21 July 2017 A visual perceptual descriptor with depth feature for image retrieval
Author Affiliations +
Proceedings Volume 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017); 104201K (2017) https://doi.org/10.1117/12.2282077
Event: Ninth International Conference on Digital Image Processing (ICDIP 2017), 2017, Hong Kong, China
Abstract
This paper proposes a visual perceptual descriptor (VPD) and a new approach to extract perceptual depth feature for 2D image retrieval. VPD mimics human visual system, which can easily distinguish regions that have different textures, whereas for regions which have similar textures, color features are needed for further differentiation. We apply VPD on the gradient direction map of an image, capture texture-similar regions to generate a VPD map. We then impose the VPD map on a quantized color map and extract color features only from the overlapped regions. To reflect the nature of perceptual distance in single 2D image, we propose and extract the perceptual depth feature by computing the nuclear norm of the sparse depth map of an image. Extracted color features and the perceptual depth feature are both incorporated to a feature vector, we utilize this vector to represent an image and measure similarity. We observe that the proposed VPD + depth method achieves a promising result, and extensive experiments prove that it outperforms other typical methods on 2D image retrieval.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tianyang Wang, Tianyang Wang, Zhengrui Qin, Zhengrui Qin, } "A visual perceptual descriptor with depth feature for image retrieval", Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 104201K (21 July 2017); doi: 10.1117/12.2282077; https://doi.org/10.1117/12.2282077
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT

An approach to image clustering and retrieval
Proceedings of SPIE (April 29 2018)
Framework for image mining and retrieval
Proceedings of SPIE (June 22 2003)
WISE: a content-based Web image search engine
Proceedings of SPIE (December 21 2000)
Subjective perception of natural scenes: the role of color
Proceedings of SPIE (January 12 2003)

Back to Top