In this paper, an approach for image analysis and classification is presented. It is based on a topology preserving approach to automatically create a relevance map from salient areas in natural images. It also derives a set of well-structured representations from low-level description to drive the final classification. The backbone of this approach is a distribution mapping strategy involving two basic modules: structured low-level feature extraction using convolution neural network and a topology preservation module based on a growing neural gas network. Classification is achieved by simulating the high-level topdown visual information perception in primates followed by incremental Bayesian parameter estimation. The proposed modular system architecture offers straightforward expansion to include user relevance feedback, contextual input, and multimodal information if available.
展开▼
