RST-invariant sketch retrieval based on circular description

Abstract

The explosive growth in touchscreen smartphones and tablets need simpler and intelligent image retrieval method to offer the convenience for users. Sketch based image retrieval (SBIR) which is based on a free hand sketch has recently attracted more attention, but current methods are sensitive to rotation, scaling and translation (RST). In this paper, we introduce an efficient SBIR method called RST-Invariant Circular Description (RICD). The proposed method utilizes saliency map and boundary information to detect salient contours for each image, then uses patch hashing to eliminate the deformations and redundancies of sketches. To achieve rotational invariance, we describe salient contours using circular description. The experiment results on two public datasets demonstrated that the proposed method outperforms the state-of-the-arts in both natural and product images, and handles rotation, scaling and translation transformations.