scholarly journals ALPHABETS IMAGE IDENTIFICATION USING ADVANCED LOCAL BINARY PATTERN AND CHAIN CODE ALGORITHM

2021 ◽  
Vol 2 (2) ◽  
pp. 68
Author(s):  
Daniel Setiawan Cahyono ◽  
Shinta Estri Wahyuningrum
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Local Binary Pattern ◽  
Image Transformation ◽  
Digital Text ◽  
Image Preprocessing ◽  
Chain Code ◽  
Image Identification ◽  
Optical Character ◽  
Code Algorithm

Optical Character Recognition (OCR) is a method for computer to process an image that contains some text and then try to find any characters in that image, then convert it to digital text. In this research, Advanced Local Binary Pattern and Chain Code algorithm will be tested to identify alphabets in the image. Several method image preprocessing are also needed, such as image transformation, image rescaling, grayscale conversion, edge detection and edge thinning.

scholarly journals Improving the Accuracy of Tesseract 4.0 OCR Engine Using Convolution-Based Preprocessing

Symmetry ◽  
2020 ◽  
Vol 12 (5) ◽  
pp. 715
Author(s):  
Dan Sporici ◽  
Elena Cușnir ◽  
Costin-Anton Boiangiu
Keyword(s):  
Reinforcement Learning ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Edit Distance ◽  
Ground Truth ◽  
Image Preprocessing ◽  
Optical Character ◽  
Great Performance ◽  
Relative Change ◽  
Reinforcement Learning Model

Optical Character Recognition (OCR) is the process of identifying and converting texts rendered in images using pixels to a more computer-friendly representation. The presented work aims to prove that the accuracy of the Tesseract 4.0 OCR engine can be further enhanced by employing convolution-based preprocessing using specific kernels. As Tesseract 4.0 has proven great performance when evaluated against a favorable input, its capability of properly detecting and identifying characters in more realistic, unfriendly images is questioned. The article proposes an adaptive image preprocessing step guided by a reinforcement learning model, which attempts to minimize the edit distance between the recognized text and the ground truth. It is shown that this approach can boost the character-level accuracy of Tesseract 4.0 from 0.134 to 0.616 (+359% relative change) and the F1 score from 0.163 to 0.729 (+347% relative change) on a dataset that is considered challenging by its authors.

RESEARCH ON CHINESE OCR IN TAIWAN

1991 ◽  
Vol 05 (01n02) ◽  
pp. 139-164 ◽  
Author(s):  
FANG-HSUAN CHENG ◽  
WEN-HSING HSU
Keyword(s):  
Feature Extraction ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Chinese Character ◽  
Chinese Characters ◽  
Image Preprocessing ◽  
Large Sets ◽  
Basic Line ◽  
Optical Character ◽  
Taiwan Chinese

This paper describes typical research on Chinese optical character recognition in Taiwan. Chinese characters can be represented by a set of basic line segments called strokes. Several approaches to the recognition of handwritten Chinese characters by stroke analysis are described here. A typical optical character recognition (OCR) system consists of four main parts: image preprocessing, feature extraction, radical extraction and matching. Image preprocessing is used to provide the suitable format for data processing. Feature extraction is used to extract stable features from the Chinese character. Radical extraction is used to decompose the Chinese character into radicals. Finally, matching is used to recognize the Chinese character. The reasons for using strokes as the features for Chinese character recognition are the following. First, all Chinese characters can be represented by a combination of strokes. Second, the algorithms developed under the concept of strokes do not have to be modified when the number of characters increases. Therefore, the algorithms described in this paper are suitable for recognizing large sets of Chinese characters.

scholarly journals Improve OCR Accuracy with Advanced Image Preprocessing using Machine Learning with Python

2020 ◽  
Vol 9 (7) ◽  
pp. 1026-1030
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Image Preprocessing ◽  
Optical Character ◽  
Handwritten Text ◽  
Printed Text ◽  
Learning Machine

Optical Character Recognition or Optical Character Reader (OCR) is a pattern-based method consciousness that transforms the concept of electronic conversion of images of handwritten text or printed text in a text compiled. Equipment or tools used for that purpose are cameras and apartment scanners. Handwritten text is scanned using a scanner. The image of the scrutinized document is processed using the program. Identification of manuscripts is difficult compared to other western language texts. In our proposed work we will accept the challenge of identifying letters and letters and working to achieve the same. Image Preprocessing techniques can effectively improve the accuracy of an OCR engine. The goal is to design and implement a machine with a learning machine and Python that is best to work with more accurate than OCR's pre-built machines with unique technologies such as MatLab, Artificial Intelligence, Neural networks, etc.

Optical Character Recognition System for Nastalique Urdu-Like Script Languages Using Supervised Learning

2019 ◽  
Vol 33 (10) ◽  
pp. 1953004 ◽  
Author(s):  
S. S. R. Rizvi ◽  
A. Sagheer ◽  
K. Adnan ◽  
A. Muhammad
Keyword(s):  
Supervised Learning ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Complex Structure ◽  
Recognition Rate ◽  
Digital Text ◽  
Memory Space ◽  
Optical Character ◽  
Digital Format ◽  
Printed Text

There are two main techniques to convert written or printed text into digital format. The first technique is to create an image of written/printed text, but images are large in size so they require huge memory space to store, as well as text in image form cannot be undergo further processes like edit, search, copy, etc. The second technique is to use an Optical Character Recognition (OCR) system. OCR’s can read documents and convert manual text documents into digital text and this digital text can be processed to extract knowledge. A huge amount of Urdu language’s data is available in handwritten or in printed form that needs to be converted into digital format for knowledge acquisition. Highly cursive, complex structure, bi-directionality, and compound in nature, etc. make the Urdu language too complex to obtain accurate OCR results. In this study, supervised learning-based OCR system is proposed for Nastalique Urdu language. The proposed system evaluations under a variety of experimental settings apprehend 98.4% training results and 97.3% test results, which is the highest recognition rate ever achieved by any Urdu language OCR system. The proposed system is simple to implement especially in software front of OCR system also the proposed technique is useful for printed text as well as handwritten text and it will help in developing more accurate Urdu OCR’s software systems in the future.

Smart Reader for Visually Challenged Using Optical Character Recognition and Text-To-Speech

2020 ◽  
pp. 205-208
Author(s):  
Sowmya R ◽  
Sushma S Jagtap ◽  
Gnanamoorthy Kasthuri
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Speech Synthesis ◽  
Read Aloud ◽  
Text To Speech ◽  
Digital Text ◽  
Optical Character ◽  
The People ◽  
Text To Speech Synthesis ◽  
Visually Challenged

Assistive technology uses assistive, adaptive and rehabilitative devices for people with disabilities. It’s assessed there are about 36 million people with visual impairment in the world and a further 216 million who lead life with moderate to severe visual impairments. Leveraging technology has helped the visually challenged in carrying out tasks on par with the people blessed with vision particularly in the activities of reading and writing. In the proposed work, an image scanning device attached to a microcontroller is designed. This device is designed in the form of hand gloves for ease of usage. The glove with the camera at the fingertip, when rolled over lines of text, scans the information and converts it into digital text with Optical Character Recognition (OCR). The converted digital text is finally read aloud using Text-to-speech synthesis. The results obtained were accurate and met the standards of operability.

scholarly journals IMAGE BACKGROUND PROCESSING FOR COMPARING ACCURACY VALUES OF OCR PERFORMANCE

2020 ◽  
Vol 16 (1) ◽  
pp. 33-38
Author(s):  
Desiana Nur Kholifah ◽  
Hendri Mahmud Nawawi ◽  
Indra Jiwana Thira
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Visual Context ◽  
Document Images ◽  
Digital Text ◽  
Thresholding Method ◽  
Optical Character ◽  
Text Images ◽  
Background Image

Optical Character Recognition (OCR) is an application used to process digital text images into text. Many documents that have a background in the form of images in the visual context of the background image increase the security of documents that state authenticity, but the background image causes difficulties with OCR performance because it makes it difficult for OCR to recognize characters overwritten by background images. By removing background images can maximize OCR performance compared to document images that are still background. Using the thresholding method to eliminate background images and look for recall values, precision, and character recognition rates to determine the performance value of OCR that is used as the object of research. From eliminating the background image with thresholding, an increase in performance on the three types of OCR is used as the object of research.

scholarly journals Two-Dimensional Optical Character Recognition of Mouse Drawn in Turkish Capital Letters Using Multi-Layer Perceptron Classification

2019 ◽  
Vol 54 (4) ◽  
Author(s):  
Ehsan Ali Al-Zubaidi ◽  
Maad M. Mijwil ◽  
Aysar Sh. Alsaadi
Keyword(s):  
Machine Learning ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Back Propagation ◽  
Text Recognition ◽  
Back Propagation Algorithm ◽  
Digital Text ◽  
Development Environment ◽  
Optical Character ◽  
Printed Materials

The Optical Character Recognition (OCR) is software for text recognition that takes an image containing text, to transform it into strings, then save them into a format that make it able to use in text editing programs. The OCR plays a significant role in the transformation of printed materials into digital text files. These digital files can be very useful for children and adults who have awkward reading. This is because a digital text can be used with computer programs that allow people to read them in different ways. In this paper, we developed system for Turkish character recognition under visual studio (C#) development environment, where machine learning is used to accurately predict optical characters, the reason why it has a high precision and high recognition speed through deep learning, which is one of the machine learning methods for OCR when drawing letters by mouse on the screen, then recognize by using back propagation algorithm.

scholarly journals Optical Character Recognition Citra Kata Kanji Menggunakan Ekstraksi Fitur Algoritma Chain Code dan Algoritma L1-Metric

2021 ◽  
Vol 9 (2) ◽  
pp. 110
Author(s):  
Kevin Laurence Hartono ◽  
Karman Surya ◽  
Halim Agung
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Manhattan Distance ◽  
Chain Code ◽  
Optical Character

Kanji merupakan salah satu bahasa yang berasal dari negara Jepang. Bahasa Jepang sendiri telah menyebar di berbagai negara terutama di Indonesia. Namum dikarenakan bahasa Jepang bukanlah bahasa yang mudah dipelajari karena bahasa Jepang tidak termasuk kedalam bahasa Internasional. Oleh karena itu diperlukan sistem yang bisa membaca bahasa aksara bahasa Jepang khususnya kanji. Penelitian ini akan difokuskan pada perancangan aplikasi pengenalan karakter optik dari aksara kanji menggunakan ekstraksi fitur chain code untuk melakukan pengenalan pola dari citra aksara kanji dan perhitungan jarak manhattan distance (L1 Metric). Dalam membangun aplikasi digunakan bahasa pemrograman pascal menggunakan Lazarus IDE dan integrasi sistem basis data. Proses dalam penelitian ini terdiri dari 5 tahap yaitu pre-processing, segmentasi,  filtering spasial linier, ekstraksi fitur chain code, dan perhitungan jarak nilai fitur. Jarak citra kanji yang diuji akan dibandingkan dengan citra kanji yang sudah dilatih di basis data untuk mencari jarak terkecil. Hasil pengujian yang dilakukan dengan algoritma chain code dan manhattan distance (L1 Metric) menunjukkan bahwa sebesar 21.82% citra tulisan tangan kanji berhasil dikenali dan 78.18% mengalami kegagalan dalam mengenali citra yang diuji

Sign in / Sign up

Export Citation Format

Share Document