Please use this identifier to cite or link to this item: https://ir.swu.ac.th/jspui/handle/123456789/17256
Full metadata record
DC FieldValueLanguage
dc.contributor.authorThibhodee S.
dc.contributor.authorViyanon W.
dc.date.accessioned2022-03-10T13:16:40Z-
dc.date.available2022-03-10T13:16:40Z-
dc.date.issued2021
dc.identifier.other2-s2.0-85112141217
dc.identifier.urihttps://ir.swu.ac.th/jspui/handle/123456789/17256-
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85112141217&doi=10.1145%2f3468784.3469852&partnerID=40&md5=67964cbf9a7741695e2d14dfa9672633
dc.description.abstractThis research is a study of the evaluation of full-body sketches and the principle of the human pose estimation using the OpenPose library, a method to detect 18 keypoints on a human structure. The dataset used in this research was drawing sketches of 22 first-year students, each of whom drew three drawings of three models. Detected keypoints are calculated to determine the angle and distance between keypoints, which provides 26 features. These features were modeled using ANN for predicting the grades of drawings classified as good, moderate, poor. The resulting keypoints are then taken to find the angles and distances of the skeleton, extracting 26 features and taking these features to create a model using ANN classification. The performance of the model was evaluated using with 56% accuracy © 2021 ACM.
dc.languageen
dc.subjectComputer applications
dc.subjectComputer programming
dc.subjectANN classification
dc.subjectFirst year students
dc.subjectFull body
dc.subjectHuman pose estimations
dc.subjectHuman structures
dc.subjectKeypoints
dc.subjectLearning techniques
dc.subjectThree models
dc.subjectDeep learning
dc.titleAn Application of Evaluation of Human Sketches using Deep Learning Technique
dc.typeConference Paper
dc.rights.holderScopus
dc.identifier.bibliograpycitationACM International Conference Proceeding Series. Vol , No. (2021)
dc.identifier.doi10.1145/3468784.3469852
Appears in Collections:Scopus 1983-2021

Files in This Item:
There are no files associated with this item.


Items in SWU repository are protected by copyright, with all rights reserved, unless otherwise indicated.