Individuality Representation in Character Recognition
The task of recognition that is based on handwriting characters in the Kurdish language is an interesting study in the area of computer vision and pattern recognition. In the past couple of years, numerous state-of-the-art techniques and methods have been created for pattern recognition. On the other hand, Kurdish language handwriting recognition has been seen to be more difficult when compared to other different languages. The similarities in the properties in Kurdish characters is the primary reason of the great resemblance in the features of Kurdish handwriting characters, therefore the requirement for the recognition process is critical. Consequently, to obtain accurate and precise recognition on the basis of the Kurdish handwriting character, it is crucial for the resemblances in the character properties of Kurdish handwriting to be distinguished. To identify a particular character, the style of character handwriting may be evaluated to enable the implied representation of the hidden unique features of the user’s character. Unique features may guide in recognizing characters that may be important when recognizing the correct character among similar characters. On the other hand, the problem of the resemblances in the properties of handwriting of Kurdish characters were not taken into account ,consequently leaving a high chance of reducing the similarity error for any intra-class (of the same character),with the reduction of the similarity error for any inter-class (of different characters) as well. In order to obtain higher effectiveness, this study uses discretization features for reducing the similarity error for intra-class (of the same character),with the increase of the similarity error for inter-class (of different characters)in recognition of Kurdish Handwriting characters with MAE.