Face Recognition based on Histogram of Oriented Gradients, Local Binary Pattern and SVM/HMM Classifiers
Journal Title: International Journal of Engineering Sciences & Research Technology - Year 30, Vol 3, Issue 8
Abstract
Face recognition is one of the challenging biometric technologies which has widespread applications in many fields such as access to security systems, identification of a person in law enforcement, identifying the culprit during riots, breach of security etc. In many of the face recognition techniques, the unique features of the face image are extracted and compared with the images of the database to produce better success rates. In this paper we take into account both shape and texture information to derive feature vector based on Histogram of Oriented Gradients (HOG) and Local Binary Pattern. In both algorithms, the face is divided into small regions and features are extracted. The performance of different algorithms with Support Vector Machine (SVM) and Hidden Markov Model (HMM) classifier are compared. It is found that the concatenation of feature vector derived from HOG and LBP with SVM as classifier has produced better result of 99.4% of recognition rate.
Authors and Affiliations
T R Chandrashekar
Nonlinear Process Identification using Neural Networks
In industry process control, the model identification of nonlinear systems are always difficult problems. The main aim of this paper is to establish a reliable model for the nonlinear process. In many applications...
Aircraft Recognition Using Template Matching In High Resolution Satellite Images
This paper proposes to recognize an aircraft in satellite image using template matching for accurate detection and tracking. High resolution multispectral satellite images with multi-angular look capability have...
MODELING & SIMULATION OF SOLID STATE TRANSFORMER
A New Model Solid State Transformer is used as a controllable bidirectional transmission device that can transfer power between asynchronous networks and functionally similar to back-to-back-HVDC.A solid-state tr...
Automated LPG Billing and Security System Using Wireless Sensor Networks
Wireless Sensor Networks are networks consisting of sensors as their main components. Sensors are arranged and connected with each other dynamically. We are implementing a system which can remotely monitor and co...
A SECURE WAY OF LOGIN WITH PERSUASIV E CUED CLICK POINTS AND PASSFACES
Text passwords are the most prevalent user authentication method, but have security and usability problems. Replacements such as biometric systems and tokens have their own drawbacks. Graphical passwor...