Despite significant advances in the field of face analysis over last decade, the current studies are still limited to specific face computation tasks using deep learning approaches. In this paper, we propose an end-to-end hierarchical deep learning structure, called Multi-Features Convolutional Neural Networks (MFCNN), which can comprehensively implement face analysis including age, gender, race and emotion. Moreover, we take the advantages of the mutual support among different facial features from individual tasks to improve the performance of our model. We also contribute one all-labeling dataset called Multiple Facial Features Computation (MFFC) based on Apparent-age-V2 dataset. Firstly, we train four different VGG-based classifiers to analyze facial features independently like age, gender, etc. using MFFC. Then, we systematically introduced cross-task verification approaches to demonstrate features extracted from different pre-trained models have mutual support to each other. After that, multi-task features extracted from pre-trained models are integrated to train MFCNN. Furthermore, feature fusion strategies also have been implemented to enhance our framework from accuracy and time complexity. Finally, the experimental results demonstrate that MFCNN outperforms state-of-the-art methods of face analysis by 10.3% in average and the best result improves up to 21.3% margin for emotion estimation.
","abstract_html":"<p>Despite significant advances in the field of face analysis over last decade, the current studies are still limited to specific face computation tasks using deep learning approaches. In this paper, we propose an end-to-end hierarchical deep learning structure, called Multi-Features Convolutional Neural Networks (MFCNN), which can comprehensively implement face analysis including age, gender, race and emotion. Moreover, we take the advantages of the mutual support among different facial features from individual tasks to improve the performance of our model. We also contribute one all-labeling dataset called Multiple Facial Features Computation (MFFC) based on Apparent-age-V2 dataset. Firstly, we train four different VGG-based classifiers to analyze facial features independently like age, gender, etc. using MFFC. Then, we systematically introduced cross-task verification approaches to demonstrate features extracted from different pre-trained models have mutual support to each other. After that, multi-task features extracted from pre-trained models are integrated to train MFCNN. Furthermore, feature fusion strategies also have been implemented to enhance our framework from accuracy and time complexity. Finally, the experimental results demonstrate that MFCNN outperforms state-of-the-art methods of face analysis by 10.3% in average and the best result improves up to 21.3% margin for emotion estimation.</p>","abstract_has_math":false,"creators":["Peng, Honglai","Han, Meng","He, Jing (Selena)"],"institution":null,"degree_name":"Master of Science in Computer Science (MSCS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Dr. Jing (Selena) He","Dr. Meng Han"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-05-04T07:00:00Z","date_published":"2021-05-04T07:00:00Z","updated_at":"2026-07-24T02:43:51Z","subjects":["Face computation","CNNs","Deep Learning","Features Fusion","Transfer Learning.","Computer Sciences","Data Science","Other Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.kennesaw.edu/cs_etd/46","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Jing (Selena) He","Dr. Meng Han"]},{"key":"dc:creator","label":"Author","values":["Peng, Honglai","Han, Meng","He, Jing (Selena)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-05-04T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Computer Science (MSCS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Face computation","CNNs","Deep Learning","Features Fusion","Transfer Learning.","Computer Sciences","Data Science","Other Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.kennesaw.edu/cs_etd/46"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Despite significant advances in the field of face analysis over last decade, the current studies are still limited to specific face computation tasks using deep learning approaches. In this paper, we propose an end-to-end hierarchical deep learning structure, called Multi-Features Convolutional Neural Networks (MFCNN), which can comprehensively implement face analysis including age, gender, race and emotion. Moreover, we take the advantages of the mutual support among different facial features from individual tasks to improve the performance of our model. We also contribute one all-labeling dataset called Multiple Facial Features Computation (MFFC) based on Apparent-age-V2 dataset. Firstly, we train four different VGG-based classifiers to analyze facial features independently like age, gender, etc. using MFFC. Then, we systematically introduced cross-task verification approaches to demonstrate features extracted from different pre-trained models have mutual support to each other. After that, multi-task features extracted from pre-trained models are integrated to train MFCNN. Furthermore, feature fusion strategies also have been implemented to enhance our framework from accuracy and time complexity. Finally, the experimental results demonstrate that MFCNN outperforms state-of-the-art methods of face analysis by 10.3% in average and the best result improves up to 21.3% margin for emotion estimation.
"]},{"key":"dc:title","label":"Title","values":["Profile Modeling in Hierarchical Deep Architecture by Mutual Support"]}]}],"canonical_facts":{"dc:contributor":["Dr. Jing (Selena) He","Dr. Meng Han"],"dc:creator":["Peng, Honglai","Han, Meng","He, Jing (Selena)"],"dc:date.available":["2026-05-04T07:00:00Z"],"dc:description.abstract":["Despite significant advances in the field of face analysis over last decade, the current studies are still limited to specific face computation tasks using deep learning approaches. In this paper, we propose an end-to-end hierarchical deep learning structure, called Multi-Features Convolutional Neural Networks (MFCNN), which can comprehensively implement face analysis including age, gender, race and emotion. Moreover, we take the advantages of the mutual support among different facial features from individual tasks to improve the performance of our model. We also contribute one all-labeling dataset called Multiple Facial Features Computation (MFFC) based on Apparent-age-V2 dataset. Firstly, we train four different VGG-based classifiers to analyze facial features independently like age, gender, etc. using MFFC. Then, we systematically introduced cross-task verification approaches to demonstrate features extracted from different pre-trained models have mutual support to each other. After that, multi-task features extracted from pre-trained models are integrated to train MFCNN. Furthermore, feature fusion strategies also have been implemented to enhance our framework from accuracy and time complexity. Finally, the experimental results demonstrate that MFCNN outperforms state-of-the-art methods of face analysis by 10.3% in average and the best result improves up to 21.3% margin for emotion estimation.
"],"dc:identifier":["https://digitalcommons.kennesaw.edu/cs_etd/46"],"dc:subject":["Face computation","CNNs","Deep Learning","Features Fusion","Transfer Learning.","Computer Sciences","Data Science","Other Computer Sciences"],"dc:title":["Profile Modeling in Hierarchical Deep Architecture by Mutual Support"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science in Computer Science (MSCS)"]},"updated_at":"2026-07-24T02:43:51Z"}