izpis_h1_title_alt

Računalniški vid za pametno knjižnico
ID Trček, Matej (Author), ID Skočaj, Danijel (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (2,28 MB)
MD5: 6B68971A12A32632603D00A83C64C168
PID: 20.500.12556/rul/cdc53be8-6d40-452a-bf79-5fbd5af15e2e

Abstract
S prostoročnimi vmesniki lahko tehnologijo na udoben način vključimo v vsakdanje dejavnosti. Diplomsko delo opisuje izdelavo aplikacije za prepoznavanje knjižnih platnic z barvno-globinsko kamero za rabo v pametni knjižnici. Aplikacija v globinski sliki zazna ravnino, v njej najde štirikotnik in ga naravna v ravnino kamere. V naslednjem koraku s tehnikami računalniškega vida primerja najdeno sliko s pripravljeno podatkovno bazo posnetkov knjižnih platnic in najde najboljše ujemanje. Globinska slika je zajeta s kamero Microsoft Kinect, aplikacija pa je sprogramirana v jeziku C++ z uporabo knjižnice OpenCV. Za iskanje ravnine se uporablja algoritem RANSAC, za iskanje oglišč pa je bil razvit algoritem, ki se opira na iskanje najbolj oddaljenih točk in preverjanje kotov med njimi. Za opis vzorcev se uporabljata algoritem PCA in histogram pojavitev značilk SIFT, za klasifikacijo pa algoritma SVM in k-NN ter evklidska razdalja do najboljšega primera iz vsakega razreda.

Language:Slovenian
Keywords:računalniški vid, prepoznavanje slik, globinske slike
Work type:Bachelor thesis/paper
Organization:FRI - Faculty of Computer and Information Science
Year:2016
PID:20.500.12556/RUL-81164 This link opens in a new window
Publication date in RUL:30.03.2016
Views:1801
Downloads:437
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Computer vision for smart library
Abstract:
Hands-free interfaces allow us to comfortably integrate technology into mundane tasks. This thesis describes the development of an application for book cover recognition using an RGBD camera for use in a smart library. The application detects a plane within the depth image, finds the corners of a rectangle within it and alligns it with the camera plane. Computer vision techniques are used to compare the recorded image with a prepared database of book covers to find the best match. The depth image is taken with a Microsoft Kinect camera and the application is coded in the C++ language using the OpenCV library. The plane detection uses the RANSAC algorithm while the corner detection algorithm relies on finding the most distant points and checking the corners between them. PCA projection and SIFT feature frequency histograms are used to describe the images classification is performed using SVM and k-NN algorithms and the euclidean distance to the best example of each class.

Keywords:computer vision, image recognition, range images

Similar documents

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

Back