Exploring deep features: deeper fully convolutional neural network for image segmentation

Cataloged from PDF version of thesis report.

Бібліографічні деталі
Автори:	Kamran, Sharif Amit, Bin Khaled, Md. Asif, Bin Kabir, Sabit
Інші автори:	Mostakim, Moin
Формат:	Дисертація
Мова:	English
Опубліковано:	BRAC University 2017
Предмети:	Neural network Image segmentation
Онлайн доступ:	http://hdl.handle.net/10361/8112

id	10361-8112
record_format	dspace
spelling	10361-81122022-01-26T10:10:22Z Exploring deep features: deeper fully convolutional neural network for image segmentation Kamran, Sharif Amit Bin Khaled, Md. Asif Bin Kabir, Sabit Mostakim, Moin Department of Computer Science and Engineering, BRAC University Neural network Image segmentation Cataloged from PDF version of thesis report. Includes bibliographical references (page 31-33). This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2017. Classiﬁcation of images has been a widely regarded challenge for the past decade, but a new type of object recognition problem which deals with pixellevel segmentation is posing a more complex task for both computer vision enthusiasts and researcher alike. The convolutional neural network has become a staple for any recognition task, but a new type of ConvNet which is Fully convolutional in architecture has yielded more ﬁne features and proponents. We propose a neural net where we take VGG19 [20], a well-known classiﬁcation CNN, make it fully convolutional for extracting deeper features and lastly use skip-architectures[15] for getting ﬁner output. This yields better result than the pre-existing FCN segmentation architecture [15, 25, 6]. Training was done on augmented VOC12 [4] with SBD [6]training data and validation set was used from reduced VOC12 validation dataset. The model scored mIOU of 68.1 percent in PASCAL VOC 2012 Segmentation challenge. Sharif Amit Kamran Md. Asif Bin Khaled Sabit Bin Kabir B. Computer Science and Engineering 2017-05-09T10:50:39Z 2017-05-09T10:50:39Z 2017 4/19/2017 Thesis ID 13101176 ID 12201105 ID 13101194 http://hdl.handle.net/10361/8112 en BRAC University thesis 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. 33 pages application/pdf BRAC University
institution	Brac University
collection	Institutional Repository
language	English
topic	Neural network Image segmentation
spellingShingle	Neural network Image segmentation Kamran, Sharif Amit Bin Khaled, Md. Asif Bin Kabir, Sabit Exploring deep features: deeper fully convolutional neural network for image segmentation
description	Cataloged from PDF version of thesis report.
author2	Mostakim, Moin
author_facet	Mostakim, Moin Kamran, Sharif Amit Bin Khaled, Md. Asif Bin Kabir, Sabit
format	Thesis
author	Kamran, Sharif Amit Bin Khaled, Md. Asif Bin Kabir, Sabit
author_sort	Kamran, Sharif Amit
title	Exploring deep features: deeper fully convolutional neural network for image segmentation
title_short	Exploring deep features: deeper fully convolutional neural network for image segmentation
title_full	Exploring deep features: deeper fully convolutional neural network for image segmentation
title_fullStr	Exploring deep features: deeper fully convolutional neural network for image segmentation
title_full_unstemmed	Exploring deep features: deeper fully convolutional neural network for image segmentation
title_sort	exploring deep features: deeper fully convolutional neural network for image segmentation
publisher	BRAC University
publishDate	2017
url	http://hdl.handle.net/10361/8112
work_keys_str_mv	AT kamransharifamit exploringdeepfeaturesdeeperfullyconvolutionalneuralnetworkforimagesegmentation AT binkhaledmdasif exploringdeepfeaturesdeeperfullyconvolutionalneuralnetworkforimagesegmentation AT binkabirsabit exploringdeepfeaturesdeeperfullyconvolutionalneuralnetworkforimagesegmentation
_version_	1814307617324924928

Exploring deep features: deeper fully convolutional neural network for image segmentation

Схожі ресурси