Indoor Image Representation by High-Level Semantic Features
Indoor image features extraction is a fundamental problem in multiple fields such as image processing, pattern recognition, robotics, and so on. Nevertheless, most of the existing feature extraction methods, which extract features based on pixels, color, shape/object parts or objects on images, suff...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8746125/ |
id |
doaj-e3fee1b6516644168d9b17bd6e9d6e53 |
---|---|
record_format |
Article |
spelling |
doaj-e3fee1b6516644168d9b17bd6e9d6e532021-03-29T23:21:07ZengIEEEIEEE Access2169-35362019-01-017849678497910.1109/ACCESS.2019.29250028746125Indoor Image Representation by High-Level Semantic FeaturesChiranjibi Sitaula0https://orcid.org/0000-0002-4564-2985Yong Xiang1Yushu Zhang2Xuequan Lu3Sunil Aryal4School of Information Technology, Deakin University, Burwood, VIC, AustraliaSchool of Information Technology, Deakin University, Burwood, VIC, AustraliaSchool of Information Technology, Deakin University, Burwood, VIC, AustraliaSchool of Information Technology, Deakin University, Burwood, VIC, AustraliaSchool of Information Technology, Deakin University, Burwood, VIC, AustraliaIndoor image features extraction is a fundamental problem in multiple fields such as image processing, pattern recognition, robotics, and so on. Nevertheless, most of the existing feature extraction methods, which extract features based on pixels, color, shape/object parts or objects on images, suffer from limited capabilities in describing semantic information (e.g., object association). These techniques, therefore, involve undesired classification performance. To tackle this issue, we propose the notion of high-level semantic features and design four steps to extract them. Specifically, we first construct the objects pattern dictionary through extracting raw objects in the images, and then retrieve and extract semantic objects from the objects pattern dictionary. We finally extract our high-level semantic features based on the calculated probability and delta parameter. The experiments on three publicly available datasets (MIT-67, Scene15, and NYU V1) show that our feature extraction approach outperforms the state-of-the-art feature extraction methods for indoor image classification, given a lower dimension of our features than those methods.https://ieeexplore.ieee.org/document/8746125/image classificationFeature extractionimage representationobjects pattern dictionarysemantic objects |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Chiranjibi Sitaula Yong Xiang Yushu Zhang Xuequan Lu Sunil Aryal |
spellingShingle |
Chiranjibi Sitaula Yong Xiang Yushu Zhang Xuequan Lu Sunil Aryal Indoor Image Representation by High-Level Semantic Features IEEE Access image classification Feature extraction image representation objects pattern dictionary semantic objects |
author_facet |
Chiranjibi Sitaula Yong Xiang Yushu Zhang Xuequan Lu Sunil Aryal |
author_sort |
Chiranjibi Sitaula |
title |
Indoor Image Representation by High-Level Semantic Features |
title_short |
Indoor Image Representation by High-Level Semantic Features |
title_full |
Indoor Image Representation by High-Level Semantic Features |
title_fullStr |
Indoor Image Representation by High-Level Semantic Features |
title_full_unstemmed |
Indoor Image Representation by High-Level Semantic Features |
title_sort |
indoor image representation by high-level semantic features |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
Indoor image features extraction is a fundamental problem in multiple fields such as image processing, pattern recognition, robotics, and so on. Nevertheless, most of the existing feature extraction methods, which extract features based on pixels, color, shape/object parts or objects on images, suffer from limited capabilities in describing semantic information (e.g., object association). These techniques, therefore, involve undesired classification performance. To tackle this issue, we propose the notion of high-level semantic features and design four steps to extract them. Specifically, we first construct the objects pattern dictionary through extracting raw objects in the images, and then retrieve and extract semantic objects from the objects pattern dictionary. We finally extract our high-level semantic features based on the calculated probability and delta parameter. The experiments on three publicly available datasets (MIT-67, Scene15, and NYU V1) show that our feature extraction approach outperforms the state-of-the-art feature extraction methods for indoor image classification, given a lower dimension of our features than those methods. |
topic |
image classification Feature extraction image representation objects pattern dictionary semantic objects |
url |
https://ieeexplore.ieee.org/document/8746125/ |
work_keys_str_mv |
AT chiranjibisitaula indoorimagerepresentationbyhighlevelsemanticfeatures AT yongxiang indoorimagerepresentationbyhighlevelsemanticfeatures AT yushuzhang indoorimagerepresentationbyhighlevelsemanticfeatures AT xuequanlu indoorimagerepresentationbyhighlevelsemanticfeatures AT sunilaryal indoorimagerepresentationbyhighlevelsemanticfeatures |
_version_ |
1724189701800198144 |