INDOOR-OUTDOOR IMAGE CLASSIFICATION USING DICHROMATIC REFLECTION MODEL AND HARALICK FEATURES

The problem of indoor-outdoor image classification using supervised learning is addressed in this paper. Conventional indoor-outdoor image classification methods, partition an image into predefined sub-blocks for feature extraction. However in this paper, we use a simple color segmentation stage to...

Full description

Bibliographic Details
Main Author: A. NADIAN-GHOMSHEH
Format: Article
Language:English
Published: Taylor's University 2018-03-01
Series:Journal of Engineering Science and Technology
Subjects:
Online Access:http://jestec.taylors.edu.my/Vol%2013%20issue%203%20March%202018/13_3_14.pdf
_version_ 1811325371031748608
author A. NADIAN-GHOMSHEH
author_facet A. NADIAN-GHOMSHEH
author_sort A. NADIAN-GHOMSHEH
collection DOAJ
description The problem of indoor-outdoor image classification using supervised learning is addressed in this paper. Conventional indoor-outdoor image classification methods, partition an image into predefined sub-blocks for feature extraction. However in this paper, we use a simple color segmentation stage to acquire meaningful regions from the image for feature extraction. The features that are used to describe an image are color correlated temperature, Haralick features, segment area and segment position. For the classification phase, an MLP was trained and tested using a dataset of 800 images. A classification accuracy of 94% compared with the result of other state of the art indoor-outdoor image classification methods showed the efficiency of the proposed method.
first_indexed 2024-04-13T14:33:09Z
format Article
id doaj.art-b7cd3cbbd7b845bb8077fb05330380b9
institution Directory Open Access Journal
issn 1823-4690
language English
last_indexed 2024-04-13T14:33:09Z
publishDate 2018-03-01
publisher Taylor's University
record_format Article
series Journal of Engineering Science and Technology
spelling doaj.art-b7cd3cbbd7b845bb8077fb05330380b92022-12-22T02:43:09ZengTaylor's UniversityJournal of Engineering Science and Technology1823-46902018-03-01133739754INDOOR-OUTDOOR IMAGE CLASSIFICATION USING DICHROMATIC REFLECTION MODEL AND HARALICK FEATURESA. NADIAN-GHOMSHEH0Cyber Space Research Institute, Shahid Beheshti The problem of indoor-outdoor image classification using supervised learning is addressed in this paper. Conventional indoor-outdoor image classification methods, partition an image into predefined sub-blocks for feature extraction. However in this paper, we use a simple color segmentation stage to acquire meaningful regions from the image for feature extraction. The features that are used to describe an image are color correlated temperature, Haralick features, segment area and segment position. For the classification phase, an MLP was trained and tested using a dataset of 800 images. A classification accuracy of 94% compared with the result of other state of the art indoor-outdoor image classification methods showed the efficiency of the proposed method.http://jestec.taylors.edu.my/Vol%2013%20issue%203%20March%202018/13_3_14.pdfIndoor-outdoor image classificationcolor correlated temperatureHaralick featureco-occurrence matrix
spellingShingle A. NADIAN-GHOMSHEH
INDOOR-OUTDOOR IMAGE CLASSIFICATION USING DICHROMATIC REFLECTION MODEL AND HARALICK FEATURES
Journal of Engineering Science and Technology
Indoor-outdoor image classification
color correlated temperature
Haralick feature
co-occurrence matrix
title INDOOR-OUTDOOR IMAGE CLASSIFICATION USING DICHROMATIC REFLECTION MODEL AND HARALICK FEATURES
title_full INDOOR-OUTDOOR IMAGE CLASSIFICATION USING DICHROMATIC REFLECTION MODEL AND HARALICK FEATURES
title_fullStr INDOOR-OUTDOOR IMAGE CLASSIFICATION USING DICHROMATIC REFLECTION MODEL AND HARALICK FEATURES
title_full_unstemmed INDOOR-OUTDOOR IMAGE CLASSIFICATION USING DICHROMATIC REFLECTION MODEL AND HARALICK FEATURES
title_short INDOOR-OUTDOOR IMAGE CLASSIFICATION USING DICHROMATIC REFLECTION MODEL AND HARALICK FEATURES
title_sort indoor outdoor image classification using dichromatic reflection model and haralick features
topic Indoor-outdoor image classification
color correlated temperature
Haralick feature
co-occurrence matrix
url http://jestec.taylors.edu.my/Vol%2013%20issue%203%20March%202018/13_3_14.pdf
work_keys_str_mv AT anadianghomsheh indooroutdoorimageclassificationusingdichromaticreflectionmodelandharalickfeatures