Image Retrieval With Fisher Vectors Of Binary Features

Abstract

Recently, the Fisher vector representation of local features has attracted much attention because of its effectiveness in both image classification and image retrieval. Another trend in the area of image retrieval is the use of binary features such as ORB, FREAK, and BRISK. Considering the significant performance improvement for accuracy in both image classification and retrieval by the Fisher vector of continuous feature descriptors, if the Fisher vector were also to be applied to binary features, we would receive similar benefits in binary feature based image retrieval and classification. In this paper, we derive the closed-form approximation of the Fisher vector of binary features modeled by the Bernoulli mixture model. We also propose accelerating the Fisher vector by using the approximate value of posterior probability. Experiments show that the Fisher vector representation significantly improves the accuracy of image retrieval compared with a bag of binary words approach.

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keyuchida2016image

Related papers

• Aggregating Binary Local Descriptors For Image Retrieval (2016)7.16
• Content-based Image Retrieval Based On Late Fusion Of Binary And Local Descriptors (2017)4.52
• Local Feature Detectors, Descriptors, And Image Representations: A Survey (2016)0.00
• Fine-grained Image Classification And Retrieval By Combining Visual And Locally Pooled Textual Features (2020)10.48
• Siamese Network Of Deep Fisher-vector Descriptors For Image Retrieval (2017)0.00
• Face Retrieval Using Frequency Decoded Local Descriptor (2017)10.61
• An Efficient Image Retrieval Based On Fusion Of Low-level Visual Features (2018)3.58
• Embedding Based On Function Approximation For Large Scale Image Search (2016)10.35