An analysis of Feature extraction and Classification Algorithms for Dangerous Object Detection

Kibria, Sakib B. and HASAN, Mohammad (2017) An analysis of Feature extraction and Classification Algorithms for Dangerous Object Detection. In: 2nd International Conference on Electrical & Electronic Engineering (ICEEE2017), 27 Dec 2017, Rajshahi, Bangladesh.

Preview

Text sakib-feature-extraction-classification-v5-CR-v2-temp.pdf - AUTHOR'S ACCEPTED Version (default) Download (809kB) | Preview

Abstract or description

One of the important practical applications of object detection and image classification can be for security enhancement. If dangerous objects e.g. knives can be identified automatically, then a lot of violence can be prevented. For this purpose, various different algorithms and methods are out there that can be used. In this paper, four of them have been investigated to find out which can identify knives from a dataset of images more accurately. Among Bag of Words, HOG-SVM, CNN and pre-trained Alexnet CNN, the deep learning CNN methods are found to give best results, though they consume significantly more resources.

Item Type:	Conference or Workshop Item (Paper)
Faculty:	School of Computing and Digital Technologies > Computing
Event Title:	2nd International Conference on Electrical & Electronic Engineering (ICEEE2017)
Event Location:	Rajshahi, Bangladesh
Event Dates:	27 Dec 2017
Depositing User:	Mohammad HASAN
Date Deposited:	13 Mar 2018 15:00
Last Modified:	24 Feb 2023 13:50
URI:	https://eprints.staffs.ac.uk/id/eprint/4248

Actions (login required)

View Item