Offline optical character recognition (OCR) method: An effective method for scanned documents

We examine the use of character image analysis coupled with contextual information in complex data gathering forms to identify and correct optical character recognition (OCR) system rejection and substitution errors. Segmented characters from a complex data gathering form are initially classified using an OCR engine based on a combination of Karhunen-Loeve transforms and a back-propagation neural network. Systems of equations are derived from the data gathering form to determine the values of characters rejected by the OCR engine and to verify the consistency of the data captured. If the OCR results for a single form are determined to be inconsistent with respect to the form's data relationships, a set of decision algorithms which incorporates a second neural network and uses additional character features is used to tag characters according to their likelihood of substitution error. Potential substitution errors are incrementally added to the set of OCR reject errors and are processed through dynamically selected systems of equations and search techniques which correct both error classes. We provide experimental results and determine the extent to which errors can be detected and corrected for various OCR error rates.

To date, most optical character recognition (OCR) systems process binary document images, and the quality of the input image strongly affects their performance. Since a binarization process is inherently lossy, different algorithms typically produce different binary images from the same gray scale image. The objective of this research is to study effects of global binarization algorithms on the performance of OCR systems. Several binarization methods were examined: the best fixed threshold value for the data set, the ideal histogram method, and Otsu's algorithm. Four contemporary OCR systems and 50 hard copy pages containing 91,649 characters were used in the experiments. These pages were digitized at 300 dpi and 8 bits/pixel, and 36 different threshold values (ranging from 59 to 199 in increments of 4) were used. The resulting 1,800 binary images were processed by all four OCR systems. All systems made approximately 40% more errors from images generated by Otsu's method than those of the ideal histogram method. Two of the systems made approximately the same number of errors from images generated by the best fixed threshold value and Otsu's method.

Character recognition systems have contributed tremendously to the automation of data entry process. Many systems are present in software for character recognition. Digital signal processing has traditionally been done using enhanced microprocessors. While the high volume of generic product provides a low cost solution, its performance fall seriously short for many applications. Until recently, the only alternatives were to develop custom hardware (typically board level or ASIC), buy expensive fixed function processors (e.g. an FFT chip), or use an array of microprocessors. FPGAs offer an opportunity to accelerate your digital signal processing application up to 1000 times over a traditional DSP microprocessor. The main goal here is designing an optical character recognition (OCR) system in FPGA and to develop algorithms which are suitable for hardware implementation of OCR. The application proposed here is automatic calibration of measuring instrument based on OCR system in FPGA. This solution benefits from significant reducing of work quantity for calibration as well as from better replication and objectivity of measuring. The system entirely eliminates influence of the operator on the uncertainty calibration. As system is using FPGA there are many issues to be overcome like speed of operation, programmability and power consumption.

In this paper we present an end-to-end trainable optical character recognition (OCR) system for recognizing machine-printed text in Thai documents. The end-to-end OCR system is based on a script-independent methodology using hidden Markov models. Our system provides an integrated workflow beginning with annotation and transcription of training images to performing OCR on new images with models trained on transcribed training images. The efficacy of our end-to-end OCR system is demonstrated by rapidly configuring our OCR engine for the Thai script. We present experimental results on Thai documents to highlight the specific challenges posed by the Thai script and analyze the recognition performance as a function of amount of training data.

This study designed a finger-worn device-named the Chinese FingerReader-that can be practically applied by visually impaired users for recognizing traditional Chinese characters on the micro internet of things (IoT) processor. The device is portable, easy to operate, and designed to be worn on the index finger. The Chinese FingerReader on the index finger contains a small camera and buttons. The small camera captures images by identifying the relative position of the index finger to the printed text, and the buttons are applied to capture an image by visually impaired users and provide the audio output of the corresponding Chinese character by a voice prompt. To recognize Chinese characters, English letters, and numbers, a robust Chinese optical character recognition (OCR) system was developed according to the training strategy of an augmented convolution neural network algorithm. The proposed Chinese OCR system can segment a single character from the captured image, and the system can accurately recognize rotated Chinese characters. The experimental results revealed that compared with the OCR application programming interfaces of Google and Microsoft, the proposed OCR system obtains 95% accuracy rate in dealing with rotated character images where the Google and Microsoft OCR APIs only obtain 65% and 34% accuracy rates. These results illustrate that the proposed OCR system was more suitable for the needs of visually impaired people in actual use. Finally, three usage scenarios were simulated, and the accuracy and operational performance of the system were tested. Field tests of this system were conducted for visually impaired users to verify its feasibility.

Many current optical character recognition (OCR) systems attempt to decompose printed pages into a set of zones, each containing a single column of text, before converting the characters into coded form. The authors present a methodology for automatically assessing the accuracy of such decompositions, and demonstrate its use in evaluating six OCR systems.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

The main problems of Optical Character Recognition (OCR) systems are solved if printed latin text is considered. Since OCR systems are based upon binary images, their results are poor if the text is degraded. In this paper a codex consisting of ancient manuscripts is investigated. Due to environmental effects the characters of the analyzed codex are washed out which leads to poor results gained by state of the art binarization methods. Hence, a segmentation free approach based on local descriptors is being developed. Regarding local information allows for recognizing characters that are only partially visible. In order to recognize a character the local descriptors are initially classified with a Support Vector Machine (SVM) and then identified by a voting scheme of neighboring local descriptors. State of the art local descriptor systems are evaluated in this paper in order to compare their performance for the recognition of degraded characters.

Optical Character Recognition (OCR) deals with automated recognition of characters that are in the format of digital image. OCR refers to the process by which scanned images are electronically processed and converted to an editable document. Handwritten and printed texts are the primary research areas of an OCR. Many OCR systems are commercially available for English and Arabic characters but there is still no recognition system available which yields higher recognition rate even though the scanned images are of high quality. The general framework of a Tamil OCR in the literature involves: preprocessing, line segmentation, word segmentation, character segmentation, feature extraction and recognition of characters. OCR for printed Tamil documents poses challenge owing to: one line may have different font styles, presence of pictures, multi columns, touching of adjacent characters, presence of broken characters, low print quality and complex layout. Furthermore, when comparing 26 alphabets in English, Tamil language has 247 alphabets which makes the recognition more difficult. There are few OCRs for Tamil language that are freely available with a moderate recognition rate as the performance comparisons of such OCRs are not available on a benchmark dataset. In this paper we compare OCRs for printed Tamil texts on four different types of documents: books, magazines, newspapers and pamphlets. Furthermore we propose a post-processing error correction technique to the tested OCRs which reduces the overall mean error rate by nearly 10% on those four categories.

A VLSI implementation of the optical Chinese character recognition (OCCR) system with pipelined and parallel structure is presented. We also propose an efficient method for performing block classification and character segmentation as well as an effective and adaptive feature extraction algorithm for recognizing multifont printed Chinese characters. With the complex and huge amount of data involved in Chinese characters, their recognition requires numerous complex computations. Therefore, to improve the recognition efficiency for practical applications, a VLSI chip is designed and fabricated. To preserve a certain degree of flexibility so that various recognition algorithms can be implemented with the system, only the most time-consumig parts are implemented into the VLSI circuit. By combining the VLSI technology and the effective Chinese character recognition algorithm, a practical OCCR system with high speed, high-recognition rate, and accumulated learning capability is developed. Based on the experimental results, the VLSI chip can process up to 200 characters/s, which is one hundred times faster than the original software algorithm. The recognition rates of three different test conditions are also given.

Optical character recognition (OCR) systems have been widely used to convert documents into digital form. There are lots of both commercial and open source OCR systems available, but a benchmark on Turkish OCR is nonexistent. In this work, we first prepared two publicly available datasets for Turkish OCR, consisting of scanned document images and mobile camera captured document images. Then, we evaluated the Turkish OCR performance of three popular open source OCR systems (Tesseract, CuneiForm, GOCR) on the datasets. Tesseract outperformed the other two on both datasets.

To improve the readability, image compression, and optical character recognition (OCR) system performance for two-tone (binary) text image data, we investigated morphological methods of image processing. We found them to be fast and effective not only with noise text images but with relatively noise-free images as well. Using morphology, we improved text image readability as judged in a blind test, increased compression ratio using CCITT Group 4, and reduced OCR error (cluster) rates in a commercial omnifront scanner.

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the documents textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

Segmentation is one of the important steps of character recognition system. It is an important step because inaccurate segmentation of characters will cause errors in the recognition stage. In optical character Recognition (OCR) system the presence of touching characters and broken characters decreases the accuracy rate of character recognition. Touching of half character or full character with other full character makes the character segmentation very challenging or difficult task. Segmentation of the broken character is quite difficult because vertical profile projection technique assumes the broken parts of the characters as individual characters. In this paper, we have proposed the method of segmentation for touching and broken characters of handwritten Punjabi text that is the Gurumukhi script. The main purpose of this paper is to provide the new segmentation technique based on neighboring pixels for broken characters and increase the accuracy for touching characters.

With the increasing demand for digitization, Optical Character Recognition (OCR) systems play a vital role in digitizing physical manuscripts. Several methods have been successfully deployed in the OCR domain. However, they often face challenges when dealing with low-resource regional scripts because of the limited training data and complex structure of characters. In such a scenario, Siamese Network (SN) meta-learning offers a promising solution for this problem by enabling quick adaptation to new tasks with minimal training data. Despite the success of SNs in various classification tasks, the traditional SN architecture seeks a compelling upgrade to improve its ability to distinguish between similar-looking characters of regional scripts. In this research paper, we propose a novel Priority-Smart Network (PSN) framework for traditional SN architectures, which can easily be incorporated into existing CNN backbone and improve their ability to identify characters in low-resource regional scripts. Furthermore, we propose the Enhanced Differential Edge Detection (EDED) preprocessing strategy explicitly designed for OCR tasks. We rigorously investigate and evaluate three benchmark low-resource script datasets to establish the effectiveness of our proposed techniques. Our experimentation results showcase significant advancements in character recognition accuracy and robustness, emphasizing the potential of SN combined with the PSN framework and EDED strategy for improving OCR systems in low-resource script.

Manual Data Collection from a student's exam-sheets is always a tedious job which exacts ample amount of time and effort. This paper has suggested a novel approach for developing an automatic, adaptive, fast and reliable system capable of recognizing enrolment number and corresponding marks of student from answer sheet and storing it in the host computer. This system consist a hardware which picks out sheets one by one from a bundle and captures image of the front page of each answer script. This image is processed by proposed robust extraction and noise removal algorithm adaptive to environmental conditions. It is then passed through Optical Character Recognition (OCR) system which extracts characters using correlation. Accuracy of system depends on the sample space size of OCR system. In our experiment we have archived average 81% accuracy in various light and paper (Exam-Sheet) condition. We had trained the OCR with 50 samples of numerals set (0–9). In this way developed system will not only replace the traditional tiring way of manual writing of marks in database but in addition can calculate average marks of all students, ranges of marks for assigning different grade and provide grade for each student automatically