A character being sketched in hand differs individually depends upon a number of factors.The emotion, mood, age, health condition etc of the writer along with the variation provided by the pen used.
A character being sketched in hand differs individually depends upon a number of factors.The emotion, mood, age, health condition etc of the writer along with the variation provided by the pen used.Tags: Motivation Section Phd ThesisElements Of An Action Research PaperGmat Essay TemplateBusiness Plan InformationHomework Assignment AppBiofuel Research Paper
All makes numerous variations in a character being written by different individuals at different parts of the world.
The complexity of our problem thus lies in the complexity of our language added up to the huge variations in penning down the characters that vary individually.
Joseph 's College of Engineering & Technology, Palai, Kerala, India-686579 Abstract The handwriting recognition in Malayalam is a challenging as well as emerging area of pattern recognition.
From the preprocessed image, we were extracted two features: SURF feature and Curvature feature.
The recognition of scripts is a tedious process for South Indian languages like Malayalam, Kannada, Tamil, Telugu etc.
This is mainly due to the large character set, presence of compound characters and so on.In the second phase, Malayalam sentences were used.From the preprocessed image, we were extracted two features: classifier.The universal language English presents itself simple with only 26 characters - not forgetting the divisions based on the case of letters.Several researchers have come out with notable accuracy in the handwritten recognition of English by virtue of this.An important feature of Malayalam language is its enormous character set.Thus the identification of characters may be posing another challenge in the form of similarity between the characters.Finally, the result of both the classifiers was combined to get the final results.The system showed an accuracy of 89.2% in the first phase.Here we propose a novel method for handwriting recognition by using two dissimilar classifiers.It can also be called as an ensemble method in which multiple classifiers are combined to solve a particular problem and thereby improve the performance of the system. In the first phase, 33 isolated characters in Malayalam were used.