Many applications dealing with image management need a technique for removing duplicate images or for grouping related (near-duplicate) images in a database. This paper proposes a concentric circle-based image signature which makes it possible to detect near-duplicates rapidly and accurately. An image is partitioned by radius and angle levels from the center of the image. Feature values are calculated using the average or variation between the partitioned sub-regions. The feature values distributed in sequence are formed into an image signature by hash generation. The hashing facilitates storage space reduction and fast matching. The performance was evaluated through discriminability and robustness tests. Using these tests, the particularity among the different images and the invariability among the modified images are verified, respectively. In addition, we also measured the discriminability and robustness by the distribution analysis of the hashed bits. The proposed method is robust to various modifications, as shown by its average detection rate of 98.99%. The experimental results showed that the proposed method is suitable for near-duplicate detection in large databases.

Concentric Circle-Based Image Signature for Near-Duplicate Detection in Large Databases

Image replica detection system can be used by the owners of digital multimedia content to protect their rights against unauthorised use of their material. The paper presents a new approach for content-based image replica detection. A concept of singular energy trajectory is introduced and evaluated. It appears that this trajectory is invariant to many image operations. Moreover, the trajectories of original images and distorted copies are highly correlated. These properties make the proposed method a good tool for image replica detection.

Trajectory of singular energies for image replica detection

The chapter presents a method for content based image replica detection. In this method a compact image signature is extracted. The signature depends on image content, carries distinctive image information, and is invariant to many widely used image processing techniques, which do not lead to significant loss of information, such as lossy compression, resizing, color enhancements and simple rotations. The detection of unmodified and modified image replicas is performed by matching signatures of query images to signatures of original images. The signature is designed to be usable in big image databases and even in video databases. It can be characterized by the following properties: small size (a few dozen bytes), fast extraction and matching, high detection rate for basic image processing techniques. A few millions of signatures per second can be compared on a modern PC.

The Method for Image Copy Detection Robust to Basic Image Processing Techniques

This paper presents an image description and matching scheme using synthetic features for a recommendation service. The recommendation service is an example of smart search because it offers something before a user’s request. In the proposed extraction scheme, an image is described by synthesized spatial and statistical features. The spatial feature is designed to increase the discriminability by reflecting delicate variations. The statistical feature is designed to increase the robustness by absorbing small variations. For extracting spatial features, we partition the image into concentric circles and extract four characteristics using a spatial relation. To extract statistical features, we adapt three transforms into the image and compose a 3D histogram as the final statistical feature. The matching schemes are designed hierarchically using the proposed spatial and statistical features. The result shows that each feature is better than the compared algorithms that use spatial or statistical features. Additionally, if we adapt the proposed whole extraction and matching scheme, the overall performance will become 98.44% in terms of the correct search ratio. Keywords: Image description, image matching, recommendation service, spatial feature, statistical feature.

Image Description and Matching Scheme Using Synthetic Features for Recommendation Service

The paper presents a method for content based still-image replica detection. This method uses a compact image signature which depends on image content and is invariant to many widely used image processing techniques, such as lossy compression, resizing, resampling, color enhancements and simple rotations. The signature is designed to be usable in big image database: it has small size (a few dozen bytes), the extraction is fast and the comparison of image signatures is very fast. More than million of image signatures per second can be compared on a modern PC. Usage of the method within a framework for digital rights infringements detection in the World Wide Web is also discussed.

/pdf/still-image-copy-detection-algorithm-robust-to-basic-image-1splz4dmos.pdf

G. Galinski

Papers

Still image copy detection algorithm robust to basic image modifications