A Neural Network Based Framework for Directional Primitive Extraction

摘要

This paper describes a computational framework for the extraction of low-level directional primitives in images. The system is divided in two stages. The first one consists of the low level directional primitive extraction, through the Gabor wavelet decomposition. The second one consists of the reduction of the high dimensionality of the Gabor decomposition results by means of auto-organised structures. The main advantages of the system introduced are two: it provides accurate and reliable information, and it produces good results on different image types without intervention of the final user. These advantages will be demonstrated by comparing our system with a classical edge detector.