Fast color classification 1995 (English)Independent thesis Advanced level (degree of Master (One Year))Student thesis

Abstract [en]

Multicolored pictures in newspaper are printed with arrays of dots in four colors: cyan, magenta, yellow and black. During the printing process, the operation of the printing press needs to control the amount of ink of the different colors. CBD (Centre for Image Analysis and Computer Graphics) has developed a system (MALCOLM), that recognizes the pixels in a digital image, recorded from a multicolored picture, and classifies each pixel into nine color classes, using neutral network algorithms. The system is now a working prototype. The goal of this project was to reduce the classification time of an image, from eight minutes to one second. To find suitable harware solutions for the algorithms we have divided the whole classifying system into smaller parts. These parts have been analyzed in detail. A discussion is made about how parallel approches (both SIMD and MIMD) could be implemented. Pipelining and recursivety are discussed. We suggest three solutions for the problem that are presented in detail.

Place, publisher, year, edition, pages

1995.

Keywords [en]

image analysis, neural networks, color classification, hardware, multicolor printing

Identifiers

URN: urn:nbn:se:hh:diva-7200Local ID: U1069OAI: oai:DiVA.org:hh-7200DiVA, id: diva2:362248

Uppsok

Technology

Note

Denna uppsats kan beställas från arkivet / This paper can be ordered from the archive. Kontakta / Contact: arkivet@hh.seAvailable from: 2010-11-09 Created: 2010-11-09Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation

School of Business and Engineering (SET)

Search outside of DiVA

GoogleGoogle ScholarTotal: 40 hits