Some Studies for Rotational Invariance in Convolutional Neural Networks.
Date of Submission
December 2018
Date of Award
Winter 12-12-2019
Institute Name (Publisher)
Indian Statistical Institute
Document Type
Master's Dissertation
Degree Name
Master of Technology
Subject Name
Computer Science
Department
Electronics and Communication Sciences Unit (ECSU-Kolkata)
Supervisor
Das, Swagatam (ECSU-Kolkata; ISI)
Abstract (Summary of the Work)
Computer vision is an amazing field of using computing machinery to resemble human vision system where common tasks include image recognition. Convolutional Neural Networks(CNNs) has shown amazing capabilities for such tasks. Besides several advantages, CNNs are significantly susceptible to the rotational transformation of images. CNNs from the input images tries to abstract each image by learning local knowledge using convolutional filters applied over all parts of the image. We propose two methods for considering rotational invariance in learning. The first method uses rotational invariant filter method. The second method uses nonlinear neighbourhood component analysis for learning specialized filters for which the two images of the same class but in different rotational space lie close to each other. We discuss future scope solution for the NCA method.
Control Number
ISI-DISS-2018-383
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
DOI
http://dspace.isical.ac.in:8080/jspui/handle/10263/6949
Recommended Citation
Sawant, Yash M., "Some Studies for Rotational Invariance in Convolutional Neural Networks." (2019). Master’s Dissertations. 368.
https://digitalcommons.isical.ac.in/masters-dissertations/368
Comments
ProQuest Collection ID: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:28843459