Morphological Shared-Weight Neural Network for Face Recognition

An algorithm based on morphological shared-weight neural network is introduced. Being nonlinear and translation-invariant, the MSNN can be used to create better generalization during face recognition. Feature extraction is performed on grayscale images using hit-miss transforms that are independent of gray-level shifts. The output is then learned by interacting with the classification process. The feature extraction and classification networks are trained together, allowing the MSNN to simultaneously learn feature extraction and classification for a face. For evaluation, we test for robustness under variations in gray levels and noise while varying the network's configuration to optimize recognition efficiency and processing time. Results show that the MSNN performs better for grayscale image pattern classification than ordinary neural networks.

Autorentext

Lih Chieh Png was the last batch of MSc Computation (2004) students to graduate from The University of Manchester Institute of Science and Technology (UMIST) before the merger with The University of Manchester. After graduation, he returned to Singapore and has been working at Nanyang Technological University as a research associate for six years.