Facial expression recognition system with five layer convolution neural network (Record no. 6158)

MARC details
000 -LEADER
fixed length control field 02091nam a22001937a 4500
003 - CONTROL NUMBER IDENTIFIER
control field OSt
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20220107122843.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 180717b xxu||||| |||| 00| 0 eng d
040 ## - CATALOGING SOURCE
Transcribing agency IIITMK
100 ## - MAIN ENTRY--PERSONAL NAME
Personal name Rajalekshmi M. G. (93517010)
9 (RLIN) 14513
245 ## - TITLE STATEMENT
Title Facial expression recognition system with five layer convolution neural network
300 ## - PHYSICAL DESCRIPTION
Extent MPhil CS 2017-2018
500 ## - GENERAL NOTE
General note Abstract <br/><br/>Now a days facial expression recognition field is growing and playing important <br/>role in communication. Facial expression recognition has been an active research area in <br/>the past ten years, with growing application areas including avatar animation, neuro <br/>marketing and sociable robots. The recognition of facial expressions is not an easy <br/>problem for machine learning methods, since people can vary significantly in the way <br/>they show their expressions. However, facial expressions change so subtly that <br/>recognition accuracy of most largely depend on feature extraction. In this work, we <br/>propose two independent methods for this very task. The first method uses facial <br/>expression recognition system using with five layer convolutional neural network, while <br/>the second method is an 8-layer convolutional neural network (CNN) or Alex net.In the <br/>first method to achieve facial expression recognition based on a deep CNN. Firstly we <br/>implement face detection by using Haar-like features and histogram equalization. Then we <br/>construct a five-layer CNN architecture, including two convolutional layers and two <br/>subsampling layers (C-S-C-S). Finally, a Softmax classifier is used for multi-<br/>classification.Second method,created an 8-layer CNN with five convolutional layers, and <br/>three fully connected layers. This module, to reduce redundancy of same features learned, <br/>considers mutual information between filters of the same layer, and processes the best set <br/>of features for the next layer. <br/>
502 ## - DISSERTATION NOTE
Degree type MPhil CS
Name of granting institution 2017-2018
Year degree granted INT
-- Dr. Elizabeth Sherly
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element FACIAL EXPRESSION RECOGNITION
9 (RLIN) 14514
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element CNN
9 (RLIN) 14515
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element MACHINE LEARNING
9 (RLIN) 14516
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme Dewey Decimal Classification
Koha item type
Holdings
Withdrawn status Lost status Source of classification or shelving scheme Damaged status Not for loan Collection code Home library Current library Shelving location Date acquired Total Checkouts Barcode Date last seen Price effective from Koha item type
    Dewey Decimal Classification     Non Fiction IIITM-K Kerala University of Digital Sciences, Innovation and Technology Knowledge Centre   17/07/2018   R-1440 17/07/2018 17/07/2018 Project Reports