9 pages, 4 figures, 4 tables, 2 algorithms, accepted in the International Conference of Digital Image Processing and Pattern Recognition (DPPR), London, UK, November 2020
Optical Character Recognition (OCR) is the process of extracting digitized text from images of scanned documents. While OCR systems have already matured in many languages, they still have shortcomings in cursive languages with overlapping letters such as the Arabic language. This paper proposes a complete Arabic OCR system that takes a scanned image of Arabic Naskh script as an input and generates a corresponding digital document. Our Arabic OCR system consists of the following modules: Pre-processing, Word-level Feature Extraction, Character Segmentation, Character Recognition, and Post-processing. This paper also proposes an improved font-independent character segmentation algorithm that outperforms the state-of-the-art segmentation algorithms. Lastly, the paper proposes a neural network model for the character recognition task. The system has experimented on several open Arabic corpora datasets with an average character segmentation accuracy 98.06%, character recognition accuracy 99.89%, and overall system accuracy 97.94% achieving outstanding results compared to the state-of-the-art Arabic OCR systems.
This research is the second phase in a series of investigations on developing an Optical Character Recognition (OCR) of Arabic historical documents and examining how different modeling procedures interact with the problem. The first research studied the effect of Transformers on our custom-built Arabic dataset. One of the downsides of the first research was the size of the training data, a mere 15000 images from our 30 million images, due to lack of resources. Also, we add an image enhancement layer, time and space optimization, and Post-Correction layer to aid the model in predicting the corr…
When Do VLMs Help Arabic Manuscript OCR? A Cross-Dataset Study
Qatar Computing Research Institute（卡塔尔计算研究所）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）；Northwestern University in Qatar（卡塔尔西北大学）；University of Doha for Science Technology（多哈科技大学）
Leipzig University（莱比锡大学）；Aga Khan University（阿迦汗大学）；Roshan Institute for Persian Studies, University of Maryland, College Park（马里兰大学帕克分校罗尚波斯研究中心）
The OpenITI team has achieved Optical Character Recognition (OCR) accuracy rates for classical Arabic-script texts in the high nineties. These numbers are based on our tests of seven different Arabic-script texts of varying quality and typefaces, totaling over 7,000 lines. These accuracy rates not only represent a distinct improvement over the actual accuracy rates of the various proprietary OCR options for classical Arabic-script texts, but, equally important, they are produced using an open-source OCR software, thus enabling us to make this Arabic-script OCR technology freely available to th…
Contrary to popular belief, Optical Character Recognition (OCR) remains a challenging problem when text occurs in unconstrained environments, like natural scenes, due to geometrical distortions, complex backgrounds, and diverse fonts. In this paper, we present a segmentation-free OCR system that combines deep learning methods, synthetic training data generation, and data augmentation techniques. We render synthetic training data using large text corpora and over 2000 fonts. To simulate text occurring in complex natural scenes, we augment extracted samples with geometric distortions and with a …
University Sains Malaysia（马来西亚理科大学）；University of Sindh（信德大学）
A large number of publications are available for the Optical Character Recognition (OCR). Significant researches, as well as articles are present for the Latin, Chinese and Japanese scripts. Arabic script is also one of mature script from OCR perspective. The adaptive languages which share Arabic script or its extended characters; still lacking the OCRs for their language. In this paper we present the efforts of researchers on Arabic and its related and adapted languages. This survey is organized in different sections, in which introduction is followed by properties of Sindhi Language. OCR pro…
University of Vigo（维戈大学）；University of Sfax, National School of Engineers (ENIS)（斯法克斯大学国家工程师学院）
In this paper we propose a robust approach for text extraction and recognition from video clips which is called Neuro-Fuzzy system for Arabic Video OCR. In Arabic video text recognition, a number of noise components provide the text relatively more complicated to separate from the background. Further, the characters can be moving or presented in a diversity of colors, sizes and fonts that are not uniform. Added to this, is the fact that the background is usually moving making text extraction a more intricate process. Video include two kinds of text, scene text and artificial text. Scene text i…
The use of OCR in postal services is not yet universal and there are still many countries that process mail sorting manually. Automated Arabic/Indian numeral Optical Character Recognition (OCR) systems for Postal services are being used in some countries, but still there are errors during the mail sorting process, thus causing a reduction in efficiency. The need to investigate fast and efficient recognition algorithms/systems is important so as to correctly read the postal codes from mail addresses and to eliminate any errors during the mail sorting stage. The objective of this study is to rec…
In this work we propose an OCR scheme for manuscripts printed in Rashi font that is an ancient Hebrew font and corresponding dialect used in religious Jewish literature, for more than 600 years. The proposed scheme utilizes a convolution neural network (CNN) for visual inference and Long-Short Term Memory (LSTM) to learn the Rashi scripts dialect. In particular, we derive an AutoML scheme to optimize the CNN architecture, and a book-specific CNN training to improve the OCR accuracy. The proposed scheme achieved an accuracy of more than 99.8% using a dataset of more than 3M annotated letters fr…
Classifying pages or text lines into font categories aids transcription because single font Optical Character Recognition (OCR) is generally more accurate than omni-font OCR. We present a simple framework based on Convolutional Neural Networks (CNNs), where a CNN is trained to classify small patches of text into predefined font classes. To classify page or line images, we average the CNN predictions over densely extracted patches. We show that this method achieves state-of-the-art performance on a challenging dataset of 40 Arabic computer fonts with 98.8\% line level accuracy. This same method…
OCR algorithms have received a significant improvement in performance recently, mainly due to the increase in the capabilities of artificial intelligence algorithms. However, this advancement is not evenly distributed over all languages. Urdu is among the languages which did not receive much attention, especially in the font independent perspective. There exists no automated system that can reliably recognize printed Urdu text in images and videos across different fonts. To help bridge this gap, we have developed Qaida, a large scale data set with 256 fonts, and a complete Urdu lexicon. We hav…
Centre for Vision Information Technology International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院视觉信息技术中心）
Scene-text recognition is remarkably better in Latin languages than the non-Latin languages due to several factors like multiple fonts, simplistic vocabulary statistics, updated data generation tools, and writing systems. This paper examines the possible reasons for low accuracy by comparing English datasets with non-Latin languages. We compare various features like the size (width and height) of the word images and word length statistics. Over the last decade, generating synthetic datasets with powerful deep learning techniques has tremendously improved scene-text recognition. Several control…
Handwritten numeral recognition is in general a benchmark problem of Pattern Recognition and Artificial Intelligence. Compared to the problem of printed numeral recognition, the problem of handwritten numeral recognition is compounded due to variations in shapes and sizes of handwritten characters. Considering all these, the problem of handwritten numeral recognition is addressed under the present work in respect to handwritten Arabic numerals. Arabic is spoken throughout the Arab World and the fifth most popular language in the world slightly before Portuguese and Bengali. For the present wor…
Jadavpur University（贾达沃普尔大学）；Atrenta (I) Pvt. Ltd（阿特伦塔（印度）私人有限公司）；MCKV Institute of Engineering（MCKV工程学院）
The work presents a comparative assessment of seven different feature sets for recognition of handwritten Arabic numerals using a Multi Layer Perceptron (MLP) based classifier. The seven feature sets employed here consist of shadow features, octant centroids, longest runs, angular distances, effective spans, dynamic centers of gravity, and some of their combinations. On experimentation with a database of 3000 samples, the maximum recognition rate of 95.80% is observed with both of two separate combinations of features. One of these combinations consists of shadow and centriod features, i. e. 8…
Although lots of progress were made in Text Recognition/OCR in recent years, the task of font recognition is remaining challenging. The main challenge lies in the subtle difference between these similar fonts, which is hard to distinguish. This paper proposes a novel font recognizer with a pluggable module solving the font recognition task. The pluggable module hides the most discriminative accessible features and forces the network to consider other complicated features to solve the hard examples of similar fonts, called HE Block. Compared with the available public font recognition systems, o…
Arabic is one of the languages that present special challenges to Optical character recognition (OCR). The main challenge in Arabic is that it is mostly cursive. Therefore, a segmentation process must be carried out to determine where the character begins and where it ends. This step is essential for character recognition. This paper presents Arabic character segmentation algorithm. The proposed algorithm uses the projection-based approach concepts to separate lines, words, and characters. This is done using profile's amplitude filter and simple edge tool to find characters separations. Our al…
ReceiptSense: Beyond Traditional OCR -- A Dataset for Receipt Understanding
Innsbruck University（因斯布鲁克大学）；High Institute for Computers（计算机与管理信息高级学院）；Chungbuk National University（Chungbuk国立大学）；Louisville University（路易斯维尔大学）；University of Innsbruck（因斯布鲁克大学）
Society for Natural Language Technology Research（自然语言技术研究协会）；Techno India University（Techno印度大学）
This paper presents a printed Bengali and English text OCR system developed by us using a single hidden BLSTM-CTC architecture having 128 units. Here, we did not use any peephole connection and dropout in the BLSTM, which helped us in getting better accuracy. This architecture was trained by 47,720 text lines that include English words also. When tested over 20 different Bengali fonts, it has produced character level accuracy of 99.32% and word level accuracy of 96.65%. A good Indic multi script OCR system is also developed by Google. It sometimes recognizes a character of Bengali into the sam…
There are many difficulties facing a handwritten Arabic recognition system such as unlimited variation in human handwriting, similarities of distinct character shapes, interconnections of neighbouring characters and their position in the word. The typical Optical Character Recognition (OCR) systems are based mainly on three stages, preprocessing, features extraction and recognition. This paper proposes new methods for handwritten Arabic character recognition which is based on novel preprocessing operations including different kinds of noise removal also different kind of features like structur…
Identifying the type of font (e.g., Roman, Blackletter) used in historical documents can help optical character recognition (OCR) systems produce more accurate text transcriptions. Towards this end, we present an active-learning strategy that can significantly reduce the number of labeled samples needed to train a font classifier. Our approach extracts image-based features that exploit geometric differences between fonts at the word level, and combines them into a bag-of-word representation for each page in a document. We evaluate six sampling strategies based on uncertainty, dissimilarity and…
Optical character recognition (OCR) is a fundamental problem in computer vision. Research studies have shown significant progress in classifying printed characters using deep learning-based methods and topologies. Among current algorithms, recurrent neural networks with long-short term memory blocks called RNN-LSTM have provided the highest performance in terms of accuracy rate. Using the top 5,000 French words collected from the internet including all signs and accents, RNN-LSTM models were trained and tested for several cases. Six fonts were used to generate OCR samples and an additional dat…
Sharif University of Technology（谢里夫理工大学）；National University of Singapore（新加坡国立大学）；Shahid Beheshti University（沙希德·贝赫什提大学）
In this paper, we introduce a model-based omnifont Persian OCR system. The system uses a set of 8 primitive elements as structural features for recognition. First, the scanned document is preprocessed. After normalizing the preprocessed image, text rows and sub-words are separated and then thinned. After recognition of dots in sub-words, strokes are extracted and primitive elements of each sub-word are recognized using the strokes. Finally, the primitives are compared with a predefined set of character identification vectors in order to identify sub-word characters. The separation and recognit…
Arabic text recognition is a challenging task because of the cursive nature of Arabic writing system, its joint writing scheme, the large number of ligatures and many other challenges. Deep Learning DL models achieved significant progress in numerous domains including computer vision and sequence modelling. This paper presents a model that can recognize Arabic text that was printed using multiple font types including fonts that mimic Arabic handwritten scripts. The proposed model employs a hybrid DL network that can recognize Arabic printed text without the need for character segmentation. The…
A Kannada OCR, named Lipi Gnani, has been designed and developed from scratch, with the motivation of it being able to convert printed text or poetry in Kannada script, without any restriction on vocabulary. The training and test sets have been collected from over 35 books published between the period 1970 to 2002, and this includes books written in Halegannada and pages containing Sanskrit slokas written in Kannada script. The coverage of the OCR is nearly complete in the sense that it recognizes all the punctuation marks, special symbols, Indo-Arabic and Kannada numerals and also the intersp…
In this paper we evaluate Optical Character Recognition (OCR) of 19th century Fraktur scripts without book-specific training using mixed models, i.e. models trained to recognize a variety of fonts and typesets from previously unseen sources. We describe the training process leading to strong mixed OCR models and compare them to freely available models of the popular open source engines OCRopus and Tesseract as well as the commercial state of the art system ABBYY. For evaluation, we use a varied collection of unseen data from books, journals, and a dictionary from the 19th century. The experime…
MSDA group, Mohammed VI Polytechnic University (UM6P)（穆罕默德六世理工大学）
Significant number of researches have been developed recently around intelligent system for traffic management, especially, OCR based license plate recognition, as it is considered as a main step for any automatic traffic management system. Good quality data sets are increasingly needed and produced by the research community to improve the performance of those algorithms. Furthermore, a special need of data is noted for countries having special characters on their licence plates, like Morocco, where Arabic Alphabet is used. In this work, we present a labeled open data set of circulation plates…
Some historical and more recent printed documents have been scanned or stored at very low resolutions, such as 60 dpi. Though such scans are relatively easy for humans to read, they still present significant challenges for optical character recognition (OCR) systems. The current state-of-the art is to use super-resolution to reconstruct an approximation of the original high-resolution image and to feed this into a standard OCR system. Our novel end-to-end method bypasses the super-resolution step and produces better OCR results. This approach is inspired from our understanding of the human vis…
M. S. Ramaiah Institute of Technology（M. S. 拉迈亚理工学院）
Intensive research has been done on optical character recognition ocr and a large number of articles have been published on this topic during the last few decades. Many commercial OCR systems are now available in the market, but most of these systems work for Roman, Chinese, Japanese and Arabic characters. There are no sufficient number of works on Indian language character recognition especially Kannada script among 12 major scripts in India. This paper presents a review of existing work on printed Kannada script and their results. The characteristics of Kannada script and Kannada Character R…
Techo Startup Center (TSC)（德卓创业中心）；Royal University of Phnom Penh (RUPP)（金边皇家大学）
This paper presents an end-to-end deep convolutional recurrent neural network solution for Khmer optical character recognition (OCR) task. The proposed solution uses a sequence-to-sequence (Seq2Seq) architecture with attention mechanism. The encoder extracts visual features from an input text-line image via layers of residual convolutional blocks and a layer of gated recurrent units (GRU). The features are encoded in a single context vector and a sequence of hidden states which are fed to the decoder for decoding one character at a time until a special end-of-sentence (EOS) token is reached. T…
Sousse University, National Engineering School of Sousse（苏塞大学，苏塞国家工程学院）；LATIS - Laboratory of Advanced Technology and Intelligent Systems（先进技术与智能系统实验室（LATIS））
Current systems used by the Tunisian national archives for the automatic transcription of archival documents are hindered by many issues related to the performance of the optical character recognition (OCR) tools. Indeed, using a classical OCR system to transcribe and index ancient Arabic documents is not a straightforward task due to the idiosyncrasies of this category of documents, such as noise and degradation. Thus, applying an enhancement method or a denoising technique remains an essential prerequisite step to ease the archival document image analysis task. The state-of-the-art methods a…
A line of a bilingual document page may contain text words in regional language and numerals in English. For Optical Character Recognition (OCR) of such a document page, it is necessary to identify different script forms before running an individual OCR system. In this paper, we have identified a tool of morphological opening by reconstruction of an image in different directions and regional descriptors for script identification at word level, based on the observation that every text has a distinct visual appearance. The proposed system is developed for three Indian major bilingual documents, …
Al Imam Mohammad Ibn Saud Islamic University（伊玛目穆罕默德·本·沙特伊斯兰大学）；Cairo University（开罗大学）
Arabic language is one of the most popular languages in the world. Hundreds of millions of people in many countries around the world speak Arabic as their native speaking. However, due to complexity of Arabic language, recognition of printed and handwritten Arabic text remained untouched for a very long time compared with English and Chinese. Although, in the last few years, significant number of researches has been done in recognizing printed and handwritten Arabic text, it stills an open research field due to cursive nature of Arabic script. This paper proposes automatic printed Arabic text …
