Bhupendra Singh

Bio: Bhupendra Singh is an academic researcher from Amity University. The author has contributed to research in topics: Radiation pattern & Antenna rotator. The author has an hindex of 4, co-authored 13 publications receiving 63 citations. Previous affiliations of Bhupendra Singh include Guru Gobind Singh Indraprastha University.

Face detection by haar cascade classifier with simple and complex backgrounds images using opencv implementation

Abstract: This paper considers the problem of face detection in first attempt using haar cascade classifier from images containing simple and complex backgrounds. It is one of the best detector in terms of reliability and speed. Experiments were carried out on standard database i.e. Indian face database (IFD) and Caltech database. All images are frontal face images because side face views are harder to detect with this technique. Opencv 2.4.2 is used to implement the haar cascade classifier. We achieved 100% face detection rate on Indian database containing simple background and 93.24% detection rate on Caltech database containing complex background. Haar cascade classifier provides high accuracy even the images are highly affected by the illumination. The haar cascade classifier has shown superior performance with simple background images.

Comparison Of Feature Extraction Algorithms For Gender Classification From Face Images

Abstract: Gender Classification is the hot research topic from last two decades but still a gap exist between the requirements and actual performances. This gap lies due to the variation in pose, expression and illumination condition etc. Gender classification of face images is the process of identification of gender by their facial images. In this paper we compared the performance of two feature extraction algorithm i.e. Local binary pattern (LBP) and Histogram of oriented gradient (HOG) in order to determine the more efficient approach for gender classification from face images. Haar Cascade Classifier is used for the face detection from an image. Histogram equalization normalization technique is used for normalizing illumination effects. Support vector machine (SVM) is used as a classifier for gender classification. We implement gender classification system architecture using OpenCv 2.4.2. Indian face database (IFD) is used for the experiment . Experimental results on Indian face database show that HOG is more efficient approach for gender classification and improves gender recognition rate upto 95.56%. KeywordsGender classification, Haar cascade classifier, Histogram of oriented gradient, Local binary pattern, Support vector machine.

SRR loaded Microstrip patch antenna for Bluetooth, HIPERLAN/WLAN and WIMAX

Abstract: In this paper, A Microstrip patch antenna with multiband characteristics is demonstrated. At the first, Conventional patch antenna is made for 2.4GHz frequency. By introducing SRR (Split Ring Resonator) loaded patch, the proposed antenna works on resonant frequencies of 2.45 GHz, 3.5 GHz and 5.2 GHz. The antenna is suitable for WiMAX, HIPERLAN/WLAN and Bluetooth applications. CST Microwave Studio suit 2014 is used for simulating the proposed design. The Antenna parameters like Reflection Coefficient, VSWR, Gain, Radiation Pattern and surface current are simulated to analyze the performance of antenna.

Hardware Implementation of Viterbi Decoder for Wireless Applications

Abstract: In 2G mobile terminals, the VD consumes approximately one third of the power consumption of a baseband mobile transceiver. Thus, in 3G mobile systems, it is essential to reduce the power consumption of the VD. In this report the register exchange (RE) method, adopting a pointer concept, is used to implement the survivor memory unit (SMU) of the VD. For the implementation part, hardware implementation of MLVD through Synopsys Design Compiler Synthesis is done. For synthesis UMC-180nm Library is used.

Fusion of Domain-Specific and Trainable Features for Gender Recognition From Face Images

Abstract: The popularity and the appeal of systems which are able to automatically determine the gender from face images are growing rapidly. Such a great interest arises from the wide variety of applications, especially in the fields of retail and video surveillance. In recent years, there have been several attempts to address this challenge, but a definitive solution has not yet been found. In this paper, we propose a novel approach that fuses domain-specific and trainable features to recognize the gender from face images. In particular, we use the SURF descriptors extracted from 51 facial landmarks related to eyes, nose, and mouth as domain-dependent features, and the COSFIRE filters as trainable features. The proposed approach turns out to be very robust with respect to the well-known face variations, including different poses, expressions, and illumination conditions. It achieves state-of-the-art recognition rates on the GENDER-FERET (94.7%) and on the labeled faces in the wild (99.4%) data sets, which are two of the most popular benchmarks for gender recognition. We further evaluated the method on a new data set acquired in real scenarios, the UNISA-Public, recently made publicly available. It consists of 206 training (144 male, 62 female) and 200 test (139 male, 61 female) images that are acquired with a real-time indoor camera capturing people in regular walking motion. Such experiment has the aim to assess the capability of the algorithm to deal with face images extracted from videos, which are definitely more challenging than the still images available in the standard data sets. Also for this data set, we achieved a high recognition rate of 91.5%, that confirms the generalization capabilities of the proposed approach. Of the two types of features, the trainable COSFIRE filters are the most effective and, given their trainable character, they can be applied in any visual pattern recognition problem.

Face Detection using Haar Cascades to Filter Selfie Face Image on Instagram

Abstract: Instagram is one of the fastest growing social media in recent years. Instagram is a popular social media that is used to share images. An image search on Instagram can use a particular keyword or often called hashtag. There are no rules in giving hashtag when users upload pictures. It makes the hashtag given sometimes not related to the uploaded image. There are images whose contents are dominated by selfie face. It causes the background image or location of an image not to be conveyed entirely. The purpose of this study is to filter selfie face images on search results based on hashtags on Instagram by combining web data extraction technique and human face detection technique using the Haar Cascade method. The experiment was carried out by determining several hashtags as the basis for image search on Instagram. Experimental results show that the applied method produces an accuracy value of 71.48% for detecting human faces. According to the result of human face detection, Haar Cascade method can filter selfie face images that have an accuracy value of 64,6%. We use this assumption because basically, selfie face images contain a human face.

Gender recognition from face images with trainable COSFIRE filters

Abstract: Gender recognition from face images is an important application in the fields of security, retail advertising and marketing. We propose a novel descriptor based on COSFIRE filters for gender recognition. A COSFIRE filter is trainable, in that its selectivity is determined in an automatic configuration process that analyses a given prototype pattern of interest. We demonstrate the effectiveness of the proposed approach on a new dataset called GENDER-FERET with 474 training and 472 test samples and achieve an accuracy rate of 93.7%. It also outperforms an approach that relies on handcrafted features and an ensemble of classifiers. Furthermore, we perform another experiment by using the images of the Labeled Faces in the Wild (LFW) dataset to train our classifier and the test images of the GENDER-FERET dataset for evaluation. This experiment demonstrates the generalization ability of the proposed approach and it also outperforms two commercial libraries, namely Face++ and Luxand.

A Convolutional Neural Network for Gender Recognition Optimizing the Accuracy/Speed Tradeoff

Abstract: Gender recognition has been among the most investigated problems in the last years; although several contributions have been proposed, gender recognition in unconstrained environments is still a challenging problem and a definitive solution has not been found yet. Furthermore, Deep Convolutional Neural Networks (DCNNs) achieve very interesting performance, but they typically require a huge amount of computational resources (CPU, GPU, RAM, storage), that are not always available in real systems, due to their cost or to specific application constraints (when the application needs to be installed directly on board of low-power smart cameras, e.g. for digital signage). In the latest years the Machine Learning community developed an interest towards optimizing the efficiency of Deep Learning solutions, in order to make them portable and widespread. In this work we propose a compact DCNN architecture for Gender Recognition from face images that achieves approximately state of the art accuracy at a highly reduced computational cost (almost five times). We also perform a sensitivity analysis in order to show how some changes in the architecture of the network can influence the tradeoff between accuracy and speed. In addition, we compare our optimized architecture with popular efficient CNNs on various common benchmark dataset, widely adopted in the scientific community, namely LFW, MIVIA-Gender, IMDB-WIKI and Adience, demonstrating the effectiveness of the proposed solution.