Citation

Chan, Wai Ti (2013) Application of optical character recognition in the processing in the processing of thermal images. Masters thesis, Multimedia University.

Full text not available from this repository.

Abstract

The present-day reliance on metadata in obtaining information from thermal images means that in the absence of metadata, estimating temperatures from thermal images would have to be done with user intervention, which is time-consuming when there are many thermal images to consider. This research intends to develop a program to estimate temperatures from thermal images without metadata, so that a wider range of sources of thermal images, such as scans from documents, can be handled in large numbers. To facilitate this research, thermal images of various subjects are used as sample images to test the program. A method to estimate temperatures from thermal images without metadata and without the need for manual input has been developed, by making use of optical character recognition to have the program automatically read the temperature scales on thermal images for the necessary information. This method utilizes correlation coefficients to compare images of objects with images of known characters. There were problems that arose from the small text in thermal images captured using present-day commercial thermal imagers, and solutions have been devised for these to ensure that the program is accurate and persistent.

Item Type:	Thesis (Masters)
Additional Information:	Call No.: TA1570 T43 2013
Subjects:	T Technology > TJ Mechanical Engineering and Machinery
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	20 May 2014 06:57
Last Modified:	20 May 2014 06:57
URII:	http://shdl.mmu.edu.my/id/eprint/5534

Downloads

Edit (login required)