Automatic Identification of Handwritten Scripts
P. Ramanathan · 2014
Automatic identification of handwritten script facilitates many important applications such as automatic transcription of multilingual documents and search for documents on the Web containing a particular script. The increase in usage of handheld devices which accept handwritten input has created a growing demand for algorithms that can efficiently analyze and retrieve handwritten data. This paper proposes a method to classify words and lines in a handwritten document and deals with filtration of noisy data using mean and median filters. The structural features are extracted by using the special algorithm. These features are classified based on different spatial and temporal features extracted from the strokes of the characters. This method will be worked efficiently compared to the conventional character recognition soft wares.