Aplikacija za štetje objektov v slikah

diplomsko delo

Jaša Kerec (Author), Matej Kristan (Mentor), Luka Čehovin (Co-mentor)

Abstract

V diplomski nalogi naslavljamo problem štetja objektov v slikah. Ročno štetje objektov je lahko zelo časovno potratno in izpostavljeno človeškim napakam, ko imamo ogromno slik z veliko objekti. Obstajajo aplikacije, ki ponujajo štetje različnih kategorij objektov z že natreniranimi modeli. Naša rešitev pa je nekoliko drugačna, saj predlagamo izdelavo spletne aplikacije, ki uporablja konvolucijske nevronske mreže za štetje objektov. Z enostavno uporabo spletne aplikacije uporabniku ponudimo treniranje lastnih modelov ter uporabo lastnih in že natreniranih modelov za štetje objektov v slikah. Spletno aplikacijo zgradimo z modernimi tehnologijami, kot so React, NodeJS, Tornado in PyTorch. Na koncu nas zanima, ali izdelana aplikacija res prispeva k hitrejšemu in natančnejšemu štetju ter ali je aplikacija dobro izdelana z vidika zmogljivosti, dostopnosti, uporabe dobrih praks in optimizacije za spletne iskalnike. Ugotovimo, da je aplikacija zgrajena dobro, saj na testiranju dosežemo odlične rezultate. Prav tako ugotovimo, da z aplikacijo objekte preštejemo bistveno hitreje kot na roke. Primerjamo tudi natančnost, priklic in mero F1 med metodama Faster R-CNN in FamNet . Ugotovimo, da ima slednja metoda večjo vrednost priklica, metoda Faster R-CNN pa večji vrednosti natančnosti in mere F1.

Keywords

štetje objektov;Faster R-CNN;FamNet;računalništvo in informatika;univerzitetni študij;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2022
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FRI - Faculty of Computer and Information Science
Publisher:	[J.Kerec]
UDC:	004.9(043.2)
COBISS:	123324419
Views:	48
Downloads:	17
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Application for counting objects in images
Secondary abstract:	In diploma thesis we address the problem of counting objects in images. Manual object counting can be very time consuming and prone to human error when we have a large number of images with many objects. There are applications that offer counting different categories of objects with pre-trained models. We offer a slightly different solution. We propose the development of a web application that uses convolutional neural networks to count objects. With easy-to-use web application, we offer the user to train their own models and to use their own and pre-trained models to count objects in images. We build the web application using modern technologies such as React, NodeJS, Tornado and PyTorch. Finally, we want to know whether the built application really contributes to faster and more accurate counting and whether the application is well designed in terms of performance, accessibility, use of best practices and search engine optimization. We conclude that the application is well built, as we achieve excellent results in the testing. We also find that the application counts objects significantly faster than manually. We also compare the precision, recall and F1-score of the Faster R-CNN and FamNet methods. We find that the FamNet method has a higher recall value, while the Faster R-CNN method has higher precision and F1-score values.
Secondary keywords:	object counting;neural networks;Faster R-CNN;FamNet;computer science;computer and information science;diploma;Spletne aplikacije;Nevronske mreže (računalništvo);Računalništvo;Univerzitetna in visokošolska dela;
Type (COBISS):	Bachelor thesis/paper
Study programme:	1000468
Embargo end date (OpenAIRE):	1970-01-01
Thesis comment:	Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages:	46 str.
ID:	16448527