FEATURE EXTRACTION: A NEURAL NETvVORI( ORIENTED APPROACH

Extracting features from digital images is the first goal of almost all image understanding systems. It is also difficult to solve because of the presence of noises and various photometric anomalies. Another difficulty for it is the fact that features and objects are recognized by using not only the information contained in image data but also our a priori knowledge about the semantics of the world. Thus, a feature extraction system should be robust to reduce the influence of noises and flexible to integrate different levels of knowledge for a wide range of data. In this paper, a two-stage paradigm for feature extraction is proposed, based on our conjectures about human vision ability. It includes local feature grouping and new feature describing. Based on laws of perceptual grouping and neural network modeling, we develop a novel approach for feature grouping, which finds the partion of an image into so called feature-support regions. In order to give abstract descript.ions to these regions, one needs a priori knowledge about their semantics to construct models. So we also discuss model driven methods for feature describing. To demonstrate our approach, we present its application in the limited domain of finding and describing st.raight lines in a digital image. This approach can be extended to extract other more complex symbolic image events like arcs, polylines, and polygons.