Face Recognition with Facial Occlusion Based on Local Cycle Graph Structure Operator
Authors:
- Jucheng YangJYJucheng Yang
- Lingchao ZhangLZLingchao Zhang
- Meng LiMLMeng Li
- Tingting ZhaoTZTingting Zhao
- Yarui ChenYCYarui Chen
- Jianzheng LiuJLJianzheng Liu
- Na LiuNLNa Liu
Open Access
- 29 August 2018
- book chapter
- Published by IntechOpen
Abstract
Facial occlusion is a difficulty in the field of face recognition. The lack of features caused by occlusion may reduce the face recognition rate greatly. How to extract the identified features from the occluded faces has a profound effect on face recognition. This chapter presents a Local Cycle Graph Structure (LCGS) operator, which makes full use of the information of the pixels around the target pixel with its neighborhood of 3 × 3. Thus, the recognition with the extracted features is more efficient. We apply the extreme learning machine (ELM) classifier to train and test the features extracted by LCGS algorithm. In the experiment, we use the olivetti research laboratory (ORL) database to simulate occlusion randomly and use the AR database for physical occlusion. Physical coverings include scarves and sunglasses. Experimental results demonstrate that our algorithm yields a state-of-the-art performance.Keywords
This publication has 12 references indexed in Scilit:
- A novel fusion method of PCA and LDP for facial expression feature extractionOptik, 2016
- Face recognition with Symmetric Local Graph Structure (SLGS)Expert Systems with Applications, 2014
- Human Identification Using Finger ImagesIEEE Transactions on Image Processing, 2011
- Face recognition based on extreme learning machineNeurocomputing, 2011
- Face Recognition Using Local Graph Structure (LGS)2011
- Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting ConditionsIEEE Transactions on Image Processing, 2010
- Performance evaluation of texture measures with classification based on Kullback discrimination of distributions2002
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- A direct LDA algorithm for high-dimensional data — with application to face recognitionPattern Recognition, 2001
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991