scholarly journals Prediction of the Optical Character Recognition Accuracy based on the Combined Assessment of Image Binarization Results

2015 ◽  
Vol 21 (6) ◽  
Author(s):  
Piotr Lech ◽  
Krzysztof Okarma
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Recognition Accuracy ◽  
Image Binarization ◽  
Optical Character

scholarly journals Robust Combined Binarization Method of Non-Uniformly Illuminated Document Images for Alphanumerical Character Recognition

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2914
Author(s):  
Hubert Michalak ◽  
Krzysztof Okarma
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Recognition Accuracy ◽  
Image Data ◽  
Document Images ◽  
Historical Document ◽  
Image Binarization ◽  
Optical Character ◽  
Binarization Method ◽  
Camera Sensors

Image binarization is one of the key operations decreasing the amount of information used in further analysis of image data, significantly influencing the final results. Although in some applications, where well illuminated images may be easily captured, ensuring a high contrast, even a simple global thresholding may be sufficient, there are some more challenging solutions, e.g., based on the analysis of natural images or assuming the presence of some quality degradations, such as in historical document images. Considering the variety of image binarization methods, as well as their different applications and types of images, one cannot expect a single universal thresholding method that would be the best solution for all images. Nevertheless, since one of the most common operations preceded by the binarization is the Optical Character Recognition (OCR), which may also be applied for non-uniformly illuminated images captured by camera sensors mounted in mobile phones, the development of even better binarization methods in view of the maximization of the OCR accuracy is still expected. Therefore, in this paper, the idea of the use of robust combined measures is presented, making it possible to bring together the advantages of various methods, including some recently proposed approaches based on entropy filtering and a multi-layered stack of regions. The experimental results, obtained for a dataset of 176 non-uniformly illuminated document images, referred to as the WEZUT OCR Dataset, confirm the validity and usefulness of the proposed approach, leading to a significant increase of the recognition accuracy.

scholarly journals Handwritten Bangla Numerical Digit Recognition Using Fine Regulated Deep Neural Network

2021 ◽  
Vol 9 (2) ◽  
pp. 73-84
Author(s):  
Md. Shahadat Hossain ◽  
Md. Anwar Hossain ◽  
AFM Zainul Abadin ◽  
Md. Manik Ahmed
Keyword(s):  
Neural Network ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Network Performance ◽  
Deep Neural Network ◽  
Recognition Accuracy ◽  
Digit Recognition ◽  
Optical Character ◽  
Regularization Parameters ◽  
Handwritten Recognition

The recognition of handwritten Bangla digit is providing significant progress on optical character recognition (OCR). It is a very critical task due to the similar pattern and alignment of handwriting digits. With the progress of modern research on optical character recognition, it is reducing the complexity of the classification task by several methods, a few problems encounter during recognition and wait to be solved with simpler methods. The modern emerging field of artificial intelligence is the Deep Neural Network, which promises a solid solution to these few handwritten recognition problems. This paper proposed a fine regulated deep neural network (FRDNN) for the handwritten numeric character recognition problem that uses convolutional neural network (CNN) models with regularization parameters which makes the model generalized by preventing the overfitting. This paper applied Traditional Deep Neural Network (TDNN) and Fine regulated deep neural network (FRDNN) models with a similar layer experienced on BanglaLekha-Isolated databases and the classification accuracies for the two models were 96.25% and 96.99%, respectively over 100 epochs. The network performance of the FRDNN model on the BanglaLekha-Isolated digit dataset was more robust and accurate than the TDNN model and depend on experimentation. Our proposed method is obtained a good recognition accuracy compared with other existing available methods.

scholarly journals Pashtu Numerals Recognition through Convolutional Neural Networks

2019 ◽  
pp. 91-96
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Recognition Accuracy ◽  
Research Use ◽  
Optical Character ◽  
Classification Tasks ◽  
Scanned Images

In the proposed paper we introduce a new Pashtu numerals dataset having handwritten scanned images. We make the dataset publically available for scientific and research use. Pashtu language is used by more than fifty million people both for oral and written communication, but still no efforts are devoted to the Optical Character Recognition (OCR) system for Pashtu language. We introduce a new method for handwritten numerals recognition of Pashtu language through the deep learning based models. We use convolutional neural networks (CNNs) both for features extraction and classification tasks. We assess the performance of the proposed CNNs based model and obtained recognition accuracy of 91.45%.

IMPROVEMENT OF THE COLOR TEXT IMAGE BINARIZATION METHOD USING THE MINIMUM-DISTANCE CLASSIFIER

2021 ◽  
Vol 4 (1) ◽  
pp. 57-70
Author(s):  
Marina V. Polyakova ◽  
Alexandr G. Nesteryuk
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Minimum Distance ◽  
Color Images ◽  
Connected Components ◽  
Image Binarization ◽  
Optical Character ◽  
Binarization Method ◽  
Text Images

Optical character recognition systems for the images are used to convert books and documents into electronic form, to automate accounting systems in business, when recognizing markers using augmented reality technologies and etс. The quality of optical character recognition, provided that binarization is applied, is largely determined by the quality of separation of the foreground pixels from the background. Methods of text image binarization are analyzed and insufficient quality of binarization is noted. As a way of research the minimum-distance classifier for the improvement of the existing method of binarization of color text images is used. To improve the quality of the binarization of color text images, it is advisable to divide image pixels into two classes, “Foreground” and “Background”, to use classification methods instead of heuristic threshold selection, namely, a minimum-distance classifier. To reduce the amount of processed information before applying the classifier, it is advisable to select blocks of pixels for subsequent processing. This was done by analyzing the connected components on the original image. An improved method of the color text image binarization with the use of analysis of connected components and minimum-distance classifier has been elaborated. The research of the elaborated method showed that it is better than existing binarization methods in terms of robustness of binarization, but worse in terms of the error of the determining the boundaries of objects. Among the recognition errors, the pixels of images from the class labeled “Foreground” were more often mistaken for the class labeled “Background”. The proposed method of binarization with the uniqueness of class prototypes is recommended to be used in problems of the processing of color images of the printed text, for which the error in determining the boundaries of characters as a result of binarization is compensated by the thickness of the letters. With a multiplicity of class prototypes, the proposed binarization method is recommended to be used in problems of processing color images of handwritten text, if high performance is not required. The improved binarization method has shown its efficiency in cases of slow changes in the color and illumination of the text and background, however, abrupt changes in color and illumination, as well as a textured background, do not allowing the binarization quality required for practical problems.

scholarly journals SLOPE AND CURVE CODING TO RECOGNIZE ENGLISH NUMERALS

2020 ◽  
Vol 8 (2) ◽  
pp. 15-20
Author(s):  
Binod Kumar Prasad
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Recognition Accuracy ◽  
Recognition System ◽  
The Novel ◽  
Nearest Neighbour ◽  
Global Database ◽  
Optical Character ◽  
Individual Character ◽  
Nearest Neighbour Classifier

Purpose: Lines and Curves are important parts of characters in any script. Features based on lines and curves go a long way to characterize an individual character as well as differentiate similar-looking characters. The present paper proposes an English numerals recognition system using feature elements obtained from the novel and efficient coding of the curves and local slopes. The purpose of this paper is to recognize English numerals efficiently to develop a reliable Optical Character recognition system. Methodology: K-Nearest Neighbour classification technique has been implemented on a global database MNIST to get an overall recognition accuracy rate of 96.7 %, which is competitive to other reported works in literature. Distance features and slope features are extracted from pre-processed images. The feature elements from training images are used to train K-Nearest-Neighbour classifier and those from test images have been used to classify them. Main Findings: The findings of the current paper can be used in Optical Character Recognition (OCR) of alphanumeric characters of any language, automatic reading of amount on bank cheque, address written on envelops, etc. Implications: Due to the similarity in structures of some numerals like 2, 3, and 8, the system produces respectively lower recognition accuracy rates for them. Novelty: The ways of finding distance and slope features to differentiate the curves in the structure of English Numerals is the novelty of this work.

Sign in / Sign up

Export Citation Format

Share Document