A novel approach for salient image regions detection and description

This paper proposes a new algorithm for visual landmarks detection and description. The detection is achieved using a hierarchical grouping mechanism, which combines a color contrast measure defined between regions with internal region descriptors and with attributes of the shared boundary. This detector reliably finds the same salient regions under different viewing conditions. Then, geometrically and photometrically normalized regions are characterized by a kernel-based descriptor. This descriptor is rotation-invariant and robust against noise. Several tests are conducted in order to compare the proposed approach with other similar approaches. Experimental results prove that the performance of our proposal is high in terms of computational consuming and visual landmark detection and description abilities.