Pashto Characters Recognition Using Multi-Class Enabled Support Vector Machine

During the last two decades signicant work has been reported in the eld of cursive language’s recognition especially,in the Arabic,the Urdu and the Persian languages.The unavailability of such work in the Pashto language is because of:the absence of a standard database and of signicant research work that ultimately acts as a big barrier for the research community.The slight change in the Pashto characters’shape is an additional challenge for researchers.This paper presents an efcient OCR system for the handwritten Pashto characters based on multi-class enabled support vector machine using manifold feature extraction techniques.These feature extraction techniques include,tools such as zoning feature extractor,discrete cosine transform,discrete wavelet transform,and Gabor lters and histogram of oriented gradients.A hybrid feature map is developed by combining the manifold feature maps.This research work is performed by developing a medium-sized dataset of handwritten Pashto characters that encapsulate 200 handwritten samples for each 44 characters in the Pashto language.Recognition results are generated for the proposed model based on a manifold and hybrid feature map.An overall accuracy rates of 63.30%,65.13%,68.55%,68.28%,67.02%and 83%are generated based on a zoning technique,HoGs,Gabor lter,DCT,DWT and hybrid feature maps respectively.Applicability of the proposed model is also tested by comparing its results with a convolution neural network model.The convolution neural network-based model generated an accuracy rate of 81.02%smaller than the multi-class support vector machine.The highest accuracy rate of 83%for the multi-class SVM model based on a hybrid feature map reects the applicability of the proposed model.

Quantification of Blur and Its Applications

Human visual sense has two aspects in our feeling for blurred image, that is, one is the amount of blur depending on object size, the other is the amount of blur independent of the object size. In the former for example, when the image size becomes larger, the author feels smaller amount blur. The quantitative evaluation based on entropy for blurred images is proposed in this paper. The author calls this metric ＂variation entropy＂. This metric has two kinds of aspects that coincide with the human visual sense. The first is the absolute evaluation of blur, and the second is the relative evaluation of blur. The former can be quantified by variation entropy for a unit boundary length （or L-type variation entropy： HL ）, which is dependent on resolution, and the latter can be quantified by variation entropy for a unit area （or A-type variation entropy： H^A ）, which is independent of resolution. These two metrics have complementary properties. At last, two variation entropies are applied to the standard kanji character database, and then the strong relation between variation entropy and accuracy of recognition is discussed. The tendency of writing skills for grades is evaluated by applying the metric to a database collected from school children.