Optical Character Recognition on images with colorful background (CROSBI ID 672433)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Brisinello, Matteo ; Grbić, Ratko ; Stefanović, Dejan ; Pečkai-Kovač, Robert
engleski
Optical Character Recognition on images with colorful background
In this paper, a preprocessing method is presented for improving Tesseract Optical Character Recognition (OCR) performance on images with colorful background. The proposed method consists of two steps. At first, a text segmentation method is performed which attempts to extract the text from the colorful background. This step is based on input image clustering into k images. In the second step, a classifier is used to identify the image containing text among k images resulting from the previous step. OCR is then performed on the identified image. The proposed preprocessing method improves Tesseract OCR performance by approximately 20%.
OCR ; images with colorful background ; image segmentation ; image classification
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
1-6.
2018.
objavljeno
10.1109/ICCE-Berlin.2018.8576202
Podaci o matičnoj publikaciji
2018 IEEE 8th International Conference on Consumer Electronics - Berlin (ICCE-Berlin)
Berlin: Institute of Electrical and Electronics Engineers (IEEE)
978-1-5386-6095-9
2166-6822
2166-6814
Podaci o skupu
IEEE 8th International Conference on Consumer Electronics
poster
02.09.2018-05.09.2018
Berlin, Njemačka