Deep q-network (DQN) partialocclusion segmentation and Backtracking search optimization algorithm (BSOA) with optical Flow reconstruction for facial expression emotion recognition (Record no. 22703)

MARC details
000 -LEADER
fixed length control field a
003 - CONTROL NUMBER IDENTIFIER
control field OSt
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20250424094408.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 250424b xxu||||| |||| 00| 0 eng d
040 ## - CATALOGING SOURCE
Original cataloging agency AIKTC-KRRC
Transcribing agency AIKTC-KRRC
100 ## - MAIN ENTRY--PERSONAL NAME
9 (RLIN) 25966
Author Sudha, S. S.
245 ## - TITLE STATEMENT
Title Deep q-network (DQN) partialocclusion segmentation and Backtracking search optimization algorithm (BSOA) with optical Flow reconstruction for facial expression emotion recognition
250 ## - EDITION STATEMENT
Volume, Issue number Vol.15(2), Oct
260 ## - PUBLICATION, DISTRIBUTION, ETC.
Place of publication, distribution, etc. Chennai
Name of publisher, distributor, etc. ICT Academy
Year 2024
300 ## - PHYSICAL DESCRIPTION
Pagination 3473-3481p.
520 ## - SUMMARY, ETC.
Summary, etc. Video facial expression recognition (FER) has garnered a lot of<br/>attention recently and is helpful for several applications. Although<br/>many algorithms demonstrate impressive performance in a controlled<br/>environment without occlusion, identification in the presence of partial<br/>facial occlusion remains a challenging issue. Solutions based on<br/>reconstructing the obscured area of the face have been suggested as a<br/>way to deal with occlusions. These options mostly rely on the face’s<br/>shape or texture. Nonetheless, the resemblance in facial expressions<br/>among individuals appears to be a valuable advantage for the<br/>reconstruction. For semantic segmentation based on occlusions,<br/>Reinforcement Learning (RL) is introduced as the initial stage. From<br/>a pool of unlabeled data, an agent learns a policy to choose a subset of<br/>tiny informative image patches to be tagged instead of full images. In<br/>the second stage, a trained Backtracking Search Algorithm (BSA) is<br/>used to rebuild optical flows that have been distorted by the occlusion.<br/>On obtaining optical flows estimated from occluded facial frames, AEs<br/>restore optical flows of occluded regions. These recovered optical flows<br/>become inputs to anticipate classes f expressions. Optical flux<br/>reconstructions then classify stages. This study evaluates classification<br/>model’s performances for face expression identification based on Very<br/>Deep Convolution Networks (VGGNet). Furthermore, it produces more<br/>accurate confusion matrices and proposes approaches for the KMU-<br/>FED and CK+ databases, respectively. The results are evaluated using<br/>metrics including recall, f-measure, accuracy, and precision.
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
9 (RLIN) 4622
Topical term or geographic name entry element Computer Engineering
700 ## - ADDED ENTRY--PERSONAL NAME
9 (RLIN) 25967
Co-Author Suganya, S. S.
773 0# - HOST ITEM ENTRY
Place, publisher, and date of publication Chennai ICT Academy
Title ICTACT Journal on Soft Computing (IJSC)
856 ## - ELECTRONIC LOCATION AND ACCESS
URL https://ictactjournals.in/paper/IJSC_Vol_15_Iss_2_Paper_12_3556_3566.pdf
Link text Click here
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme Dewey Decimal Classification
Koha item type Articles Abstract Database
Holdings
Withdrawn status Lost status Source of classification or shelving scheme Damaged status Not for loan Home library Current library Shelving location Date acquired Total Checkouts Barcode Date last seen Price effective from Koha item type
    Dewey Decimal Classification     School of Engineering & Technology School of Engineering & Technology Archieval Section 24/04/2025   2025-0652 24/04/2025 24/04/2025 Articles Abstract Database
Unique Visitors hit counter Total Page Views free counter
Implemented and Maintained by AIKTC-KRRC (Central Library).
For any Suggestions/Query Contact to library or Email: librarian@aiktc.ac.in | Ph:+91 22 27481247
Website/OPAC best viewed in Mozilla Browser in 1366X768 Resolution.