Zernike Moments Based Handwritten Pashto Character Recognition Using Linear Discriminant Analysis

Abstract

This paper presents an efficient Optical Character Recognition (OCR) system for offline isolated Pashto characters recognition. Developing an OCR system for handwritten character recognition is a challenging task because of the handwritten characters vary both in shape and in style and most of the time the handwritten characters also vary among the individuals. The identification of the inscribed Pashto letters becomes even palling due to the unavailability of a standard handwritten Pashto characters database. For experimental and simulation purposes a handwritten Pashto characters database is developed by collecting handwritten samples from the students of the university on A4 sized page. These collected samples are then scanned, stemmed and preprocessed to form a medium sized database that encompasses 14784 handwritten Pashto character images (336 distinguishing handwritten samples for each 44 characters in Pashto script). Furthermore, the Zernike moments are considered as a feature extractor tool for the proposed OCR system to extract features of each individual character. Linear Discriminant Analysis (LDA) is followed as a recognition tool for the proposed recognition system based on the calculated features map using Zernike moments. Applicability of the proposed system is tested by validating it with 10-fold cross-validation method and an overall accuracy of 63.71% is obtained for the handwritten Pashto isolated characters using the proposed OCR system.

End-to-end OCR text recognition method for power equipment nameplate based on image enhancement and template matching

“…In order to improve the efficiency and quality of collecting end-to-end OCR character features of power equipment nameplates, the data are classified, the laws and the actual situation in the collection process are analyzed, and the corresponding data features are summarized, which lays a basic environment for the application and collection of end-toend OCR character features of power equipment nameplates [5][6]. Template matching is to use predefined templates to find and match areas similar to templates in images.…”

A Dynamic Optimization-Based Ensemble Learning Method for Traditional Chinese Medicine Named Entity Recognition

“…Although there are some proven effective feature extraction methods available, such as zoning and HOG feature extraction techniques [38] and Zernike moments [39], in the field of TCM entity recognition, BERT-BILSTM based feature extraction is considered to be the most effective. For the original input X, the pretrained model BERT was first used to extract the general semantics to obtain an output of dimensions (N, 768).…”

Utilizing the collective wisdom of fintech in the gcc region: A systematic mapping approach

“…Some of the researchers performed case studies to inform people about FinTech applications and flaws in the traditional business models. While some researchers inspired from the extensive applications of machine learning techniques in diverse domains (healthcare, 124 internet security, [125][126][127] text recognition domain, [128][129][130] and many others) suggested machine learning models during the development of FinTech-driven applications to analyze the sentiments of the population regarding FinTech applications. List of other models and other techniques suggested are depicted in Table 4 below.…”