Feature hashing

About: Feature hashing is a research topic. Over the lifetime, 993 publications have been published within this topic receiving 51462 citations.

A Secure and Robust DCT-Based Hashing Scheme for Image Authentication

Abstract: The purpose of an image hash function is to provide a compact representation of an image that can be used for authentication purposes. Designing a good image hash function requires the consideration of many issues like robustness, security and tamper detection with precise localization. In this paper, we focus our attention towards DCT-based hashing schemes for image authentication. We first highlight the problems that we have discovered in some of the existing DCT-based hashing schemes proposed in the literature. We then propose solutions to counter these problems. We present experimental results to show the effectiveness of our proposed scheme. Although we focus on DCT-based hashing techniques, however, the type of problems highlighted in this paper may be present in other spatial or transform domain image hashing techniques as well.

Dynamic Multi-probe LSH: An I/O Efficient Index Structure for Approximate Nearest Neighbor Search

Abstract: Locality-Sensitive Hashing LSH is widely used to solve approximate nearest neighbor search problems in high-dimensional spaces. The basic idea is to map the "nearby" objects into a same hash bucket with high probability. A significant drawback is that LSH requires a large number of hash tables to achieve good search quality. Multi-probe LSH was proposed to reduce the number of hash tables by looking up multiple buckets in each table. While optimized for a main memory database, it is not optimal when multi-dimensional vectors are stored in a secondary storage, because the probed buckets may be randomly distributed in different physical pages. In order to optimize the I/O efficiency, we propose a new method called Dynamic Multi-probe LSH which groups small hash buckets into a single bucket by dynamically increasing the number of hash functions during the index construction. Experimental results show that our method is significantly more I/O efficient.

Pattern hashing - object recognition based on a distributed local appearance model

Abstract: This paper proposes "Pattern Hashing" as a new scheme for object recognition by effectively introducing an appearance-based approach into the framework of a geometric feature-based approach. We compose multiple bases using a combination of arbitrary three interest points in the model object, compute the geometric invariant for similarity transformation for each basis, and apply a hash function to it. Each image patch consists of pixels which are near the basis vector. We divide the model object image into multiple partial image patches, and create various appearances on the hash table as a distributed local appearance model. In the recognition stage, fast model selection is efficiently executed by the hashing technique, and then appearance pattern matching and voting procedure extract the target object in the input image. Through experiment with a face image database, we demonstrate that partly occluded object regions or multiple object positions can indeed be detected by the proposed algorithm.

An Efficient Strategy for Collision Resolution in Hash Tables

Abstract: paper presents NFO, a new and innovative technique for collision resolution based on single dimensional arrays. Hash collisions are practically unavoidable when hashing a random subset of a large set of possible keys and should be seen as an event that can disrupt the normal operations or flow of hash functions computing an index into an array of buckets or slots. Hash tables provide efficient table implementations but then its performance is greatly affected if there are high loads of collisions. This new approach intends to manage these collisions effectively and properly although there are some algorithms for handling collisions currently. NFO incorporates certain features to resolve some problems of existing techniques. The performance of our approach is quantified via analytical modeling and software simulations. Efficient implementations that are easily realizable and productive in modern technologies are discussed. The performance benefits are significant and require machines with moderate memory and speed specifications. Depending on observations of the results of implementation of the proposed approach or technique on a set of real data of several types, all results are registered and analyzed.

Locality-Sensitive Hashing with Margin Based Feature Selection

Abstract: We propose a learning method with feature selection for Locality-Sensitive Hashing. Locality-Sensitive Hashing converts feature vectors into bit arrays. These bit arrays can be used to perform similarity searches and personal authentication. The proposed method uses bit arrays longer than those used in the end for similarity and other searches and by learning selects the bits that will be used. We demonstrated this method can effectively perform optimization for cases such as fingerprint images with a large number of labels and extremely few data that share the same labels, as well as verifying that it is also effective for natural images, handwritten digits, and speech features.