{"id":{"repo_id":"baylor","oai_identifier":"oai:baylor-ir.tdl.org:2104/11590"},"canonical_url":"https://search.dev.ndltd.org/etd/baylor/oai:baylor-ir.tdl.org:2104/11590","repository":{"repo_id":"baylor","name":"Baylor University","base_url":"https://baylor-ir.tdl.org/server/oai/request"},"display":{"title":"On the performance of convolutional neural networks initialized with Gabor filters.","abstract":"Over the years, image recognition has been gaining popularity due to its various possible usages. Convolutional Neural Networks (CNNs) have been the classic approach taken on by many researchers because of their capability to learn through the parameter space given a sufficient amount of representative data. When observing a fully trained CNN, researchers have found that the pattern on the kernel filters (convolution window) of the receptive convolutional layer closely resembles the Gabor filters. Gabor filters have existed for a long time, and researchers have been using them for texture analysis. Given the nature and purpose of the receptive layer of CNN, Gabor filters could act as a suitable replacement strategy for the randomly initialized kernels of the receptive layer in CNN, which could potentially boost the performance without any regard to the nature of the dataset. The findings in this thesis show that when low-level kernel filters are initialized with Gabor filters, there is a boost in accuracy, Area Under ROC (Receiver Operating Characteristic) Curve (AUC), minimum loss, and speed in some cases based on the complexity of the dataset.","abstract_html":"Over the years, image recognition has been gaining popularity due to its various possible usages. Convolutional Neural Networks (CNNs) have been the classic approach taken on by many researchers because of their capability to learn through the parameter space given a sufficient amount of representative data. When observing a fully trained CNN, researchers have found that the pattern on the kernel filters (convolution window) of the receptive convolutional layer closely resembles the Gabor filters. Gabor filters have existed for a long time, and researchers have been using them for texture analysis. Given the nature and purpose of the receptive layer of CNN, Gabor filters could act as a suitable replacement strategy for the randomly initialized kernels of the receptive layer in CNN, which could potentially boost the performance without any regard to the nature of the dataset. The findings in this thesis show that when low-level kernel filters are initialized with Gabor filters, there is a boost in accuracy, Area Under ROC (Receiver Operating Characteristic) Curve (AUC), minimum loss, and speed in some cases based on the complexity of the dataset.","abstract_has_math":false,"creators":["Rai, Mehang, 1996-"],"institution":"Baylor University.","degree_name":"M.S.","degree_level":"Masters","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Rivas Perea, Pablo, 1980-"],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-08","date_published":"2021-08","updated_at":"2026-07-24T01:08:00Z","subjects":["Convolutional neural network (CNN)","Gabor filter.","Object recognition."],"languages":["en"],"rights":["Baylor University works are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. Contact libraryquestions@baylor.edu for inquiries about permission."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2104/11590","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Rivas Perea, Pablo, 1980-"]},{"key":"dc:creator","label":"Author","values":["Rai, Mehang, 1996-"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2021-10-08T13:44:29Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2021-10-08T13:44:29Z"]},{"key":"dc:date.issued","label":"Date","values":["2021-08"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Baylor University."]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Convolutional neural network (CNN)","Gabor filter.","Object recognition."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Baylor University works are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. Contact libraryquestions@baylor.edu for inquiries about permission."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2104/11590"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Over the years, image recognition has been gaining popularity due to its various possible usages. Convolutional Neural Networks (CNNs) have been the classic approach taken on by many researchers because of their capability to learn through the parameter space given a sufficient amount of representative data. When observing a fully trained CNN, researchers have found that the pattern on the kernel filters (convolution window) of the receptive convolutional layer closely resembles the Gabor filters. Gabor filters have existed for a long time, and researchers have been using them for texture analysis. Given the nature and purpose of the receptive layer of CNN, Gabor filters could act as a suitable replacement strategy for the randomly initialized kernels of the receptive layer in CNN, which could potentially boost the performance without any regard to the nature of the dataset. The findings in this thesis show that when low-level kernel filters are initialized with Gabor filters, there is a boost in accuracy, Area Under ROC (Receiver Operating Characteristic) Curve (AUC), minimum loss, and speed in some cases based on the complexity of the dataset."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["On the performance of convolutional neural networks initialized with Gabor filters."]}]}],"canonical_facts":{"dc:contributor.advisor":["Rivas Perea, Pablo, 1980-"],"dc:creator":["Rai, Mehang, 1996-"],"dc:date.accessioned":["2021-10-08T13:44:29Z"],"dc:date.available":["2021-10-08T13:44:29Z"],"dc:date.issued":["2021-08"],"dc:description.abstract":["Over the years, image recognition has been gaining popularity due to its various possible usages. Convolutional Neural Networks (CNNs) have been the classic approach taken on by many researchers because of their capability to learn through the parameter space given a sufficient amount of representative data. When observing a fully trained CNN, researchers have found that the pattern on the kernel filters (convolution window) of the receptive convolutional layer closely resembles the Gabor filters. Gabor filters have existed for a long time, and researchers have been using them for texture analysis. Given the nature and purpose of the receptive layer of CNN, Gabor filters could act as a suitable replacement strategy for the randomly initialized kernels of the receptive layer in CNN, which could potentially boost the performance without any regard to the nature of the dataset. The findings in this thesis show that when low-level kernel filters are initialized with Gabor filters, there is a boost in accuracy, Area Under ROC (Receiver Operating Characteristic) Curve (AUC), minimum loss, and speed in some cases based on the complexity of the dataset."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/2104/11590"],"dc:language.iso":["en"],"dc:rights":["Baylor University works are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. Contact libraryquestions@baylor.edu for inquiries about permission."],"dc:subject":["Convolutional neural network (CNN)","Gabor filter.","Object recognition."],"dc:title":["On the performance of convolutional neural networks initialized with Gabor filters."],"dc:type":["Thesis"],"thesis:degree_level":["Masters"],"thesis:degree_name":["M.S."],"thesis:institution_name":["Baylor University."]},"updated_at":"2026-07-24T01:08:00Z"}