WECIA Graph: Visualization of Classification Performance Dependency on Grayscale Conversion Setting
Grayscale conversion is a popular operation performed within image pre-processing of many computer vision systems, including systems aimed at generic object categorization. The grayscale conversion is a lossy operation. As such, it can signicantly in uence performance of the systems. For generic ob...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Brno University of Technology
2018-12-01
|
Series: | Mendel |
Subjects: | |
Online Access: | https://mendel-journal.org/index.php/mendel/article/view/8 |
id |
doaj-342950c7e1014b2f950f3300af48e660 |
---|---|
record_format |
Article |
spelling |
doaj-342950c7e1014b2f950f3300af48e6602021-07-21T07:38:33ZengBrno University of TechnologyMendel1803-38142571-37012018-12-0124210.13164/mendel.2018.2.0418WECIA Graph: Visualization of Classification Performance Dependency on Grayscale Conversion SettingPavel Skrabanek0Sule Yildirim Yayilgan1Brno University of Technology, Faculty of Mechanical Engineering, Institute of Automation and Computer ScienceNorwegian University of Science and Technology, Department of Information Security and Communication Technology Grayscale conversion is a popular operation performed within image pre-processing of many computer vision systems, including systems aimed at generic object categorization. The grayscale conversion is a lossy operation. As such, it can signicantly in uence performance of the systems. For generic object categorization tasks, a weighted means grayscale conversion proved to be appropriate. It allows full use of the grayscale conversion potential due to weighting coefficients introduced by this conversion method. To reach a desired performance of an object categorization system, the weighting coefficients must be optimally setup. We demonstrate that a search for an optimal setting of the system must be carried out in a cooperation with an expert. To simplify the expert involvement in the optimization process, we propose a WEighting Coefficients Impact Assessment (WECIA) graph. The WECIA graph displays dependence of classication performance on setting of the weighting coefficients for one particular setting of remaining adjustable parameters. We point out a fact that an expert analysis of the dependence using the WECIA graph allows identication of settings leading to undesirable performance of an assessed system. https://mendel-journal.org/index.php/mendel/article/view/8computer visiongeneric object categorizationgrayscale conversionweighted means grayscale conversionclassificationperformance evaluation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Pavel Skrabanek Sule Yildirim Yayilgan |
spellingShingle |
Pavel Skrabanek Sule Yildirim Yayilgan WECIA Graph: Visualization of Classification Performance Dependency on Grayscale Conversion Setting Mendel computer vision generic object categorization grayscale conversion weighted means grayscale conversion classification performance evaluation |
author_facet |
Pavel Skrabanek Sule Yildirim Yayilgan |
author_sort |
Pavel Skrabanek |
title |
WECIA Graph: Visualization of Classification Performance Dependency on Grayscale Conversion Setting |
title_short |
WECIA Graph: Visualization of Classification Performance Dependency on Grayscale Conversion Setting |
title_full |
WECIA Graph: Visualization of Classification Performance Dependency on Grayscale Conversion Setting |
title_fullStr |
WECIA Graph: Visualization of Classification Performance Dependency on Grayscale Conversion Setting |
title_full_unstemmed |
WECIA Graph: Visualization of Classification Performance Dependency on Grayscale Conversion Setting |
title_sort |
wecia graph: visualization of classification performance dependency on grayscale conversion setting |
publisher |
Brno University of Technology |
series |
Mendel |
issn |
1803-3814 2571-3701 |
publishDate |
2018-12-01 |
description |
Grayscale conversion is a popular operation performed within image pre-processing of many computer vision systems, including systems aimed at generic object categorization. The grayscale conversion is a lossy operation. As such, it can signicantly in uence performance of the systems. For generic object categorization tasks, a weighted means grayscale conversion proved to be appropriate. It allows full use of the grayscale
conversion potential due to weighting coefficients introduced by this conversion method. To reach a desired performance of an object categorization system, the weighting coefficients must be optimally setup. We demonstrate that a search for an optimal setting of the system must be carried out in a cooperation with an expert. To simplify the expert involvement in the optimization process, we propose a WEighting Coefficients Impact Assessment (WECIA) graph. The WECIA graph displays dependence of classication performance on setting of the weighting coefficients for one particular setting of remaining adjustable parameters. We point out a fact that an expert analysis of the dependence using the WECIA graph allows identication of settings leading to undesirable performance of an assessed system.
|
topic |
computer vision generic object categorization grayscale conversion weighted means grayscale conversion classification performance evaluation |
url |
https://mendel-journal.org/index.php/mendel/article/view/8 |
work_keys_str_mv |
AT pavelskrabanek weciagraphvisualizationofclassificationperformancedependencyongrayscaleconversionsetting AT suleyildirimyayilgan weciagraphvisualizationofclassificationperformancedependencyongrayscaleconversionsetting |
_version_ |
1721292925084631040 |