Expressive Local Feature Match for Image Search

Zechao Hu; Adrian Gheorghe Bors

Expressive Local Feature Match for Image Search

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Content-based image retrieval (CBIR) aims to search the most similar images to a given query content, from a large pool of images. Existing state of the art works would extract a compact global feature vector for each image and then evaluate their similarity. Although some CBIR works utilize local features to get better retrieval results, they either would require extra codebook training or use re-ranking for improving the retrieved results. In this work, we propose a many-to-many local feature matching for large scale CBIR tasks. Unlike existing local feature based algorithms which tend to extract large amounts of short-dimensional local features from each image, the characteristic feature representation in the proposed approach is modeled for each image aiming to employ fewer but more expressive local features. Characteristic latent features are selected using k-means clustering and then fed into a similarity measure, without using complex matching kernels or codebook references. Despite the straightforwardness of the proposed CBIR method, experimental results indicate state of art results on several benchmark datasets.

Original language	English
Title of host publication	International Conference on Pattern Recognition (ICPR)
Place of Publication	Montréal, Québec, Canada
Publisher	IEEE
Pages	1386-1392
Publication status	Published - Jul 2022

Bibliographical note

© IEEE 2022. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

Access to Document

Expressive Local Feature Match for Image Search
© IEEE 2022. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details
Accepted author manuscript, 2.01 MB

Cite this

@inproceedings{1129d09779034a04a2eb281b9b28e9db,

title = "Expressive Local Feature Match for Image Search",

abstract = "Content-based image retrieval (CBIR) aims to search the most similar images to a given query content, from a large pool of images. Existing state of the art works would extract a compact global feature vector for each image and then evaluate their similarity. Although some CBIR works utilize local features to get better retrieval results, they either would require extra codebook training or use re-ranking for improving the retrieved results. In this work, we propose a many-to-many local feature matching for large scale CBIR tasks. Unlike existing local feature based algorithms which tend to extract large amounts of short-dimensional local features from each image, the characteristic feature representation in the proposed approach is modeled for each image aiming to employ fewer but more expressive local features. Characteristic latent features are selected using k-means clustering and then fed into a similarity measure, without using complex matching kernels or codebook references. Despite the straightforwardness of the proposed CBIR method, experimental results indicate state of art results on several benchmark datasets.",

author = "Zechao Hu and Bors, {Adrian Gheorghe}",

note = "{\textcopyright} IEEE 2022. This is an author-produced version of the published paper. Uploaded in accordance with the publisher{\textquoteright}s self-archiving policy. Further copying may not be permitted; contact the publisher for details",

year = "2022",

month = jul,

language = "English",

pages = "1386--1392",

booktitle = "International Conference on Pattern Recognition (ICPR)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Expressive Local Feature Match for Image Search

AU - Hu, Zechao

AU - Bors, Adrian Gheorghe

N1 - © IEEE 2022. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

PY - 2022/7

Y1 - 2022/7

N2 - Content-based image retrieval (CBIR) aims to search the most similar images to a given query content, from a large pool of images. Existing state of the art works would extract a compact global feature vector for each image and then evaluate their similarity. Although some CBIR works utilize local features to get better retrieval results, they either would require extra codebook training or use re-ranking for improving the retrieved results. In this work, we propose a many-to-many local feature matching for large scale CBIR tasks. Unlike existing local feature based algorithms which tend to extract large amounts of short-dimensional local features from each image, the characteristic feature representation in the proposed approach is modeled for each image aiming to employ fewer but more expressive local features. Characteristic latent features are selected using k-means clustering and then fed into a similarity measure, without using complex matching kernels or codebook references. Despite the straightforwardness of the proposed CBIR method, experimental results indicate state of art results on several benchmark datasets.

AB - Content-based image retrieval (CBIR) aims to search the most similar images to a given query content, from a large pool of images. Existing state of the art works would extract a compact global feature vector for each image and then evaluate their similarity. Although some CBIR works utilize local features to get better retrieval results, they either would require extra codebook training or use re-ranking for improving the retrieved results. In this work, we propose a many-to-many local feature matching for large scale CBIR tasks. Unlike existing local feature based algorithms which tend to extract large amounts of short-dimensional local features from each image, the characteristic feature representation in the proposed approach is modeled for each image aiming to employ fewer but more expressive local features. Characteristic latent features are selected using k-means clustering and then fed into a similarity measure, without using complex matching kernels or codebook references. Despite the straightforwardness of the proposed CBIR method, experimental results indicate state of art results on several benchmark datasets.

M3 - Conference contribution

SP - 1386

EP - 1392

BT - International Conference on Pattern Recognition (ICPR)

PB - IEEE

CY - Montréal, Québec, Canada

ER -