Robust Visual Identifier for Cropped Natural Photos
The cropping of image is one of most popular functions in current image editing software for general digital camera users. And image-based identifier system is needed for wide distribution of digital image products. In this paper, we propose new concept of visual identifier for digital photos and visual identifier system structure robust against especially cropped natural photos. Visual identifier is new concept with different ground truth rather than retrieval. In the proposed identifier system, local corner is used as main co-location position and local gradient histogram is applied to describe feature in each position. And for robust matching we use simple random sample consensus method. Since image cropping can be considered as a kind of translation, linear model is sufficient as geometric transform model. For experiment we make 11 kinds of modifications of original images and evaluate performance of the proposed algorithm. From experiment results, our proposed algorithm shows better performance relative to previous MPEG-7 visual descriptors.
KeywordsGround Truth Motion Vector Query Image Similarity Match Matching Position
Unable to display preview. Download preview PDF.
- 1.ISO/MPEG N4358, Text of ISO/IEC Final Draft International Standard 15938-3 Information Technology - Multimedia Content Description Interface - Part 3 Visual, MPEG Video Group, Sydney (July 2001)Google Scholar
- 3.Oh, W.-G., Cho, I.-H., Cho, A.-Y., Kim, H.-M., Jeong, D.-S., Kim, H.-K., Heo(KT), S.-P.: Feasibility Test of MPEG-7 Visual Descriptors as a Visual Identifier Descriptor, MPEG Doc. No. M12202, Pozan (July 2005)Google Scholar
- 4.ISO/MPEG N4224, Text of ISO/IEC Final Draft International Standard 15938-4 Information Technology - Multimedia Content Description Interface - Part 4 Audio, MPEG Audio Group, Sydney (July 2001)Google Scholar
- 5.Choi, J.-G., Oh, W.-G., Cho, A.-Y., Cho, I.-H., Kim, H.-M., Jeong, D.-S., Kim, H.-K.: Proposed test conditions for MPEG-7 Visual Core Experiments 6, MPEG Doc. No. M12841, Bangkok (January 2006)Google Scholar
- 6.Harris, C., Stephens, M.: A combined corner and edge detector. In: Proc. Alvey Vision Conf. Univ, Manchester, pp. 147–151 (1988)Google Scholar