Compact Image Fingerprint Via Multiple Kernel Hashing

Abstract

Image fingerprinting is regarded as an alternative approach to watermarking in terms of near-duplicate detection application. It consists of feature extraction and feature indexing. Generally, the former is mainly related to discrimination, robustness, and security while the latter closely focuses on the efficiency of fingerprints search. To enable fast fingerprints searching over a very large database, we propose a new kernelized multiple feature hashing method to convert the real-value fingerprints into compact binary-value fingerprints. During the process of converting, the proposed hashing method jointly utilizes the kernel trick and multiple feature fusion strategy to map the image represented by multiple features into a compact binary code. With the help of the kernel function, the hashing method can be applied to any format (such as string, graph, set, and so on) as long as there is an associated kernel function available for similarity measurement. In addition, taking multiple features into account aims at improving the discriminability since these multiple evidences are complementary to each other. The extensive experimental results show that the proposed algorithm outperforms state-of-the-art kernelized hashing methods by up to 10 percent.

An unsupervised domain adaptation brain CT segmentation method across image modalities and diseases

“…In the first part, we use the perceptual hash algorithm to calculate the image fingerprints of each image. The image fingerprint algorithm extracts image features and creates digital content as an identifier (Zou et al, 2015); (Lamon et al, 2001). See below for specific steps to calculate the similarity.…”

Effective and Efficient Content Redundancy Detection of Web Videos

“…The affinity relations of videos in HSV and LBP spaces are preserved in the training of the hash functions. A similar approach called kernelized multiple feature hashing (KMFH) is proposed by Zou et al [24]. Alternative fusion strategies include multiple instance learning [25] and ensemble fusion [9], which are similar to the idea of CompoundEyes.…”

Quantization-based hashing: a general framework for scalable image and video retrieval

“…To deal with the novel data point, the hashing functions have to be learned. Some methods [26,7,42] learn the hash function during the learning of hash codes. While some others [35,11,43,5] propose out-of-sample extension.…”