Abstract
Images have become main sources for the informa-tion, learning, and entertainment, but due to the advancement and progress in multimedia technologies, millions of images are shared on Internet daily which can be easily duplicated and redistributed. Distribution of these duplicated and transformed images cause a lot of problems and challenges such as piracy, redundancy, and content-based image indexing and retrieval. To address these problems, copy detection system based on local features are widely used. Initially, keypoints are detected and represented by some robust descriptors. The descriptors are computed over the affine patches around the keypoints, these patches should be repeatable under photometric and geometric transformations. However, there exist two main challenges with patch based descriptors, (1) the affine patch over the keypoint can produce similar descriptors under entirely different scene or the context which causes “ambiguity”, and (2) the descriptors are not enough “distinctive” under image noise. Due to these limitations, the copy detection systems suffer in performance. We present a framework that makes descriptor more distinguishable and robust by influencing them with the texture and gradients in vicinity. The experimental evaluation on keypoints matching and image copy detection under severe transformations shows the effectiveness of the proposed framework.
Highlights
With the availability of Internet and powerful open access image editing tools, it has become so easy and convenient to edit the images and distribute to others
Image retrieval applications can be categorized into three types: near duplicate image detection, image copy detection, and similar image detection
Image copy detection and partial duplicate detection are interchangeably used [1] and this is the subset of near duplicate image detection — original image is altered with changes in color, scale, partial occlusion, rotation, etc
Summary
With the availability of Internet and powerful open access image editing tools, it has become so easy and convenient to edit the images and distribute to others. Partial image copy detection and near duplicate detection are still very challenging [1], [2]. Image retrieval applications can be categorized into three types: near duplicate image detection, image copy detection, and similar image detection. Similar image detection applications are widely used by many image search engines such as Google image. In these applications global features such as color histograms, variance, and image entropy are mostly used. We mainly focus on content-based image copy detection which comprises of image copy detection and near duplicate image detection, these applications are potentially needed for piracy, copyright violation, and efficient image searching
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
