Semantička segmentacija za manipuliranje odjevnim predmetima

undergraduate thesis

• Title (english): Semantic segmentation for garment manipulation
• Author: Elena Wachtler
• Mentor: Tamara Petrović (mentor)
• Committee member: Tamara Petrović (član povjerenstva)
• Committee member: Ana Milas (član povjerenstva)
• Committee member: Marijana Peti (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Klasifikacija slika pokušava predvidjeti klasu dotad neviđene slike na osnovu velikog broja primjera kojima je klasa poznata. Takav problem nailazi na razna rješenja, većinom u području umjetne inteligencije. Danas su za rješavanje ovog problema vrlo često korištene konvolucijske neuronske mreže. Upravo je taj alat umjetne inteligencije korišten za klasifikaciju odjevnih predmeta u slici u ovome radu. U radu je implementirana klasifikacija odjevnih predmeta pomoću konvolucijskih reuronskih mreža trenirana na FashionMNIST i DeepFashion skupovima podataka te je analizirana točnost za različite testne skupove.

Abstract (english)

Image classification is an attempt to predict the class of an image that has not yet been seen, based on a large dataset of examples to which a class is known. This problem has many possible solutions, most of which come from artificial intelligence. A very commonly used way to solve this issue today are convolutional neural networks, and that is the tool of artificial intelligence chosen to solve the issue of classification of fashion apparel in this particular paper. In this thesis a method for classification is implemented, which is bazen on convolutional neural networks and is trained on FashionMNIST and DeepFashion datasets. Quality of the method is analyzed for different test datasets.

• Keywords: konvolucijska neuronska mreža; klasifikacija slika
• Keywords (english): convolutional neural network; image classification
• Language: croatian
• URN:NBN: urn:nbn:hr:168:889513
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-15 11:27:25