Detection of near-duplicate images for web search

Foo, Jun Jie; Zobel, Justin; Sinha, Ranjan; Tahaghoghi, S. M. M.

doi:10.1145/1282280.1282360

Cited by 26 publications

(23 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that the secure SIFT proposed in this paper only introduces errors due to the rounding operation in Eq. (9). For the sake of notation simplification, we will simply use ρ in place of ρ ij in the following if there is no confusion.…”

Section: Difference Of Gaussian In the Encrypted Domainmentioning

confidence: 99%

See 1 more Smart Citation

Homomorphic encryption-based secure SIFT for privacy-preserving feature extraction

Hsu

Pei

2011

SPIE Proceedings

View full text Add to dashboard Cite

Privacy has received much attention but is still largely ignored in the multimedia community. Consider a cloud computing scenario, where the server is resource-abundant and is capable of finishing the designated tasks, it is envisioned that secure media retrieval and search with privacy-preserving will be seriously treated. In view of the fact that scale-invariant feature transform (SIFT) has been widely adopted in various fields, this paper is the first to address the problem of secure SIFT feature extraction and representation in the encrypted domain. Since all the operations in SIFT must be moved to the encrypted domain, we propose a homomorphic encryption-based secure SIFT method for privacy-preserving feature extraction and representation based on Paillier cryptosystem. In particular, homomorphic comparison is a must for SIFT feature detection but is still a challenging issue for homomorphic encryption methods. To conquer this problem, we investigate a quantization-like secure comparison strategy in this paper. Experimental results demonstrate that the proposed homomorphic encryption-based SIFT performs comparably to original SIFT on image benchmarks, while preserving privacy additionally. We believe that this work is an important step toward privacy-preserving multimedia retrieval in an environment, where privacy is a major concern.

show abstract

Section: Difference Of Gaussian In the Encrypted Domainmentioning

confidence: 99%

“…SIFT is an algorithm of detecting and describing local features in images and has been widely used [8][9][10][11] due to its powerful attack-resilient feature point detection mechanism. In this paper, we focus on presenting a homomorphic encryption-based secure SIFT method for privacy-preserving feature extraction and representation.…”

Section: Introductionmentioning

confidence: 99%

Homomorphic encryption-based secure SIFT for privacy-preserving feature extraction

Hsu

Pei

2011

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…In particular, the task of detecting near-duplicate images becomes increasingly important in many applications of Multimedia Information Retrieval (MIR) -e.g., detecting illegally copied images on the Web [6] or detecting near-duplicate keyframe retrieval from videos [14]. We refer to such a problem as the Near-Duplicate (ND) problem, informally defined as follows:…”

Section: Introductionmentioning

confidence: 99%

“…The local feature based approach focuses on partial areas of image, i.e., keypoints, that can represent the characteristics of the entire image [8,14]. To detect near-duplicated images, these approaches measure the similarity between two images by matching the keypoints [8,6] and clustering the feature vectors [5,10].…”

Section: Introductionmentioning

confidence: 99%

BASIL: Effective Near-Duplicate Image Detection Using Gene Sequence Alignment

Kim

Chang

Lee

et al. 2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Finding near-duplicate images is a task often found in Multimedia Information Retrieval (MIR). Toward this effort, we propose a novel idea by bridging two seemingly unrelated fields -MIR and Biology. That is, we propose to use the popular gene sequence alignment algorithm in Biology, i.e., BLAST, in detecting near-duplicate images. Under the new idea, we study how various image features and gene sequence generation methods (using gene alphabets such as A, C, G, and T in DNA sequences) affect the accuracy and performance of detecting near-duplicate images. Our proposal, termed as BLASTed Image Linkage (BASIL), is empirically validated using various real data sets. This work can be viewed as the "first" step toward bridging MIR and Biology fields in the well-studied near-duplicate image detection problem.

show abstract

“…Image family discovery is related to image clustering [9,8] and near-duplicate image detection [2,12,6], however it is dierent in three respects: 1) We use the term family to indicate groups of images having high visual similarity with possible change in color, viewpoint, scale, .. etc. In that sense it is a special case of an image cluster, which might refer to a visual category or a type of natural scenes [5], and more general than near-duplicates as dened in [12].…”

Section: Introductionmentioning

confidence: 99%

Towards automated large scale discovery of image families

Aly

Welinder

Munich³

et al. 2009

2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

Gathering large collections of images is quite easy nowadays with the advent of image sharing websites, such as ickr.com. However, such collections inevitably contain duplicates and highly similar images, what we refer to as image families. Automatic discovery and cataloguing of such similar images in large collections is important for many applications, e.g. image search, image collection visualization, and research purposes among others. In this work, we investigate this problem by thoroughly comparing two broad approaches for measuring image similarity: global vs. local features. We assess their performance as the image collection scales up to over 11,000 images with over 6,300 families. We present our results on three datasets with dierent statistics, including two new challenging datasets. Moreover, we present a new algorithm to automatically determine the number of families in the collection with promising results.

show abstract

Detection of near-duplicate images for web search

Cited by 26 publications

References 19 publications

Homomorphic encryption-based secure SIFT for privacy-preserving feature extraction

Homomorphic encryption-based secure SIFT for privacy-preserving feature extraction

BASIL: Effective Near-Duplicate Image Detection Using Gene Sequence Alignment

Towards automated large scale discovery of image families

Contact Info

Product

Resources

About