{"id":{"repo_id":"texas-state","oai_identifier":"oai:digital.library.txst.edu:10877/13109"},"canonical_url":"https://search.dev.ndltd.org/etd/texas-state/oai:digital.library.txst.edu:10877/13109","repository":{"repo_id":"texas-state","name":"Texas State University","base_url":"https://digital.library.txst.edu/server/oai/request"},"display":{"title":"Real-Time Low-Resolution Face Recognition using Local Binary Pattern Histograms, Eigenface, and Fisherface Algorithms","abstract":"Nowadays, face recognition plays a vital role in various security, access control, and surveillance systems. In computer vision, automatic face recognition is a challenging job in the last couple of decades. Changes in illumination, image resolutions, the variation of light and posture of the face are still significant problems in face recognition. This research presents an improved real-time face recognition system at low-resolution of 15 pixels (px) with the pose, emotion, and resolution variations. We designed our datasets, named LRD200 and LRD100, and used them for training and classification. The ViolaJones algorithm was used to detect the faces, and the face recognition part receives the face image from the face detection part to process it using the Local Binary Pattern Histograms (LBPH), Eigenface, and Fisherface algorithms with image preprocessing using Contrast Limited Adaptive Histogram Equalization (CLAHE) technique. The face database in this system can be updated through a standalone Android application (app) along with automatic restarting of training and recognition process with the updated database. At 15 px, real-time face recognition accuracies using LBPH, Eigenface, and Fisherface algorithms along with CLAHE were 78.40%, 72.25%, and 81.40% respectively. At 45 px the accuracies were 98.05%, 90.11%, and 93.92% respectively. Using the combination of the LBPH and the Fisherface algorithm along with CLAHE method, an optimum of 96.55% face recognition accuracy was achieved with 50 images per person in the database. The face recognition accuracy decreased with the increase in the number of subjects in the database. The accuracy was 97.24% at 45 px with 5 persons in the database. With 15 persons in the database, the recognition rate was 91.19% using the combined algorithm and CLAHE. This face recognition system can be employed for law enforcement purposes where the surveillance cameras capture low-resolution images because of the distance of the person from the camera. It can also be used as a surveillance system in crowded places such as airports or bus stations to reduce the risk of possible criminal threats.","abstract_html":"Nowadays, face recognition plays a vital role in various security, access control, and surveillance systems. In computer vision, automatic face recognition is a challenging job in the last couple of decades. Changes in illumination, image resolutions, the variation of light and posture of the face are still significant problems in face recognition. This research presents an improved real-time face recognition system at low-resolution of 15 pixels (px) with the pose, emotion, and resolution variations. We designed our datasets, named LRD200 and LRD100, and used them for training and classification. The ViolaJones algorithm was used to detect the faces, and the face recognition part receives the face image from the face detection part to process it using the Local Binary Pattern Histograms (LBPH), Eigenface, and Fisherface algorithms with image preprocessing using Contrast Limited Adaptive Histogram Equalization (CLAHE) technique. The face database in this system can be updated through a standalone Android application (app) along with automatic restarting of training and recognition process with the updated database. At 15 px, real-time face recognition accuracies using LBPH, Eigenface, and Fisherface algorithms along with CLAHE were 78.40%, 72.25%, and 81.40% respectively. At 45 px the accuracies were 98.05%, 90.11%, and 93.92% respectively. Using the combination of the LBPH and the Fisherface algorithm along with CLAHE method, an optimum of 96.55% face recognition accuracy was achieved with 50 images per person in the database. The face recognition accuracy decreased with the increase in the number of subjects in the database. The accuracy was 97.24% at 45 px with 5 persons in the database. With 15 persons in the database, the recognition rate was 91.19% using the combined algorithm and CLAHE. This face recognition system can be employed for law enforcement purposes where the surveillance cameras capture low-resolution images because of the distance of the person from the camera. It can also be used as a surveillance system in crowded places such as airports or bus stations to reduce the risk of possible criminal threats.","abstract_has_math":false,"creators":["Paul, Kamal Chandra"],"institution":"Texas State University","degree_name":"Master of Science","degree_level":"Masters","degree_discipline":"Engineering","degree_department":null,"school":null,"contributors":[],"advisors":["Aslan, Semih"],"committee_chairs":[],"committee_members":["Stapleton, William","Asiabanpour, Bahram"],"year":2018,"date_issued":"2018-12","date_published":"2018-12","updated_at":"2026-07-27T21:22:32Z","subjects":["face recognition","LBPH","fisherface","eigenface","OpenCV","Python","CLAHE","computer vision"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10877/13109","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Aslan, Semih"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Stapleton, William","Asiabanpour, Bahram"]},{"key":"dc:creator","label":"Author","values":["Paul, Kamal Chandra"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2021-01-13T15:48:01Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2021-01-13T15:48:01Z"]},{"key":"dc:date.issued","label":"Date","values":["2018-12"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Texas State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["face recognition","LBPH","fisherface","eigenface","OpenCV","Python","CLAHE","computer vision"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10877/13109"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Nowadays, face recognition plays a vital role in various security, access control, and surveillance systems. In computer vision, automatic face recognition is a challenging job in the last couple of decades. Changes in illumination, image resolutions, the variation of light and posture of the face are still significant problems in face recognition. This research presents an improved real-time face recognition system at low-resolution of 15 pixels (px) with the pose, emotion, and resolution variations. We designed our datasets, named LRD200 and LRD100, and used them for training and classification. The ViolaJones algorithm was used to detect the faces, and the face recognition part receives the face image from the face detection part to process it using the Local Binary Pattern Histograms (LBPH), Eigenface, and Fisherface algorithms with image preprocessing using Contrast Limited Adaptive Histogram Equalization (CLAHE) technique. The face database in this system can be updated through a standalone Android application (app) along with automatic restarting of training and recognition process with the updated database. At 15 px, real-time face recognition accuracies using LBPH, Eigenface, and Fisherface algorithms along with CLAHE were 78.40%, 72.25%, and 81.40% respectively. At 45 px the accuracies were 98.05%, 90.11%, and 93.92% respectively. Using the combination of the LBPH and the Fisherface algorithm along with CLAHE method, an optimum of 96.55% face recognition accuracy was achieved with 50 images per person in the database. The face recognition accuracy decreased with the increase in the number of subjects in the database. The accuracy was 97.24% at 45 px with 5 persons in the database. With 15 persons in the database, the recognition rate was 91.19% using the combined algorithm and CLAHE. This face recognition system can be employed for law enforcement purposes where the surveillance cameras capture low-resolution images because of the distance of the person from the camera. It can also be used as a surveillance system in crowded places such as airports or bus stations to reduce the risk of possible criminal threats."]},{"key":"dc:format","label":"Dc Format","values":["Text"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["1 file (.pdf)"]},{"key":"dc:title","label":"Title","values":["Real-Time Low-Resolution Face Recognition using Local Binary Pattern Histograms, Eigenface, and Fisherface Algorithms"]}]}],"canonical_facts":{"dc:contributor.advisor":["Aslan, Semih"],"dc:contributor.committeemember":["Stapleton, William","Asiabanpour, Bahram"],"dc:creator":["Paul, Kamal Chandra"],"dc:date.accessioned":["2021-01-13T15:48:01Z"],"dc:date.available":["2021-01-13T15:48:01Z"],"dc:date.issued":["2018-12"],"dc:description.abstract":["Nowadays, face recognition plays a vital role in various security, access control, and surveillance systems. In computer vision, automatic face recognition is a challenging job in the last couple of decades. Changes in illumination, image resolutions, the variation of light and posture of the face are still significant problems in face recognition. This research presents an improved real-time face recognition system at low-resolution of 15 pixels (px) with the pose, emotion, and resolution variations. We designed our datasets, named LRD200 and LRD100, and used them for training and classification. The ViolaJones algorithm was used to detect the faces, and the face recognition part receives the face image from the face detection part to process it using the Local Binary Pattern Histograms (LBPH), Eigenface, and Fisherface algorithms with image preprocessing using Contrast Limited Adaptive Histogram Equalization (CLAHE) technique. The face database in this system can be updated through a standalone Android application (app) along with automatic restarting of training and recognition process with the updated database. At 15 px, real-time face recognition accuracies using LBPH, Eigenface, and Fisherface algorithms along with CLAHE were 78.40%, 72.25%, and 81.40% respectively. At 45 px the accuracies were 98.05%, 90.11%, and 93.92% respectively. Using the combination of the LBPH and the Fisherface algorithm along with CLAHE method, an optimum of 96.55% face recognition accuracy was achieved with 50 images per person in the database. The face recognition accuracy decreased with the increase in the number of subjects in the database. The accuracy was 97.24% at 45 px with 5 persons in the database. With 15 persons in the database, the recognition rate was 91.19% using the combined algorithm and CLAHE. This face recognition system can be employed for law enforcement purposes where the surveillance cameras capture low-resolution images because of the distance of the person from the camera. It can also be used as a surveillance system in crowded places such as airports or bus stations to reduce the risk of possible criminal threats."],"dc:format":["Text"],"dc:format.medium":["1 file (.pdf)"],"dc:identifier.uri":["https://hdl.handle.net/10877/13109"],"dc:language.iso":["en"],"dc:subject":["face recognition","LBPH","fisherface","eigenface","OpenCV","Python","CLAHE","computer vision"],"dc:title":["Real-Time Low-Resolution Face Recognition using Local Binary Pattern Histograms, Eigenface, and Fisherface Algorithms"],"dc:type":["Thesis"],"thesis:degree_discipline":["Engineering"],"thesis:degree_level":["Masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Texas State University"]},"updated_at":"2026-07-27T21:22:32Z"}