A Neural Approach to Cursive Handwritten Character Recognition Using Features Extracted from Binarization Technique - Complex System Modelling and Control Through Intelligent Soft Computations - page 752

Table 3 Confusion matrix representing the performance of the neural network classi er

Fig. 16 Three dimensional plot of confusion matrix representing the performance of the neural
network classi er

handwritten Devnagri digits using diffusion half toning algorithm. 16-segment
display concept has been used here for feature extraction. They proposed a neural
classi er for classi cation of isolated digits. Here they achieved accuracy level up