is to present a unified framework for human action and activity recognition by analysing the effect of computation of spatial distribution of gradients (SDGs) on average energy silhouette images (AESIs). Based on the analysis of SDGs computation at various decomposition levels, an effective approach to compute the SDGs is developed. The AESI is constructed for the representation of the shape of action and activity and these are the reflection of 3-D pose into 2-D pose. To describe the AESIs, the SDGs at various sublevels and sum of the directional pixels (SDPs) variations is computed. The temporal content of the activity is computed through R-transform (RT). Finally, the shape computed through SDGs and SDPs, and temporal evidences through RT of the human body is fused together at the recognition stage, which results in a new powerful unified feature map model. The performance of the proposed framework is evaluated on three different publicly available datasets, i.e., Weizmann, KTH, and Ballet and the recognition accuracy is computed using hybrid classifier. The highest recognition accuracy achieved on these datasets is compared with the similar state-of-the-art techniques and demonstrate the superior performance.

A proposed unified framework for the recognition of human activity by exploiting the characteristics of action dynamics

The aim of this paper is to present a novel integrated framework for the recognition of human actions using a spatial distribution of edge gradient (SDEG) of human pose and detailed geometric orientation of a human silhouette in a video sequence. The combined descriptor endows a wealthy feature vector dictionary having both the appearance and angular kinematics information that significantly wraps the local and global information and provides discriminative depiction for the action recognition. The SDEG is computed on a still image at different levels of resolution of sub-images, and still images of the human poses are extracted from the input video sequence using fuzzy trapezoidal membership function based on the normalized histogram distance between the contiguous segment frames. The change of geometric orientation of human silhouette with time is computed using normalized R -Transform. To validate the performance of the proposed approach, extensive experiments are conducted on five publicly available human action datasets i.e. Weizmann, KTH, Ballet Movements, Multi-view i3dPost, and IXMAS. The recognition accuracy achieved on these datasets demonstrates that the proposed approach has an abundant discriminating power of recognizing the variety of actions. Moreover, the proposed approach yields superior results when compared with similar state-of-the-art methods. A combined algorithm based on shape and motion features of human activity.A single key pose is used for estimation of shape using edges.A single global key pose is extracted from video signal by exploiting local notion.The temporal motion feature is computed using R -transform.Robustness of the algorithm is demonstrated on the varied dataset.

Integrated approach for human action recognition using edge spatial distribution, direction pixel and -transform

In this article, a simple yet proficient approach for the recognition of human action and Activity is presented. This method is based on the integration of translation and rotation of the human body. The proposed framework undergoes three major steps: (i) the shape of the human action/activity is represented through the computation of average energy images using edge spatial distribution of gradients along with the directional variation of the pixel values, (ii) the orientation-based rotational information of the human action is computed through -transform and (iii) a descriptor is developed by the fusion of translational features with rotational features. The fusion of features possesses the advantages exhibited by both local and global features of the silhouette and thus provides the discriminating feature representation for human activity recognition. The performance of descriptor is evaluated through a hybrid approach of support vector machine and the nearest neighbour classifiers on standard data set. The proposed method has shown superior results in terms of recognition accuracy in comparison with other state-of-the-art methods.

Simple and intelligent system to recognize the expression of speech-disabled person

The objective of this work is to recognize 40 basic hand gestures. The main features used are centroid in the hand, presence of thumb and number of peaks in the hand gesture. The algorithm is based on the shape based features by keeping in the mind that shape of human hand is same for all human beings except in some situations. The hand gestures are captured and stored in the disk. The stored images converted into binary images and then pre-processing is performed to eliminate noise using Otsus method. The features are extracted using vision based hand gesture recognition techniques. On the basis of these features a five bit binary sequence is generated. The classification is performed by rule based classification approach. The algorithm is tested for 40 different hand gestures with the database of 200 images taken from a simple camera of 3.2 mega pixels.

Covariate Conscious Approach for Gait Recognition Based Upon Zernike Moment Invariants

Gait recognition, i.e., identification of an individual from his/her walking pattern is an emerging field. While existing gait recognition techniques perform satisfactorily in normal walking conditions, their performance tend to suffer drastically with variations in clothing and carrying conditions. In this paper, we propose a novel covariate cognizant framework to deal with the presence of such covariates. We describe gait motion by forming a single 2-D spatio-temporal template from video sequence, called average energy silhouette image (AESI). Zernike moment invariants are then computed to screen the parts of AESI infected with covariates. Following this, features are extracted from spatial distribution of oriented gradients and novel mean of directional pixels methods. The obtained features are fused together to form the final well-endowed feature set. Experimental evaluation of the proposed framework on three publicly available datasets, i.e., CASIA Dataset B, OU-ISIR Treadmill Dataset B, and USF Human-ID challenge dataset with recently published gait recognition approaches, prove its superior performance.

Proposal of a New Steganographic Approach

In the present work, an effort has been made to propose and implement a new steganographic technique for images by modifying existing algorithms. This technique uses LSB steganography as the basis and randomly disperses the secret message over the entire image to ensure that the secret message cannot be obtained easily from the image. Detailed visual and statistical analysis of the algorithm reveals that it yields satisfactory results. When compared with other existing algorithms, it is easy to prove that the difficulty of decoding the proposed algorithm is high.

An efficient interpretation of hand gestures to control smart interactive television

In the recent era of smart world, smarter technologies are gaining focus on human computer interaction (HCI) systems, and traditional ways like remote control, mouse, keyboard, etc. are becoming less popular. This paper presents a framework of simple yet efficient approach for future applications of the new age smart and intelligent technologies that shall enhance the HCI specifically for smart television. Hand gesture recognition (HGR)-based model is proposed for wireless control of smart interactive television (SITV), which includes controlling volume and selecting channels. The proposed framework undergoes three steps: 1) the hand gesture of the person is detected by using shape, colour and skin similarity; 2) the extracted features are classified by using rule-based classification and a gesture code is generated; 3) the classified gesture is interpreted by a novel interpreter. The performance of the proposed framework is evaluated with different peoples hand gestures and compared with the techniques of others.

Performance comparison of 6T SRAM cell using bulk MOSFET and double gate (DG) MOSFET

In recent technologies, device scaling leads to increase in dynamic power, sub threshold leakage, and degradation of noise margins which are vital obstacles in future generation memory circuits. This paper explores the design of a 6T cell of SRAM. A low power, large SNM 6T cell using conventional MOSFET and DG MOSFET is designed and the results of simulation using ATLAS shows that a 6T cell using DG MOSFET gives better performance compared to conventional MOSFET in terms of SNM even at low supply voltages down to 0.3V.

An Efficient Approach for the Recognition of Hand Gestures from Very Low Resolution Images

In this paper, a simple and effective approach for the recognition of hand gestures from very low resolution images is proposed. Enhancement of the low resolution images has always been the key focus in the processing of the digital images. Images with resolution as low as [50×50 pixels] are also considered for recognition. The gestures under consideration here are the number of fingers (one, two, three, four or five) raised by the person. The low resolution gesture image captured from web camera, mobile phone, or low cost cameras is processed systematically to output the number of fingers raised. Simple concepts of the geometry of the hand have been used for the recognition of hand gesture from the input low resolution images. The proposed method extracts the hand gesture directly from the low resolution image without the need of reconstruction to a high resolution image or use of any classifier. The proposed method is based on the generation of a mask for the image which is critical in the recognition of the hand gesture. This method is tested on publically available dataset of Marcel-Triesch. The high accuracy of the experimental results show the superior performance of the proposed method for the recognition of hand gesture from low resolution images.