AI based facial recognition for unique identification of animals (Record no. 6512)

MARC details
000 -LEADER
fixed length control field 02541nam a22002057a 4500
003 - CONTROL NUMBER IDENTIFIER
control field OSt
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20220107122851.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 190621b xxu||||| |||| 00| 0 eng d
040 ## - CATALOGING SOURCE
Transcribing agency IIITMK
100 ## - MAIN ENTRY--PERSONAL NAME
Personal name Muhammed Hassan M (91617011)
9 (RLIN) 15918
245 ## - TITLE STATEMENT
Title AI based facial recognition for unique identification of animals
300 ## - PHYSICAL DESCRIPTION
Extent MSC MI 2017-2019
500 ## - GENERAL NOTE
General note I am part of a project that has the overall scope as Animal face detection<br/>and recognition using deep learning techniques.Animal Facial Recognition is<br/>a fairly complex task as it would require using a unique identier that distinguishes<br/>one animal in a species from another. This will involve identifying<br/>unique characteristics for an animal that makes it identiable. The possibilities<br/>being explored include colour, texture, face geometry and birth patterns<br/>to uniquely identify an animal from all four sides (front, back and two sides).<br/>The animals being considered are cows, cats, dogs and rabbits.The scope of<br/>my project work is to extract features to determine the unique geometry of<br/>the frontal face. To extract the face geometry, identifying facial landmarks of<br/>the selected animals was the rst step. This is something that has to be built<br/>from ground up as facial landmark denitions of these animals are not available<br/>in public domain.I started by trying out a face landmark detection with<br/>simple neural net and annotated landmarks in a CSV le. While this technique<br/>works well with human face detection, the results with animals were<br/>not as expected. I then tried Mask RCNN based approach. M-RCNN is a<br/>state-of-the-art model for object detection. It is a deep neural network aimed<br/>to solve instance segmentation problem in machine learning or computer vision.I<br/>have now created a model - Mask-Region based Convolutional Neural<br/>Network(M-RCNN) for identifying the facial landmarks like eyes, muzzle etc.<br/>of cattle.The methodology included creating an annotated landmark data for<br/>training and building a model for testing.It only takes the region of interest<br/>within an object and these regions will be passed to the further neural network<br/>to give the masked region of the object. For pre-processing of images<br/>and feature extraction, several methods including Template Matching, Canny<br/>Edge Detection, transformation etc. were employed.
502 ## - DISSERTATION NOTE
Degree type MSC MI
Name of granting institution 2017-2019
Year degree granted INT
-- Jayachandran M B
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element ANIMAL FACIAL RECOGNITION
9 (RLIN) 15919
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element DEEP LEARNING
9 (RLIN) 15920
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element M-RCNN
9 (RLIN) 15921
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element ARTIFICIAL INTELLIGENCE
9 (RLIN) 15922
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   21/06/2019   R-1516 21/06/2019 21/06/2019 Project Reports