A comparative study of human engineered features and learned features in deep convolutional neural networks for image classification

van Elteren, Tim (2018) A comparative study of human engineered features and learned features in deep convolutional neural networks for image classification. Master's Internship Report, Computing Science.

Preview	Text mCS_2018_VanElterenT.pdf Download (31MB) | Preview
	Text toestemming.pdf Restricted to Registered users only Download (98kB)

Abstract

This paper covers a comparative study of human engineered features and learned features in deep convolutional networks for image classification. Human-engineered or hand-crafted features for computer vision tasks have been the defacto standard until recent developments in learning features has surpassed them in the state of the art. The goal of this paper is to learn and describe the differences between the two approaches, learn the specifics of the methods, and determine where they could benefit eachother in a hybrid architecture.

Item Type:	Thesis (Master's Internship Report)
Supervisor name:	Biehl, M. and Wilkinson, M.H.F.
Degree programme:	Computing Science
Thesis type:	Master's Internship Report
Language:	English
Date Deposited:	06 Aug 2018
Last Modified:	18 Jan 2019 11:27
URI:	https://fse.studenttheses.ub.rug.nl/id/eprint/18237

Actions (login required)

View Item