Thesis Details
Modul pro rozpoznávání nápisů pro robota
This bachelor thesis describe module design for text detection and recognition for use in robotic systems. To detect charters is used Stroke Width transform, which is applied on the input edge image. In the output image after Stroke Width transform are found connected components. For letter grouping into a words is used Hough transform, which is applied on the created binary image. This image contains points, which corresponding positions of found connected components. To recognize signs in detected areas is used Tesseract library. Before recognition detected areas are extracted and rotated into a horizontal position. This proposed detector can detect even rotated text. Accuracy of detection of the text is 75% above the test set "informační tabule".
Text detection, text recognition, Stroke Width transform, SWT, Canny Edge detector, Hough transform, connected components, CCs, Flood Fill, OCR, Tesseract.
Beran Vítězslav, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Drábek Vladimír, doc. Ing., CSc. (DCSY FIT BUT), člen
Orság Filip, Ing., Ph.D. (DITS FIT BUT), člen
Ryšavý Ondřej, doc. Ing., Ph.D. (DIFS FIT BUT), člen
@bachelorsthesis{FITBT17288, author = "Zden\v{e}k Hartman", type = "Bachelor's thesis", title = "Modul pro rozpozn\'{a}v\'{a}n\'{i} n\'{a}pis\r{u} pro robota", school = "Brno University of Technology, Faculty of Information Technology", year = 2015, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/17288/" }