Engineering of an object-counting program

Klara Nosan (2019) Engineering of an object-counting program. EngD thesis.

Preview

Abstract

Counting objects in images is an important problem in many fields, such as the field of life sciences, where counting cells in microscopic images is a fundamental analysis tool. In this Bachelor's Thesis we present ImageJ, the state of the art program for microscopic image processing in life sciences. We provide an overview of the newest version of ImageJ with an emphasis on the architecture and the API of the software. We present Learn123, a program designed to automize cell counting in microscopic images using ImageJ. We describe the process of updating Learn123 by using the most recent version of ImageJ and parallelizing the genetic algorithm used to learn cell counting. We then compare the parallel algorithm to its previous sequential version. Finally, we present a new use case of Learn123 and discuss which types of images are not suitable for object counting using ImageJ.

Item Type:

Thesis (EngD thesis)

Keywords:

object counting, image processing, ImageJ, genetic algorithm

Number of Pages:

Language of Content:

Slovenian

Mentor / Comentors:

Name and Surname	ID	Function
doc. dr. Luka Šajn	307	Mentor
dr. Uroš Čibej	300	Comentor

Link to COBISS:

http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1538173379)

Institution:

University of Ljubljana

Department:

Faculty of Computer and Information Science

Item ID:

4402

Date Deposited:

14 Mar 2019 15:13

Last Modified:

26 Mar 2019 11:27

URI:

http://eprints.fri.uni-lj.si/id/eprint/4402

Actions (login required)

View Item