Scale-Rotation Invariant Pattern Entropy for Keypoint-Based Near-Duplicate Detection

• Published in: IEEE transactions on image processing Vol. 18; no. 2; pp. 412 - 423
• Main Authors: ZHAO, Wan-Lei, NGO, Chong-Wah
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.02.2009; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Entropy; Exact sciences and technology; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image processing; Image retrieval; Information theory; Information, signal and communications theory; Invariants; Keypoints; Large-scale systems; Matching; near-duplicate detection; Neodymium; Object detection; pattern entropy (PE); Pattern matching; Pattern Recognition, Automated - methods; Photometry; Quantization; Reproducibility of Results; Rotation; Searching; Sensitivity and Specificity; Signal processing; Strontium; Subtraction Technique; Telecommunications and information theory; Video Recording - methods; visual vocabulary; Vocabulary; Scale invariance; Vocabulary; Target tracking; Keypoints; pattern entropy (PE); Similarity; Image retrieval; Information retrieval; Entropy; Algorithm; near-duplicate detection; Copyright; Rotational invariance; Intellectual property; Coherence; visual vocabulary
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2008.2008900

Near-duplicate (ND) detection appears as a timely issue recently, being regarded as a powerful tool for various emerging applications. In the Web 2.0 environment particularly, the identification of near-duplicates enables the tasks such as copyright enforcement, news topic tracking, image and video search. In this paper, we describe an algorithm, namely Scale-Rotation invariant Pattern Entropy (SR-PE), for the detection of near-duplicates in large-scale video corpus. SR-PE is a novel pattern evaluation technique capable of measuring the spatial regularity of matching patterns formed by local keypoints. More importantly, the coherency of patterns and the perception of visual similarity, under the scenario that there could be multiple ND regions undergone arbitrary transformations, respectively, are carefully addressed through entropy measure. To demonstrate our work in large-scale dataset, a practical framework composed of three components: bag-of-words representation, local keypoint matching and SR-PE evaluation, is also proposed for the rapid detection of near-duplicates.