Gender Recognition Using Fusion of Spatial and Temporal Features
Autor: | Suparna Biswas, Aritra Dey, Surya Kanta Ghosh, Kaushik Sett, Pritam Das, Neelanjan Saha, Prosun Ghosh |
---|---|
Rok vydání: | 2014 |
Předmět: |
Discrete wavelet transform
Fusion business.industry Feature vector Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Facial recognition system Knn classifier ComputingMethodologies_PATTERNRECOGNITION Geography Computer Science::Computer Vision and Pattern Recognition Face (geometry) Principal component analysis Computer vision Artificial intelligence business |
Zdroj: | Smart Innovation, Systems and Technologies ISBN: 9783319073521 |
DOI: | 10.1007/978-3-319-07353-8_13 |
Popis: | In the paper, a face recognition scheme has been proposed based on spatial and temporal features. As a first step, face images are preprocessed and then spatial and temporal features are extracted from the face images. Spatial features are obtained using principal component analysis (PCA) while Discrete Wavelet Transform (DWT) has been applied to extract temporal features. In this paper we investigate the recognition rate for the both spatial and temporal features using different fused rules. The feature vectors of test images are obtained and classified using KNN classifier. To evaluate the proposed scheme ORL database has been used providing accuracy better than the individual features. Experimental result shows improvement in recognition rate with respect to spatial domain recognition system. |
Databáze: | OpenAIRE |
Externí odkaz: |