Mustafa Ali Abuzaraida, Akram M Zeki, Ahmed M Zeki
Abstract
Recently, online character recognition approaches are gotten attention everywhere due to the raped growing of touch screen devices industry. Furthermore, keyboards and mice devises become inapplicable to be included in small devises. These reasons would open the gate for discovering new techniques which can enrich and enhance this kind of approaches. These online approaches can be used for recognizing different texts like letters, digits, or symbols. In this paper, an online system for recognizing handwritten Hindi digits is highlighted based on matching alignment algorithm. It illustrates every phase of the system in details which are: digits acquisition, preprocessing, features extraction, and recognition phase. The dataset of the system were collected by 50 writers using a touch screen laptop with 50 sample of each digit. The results of testing the proposed system showed a high accuracy rate with an average of 96%.
مصطفى علي ابوزريدة | Mustafa Ali Abuzaraida | 12625