Phalguni Gupta

Bio: Phalguni Gupta is an academic researcher from GLA University. The author has contributed to research in topics: Biometrics & Facial recognition system. The author has an hindex of 31, co-authored 327 publications receiving 4095 citations. Previous affiliations of Phalguni Gupta include Indian Institutes of Technology & Indian Institute of Technology Kanpur.

ECG to Individual Identification

Abstract: This paper presents an individual identification system using single lead electrocardiogram (ECG). The proposed techniques for P and T wave delineation are based on time derivative and adaptive thresholding. The performance of proposed delineators is evaluated on manually annotated Physionet QT database. The accuracy of delineators are quantified on mean error and standard deviation of differences between manually annotations and automated results. Especially, lower values of error in standard deviation for onset and offset of P wave fiducials are obtained as 8.1 and 6.29 while for T wave fiducials are 9.4 and 11.2 (where units are in ms). It shows the performance of P and T wave delineators is optimum and also stable in comparison to other published results. Found fiducials are processed for the extraction of heartbeat features. From each heartbeat, 19 stable features related to interval, amplitude and angle are computed. The feasibility of ECG as a new biometric is tested on proposed identification system designed on template matching and adaptive thresholding. The accuracy of identification system is achieved to 99% on the datasize of 125 recordings prepared from 25 individual ECG of Physionet.

An accurate finger vein based verification system

Abstract: This paper makes use of finger vein to propose an accurate personal authentication system. A matched filtering at various scales is applied on the vein image to reduce the effects of noise occurred due to non-uniform illumination, low local contrast, hairs and skin texture. Vein image is also enhanced by using global characteristics. Local and global characteristics of enhanced vein images are fused to obtain accurate vein pattern. Extracted veins are used for matching such that the problem of geometric deformations can be handled efficiently. For performance evaluation, a publicly available database of 3132 unconstrained finger vein images acquired from 156 subjects is used. Performance of the proposed system is found to be better than the various existing systems.

Edge-based image steganography

Abstract: This paper proposes a novel steganography technique, where edges in the cover image have been used to embed messages. Amount of data to be embedded plays an important role on the selection of edges, i.e., the more the amount of data to be embedded, larger the use of weaker edges for embedding. Experimental results have shown that the proposed technique performs better or at least at par with the state-of-the-art steganography techniques but provides higher embedding capacity.

Identification of parameters and restoration of motion blurred images

Abstract: This paper proposes a technique for restoring the motion blurred images. Restoration of blurred images is very important problem in tracking and identification of criminals, where image of a human face or number plate of a running vehicle taken in hit and run situation gets blurred due to relative motion between the imaging system and object/face. For restoration of motion blurred images, knowledge of the point spread function (PSF) is very important. The motion blur PSF is characterized by two parameters, namely blur direction and blur length. This paper also presents a method to identify the parameters of the PSF from the blurred and noisy images using the log spectrum of the blurred images. These parameters are used to restore the images. The experimental results demonstrate that the image can successfully be restored from the image with substantial amount of natural and artificial blur.

An efficient ear recognition technique invariant to illumination and pose

Abstract: This paper presents an efficient ear recognition technique which derives benefits from the local features of the ear and attempt to handle the problems due to pose, poor contrast, change in illumination and lack of registration. It uses (1) three image enhancement techniques in parallel to neutralize the effect of poor contrast, noise and illumination, (2) a local feature extraction technique (SURF) on enhanced images to minimize the effect of pose variations and poor image registration. SURF feature extraction is carried out on enhanced images to obtain three sets of local features, one for each enhanced image. Three nearest neighbor classifiers are trained on these three sets of features. Matching scores generated by all three classifiers are fused for final decision. The technique has been evaluated on two public databases, namely IIT Kanpur ear database and University of Notre Dame ear database (Collections E). Experimental results confirm that the use of proposed fusion significantly improves the recognition accuracy.

The Whale Optimization Algorithm

Abstract: The Whale Optimization Algorithm inspired by humpback whales is proposed.The WOA algorithm is benchmarked on 29 well-known test functions.The results on the unimodal functions show the superior exploitation of WOA.The exploration ability of WOA is confirmed by the results on multimodal functions.The results on structural design problems confirm the performance of WOA in practice. This paper proposes a novel nature-inspired meta-heuristic optimization algorithm, called Whale Optimization Algorithm (WOA), which mimics the social behavior of humpback whales. The algorithm is inspired by the bubble-net hunting strategy. WOA is tested with 29 mathematical optimization problems and 6 structural design problems. Optimization results prove that the WOA algorithm is very competitive compared to the state-of-art meta-heuristic algorithms as well as conventional methods. The source codes of the WOA algorithm are publicly available at http://www.alimirjalili.com/WOA.html

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Abstract: From the Publisher: The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.