New Mechanisms to Enhance the Performances of Arabic Text Recognition System

2017 ◽  
pp. 879-896 ◽  
Author(s):  
Marwa Amara ◽  
Kamel Zidi
Keyword(s):  
Neural Networks ◽  
Feature Selection ◽  
Multilayer Perceptron ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Computing Time ◽  
Recognition System ◽  
Computational Overhead ◽  
Feature Selection Techniques ◽  
Selection Of

The recognition of a character begins with analyzing its form and extracting the features that will be exploited for the identification. Primitives can be described as a tool to distinguish an object of one class from another object of another class. It is necessary to define the significant primitives during the development of an optical character recognition system. Primitives are defined by experience or by intuition. Several primitives can be extracted while some are irrelevant or redundant. The size of vector primitives can be large if a large number of primitives are extracted including redundant and irrelevant features. As a result, the performance of the recognition system becomes poor, and as the number of features increases, so does the computing time. Feature selection, therefore, is required to ensure the selection of a subset of features that gives accurate recognition and has low computational overhead. We use feature selection techniques to improve the discrimination capacity of the Multilayer Perceptron Neural Networks (MLPNNs).

scholarly journals A Gabor Wavelet Based Approach for Off-Line Recognition of ODIA Handwritten Numerals

2018 ◽  
Vol 7 (2.32) ◽  
pp. 253
Author(s):  
Abhisek Sethy ◽  
Prashanta Kumar Patra ◽  
Soumya Ranjan Nayak ◽  
Deepak Ranjan Nayak
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Feature Vector ◽  
Rbf Neural Network ◽  
Probabilistic Approach ◽  
Recognition Rate ◽  
Recognition System ◽  
Gabor Wavelet ◽  
Gabor Wavelet Transformation ◽  
Selection Of

Optical Character Recognition is one of the most interesting and highly motivated areas of research, which has been very much ap-preciated in different aspect to the area of digitations world. Here in this paper we have suggested a probabilistic approach for develop-ing recognition system for handwritten Odia numerals. To report a good  level of recognition of Odia scripts is quite challenging with respect to other Indian scripts .All the procedure are sequentially enclosed to develop an recognition model and report a successful recognition accuracy. Here we have performed the analysis over to standard handwritten numeral database named as IITBBS Odia Numeral Database, which is collected from IIT Bhubaneswar. In the suggestive recognition system we have adopted a 2D-Gabor wavelet transformation approach for selection of feature vector. Apart from it we have also noted down the dimensional reduction to the obtained feature vector by sustaining to PCA. In order to predict high recognition rate we have followed up by RBF Neural Network classifier. In addition to it we have also evaluate different version of RBF like Gaussian and Polynomial. Performing over 400 samples each of 10 categories (400*10) number of Odia numeral images, we have maintained a well-defined training and testing ratio in the clas-sifier and achieved 98.02%, 96.8%.recognition rate for the reported classifiers.  

A Study of Different Methodologies Helpful in the Identification of Offline Handwritten Script

2018 ◽  
Vol 6 (6) ◽  
pp. 307
Author(s):  
Manish M. Kayasth ◽  
Bharat C. Patel
Keyword(s):  
Feature Extraction ◽  
Character Recognition ◽  
Recognition Rate ◽  
Recognition System ◽  
Post Processing ◽  
Classification Technique ◽  
Scanned Image ◽  
Gujarati Language ◽  
High Degree ◽  
Selection Of

The entire character recognition system is logically characterized into different sections like Scanning, Pre-processing, Classification, Processing, and Post-processing. In the targeted system, the scanned image is first passed through pre-processing modules then feature extraction, classification in order to achieve a high recognition rate. This paper describes mainly on Feature extraction and Classification technique. These are the methodologies which play an important role to identify offline handwritten characters specifically in Gujarati language. Feature extraction provides methods with the help of which characters can identify uniquely and with high degree of accuracy. Feature extraction helps to find the shape contained in the pattern. Several techniques are available for feature extraction and classification, however the selection of an appropriate technique based on its input decides the degree of accuracy of recognition. 

scholarly journals A Hybrid Swarm and Gravitation-based feature selection algorithm for handwritten Indic script classification problem

2021 ◽  
Author(s):  
Ritam Guha ◽  
Manosij Ghosh ◽  
Pawan Kumar Singh ◽  
Ram Sarkar ◽  
Mita Nasipuri
Keyword(s):  
Feature Selection ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Classification Problem ◽  
Classification Model ◽  
Support Vector ◽  
Intermediate Step ◽  
Hybrid Swarm ◽  
Feature Vectors ◽  
Indic Script

AbstractIn any multi-script environment, handwritten script classification is an unavoidable pre-requisite before the document images are fed to their respective Optical Character Recognition (OCR) engines. Over the years, this complex pattern classification problem has been solved by researchers proposing various feature vectors mostly having large dimensions, thereby increasing the computation complexity of the whole classification model. Feature Selection (FS) can serve as an intermediate step to reduce the size of the feature vectors by restricting them only to the essential and relevant features. In the present work, we have addressed this issue by introducing a new FS algorithm, called Hybrid Swarm and Gravitation-based FS (HSGFS). This algorithm has been applied over three feature vectors introduced in the literature recently—Distance-Hough Transform (DHT), Histogram of Oriented Gradients (HOG), and Modified log-Gabor (MLG) filter Transform. Three state-of-the-art classifiers, namely, Multi-Layer Perceptron (MLP), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM), are used to evaluate the optimal subset of features generated by the proposed FS model. Handwritten datasets at block, text line, and word level, consisting of officially recognized 12 Indic scripts, are prepared for experimentation. An average improvement in the range of 2–5% is achieved in the classification accuracy by utilizing only about 75–80% of the original feature vectors on all three datasets. The proposed method also shows better performance when compared to some popularly used FS models. The codes used for implementing HSGFS can be found in the following Github link: https://github.com/Ritam-Guha/HSGFS.

Sign in / Sign up

Export Citation Format

Share Document