Clustering and detection of good and bad rail line anchors from images

This conference paper was presented in the International Conference on Computer and Information Technology, ICCIT 2015; Military Institute of Science and Technology (MIST)Mirpur CantonmentDhaka; Bangladesh; 21 December 2015 through 23 December 2015 [© 2015 IEEE] The conference paper's definite...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors:	Islam, Samiul, Khan, Rubayat Ahmed
Andre forfattere:	Department of Computer Science and Engineering, BRAC University
Format:	Conference paper
Sprog:	English
Udgivet:	© 2015 Institute of Electrical and Electronics Engineers Inc. 2017
Fag:	Feature detection Feature extraction Neural networks Training
Online adgang:	http://hdl.handle.net/10361/7501 http://dx.doi.org/10.1109/ICCITechn.2015.7488072

id	10361-7501
record_format	dspace
spelling	10361-75012018-07-25T10:18:39Z Clustering and detection of good and bad rail line anchors from images Islam, Samiul Khan, Rubayat Ahmed Department of Computer Science and Engineering, BRAC University Feature detection Feature extraction Neural networks Training This conference paper was presented in the International Conference on Computer and Information Technology, ICCIT 2015; Military Institute of Science and Technology (MIST)Mirpur CantonmentDhaka; Bangladesh; 21 December 2015 through 23 December 2015 [© 2015 IEEE] The conference paper's definite version is available at: http://dx.doi.org/10.1109/ICCITechn.2015.7488072 Absence of railway anchors/fasteners is a serious concern as it might lead to severe consequences such as train derailments. Hence regular inspection is an obligation to ensure safety. The third world countries choose the inspection process to be non-automatic where a trained operator moves along the rail line boarding a motor trolley checking for visual anomalies. In the previous research [1], an automatic system was proposed to overcome the cons of the running manual technique by using image processing. Two feature detection algorithms - Shi Tomasi and Harris Stephen - were used and an accuracy of 83.55% was achieved. This research presents an upgraded version of the previous work by introducing Neural Network. The addition of NN has not only speeded up the detection process but increased the accuracy significantly to approximately 93.86%. Published 2017-01-04T04:43:54Z 2017-01-04T04:43:54Z 2016-06 Conference paper Islam, S., & Khan, R. A. (2015). Clustering and detection of good and bad rail line anchors from images. Paper presented at the 2015 18th International Conference on Computer and Information Technology, ICCIT 2015, 222-226. doi:10.1109/ICCITechn.2015.7488072 978-146739930-2 http://hdl.handle.net/10361/7501 http://dx.doi.org/10.1109/ICCITechn.2015.7488072 en http://ieeexplore.ieee.org/document/7488072/ © 2015 Institute of Electrical and Electronics Engineers Inc.
institution	Brac University
collection	Institutional Repository
language	English
topic	Feature detection Feature extraction Neural networks Training
spellingShingle	Feature detection Feature extraction Neural networks Training Islam, Samiul Khan, Rubayat Ahmed Clustering and detection of good and bad rail line anchors from images
description	This conference paper was presented in the International Conference on Computer and Information Technology, ICCIT 2015; Military Institute of Science and Technology (MIST)Mirpur CantonmentDhaka; Bangladesh; 21 December 2015 through 23 December 2015 [© 2015 IEEE] The conference paper's definite version is available at: http://dx.doi.org/10.1109/ICCITechn.2015.7488072
author2	Department of Computer Science and Engineering, BRAC University
author_facet	Department of Computer Science and Engineering, BRAC University Islam, Samiul Khan, Rubayat Ahmed
format	Conference paper
author	Islam, Samiul Khan, Rubayat Ahmed
author_sort	Islam, Samiul
title	Clustering and detection of good and bad rail line anchors from images
title_short	Clustering and detection of good and bad rail line anchors from images
title_full	Clustering and detection of good and bad rail line anchors from images
title_fullStr	Clustering and detection of good and bad rail line anchors from images
title_full_unstemmed	Clustering and detection of good and bad rail line anchors from images
title_sort	clustering and detection of good and bad rail line anchors from images
publisher	© 2015 Institute of Electrical and Electronics Engineers Inc.
publishDate	2017
url	http://hdl.handle.net/10361/7501 http://dx.doi.org/10.1109/ICCITechn.2015.7488072
work_keys_str_mv	AT islamsamiul clusteringanddetectionofgoodandbadraillineanchorsfromimages AT khanrubayatahmed clusteringanddetectionofgoodandbadraillineanchorsfromimages
_version_	1814308733724917760

Clustering and detection of good and bad rail line anchors from images

Lignende værker