IET Image Processing, Volume (14), No (5), Year (2019-11) , Pages (853-861)

Title : ( KSR‐BOF: a new and exemplified method (as KSRs method) for image classification )

Authors: Mohammad Hasan Maleki , Ghosheh Abed Hodtani ,

Access to full-text not allowed by authors

Citation: BibTeX | EndNote

Abstract

Image classification is very important in pattern recognition and computer vision, where, for integrating final representation, feature pooling methods of the max-pooling, sum-pooling and average-pooling have been widely used. In this paper, we propose a new method called k-strongest responses (KSR) on the dictionary atoms for integrating the coding coefficients to generate the final representation, that, compared with the previous pooling methods, produces better performance for image classification task. Based on the KSR method, to improve classification accuracy and generate more compact and discriminative final representation, a new framework consisting of two-parts K-strongest response(KSR) and bag-of-features(BOF) is proposed. To evaluate the performance of the proposed method and framework, we apply it to Locality-constrained Linear Coding (LLC), Linear Distance Coding(LDC) and Sparse Coding(SC) by using two datasets from benchmarks of scene classification: 19-class satellite scene and UC Merced Land. The results show that the coding coefficients integrated by our method and framework are more discriminative than other methods.

Keywords

, image classification, exemplified new method, Locality, constrained Linear Coding, accuracy,
برای دانلود از شناسه و رمز عبور پرتال پویا استفاده کنید.

@article{paperid:1077144,
author = {Mohammad Hasan Maleki and Abed Hodtani, Ghosheh},
title = {KSR‐BOF: a new and exemplified method (as KSRs method) for image classification},
journal = {IET Image Processing},
year = {2019},
volume = {14},
number = {5},
month = {November},
issn = {1751-9667},
pages = {853--861},
numpages = {8},
keywords = {image classification-exemplified new method-Locality-constrained Linear Coding-accuracy-},
}

[Download]

%0 Journal Article
%T KSR‐BOF: a new and exemplified method (as KSRs method) for image classification
%A Mohammad Hasan Maleki
%A Abed Hodtani, Ghosheh
%J IET Image Processing
%@ 1751-9667
%D 2019

[Download]