A deep learning approach towards soft biometrics attributes prediction using CNN

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.

书目详细资料
Main Authors:	Kibria, Maharab, Tabassum, Ilmi, Ahmed, Fardin, Habib, Nahian
其他作者:	Chakrabarty, Amitabha
格式:	Thesis
语言:	English
出版:	Brac University 2022
主题:	Deep learning Prediction Soft biometrics UTKface dataset CNN DenseNet-169 Multi label CNN Machine learning Cognitive learning theory (Deep learning)
在线阅读:	http://hdl.handle.net/10361/15868

id	10361-15868
record_format	dspace
spelling	10361-158682022-01-26T10:16:00Z A deep learning approach towards soft biometrics attributes prediction using CNN Kibria, Maharab Tabassum, Ilmi Ahmed, Fardin Habib, Nahian Chakrabarty, Amitabha Department of Computer Science and Engineering, Brac University Deep learning Prediction Soft biometrics UTKface dataset CNN DenseNet-169 Multi label CNN Machine learning Cognitive learning theory (Deep learning) This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021. Cataloged from PDF version of thesis. Includes bibliographical references (pages 31-32). Any physical, behavioural or adhered human characteristics that we can observe from a person is known as Soft Biometric.The most common physical soft biometric attributes are height, age, ethnicity, facial hairs, gender, hair color etc. In this era of machine and deep learning, retrieving a person based on these semantic descriptions has become a major research interest. Face recognition and bounding boxes are now common implementations in IoT and surveillance systems because of the efficiency of training models. But the research on soft biometric attributes training models still lacks an amount. To overcome this, we have trained different CNN models for the best outcoming prediction result with a UTKface dataset. The dataset includes height, age and gender and 48x48 text pixels face images. The models include CNN, Multi-Headed CNN, DenseNet-169, Multi Label CNN and ResNet- 50. After training all the models we have found that the DenseNet-169 model can achieve the most accuracy for all the soft biometric classes in our dataset. The accuracy we have achieved with our model is 96.16% for age, 97.74% for ethnicity and 99.2% for age on our UTKface dataset keeping a training loss below 0.1 for the three soft-biometric traits. All the models have been trained into the same environment and it is being uploaded with the source code to the given link below: https://github.com/Kibria10/machine-learning-works. Maharab Kibria Ilmi Tabassum Fardin Ahmed Nahian Habib B. Computer Science 2022-01-11T09:28:07Z 2022-01-11T09:28:07Z 2021 2021-09 Thesis ID 17101319 ID 17101130 ID 17101450 ID 17101372 http://hdl.handle.net/10361/15868 en Brac University theses 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. 32 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Deep learning Prediction Soft biometrics UTKface dataset CNN DenseNet-169 Multi label CNN Machine learning Cognitive learning theory (Deep learning)
spellingShingle	Deep learning Prediction Soft biometrics UTKface dataset CNN DenseNet-169 Multi label CNN Machine learning Cognitive learning theory (Deep learning) Kibria, Maharab Tabassum, Ilmi Ahmed, Fardin Habib, Nahian A deep learning approach towards soft biometrics attributes prediction using CNN
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.
author2	Chakrabarty, Amitabha
author_facet	Chakrabarty, Amitabha Kibria, Maharab Tabassum, Ilmi Ahmed, Fardin Habib, Nahian
format	Thesis
author	Kibria, Maharab Tabassum, Ilmi Ahmed, Fardin Habib, Nahian
author_sort	Kibria, Maharab
title	A deep learning approach towards soft biometrics attributes prediction using CNN
title_short	A deep learning approach towards soft biometrics attributes prediction using CNN
title_full	A deep learning approach towards soft biometrics attributes prediction using CNN
title_fullStr	A deep learning approach towards soft biometrics attributes prediction using CNN
title_full_unstemmed	A deep learning approach towards soft biometrics attributes prediction using CNN
title_sort	deep learning approach towards soft biometrics attributes prediction using cnn
publisher	Brac University
publishDate	2022
url	http://hdl.handle.net/10361/15868
work_keys_str_mv	AT kibriamaharab adeeplearningapproachtowardssoftbiometricsattributespredictionusingcnn AT tabassumilmi adeeplearningapproachtowardssoftbiometricsattributespredictionusingcnn AT ahmedfardin adeeplearningapproachtowardssoftbiometricsattributespredictionusingcnn AT habibnahian adeeplearningapproachtowardssoftbiometricsattributespredictionusingcnn AT kibriamaharab deeplearningapproachtowardssoftbiometricsattributespredictionusingcnn AT tabassumilmi deeplearningapproachtowardssoftbiometricsattributespredictionusingcnn AT ahmedfardin deeplearningapproachtowardssoftbiometricsattributespredictionusingcnn AT habibnahian deeplearningapproachtowardssoftbiometricsattributespredictionusingcnn
_version_	1814308620128485376

A deep learning approach towards soft biometrics attributes prediction using CNN

相似书籍