An Accurate Handwritten Digits Recognition system Based on DWT and FCT
Mustafa Salam Kadhm, Doaa N. Mhawi, Rana Mohammed Hassan Zaki · Iraqi Journal of Science · 2018
In this paper an accurate Indian handwritten digits recognition system isproposed. The system used three proposed method for extracting the most effectingfeatures to represent the characteristic of each digit. Discrete Wavelet Transform(DWT) at level one and Fast Cosine Transform (FCT) is used for features extractionfrom the thinned image. Besides that, the system used a standard database which isADBase database for evaluation. The extracted features were classified with KNearestNeighbor (KNN) classifier based on cityblock distance function and theexperimental results show that the proposed system achieved 98.2% recognitionrate.