作者: Azhar Quddus , Moncef Gabbouj
DOI: 10.1016/S0167-8655(01)00090-3
关键词:
摘要: In this paper we present a novel technique for wavelet-based corner detection using singular value decomposition (SVD). Here SVD facilitates the selection of global natural scale in discrete wavelet transform. We define as level associated with most prominent (dominant) eigenvalue. Eigenvector corresponding to dominant eigenvalue is considered optimal scale. The corners are detected at locations modulus maxima. Results indicate suitability approach. Comparison recently proposed also provided.