Handwritten Character Recognition (HCR) is widely considered as a benchmark problem for pattern recognition and artificial intelligence. Text matching has become a popular research area in recent days as it plays a great part in pattern recognition. Different techniques for recognizing handwritten letters and digits for different languages have already been implemented throughout the world. This research aims at developing a system for recognizing Bengali handwritten characters i.e. letters and digits using Fourier Transform (FT) and Euclidean distance measurement technique. A dataset with 800 handwritten character texts from different people has been developed for this purpose and these character texts are converted to their equivalent printed version to implement this research. MATLAB has been used as an implementation tool for different preprocessing techniques like cropping, resizing, flood filling, thinning etc. Processed text images are used as input to the system and they are converted to FT. Handwritten character of different person may be of different style and angle. The input dataset is collected from various types of people including age level from 5 to 70 years, from different professions like pre-schooling students, graduate students, doctors, teachers and housewives. So, to match the input image with printed dataset (PDS) each printed data is rotated up to 450 left and right and then their FT is computed. The Euclidean distance among the input image and the rotated 30 images of each printed text are taken as intermediate distance set. The minimum value of Euclidean distance for a character is used to recognize the targeted character from the intermediate set. Wrongly detected texts are not thrown away from the system rather those are stored in the named character or digits file so that those can be used in future for deep learning. By following the proposed methodology, the research has achieved 98.88% recognition accuracy according to the input and PDS.

Handwritten Character Recognition (HCR) is widely considered as a benchmark problem for pattern recognition and artificial intelligence. Text matching has become a popular research area in recent days as it plays a great part in pattern recognition. Different techniques for recognizing handwritten letters and digits for different languages have already been implemented throughout the world. This research aims at developing a system for recognizing Bengali handwritten characters i.e. letters and digits using Fourier Transform (FT) and Euclidean distance measurement technique. A dataset with 800 handwritten character texts from different people has been developed for this purpose and these character texts are converted to their equivalent printed version to implement this research. MATLAB has been used as an implementation tool for different preprocessing techniques like cropping, resizing, flood filling, thinning etc. Processed text images are used as input to the system and they are converted to FT. Handwritten character of different person may be of different style and angle. The input dataset is collected from various types of people including age level from 5 to 70 years, from different professions like pre-schooling students, graduate students, doctors, teachers and housewives. So, to match the input image with printed dataset (PDS) each printed data is rotated up to 450 left and right and then their FT is computed. The Euclidean distance among the input image and the rotated 30 images of each printed text are taken as intermediate distance set. The minimum value of Euclidean distance for a character is used to recognize the targeted character from the intermediate set. Wrongly detected texts are not thrown away from the system rather those are stored in the named character or digits file so that those can be used in future for deep learning. By following the proposed methodology, the research has achieved 98.88% recognition accuracy according to the input and PDS.