International Journal of Advanced Research in Computer Engineering & Technology
In this paper, the focus is on the investigation of face recognition using morphological shared-weight neural network. Being nonlinear and translation-invariant, the MSNN can be used to create better generalization during face recognition. The MSNN is a heterogeneous network that produces high order features based on local features extracted by morphological operations. 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.