Locality-sensitive hashing

About: Locality-sensitive hashing is a research topic. Over the lifetime, 1894 publications have been published within this topic receiving 69362 citations.

Hamming DHT: Taming the similarity search

Abstract: The semantic meaning of a content is frequently represented by content vectors in which each dimension represents an attribute of this content, such as, keywords in a text, colors in a picture or profile information in a social network. However, one important challenge in this semantic context is the storage and retrieval of similar contents, such as the search for similar images assisting a medical procedure. Based on it, this paper presents a new Distributed Hash Table (DHT), called Hamming DHT, in which Locality Sensitive Hashing (LSH) functions, specially the Random Hyperplane Hashing (RHH), are used to generate content identifiers, propitiating a scenario in which similar contents are stored in peers nearly located in the indexing space of the proposed DHT. The evaluations of this work simulate profiles in a social network to verify if the proposed DHT is capable of reducing the number of hops required in order to improve the recall in the context of a similarity search.

Malware Signature Generation Using Locality Sensitive Hashing

Abstract: Security threats due to malicious executable are getting more serious. A lot of researchers are interested in combating malware attacks. In contrast, malicious users aim to increase the usage of polymorphism and metamorphism malware in order to increase the analysis cost and prevent being identified by anti-malware tools. Due to the intuitive similarity between different polymorphisms of a malware family, clustering is an effective approach to deal with this problem. Clustering accordingly is able to reduce the number of signatures. Therefore, we have leveraged the Suffix tree structure and Locality Sensitive Hashing (LSH) to linearly cluster malicious programs and to reduce the number of signatures significantly.

Sketch-Based Retrieval Using Content-Aware Hashing

Abstract: In this paper, we introduce a generic hashing-based approach. It aims to facilitate sketch-based retrieval on large datasets of visual shapes. Unlike previous methods where visual descriptors are extracted from overlapping grids, a content-aware selection scheme is proposed to generate candidate patches instead. Meanwhile, the saliency of each patch is efficiently estimated. Locality-sensitive hashing LSH is employed to integrate and capture both the content and saliency of patches, as well as the spatial information of visual shapes. Furthermore, hash codes are indexed so that a query can be processed in sub-linear time. Experiments on three standard datasets in terms of hand drawn shapes, images and 3D models demonstrate the superiority of our approach.

Locality Preserving Discriminative Hashing

Abstract: Hashing for large scale similarity search has become more and more popular because of its improvement in computational speed and storage reduction. Semi-supervised Hashing (SSH) has been proven effective since it integrates both labeled and unlabeled data to leverage semantic similarity while keeping robust to overfitting. However, it ignores the global label information and the local structure of the feature space. In this paper, we concentrate on these two issues and propose a novel semi-supervised hashing method called Locality Preserving Discriminative Hashing which combines two classical dimensionality reduction approaches, Linear Discriminant Analysis (LDA) and Locality Preserving Projection (LPP). The proposed method presents a rigorous formulation in which the supervised term tries to maintain the global information of the labeled data while the unsupervised term provides effective regularization to model local relationships of the unlabeled data. We apply an efficient sequential procedure to learn the hashing functions. Experimental comparisons with other state-of-the-art methods on three large scale datasets demonstrate the effectiveness and efficiency of our method.