A Hair Drawing Evaluation Algorithm for Exactness Assessment Method in Portrait Drawing Learning Assistant System

Nowadays, <i>portrait drawing</i> has become increasingly popular as a means of developing artistic skills and nurturing emotional expression. However, it is challenging for novices to start learning it, as they usually lack a solid grasp of proportions and structural foundations of the...

Full description

Saved in:
Bibliographic Details
Main Authors: Yue Zhang, Nobuo Funabiki, Erita Cicilia Febrianti, Amang Sudarsono, Chenchien Hsu
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/18/3/143
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849392677162844160
author Yue Zhang
Nobuo Funabiki
Erita Cicilia Febrianti
Amang Sudarsono
Chenchien Hsu
author_facet Yue Zhang
Nobuo Funabiki
Erita Cicilia Febrianti
Amang Sudarsono
Chenchien Hsu
author_sort Yue Zhang
collection DOAJ
description Nowadays, <i>portrait drawing</i> has become increasingly popular as a means of developing artistic skills and nurturing emotional expression. However, it is challenging for novices to start learning it, as they usually lack a solid grasp of proportions and structural foundations of the five senses. To address this problem, we have studied <i>Portrait Drawing Learning Assistant System (PDLAS)</i> for guiding novices by providing <i>auxiliary lines</i> of facial features, generated by utilizing <i>OpenPose</i> and <i>OpenCV</i> libraries. For <i>PDLAS</i>, we have also presented the <i>exactness assessment method</i> to evaluate drawing accuracy using the <i>Normalized Cross-Correlation (NCC)</i> algorithm. It calculates the <i>similarity score</i> between the drawing result and the initial portrait photo. Unfortunately, the current method does not assess the <i>hair drawing</i>, although it occupies a large part of a portrait and often determines its quality. In this paper, we present a <i>hair drawing evaluation algorithm</i> for the <i>exactness assessment method</i> to offer comprehensive feedback to users in <i>PDLAS</i>. To emphasize hair lines, this algorithm extracts the texture of the hair region by computing the eigenvalues and eigenvectors of the hair image. For evaluations, we applied the proposal to drawing results by seven students from Okayama University, Japan and confirmed the validity. In addition, we observed the <i>NCC score</i> improvement in <i>PDLAS</i> by modifying the face parts with low similarity scores from the exactness assessment method.
format Article
id doaj-art-1af4700db73c433b942ba092ef29caf5
institution Kabale University
issn 1999-4893
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-1af4700db73c433b942ba092ef29caf52025-08-20T03:40:43ZengMDPI AGAlgorithms1999-48932025-03-0118314310.3390/a18030143A Hair Drawing Evaluation Algorithm for Exactness Assessment Method in Portrait Drawing Learning Assistant SystemYue Zhang0Nobuo Funabiki1Erita Cicilia Febrianti2Amang Sudarsono3Chenchien Hsu4Department of Information and Communication Systems, Okayama University, Okayama 700-8530, JapanDepartment of Information and Communication Systems, Okayama University, Okayama 700-8530, JapanDepartment of Electrical Engineering, Politeknik Elektronika Negeri Surabaya, Surabaya 60111, IndonesiaDepartment of Electrical Engineering, Politeknik Elektronika Negeri Surabaya, Surabaya 60111, IndonesiaDepartment of Electrical Engineering, National Taiwan Normal University, Taipei 106308, TaiwanNowadays, <i>portrait drawing</i> has become increasingly popular as a means of developing artistic skills and nurturing emotional expression. However, it is challenging for novices to start learning it, as they usually lack a solid grasp of proportions and structural foundations of the five senses. To address this problem, we have studied <i>Portrait Drawing Learning Assistant System (PDLAS)</i> for guiding novices by providing <i>auxiliary lines</i> of facial features, generated by utilizing <i>OpenPose</i> and <i>OpenCV</i> libraries. For <i>PDLAS</i>, we have also presented the <i>exactness assessment method</i> to evaluate drawing accuracy using the <i>Normalized Cross-Correlation (NCC)</i> algorithm. It calculates the <i>similarity score</i> between the drawing result and the initial portrait photo. Unfortunately, the current method does not assess the <i>hair drawing</i>, although it occupies a large part of a portrait and often determines its quality. In this paper, we present a <i>hair drawing evaluation algorithm</i> for the <i>exactness assessment method</i> to offer comprehensive feedback to users in <i>PDLAS</i>. To emphasize hair lines, this algorithm extracts the texture of the hair region by computing the eigenvalues and eigenvectors of the hair image. For evaluations, we applied the proposal to drawing results by seven students from Okayama University, Japan and confirmed the validity. In addition, we observed the <i>NCC score</i> improvement in <i>PDLAS</i> by modifying the face parts with low similarity scores from the exactness assessment method.https://www.mdpi.com/1999-4893/18/3/143portrait drawingauxiliary linesOpenPoseOpenCV<i>normalized cross-correlation (NCC)</i>hair texture
spellingShingle Yue Zhang
Nobuo Funabiki
Erita Cicilia Febrianti
Amang Sudarsono
Chenchien Hsu
A Hair Drawing Evaluation Algorithm for Exactness Assessment Method in Portrait Drawing Learning Assistant System
Algorithms
portrait drawing
auxiliary lines
OpenPose
OpenCV
<i>normalized cross-correlation (NCC)</i>
hair texture
title A Hair Drawing Evaluation Algorithm for Exactness Assessment Method in Portrait Drawing Learning Assistant System
title_full A Hair Drawing Evaluation Algorithm for Exactness Assessment Method in Portrait Drawing Learning Assistant System
title_fullStr A Hair Drawing Evaluation Algorithm for Exactness Assessment Method in Portrait Drawing Learning Assistant System
title_full_unstemmed A Hair Drawing Evaluation Algorithm for Exactness Assessment Method in Portrait Drawing Learning Assistant System
title_short A Hair Drawing Evaluation Algorithm for Exactness Assessment Method in Portrait Drawing Learning Assistant System
title_sort hair drawing evaluation algorithm for exactness assessment method in portrait drawing learning assistant system
topic portrait drawing
auxiliary lines
OpenPose
OpenCV
<i>normalized cross-correlation (NCC)</i>
hair texture
url https://www.mdpi.com/1999-4893/18/3/143
work_keys_str_mv AT yuezhang ahairdrawingevaluationalgorithmforexactnessassessmentmethodinportraitdrawinglearningassistantsystem
AT nobuofunabiki ahairdrawingevaluationalgorithmforexactnessassessmentmethodinportraitdrawinglearningassistantsystem
AT eritaciciliafebrianti ahairdrawingevaluationalgorithmforexactnessassessmentmethodinportraitdrawinglearningassistantsystem
AT amangsudarsono ahairdrawingevaluationalgorithmforexactnessassessmentmethodinportraitdrawinglearningassistantsystem
AT chenchienhsu ahairdrawingevaluationalgorithmforexactnessassessmentmethodinportraitdrawinglearningassistantsystem
AT yuezhang hairdrawingevaluationalgorithmforexactnessassessmentmethodinportraitdrawinglearningassistantsystem
AT nobuofunabiki hairdrawingevaluationalgorithmforexactnessassessmentmethodinportraitdrawinglearningassistantsystem
AT eritaciciliafebrianti hairdrawingevaluationalgorithmforexactnessassessmentmethodinportraitdrawinglearningassistantsystem
AT amangsudarsono hairdrawingevaluationalgorithmforexactnessassessmentmethodinportraitdrawinglearningassistantsystem
AT chenchienhsu hairdrawingevaluationalgorithmforexactnessassessmentmethodinportraitdrawinglearningassistantsystem