![]() ![]() For example, the writing direction of the Bengali numeral ১ is from top to bottom, but it is bottom to up for the numeral ৯ in general, even though they look similar. A hypothesis behind the idea is that the writing direction and style of a particular numeral in a language are common because people learn to write numerals by practicing on the particular pattern. Such an HNR can be used in various emerging applications, including language translation, voice conversation from the typical handwritten text of any language. The main objective of this work is to build a novel HNR system integrating features of human writing style with the existing pattern recognition technique of CNN. SEWM-CNN is a suitable HNR method for Bengali and Devanagari numerals compared with other existing methods. ![]() ![]() Finally, the output label or system’s classification of the given numeral image is provided by comparing the confidence level with a predefined threshold value. Parallel to CNN’s classification operation, SEWM measures the start-end points of the numeral image, suggesting the numeral category for which measured start-end points are found close to reference start-end points of the numeral class. In the proposed system, along with such classification, its probability value (i.e., CNN’s confidence level) is also used as a regulating element. Traditionally, the classification outcome of a CNN-based system is considered according to the highest probability exposed for a particular numeral category. Start–End Writing Measure (SEWM) and its integration with CNN is the main contribution of this research. In handwritten numerals, the terminal points (i.e., the start and end positions) are considered additional properties to discriminate between similarly shaped numerals. This paper presents an enhanced HNR system to improve the classification accuracy of the similarly shaped handwritten numerals incorporating the terminals points with CNN’s recognition, which can be utilized in various emerging applications related to language translation. However, CNN seems to misclassify similarly shaped numerals (i.e., the silhouette of the numerals that look the same). Convolutional neural network (CNN) based methods have succeeded for handwritten numeral recognition (HNR) applications. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |