izpis_h1_title_alt

Zaznavanje in prepoznavanje logotipov na vozilih z računalniškim vidom
TOMAŽIČ, GAŠPER (Author), Kristan, Matej (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (2,67 MB)

Abstract
V tem diplomskem delu se posvečamo zaznavanju in prepoznavanju avtomobilskih logotipov v slikah. Kot osrednji del predlagamo postopek za detekcijo logotipov, ki temelji na odkrivanju regij MSER v sliki. Iz teh regij sestavimo kandidate za avtomobilski logotip, jih opišemo s histogramom orientacij gradientov ter z naključnimi gozdovi določimo, ali kandidatna regija predstavlja logotip, in če, kateri. Predlagali smo tudi izboljšave postopka z uporabo alternativnih barvnih prostorov, geometrijske normalizacije in uporabe lokacije registrske tablice, ki jo lahko najdemo z enakim algoritmom kot logotip. Za potrebe testiranja algoritma smo pripravili in anotirali tudi zbirko fotografij avtomobilov, ki vključuje dvajset različnih avtomobilskih znamk. Algoritem dosega več kot 70% uspešnost in z uporabo izboljšav tudi nizko število lažnih pozitivov. Čeprav se v delu osredotočimo na dokaj ozko področje, bi bilo mogoče predstavljene ideje prenesti tudi na iskanje drugih predmetov s sorodnimi lastnostmi.

Language:Slovenian
Keywords:avtomobilski logotipi, zaznavanje, MSER, HOG
Work type:Bachelor thesis/paper (mb11)
Organization:FRI - Faculty of computer and information science
Year:2015
Views:642
Downloads:298
Metadata:XML RDF-CHPDL DC-XML DC-RDF
 
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
:
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Secondary language

Language:English
Title:Computer-vision-based car logotype detection and recognition
Abstract:
This thesis addresses the problem of image-based logotype detection and recognition. A new algorithm for logotype detection in images of cars is proposed. In the first stage, the algorithm localizes all maximally-stable extremal regions as candidates of logotype parts. In the next stage, the regions are combined to create logotype candidates, which are encoded by histograms of gradients. A random forest classifier is then used to verify the candidate regions as being logotypes or not and simultaneously classify them into the type of the logotype. In addition, improvements to basic algorithm are proposed. The improvements include the use of alternative color spaces, geometric normalization and use of the car license plate location to form the logotype position prior. An annotated dataset with photographs of vehicles of twenty different makes was prepared for evaluation of the algorithm. The algorithm was able to correctly localize and recognize over 70% of car logotypes at a very low false positive rate. Despite the fact that we focus on car logotype detection, the algorithm can be easily extended to detection of arbitrary logotypes or objects that do not violate assumptions we impose on the logotype appearance.

Keywords:vehicle logos, detection, MSER, HOG

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back