Jhilik Bhattacharya

Face recognition using multimodal biometric features

This paper presents a new multimodal biometric approach using face and periocular biometric. The available face recognition algorithm performance in presence of multiple variations such as illumination, pose, expression, occlusion and plastic surgery is not satisfactory. Also, periocular biometrics face problems in presence of spectacles, head angle, hair and expression. A method which can extract multiple feature information from a single source and can give a satisfactory performance even with less number of training images is desirable. Thus combining face and periocular data obtained from the same image may increase the performance of the recognition system. A detailed performance analysis of face recognition and periocular biometric using Gabor and LBP features is carried out. This is then compared with the proposed multimodal biometric feature extraction technique. The experimental results obtained using Muct and plastic surgery face database shows that the proposed multimodal biometric performs better than other face recognition and individual biometric methods.

Age Estimation Using Gender Information

Estimating age from a facial image is a intriguing and exigent task. Aging changes both shape as well as texture and it is an irreversible, uncontrollable and personalized. The way of aging in male is different from female and hence the accuracy of age estimation process can be improved if it is preceded by gender classification. The work proposed in this paper takes care of this by using gender information for categorizing age range of the given face image. Appearance parameters (AAM), containing shape and texture variations is used for gender classification which is analyzed with two well known classifiers Neural Networks and Support Vector Machines (SVM). Gender classified appearance parameters are fed into male or female age estimator. Age estimation is then performed using Neural networks which classifies age range of the given face image. Experimental results on FG-NET age database demonstrate the effectiveness of the framework and validates that performance is better than existing approaches. The results also shows that appearance parameter from AAM increases the performance of the gender classification.

Braille Character Recognition Using Generalized Feature Vector Approach

The paper uses a multi-parameter based feature detection algorithm which efficiently detects the embossed dots from a braille print.This is further utilized to make a vision based analysis of the achieved printing quality of the braille printer developed by Central Mechanical Engineering Research Institute (CMERI). A simple approach is also proposed for the recognition of the braille characters for converting them into normal text.The technique is further modified to apply it on character recognition from interpoint braille print.

Robot relay: An optimal path planning for multiple client service

Service robots are being widely implemented to provide specialized services to mankind. Their functionality are widespread among various application domains for providing services related to surveillance, vigilance, accident reporting, mechanical labor and behavior analysis. This paper presents the application of a mobile robot X80SV in a college campus. The robot equipped with a camera makes use of a pre generated map learned by the robot by integrating GPS data and motion sensor information. The map is used for navigating our robot to the desired location for multiple request servicing based on the job specified by the client. The work presents an architecture for efficient handling of the requests for an optimal order of their execution. Optimal path is calculated considering the shortest path; the request order and the processing time required in servicing the client request. The completion of services further depends upon the decision taken after processing the visual data at the end node. The proposed architecture including map based navigation, multiple service handling, optimal service processing and visual data analysis is applied to a subset of services as demonstrated in the result section of the paper. This includes physical transfer of important documents, information about particular region, calling a person and video data transfer.

Real-Time Hand Gesture Detection and Recognition for Human Computer Interaction

This paper presents a gesture based system to interface Microsoft Word document. The system was developed using a two state discrete temporal model for gestures which works with distinct poses. The model fuses the state information along with individual pose recognition to activate the interfacing mechanism. It can be inferred from the experimental results that the model facilitates both accurate gesture recognition as well as promptness in response. The decision fusion of SURF and wavelet features prove to be robust for the current model. The selected features show a 96 percent accuracy when tested with gestures having varying background, scale, transformation and illumination conditions. The response time which varies between 3 to 3.5 second can be further improved by implementing the feature detection steps in VC++ environment instead of Matlab.

Optimized virtual honeynet with implementation of host machine as honeywall

This paper proposes a methodology for the establishing a honeynet in which host machine work as honeywall and thus take advantage of underlying architecture on which they are deployed. Such setup help to minimize the CPU and RAM load for running extra virtual machine for CDROM Roo. In this implementation various types of honeypots continue to run in virtual environment using Virtual Box as in case of Generation III Virtual Honeynet. The implementation is specific to Linux based host machine having single network interface card deployed in distributed environment. Security of the host machine is of utmost important and hence special techniques are discussed to ensure its security and methods to mitigate security risk associated with host and virtual machines. Special techniques were implemented to enhance the data control and data capturing mechanisms to generate logs and securely forward to central data collection server.

The Gaussian Maxima Filter (GMF): A new approach for scale-space smoothing of an image

The detection of fine feature from an image is often challenging. Generally, the smoothing filters used for the purpose are inadequate for such applications with the exception of bilateral and mean shift filter. A new smoothing filter termed Gaussian Maxima Filter(GMF), developed and presented here shows better performance in preserving fine features even for relatively large window size. This paper also presents necessary analysis along with experimental results obtained from GMF.

Data deduplication techniques for efficient cloud storage management: a systematic review

The exponential growth of digital data in cloud storage systems is a critical issue presently as a large amount of duplicate data in the storage systems exerts an extra load on it. Deduplication is an efficient technique that has gained attention in large-scale storage systems. Deduplication eliminates redundant data, improves storage utilization and reduces storage cost. This paper presents a broad methodical literature review of existing data deduplication techniques along with various existing taxonomies of deduplication techniques that have been based on cloud data storage. Furthermore, the paper investigates deduplication techniques based on text and multimedia data along with their corresponding taxonomies as these techniques have different challenges for duplicate data detection. This research work is useful to identify deduplication techniques based on text, image and video data. It also discusses existing challenges and significant research directions in deduplication for future researchers, and article concludes with a summary of valuable suggestions for future enhancements in deduplication.

Feeding a DNN for face verification in video data acquired by a visually impaired user

Some experiments on a face verification tool based on FaceNet are presented in this paper. The task of the system is to perform face verification in a real-time assistive system aiming at facilitating the approach between a blind person and a preselected acquaintance of his/her who enters the field of view. Face detection is made easier by the fact that an almost frontal view of the face is highly probable; verification on the contrary is difficult due to the poor quality of the acquired images and to the necessity of achieving a very low error rate. A custom database consisting of subjects required for verification is populated with face images provided by a suitable detection tool. The cascade of FaceNet and a Bayesian Classifier proves to be an effective tool for this unconstrained face verification task.

Face as Bio-Metric Password for Secure ATM Transactions

Security in banking transactions is major concern. In this paper we propose a method to use face as a biometric password along with PIN number in ATM machines. For face recognition in controlled environment Wavelet, LBP and PCA are used. This can be used to perform more secure ATM transactions. Even after authorizing the access to a user the algorithm continuously monitors the user. If a user chooses to leave the ATM machine without completing his/her ongoing transaction or moves his/her head away from the camera for 10 s then his/her session will be logged out automatically and he/she will have to restart a new transaction. Our technique can easily be combined with regular ATM machines and people do not even require any further knowledge to use ATM machines. This technique can also be combined with banking websites to provide more safe and secure online transactions for online users.