Face Recognition has been a long-standing topic in computer vision and pattern recognition field because of its wide and important applications in our daily lives such as surveillance system, access control, and so on. The current modern face recognition model, which keeps only a couple of images per person in the database, can now recognize a face with high accuracy. Moreover, the model does not need to be retrained every time a new person is added to the database.
By using the face dataset from Digital Democracy, the thesis will explore the capability of this model by comparing it with the standard convolutional neural network based on pose variations and training set sizes. First, we compare different types of pose to see their effect on the accuracy of the algorithm. Second, we train the system using different number of training images per person to see how many training samples are actually needed to maintain a reasonable accuracy.
Finally, to push the limit, we decide to train the model using only a single image per person with the help of a face generation technique to synthesize more faces. The performance obtained by this integration is found to be competitive with the previous results, which are trained on multiple images.
","abstract_html":"<p>Face Recognition has been a long-standing topic in computer vision and pattern recognition field because of its wide and important applications in our daily lives such as surveillance system, access control, and so on. The current modern face recognition model, which keeps only a couple of images per person in the database, can now recognize a face with high accuracy. Moreover, the model does not need to be retrained every time a new person is added to the database.</p> <p>By using the face dataset from Digital Democracy, the thesis will explore the capability of this model by comparing it with the standard convolutional neural network based on pose variations and training set sizes. First, we compare different types of pose to see their effect on the accuracy of the algorithm. Second, we train the system using different number of training images per person to see how many training samples are actually needed to maintain a reasonable accuracy.</p> <p>Finally, to push the limit, we decide to train the model using only a single image per person with the help of a face generation technique to synthesize more faces. The performance obtained by this integration is found to be competitive with the previous results, which are trained on multiple images.</p>","abstract_has_math":false,"creators":["Le, Khanh Duc"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Xiaozheng (Jane) Zhang"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-03-01T08:00:00Z","date_published":"2019-03-01T08:00:00Z","updated_at":"2026-07-24T01:32:08Z","subjects":["Neural Network","Computer Vision","Machine Learning","Artificial Intelligence and Robotics","Software Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.15368/theses.2019.10"],"render_values":[{"text":"10.15368/theses.2019.10","href":"https://doi.org/10.15368/theses.2019.10","code":true}]}]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/1989","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Xiaozheng (Jane) Zhang"]},{"key":"dc:creator","label":"Author","values":["Le, Khanh Duc"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2019-03-22T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Neural Network","Computer Vision","Machine Learning","Artificial Intelligence and Robotics","Software Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/1989","10.15368/theses.2019.10"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Face Recognition has been a long-standing topic in computer vision and pattern recognition field because of its wide and important applications in our daily lives such as surveillance system, access control, and so on. The current modern face recognition model, which keeps only a couple of images per person in the database, can now recognize a face with high accuracy. Moreover, the model does not need to be retrained every time a new person is added to the database.
By using the face dataset from Digital Democracy, the thesis will explore the capability of this model by comparing it with the standard convolutional neural network based on pose variations and training set sizes. First, we compare different types of pose to see their effect on the accuracy of the algorithm. Second, we train the system using different number of training images per person to see how many training samples are actually needed to maintain a reasonable accuracy.
Finally, to push the limit, we decide to train the model using only a single image per person with the help of a face generation technique to synthesize more faces. The performance obtained by this integration is found to be competitive with the previous results, which are trained on multiple images.
"]},{"key":"dc:title","label":"Title","values":["A Study of Face Embedding in Face Recognition"]}]}],"canonical_facts":{"dc:contributor":["Xiaozheng (Jane) Zhang"],"dc:creator":["Le, Khanh Duc"],"dc:date.available":["2019-03-22T07:00:00Z"],"dc:description.abstract":["Face Recognition has been a long-standing topic in computer vision and pattern recognition field because of its wide and important applications in our daily lives such as surveillance system, access control, and so on. The current modern face recognition model, which keeps only a couple of images per person in the database, can now recognize a face with high accuracy. Moreover, the model does not need to be retrained every time a new person is added to the database.
By using the face dataset from Digital Democracy, the thesis will explore the capability of this model by comparing it with the standard convolutional neural network based on pose variations and training set sizes. First, we compare different types of pose to see their effect on the accuracy of the algorithm. Second, we train the system using different number of training images per person to see how many training samples are actually needed to maintain a reasonable accuracy.
Finally, to push the limit, we decide to train the model using only a single image per person with the help of a face generation technique to synthesize more faces. The performance obtained by this integration is found to be competitive with the previous results, which are trained on multiple images.
"],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/1989","10.15368/theses.2019.10"],"dc:subject":["Neural Network","Computer Vision","Machine Learning","Artificial Intelligence and Robotics","Software Engineering"],"dc:title":["A Study of Face Embedding in Face Recognition"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-07-24T01:32:08Z"}