Pregled bibliografske jedinice broj: 908951
Improving Optical Character Recognition Performance for Low Quality Images
Improving Optical Character Recognition Performance for Low Quality Images // Proceedings of ELMAR-2017 / Muštra, Mario ; Vitas, Dijana ; Zovko-Cihlar, Branka (ur.) (ur.).
Zagreb, 2017. str. 1-5 doi:10.23919/ELMAR.2017.8124460 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 908951 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Improving Optical Character Recognition Performance for Low Quality Images
Autori
Brisinello, Matteo ; Grbić, Ratko ; Pul, Matija ; Anđelić, Tihomir
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of ELMAR-2017
/ Muštra, Mario ; Vitas, Dijana ; Zovko-Cihlar, Branka (ur.) - Zagreb, 2017, 1-5
Skup
59th International Symposium ELMAR-2017
Mjesto i datum
Zadar, Hrvatska, 18.09.2017. - 20.09.2017
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
OCR ; Tesseract ; low quality images ; image preprocessing
Sažetak
Efficient Optical Character Recognition (OCR) in images grabbed from Set-Top Boxes (STBs) plays an important role in STB testing. However, running OCR software on such images usually ends with low OCR performance since images can have low resolution, low image quality or colorful background. In order to improve OCR performance, four different image preprocessing methods are proposed. In this paper OCR is performed with Tesseract 3.5 and the relatively new Tesseract 4.0 on the images grabbed from different STBs. On the original images Tesseract 3.5 provides a 35.7% accuracy while Tesseract 4.0 attains a 70.2% accuracy. The proposed preprocessing methods improve OCR performance by 33.3% for Tesseract 3.5 and 22.6% for Tesseract 4.0 on the available images.
Izvorni jezik
Engleski
Znanstvena područja
Biologija
