Cursive Script Research Articles

An ensemble of neural networks for nonlinear segmentation of overlapped cursive script

Precise character segmentation is the only solution towards higher optical character recognition (OCR) accuracy. In cursive script, overlapped characters are serious issue in the process of character segmentations as characters are deprived from their discriminative parts using conventional linear segmentation strategy. Hence, nonlinear segmentation is an utmost need to avoid loss of characters parts and to enhance character/script recognition accuracy. This paper presents an improved approach for nonlinear segmentation of the overlapped characters in handwritten roman script. The proposed approach presents a set of rules that are derived heuristically to search character boundaries of the cursive script that is validated by using ensemble of neural confidence. Accordingly, correct boundaries are retained and incorrect are removed based on ensemble neural networks vote. Finally, based on verified valid segmentation points, characters are segmented nonlinearly. For fair comparison CEDAR benchmark database is experimented. The experimental results are much better than conventional linear character segmentation techniques reported in the state of art. Ensemble neural network play vital role to enhance character segmentation accuracy as compared to individual neural networks.

An ensemble of neural networks for nonlinear segmentation of overlapped cursive script

Precise character segmentation is the only solution towards higher Optical Character Recognition (OCR) accuracy. In cursive script, overlapped characters are serious issue in the process of character segmentations as characters are deprived from their discriminative parts using conventional linear segmentation strategy. Hence, non-linear segmentation is an utmost need to avoid loss of characters parts and to enhance character/script recognition accuracy. This paper presents an improved approach for non-linear segmentation of the overlapped characters in handwritten roman script. The proposed technique is composed of a sequence of heuristic rules based on geometrical features of characters to locate possible non-linear character boundaries in a cursive script word. However, to enhance efficiency, heuristic approach is integrated with trained ensemble neural network validation strategy for verification of character boundaries. Accordingly, correct boundaries are retained and incorrect are removed based on ensemble neural networks vote. Finally, based on verified valid segmentation points, characters are segmented non-linearly. For fair comparison CEDAR benchmark database is experimented. The experimental results are much better than conventional linear character segmentation techniques reported in the state of art. Ensemble neural network play vital role to enhance character segmentation accuracy as compared to individual neural networks.

Urdu-Text Detection and Recognition in Natural Scene Images Using Deep Learning

Urdu text is a cursive script and belongs to a non-Latin family of other cursive scripts like Arabic, Chinese, and Hindi. Urdu text poses a challenge for detection/localization from natural scene images, and consequently recognition of individual ligatures in scene images. In this paper, a methodology is proposed that covers detection, orientation prediction, and recognition of Urdu ligatures in outdoor images. As a first step, the custom FasterRCNN algorithm has been used in conjunction with well-known CNNs like Squeezenet, Googlenet, Resnet18, and Resnet50 for detection and localization purposes for images of size $320\times 240$ pixels. For ligature Orientation prediction, a custom Regression Residual Neural Network (RRNN) is trained/tested on datasets containing randomly oriented ligatures. Recognition of ligatures was done using Two Stream Deep Neural Network (TSDNN). In our experiments, five-set of datasets, containing 4.2K and 51K Urdu-text-embedded synthetic images were generated using the CLE annotation text to evaluate different tasks of detection, orientation prediction, and recognition of ligatures. These synthetic images contain 132, and 1600 unique ligatures corresponding to 4.2K and 51K images respectively, with 32 variations of each ligature (4-backgrounds and font 8-color variations). Also, 1094 real-world images containing more than 12k Urdu characters were used for TSDNN’s evaluation. Finally, all four detectors were evaluated and used to compare them for their ability to detect/localize Urdu-text using average-precision (AP). Resnet50 features based FasterRCNN was found to be the winner detector with AP of.98. While Squeeznet, Googlenet, Resnet18 based detectors had testing AP of.65,.88, and.87 respectively. RRNN achieved and accuracy of 79% and 99% for 4k and 51K images respectively. Similarly, for characters classification in ligatures, TSDNN attained a partial sequence recognition rate of 94.90% and 95.20% for 4k and 51K images respectively. Similarly, a partial sequence recognition rate of 76.60% attained for real world-images.

Aesthetic Experience of Field Cognitive Style in the Appreciation of Cursive and Running Scripts: An Eye Movement Study

This study compares the characteristics of the aesthetic experience of different cognitive styles in calligraphy style. The study used a cursive script and running script as experimental materials and the EyeLink 1000 Plus eye tracker to record eye movements while viewing calligraphy. The results showed that, in the overall analysis, there were differences in the field cognition style in total fixation counts, saccade amplitude, and saccade counts and differences in the calligraphic style in total fixation counts and saccade counts. Further local analysis found significant differences in the field cognitive style in mean pupil diameter, fixation counts, and regression in count, and that there were differences in fixation counts and regression in count in the calligraphic style, as well as interactions with the area of interest. The results indicate that the field cognitive style is characterized by different aesthetic experiences in calligraphy appreciation and that there are aesthetic preferences in calligraphy style.

서론(書論)의 기원 최완(崔瑗)의 『초서세(草書勢)』 사상에 대한 견해

서론(書論)의 기원 최완(崔瑗)의 『초서세(草書勢)』 사상에 대한 견해

서론(書論)의 기원 최완(崔瑗)의 『초서세(草書勢)』 사상에 대한 견해

서론(書論)의 기원 최완(崔瑗)의 『초서세(草書勢)』 사상에 대한 견해

Handwritten Text Recognition using Machine Learning Techniques in Application of NLP

Handwriting Detection is a technique or ability of a Computer to receive and interpret intelligible handwritten input from source such as paper documents, touch screen, photo graphs etc. Handwritten Text recognition is one of area pattern recognition. The purpose of pattern recognition is to categorizing or classification data or object of one of the classes or categories. Handwriting recognition is defined as the task of transforming a language represented in its spatial form of graphical marks into its symbolic representation. Each script has a set of icons, which are known as characters or letters, which have certain basic shapes. The goal of handwriting is to identify input characters or image correctly then analyzed to many automated process systems. This system will be applied to detect the writings of different format. The development of handwriting is more sophisticated, which is found various kinds of handwritten character such as digit, numeral, cursive script, symbols, and scripts including English and other languages. The automatic recognition of handwritten text can be extremely useful in many applications where it is necessary to process large volumes of handwritten data, such as recognition of addresses and postcodes on envelopes, interpretation of amounts on bank checks, document analysis, and verification of signatures. Therefore, computer is needed to be able to read document or data for ease of document processing.

Lucilius and Nigidius Figulus on orthographic iconicity

AbstractThe comic poet Lucilius proposed several orthographic prescriptions in the ninth book of hisSatirae, written in the period 115–110 BC. In dealing with this topic, Lucilius severely criticized Accius’ statements on orthography, refusing his proposals of doubling vowels (“geminatio vocalium”) and overgeneralization of <ei> for /i:/. Lucilius’ prescriptions, which were borrowed by the philosopher Nigidius Figulus a century later, clearly follow the iconical principles of the pseudo-Stoicσυμπάσχειν-theory. In this paper a new interpretation of the orthographic iconicity in Lucilius’ and Nigidius’ doctrine is proposed, with reference to the case morphemes of *-ŏ- and *-ā- stems. As a matter of fact, “thickening” and “thinning” of the letter-forms (addĕrevstenuāre,pinguisvstenuis) can be satisfactorily explained only by taking account of <EI> and<I>spellings in a cursive script (namely <III> vs <I>). Finally, the key to explain the technical termstenuis‘thin’ vspinguis‘thick’ is traced back to an ancient metaphor of the wool-spinning practices.

The Effects of Script and Orthographic Complexity on the Handwriting and Spelling Performance of Children With Dyslexia

Handwriting and spelling problems are often associated in dyslexia. However, the nature of their association is still unclear, and most of the existing research in this area is on deep orthographies (mainly English). The extent to which findings are applicable across languages is uncertain. This article examines the effects of script (manuscript/cursive) and orthographic complexity (complex/simple spellings) on the word dictation and word-copying performance of a group of 24 Italian children with dyslexia and handwriting difficulties (DH group, aged 8–10). Their performance was compared with that of a chronologically age–matched group (CA) and a group of younger children matched to the DH group for their handwriting skills (HA: handwriting age group). Children performed two classical handwriting tasks: the alphabet task and a sentence-copy task, and dictation and copy tasks of orthographically complex words and orthographically simple words. Copying was performed in manuscript and cursive. The results show that although the DH group shows a significant deficit in graphomotor processes, orthographic complexity more than the visual-motor characteristics of the task (i.e., script) affects their performance in handwriting. An advantage for cursive script in DH children, but not in the other two groups, emerges from the study.

Analysis of Image Pre-processing in Noisy Character Recognition

This paper demonstrates the importance of various pre-processing steps for the noisy character recognition system with the help of MATLAB simulated results. Image pre-processing is one of the first and foremost steps for working with images of noisy characters among handwritten characters, printed characters, online written characters or offline written character, and it can have mixed font characters, omni-font characters, boxed discrete character, spaced discrete character or pure cursive script writing. Pre-processing of such image aims at image noise reduction, image normalization, and image compression. This paper shows that there are various steps/methods of image pre-processing. The sequence and use of a particular step/method is used based on the application requirement. The simulation result presented in this paper highlights the usability of each pre-processing steps and review the commonly used methods of each preprocessing stage.

An efficient, font independent word and character segmentation algorithm for printed Arabic text

Characters segmentation is a necessity and the most critical stage in Arabic OCR system. It has attracted the interest of a wide range of researchers. However, the nature of the Arabic cursive script poses extra challenges that need further investigation. Therefore, having a reliable and efficient Arabic OCR system that is independent of font variations is highly required. In this paper, an indirect, font-in dependent word and character segmentation algorithm for printed Arabic text investigated. The proposed algorithm takes a binary line image as an input and produces a set of binary images consisting of one character or ligature as an output. The segmentation performed at two levels: a word segmentation performed in the first level, by employing a vertical projection at the input line image along with using Interquartile Range (IQR) method to differentiate between word gaps and within word gaps. A projection profile method used as a second level of segmentation along with a set of statistical and topological features, which are font-independent, to identify the correct segmentation points from all potential points. The APTI dataset used to test the proposed algorithm with a variety of font type, size, and style. The algorithm experimented on 1800 lines (approximately 24,816 words) with an average accuracy of 97.7% for words segmentation and 97.51% for characters segmentation.

Recognition of printed Urdu ligatures using convolutional neural networks

We present a holistic technique for recognition of text in cursive scripts using printed Urdu ligatures as a case study. Convolutional neural networks (CNNs) are trained on high-frequency ligature clusters for feature extraction and classification. A query ligature presented to the system is first divided into primary and secondary ligatures that are separately recognized and later associated in a postprocessing step to recognize the complete ligature. Experiments are carried out using transfer learning on pretrained networks as well as by training a network from scratch. The technique is evaluated on ligatures extracted from two standard databases of printed Urdu text, Urdu printed text image (UPTI) and Center of Language Engineering (CLE), as well as by combining the ligatures of the two datasets. The system realizes high recognition rates of 97.81% and 89.20% on the UPTI and CLE databases, respectively.

Arabic Cursive Text Recognition from Natural Scene Images

This paper presents a comprehensive survey on Arabic cursive scene text recognition. The recent years’ publications in this field have witnessed the interest shift of document image analysis researchers from recognition of optical characters to recognition of characters appearing in natural images. Scene text recognition is a challenging problem due to the text having variations in font styles, size, alignment, orientation, reflection, illumination change, blurriness and complex background. Among cursive scripts, Arabic scene text recognition is contemplated as a more challenging problem due to joined writing, same character variations, a large number of ligatures, the number of baselines, etc. Surveys on the Latin and Chinese script-based scene text recognition system can be found, but the Arabic like scene text recognition problem is yet to be addressed in detail. In this manuscript, a description is provided to highlight some of the latest techniques presented for text classification. The presented techniques following a deep learning architecture are equally suitable for the development of Arabic cursive scene text recognition systems. The issues pertaining to text localization and feature extraction are also presented. Moreover, this article emphasizes the importance of having benchmark cursive scene text dataset. Based on the discussion, future directions are outlined, some of which may provide insight about cursive scene text to researchers.

Islamic Calligraphy in the Special Collections of the Romanian Academy Library in Cluj-Napoca / La calligraphie islamique dans les collections speciales de la Bibliotheque de l’Academie Roumaine de Cluj-Napoca

Minor art in the West, calligraphy was revered in the Islamic world, developing in amazingly diverse and original ways and revealing the aspiration to devise a radically non-mimetic visual construction to exalt and spread the Divine Word in a culture that frowns on making an image of the divine and its creation. Paper and the emergence of bureaucratic elite prompted the development of sophisticated calligraphic styles with six standardized cursive scripts, the nature of the text or the prospective readers determining the type of writing employed for literary, religious, or administrative works. The Islamic manuscripts and books in the Romanian Academy Library of Cluj-Napoca, the legacy of the celebrated scholar Timotei Cipariu, illustrate a wide repertoire of styles, once again demonstrating the inherent potential of Islamic calligraphy for developing a variety of versatile ornamental forms, while remaining true to its key role to communicate facts and express thoughts and feelings.

Improving Urdu Recognition Using Character-Based Artistic Features of Nastalique Calligraphy

The state-of-the-art Urdu recognition approaches for Nastalique use features along with the sequence of characters’ labels for classification and recognition. In Arabic-like cursive script, the characters are joined together to form a ligature. The conventional methods process the connected stroke of ligatures as a sequence of characters. However, connected stroke of a ligature image has a sequence of pairs of characters and their joiners, instead of a sequence of characters. The character has a distinctive shape that clearly distinguishes it from other characters. The joiner preserves the connecting stroke shape of a character with the next character. In this paper, an implicit Urdu character recognition technique is presented for the Nastalique writing style that is based on recognition of characters and joiners. The detailed analysis of the Nastalique calligraphy is carried out to extract the artistic features of characters and their joiners. The presented technique is tested on Dataset-1 of 1446 ligature classes covering 3309762 ligature instances and 91129 unique Urdu words. In addition, the system is also tested on 1600 text lines of UPTI dataset called Dataset-2. The character recognition accuracies are 95.58% and 98.37% on Dataset-1 and Dataset-2, respectively. The results reveal that the system outperforms the state-of-the-art hidden Markov models and deep learning-based Urdu recognition techniques.

Two Stream Deep Neural Network for Sequence-Based Urdu Ligature Recognition

Urdu text is a complex cursive script and poses a challenge for recognition by OCR systems due to its large number of ligatures and cursive style. In literature, several techniques have been proposed to recognize Urdu ligatures. However, we have investigated that, suitable challenging datasets and the consequently higher recognition rate is needed for ligature recognition. In this paper, a hybrid model based on the holistic approach is adopted for the recognition of Urdu ligatures (compound characters). More than 3800 unique ligatures were used to generate 46K (38K training, 7K testing) synthetic ligatures with 9 different kinds of transformations along with the normal ligatures. Each ligature is processed through two streams of Deep Neural Networks, namely Alexnet and Vgg16 to obtain a unique set of features corresponding to each net. These features are fused and then used as an input to double layer Bidirectional Long Short Term (BLSTM) network for learning a model. The learned model maps ligature images to their corresponding sequence of individual Urdu characters. In the proposed methodology output is in the editable Urdu-script format. The proposed model was evaluated and have shown an accuracy of 97% on the training dataset and 80% on more than 7K parametrically different query ligatures (test-set).

Theodosius’ Sphaerica: A Second Arabic Translation

An Arabic translation of the Sphaerica of Theodosius of Bithynia (around 100 B.C.) accompanied by its Latin translation by Gerard of Cremona had been edited by P. Kunitzsch and R. Lorch in 2010. Apart from that, there exists a second Arabic translation of this text in two manuscripts in Hebrew cursive script. For readers interested in the matter, we here edit the text of Book I of the work in this second version and discuss some differences here from the version edited in 2010.

Traditions of Connoisseurship (Jian) and Eccentricity (Xie) in Fu Shan’s Calligraphy (1607–1684)

The works of the well-known erudite and master of eccentric cursive writing Fu Shan (1607–1684) have been thoroughly studied in China, but there is little research on them in art history in the Western countries, and they are barely known among Russian orientalists. Fu Shan used the legacy of ancient epigraphy to reform both cursive (caoshu) and non-cursive scripts (zhuanshu, lishu, kaishu). Fu Shan relied on the assumption that all scripts have unified plastic principles. His expressive cursive writing has basic elements of non-cursive scripts, while his non-cursive writing has the dynamic potential of a cursive script. Fu Shan’s exceptional connoisseurship made him a forerunner of the archaizing trend in the “Stele School” (beixuepai). He was also famous for his eccentric experiments with character forms and the composition of character columns that became an important element of Chinese calligraphy in the tenth and eleventh centuries. This article recounts the milestones of Fu Shan’s life, shows trends of continuity in his works, and their evolution. The quotations of Fu Shan and the most prominent examples of his work are used to study his artistic principles. This article explains Fu Shan’s “four norms, four taboos” (si nin si wu) that are connected with the specific aesthetics of mastery concealment and the principle of plastic dissonance (zhili). For Fu Shan, the lack of self-confident virtuosity (qiao) and the quality of being crude and ugly (zhuo) meant that a work of art reflected the natural order of Dao. The diversity of his artistic studies and the syncretic character of his worldview made it possible for Fu Shan to retain his artistic freedom while adhering to tradition. Due to the combinationof connoisseurship and eccentric innovation, Fu Shan’s art has preserved its integrity and the enduring value of his legacy.

焦山의 『瘞鶴銘』 硏究 : 作家와 작성 時期를 중심으로

The Inscription for the Buried Crane of the forest of stone tablets in Jiaoshan Mountain has been called ‘the best calligraphy’ in Chinese calligraphy history because of its special charm. According to the legend, a hermit buried the carcass of the beloved crane and inscribed a memorial poem on a cliff which is on the west of Jiaoshan Mountain to grieve over its death. Later, the Inscription for the Buried Crane fell into the Yangzi River after a lightning strike. In the Song Dynasty, some of the remaining stones were salvaged from the water, but these stones fell into the water again. In the Qing Dynasty, five remaining stones were salvaged. Due to these tortuous experiences, it had different texts and block-printed version in different times. The content and calligraphy of the Inscription for the Buried Crane have well reflected the Taoist style. It has been regarded as the best calligraphy that combined the advantages of seal script, regular script and cursive script. Although the inscription is incomplete, we can glimpse the writer’s aesthetics, the situation and spirit of that times through the research and study on the Inscription of the Buried Crane.

Some Sodicological Remarks on the Sorpus of the Berlin Turfan Manichaean Sogdian Manuscripts in Manichaean Script: among Books, Glossaries, Letters, Booklets, Bilingual and Trilingual Texts, Normal, Bold and Cursive Script

The paper gives a survey of the codicological variety of the Sogdian manuscripts in Manichaean script of the Berlin Turfan Collection. Book formats, paper/silk/leather type, re-used paper, scripts and plurilingualism will be examined and commented upon.