Klasifikacija proizvoda na policama temeljena na značajkama teksture slike

master's thesis

• Title (english): Image Texture Feature-based Classification of Shelved Products
• Author: Domagoj Matić
• Mentor: Sven Lončarić (mentor)
• Committee member: Sven Lončarić (predsjednik povjerenstva)
• Committee member: Marko Subašić (član povjerenstva)
• Committee member: Tomislav Petković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-02-17, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom je radu predstavljena analiza teksture slike u svrhu detekcije proizvoda na polici, ali i pronalaska praznina na policama. Metoda za analizu teksture slike ima mnogo i dijele se u četiri grupe, a u ovom radu je poseban naglasak stavljen na statističke metode: GLCM i LBP. Obje metode sadrže numeričke podatke koji omogućuju pronalaženja značajki slike na temelju tekstura u slici. Kroz rad su navedene prednosti i nedostatci za obje metode te prikazani primjeri detekcija praznina (GLCM metodom) i klasifikacija proizvoda (LBP metodom).

Abstract (english)

This paper presents the analysis of image texture for the purpose of detecting products on the shelf, but also finding gaps on the shelves. There are many methods for image texture analysis and they are divided into four groups, and in this paper special emphasis is placed on statistical methods: GLCM and LBP. Both methods contain numerical data that allows image features to be found based on the textures in the image. The paper presents the advantages and disadvantages for both methods and presents examples of gap detection (GLCM method) and product classification (LBP method).

• Keywords: analiza teksture slike; tekstura; statističke metode analize slike; GLCM; LBP; detekcija praznina; klasifikacija proizvoda
• Keywords (english): image texture analysis; texture; statistical image analysis methods; GLCM; LBP; gap detection; product classification
• Language: croatian
• URN:NBN: urn:nbn:hr:168:503783
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 15:33:35