Publication:
Classification of compressed domain images utilizing open VINO inference engine

Simple item page
dc.contributor.authorTanen_US
dc.contributor.authorZhen K.S.en_US
dc.contributor.authorBorhanuddin B.en_US
dc.contributor.authorWongen_US
dc.contributor.authorWan Y.en_US
dc.contributor.authorOoien_US
dc.contributor.authorMin T.W.en_US
dc.contributor.authorKhoren_US
dc.contributor.authorGhee J.en_US
dc.contributor.authorid57211607444en_US
dc.contributor.authorid57211600070en_US
dc.contributor.authorid57200577946en_US
dc.contributor.authorid57211610942en_US
dc.contributor.authorid57211599782en_US
dc.contributor.authorid57211598006en_US
dc.contributor.authorid57211603207en_US
dc.contributor.authorid57211607419en_US
dc.contributor.authorid57211600785en_US
dc.date.accessioned2023-05-29T07:23:24Z
dc.date.available2023-05-29T07:23:24Z
dc.date.issued2019
dc.description.abstractThis paper provides a platform to investigate and explore method of �partial decoding of JPEG images� for image classification using Convolutional Neural Network (CNN). The inference is targeting to run on computer system with x86 CPU architecture. We aimed to improve the inference speed of classification by just using part of the compressed domain image information for prediction. We will extract and use the �Discrete Cosine Transform� (DCT) coefficients from compressed domain images to train our models. The trained models are then converted into OpenVINO Intermediate Representation (IR) format for optimization. During inference stage, full decoding is not required as our model only need DCT coefficients which are presented in the process of image partial decoding. Our customized DCT model are able to achieve up to 90% validation and testing accuracy with great competence towards the conventional RGB model. We can also obtain up to 2x times inference speed boost while performing inference on CPU in compressed domain compared with spatial domain employing OpenVINO inference engine. � BEIESP.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.35940/ijeat.A2709.109119
dc.identifier.epage1678
dc.identifier.issue1
dc.identifier.scopus2-s2.0-85074561084
dc.identifier.spage1669
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85074561084&doi=10.35940%2fijeat.A2709.109119&partnerID=40&md5=438d6e2e013bdc989482bbe692335289
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/24423
dc.identifier.volume9
dc.publisherBlue Eyes Intelligence Engineering and Sciences Publicationen_US
dc.relation.ispartofAll Open Access, Bronze
dc.sourceScopus
dc.sourcetitleInternational Journal of Engineering and Advanced Technology
dc.titleClassification of compressed domain images utilizing open VINO inference engineen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS