Title: Curved Gabor Projection Entropy for Face Recognition
Abstract: The purpose of face recognition is to identify a person based on their face images. There are still some challenges and problems to be overcome, although several improvements have been achieved recently. These difficulties are mainly due to environment conditions, such as lighting changes, occlusion, changes in racial expressions and head position. This work presents an approach to face recognition based on combination of the curved Gabor filter, entropy and Support Vector Machine (SVM). The curved Gabor filter is used to perform the feature vector extraction of an image. Then, the results from the Gabor response curve are segmented into non-overlapping blocks to reduce interference from local variations in the image. The entropy is used to maintain the most representative image data and to provide a reduction in the feature vector. As classifier we use the SVM. A set of experiments was performed to evaluate this approach based on the characteristics of scenarios encountered in a real environment, using the AR face database. The results obtained from the experiments exceed the state-of-the-art approaches available in the literature in 4 of the 5 tests and the two additional final tests.
Publication Year: 2018
Publication Date: 2018-07-01
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
Cited By Count: 2
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot