We introduce an algorithm based on the morphological shared-weight neural network. 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 configuration to optimize recognition efficiency and processing time. Results show that the MSNN performs better for grayscale image pattern classification than ordinary neural networks.
One of the current approaches to vision processing, the morphological shared-weight neural network developed by Y. Won , is investigated here. Our model consists of two network stages: the first stage extracts features using morphological operations; the second stage performs classification of outputs from the last feature extraction layer.
 Y. Won et. al., Morphological Shared-Weight Networks with Applications to Automatic Target Recognition, Electronics and Telecommunications Research Institute, Daejon, South Korea, 1995.
My dissertation is also available in paperback.
Now available at Amazon:
Also available at NUS and NTU libraries in Singapore.