RECOGNITION OF MULTI-VIEW HUMAN FACES BASED ON MACHINE INTELLIGENCE USING KLT ALGORITHM
Journal: INTERNATIONAL JOURNAL OF RESEARCH -GRANTHAALAYAH (Vol.5, No. 3)Publication Date: 2017-03-30
Authors : Haripriya.K; Ramya Lakshmi.V.; Rajeswari.S; Rama.T; Vinothini.K.R;
Page : 123-134
Keywords : Face Recognition; Feature Extraction; KLT Algorithm; Local Binary Pattern.;
Abstract
Nowadays Image Processing has become a proficient domain due to the prolific techniques like face detection and face recognition. They play an important role in our society due to their use in wide range of applications such as surveillance, security, banking, and multimedia. One of major challenges faced in this technique of face recognition is difficulty in handling arbitrary pose variations in three dimensional representations. In video retrieval system, many approaches have been developed for recognition across pose variations and to assume the face poses to be known. These constraints made it semi-automatic. In this paper we propose a fully automatic method for multi-view face recognition of improving the accuracy or efficiency using local binary patterns. It uses tree-based data structure to create sub-grids. In this system we use KLT algorithm to detect and extract features automatically by using Eigen vectors and estimation of hessian value.
Other Latest Articles
- FINANCIAL INCLUSION AND PERFORMANCE OF MICRO, SMALL AND MEDIUM SCALE ENTERPRISES IN NIGERIA
- AGRICULTURAL REVOLUTION IN THE LINE OF HUMAN EVOLUTION IS THE ONSET OF NUTRITIONAL METABOLIC DISEASES, EPIDEMIC OF CANCER AND THE INFECTIOUS DISEASES
- THE FUNCTION OF INFORMAL GUANXI CIRCLE IN ANCIENT CHINA POLITICAL STRUCTURE
- MULTIMEDIA BASED SYSTEM FOR ‘AYURVEDA’ MEDICINE FOR THE NEXT GENERATION
- DIGITALIZATION OF EUROPE: A NEW CHALLENGE FOR EDUCATION
Last modified: 2017-08-19 16:47:21