Search

Optical Character Recognition OCR is an essential part of many real-world applications such as digital archiving, automatic number plate recognition, handle cheques, etc. However, developing an OCR for printed Arabic text is still a challenging and open research field due to the special characteristics of Arabic cursive script. In this paper, we propose a segmentation-based, omnifont, open-vocabulary OCR for printed Arabic text. The proposed approach doesn’t require an explicit font type recognition stage. It uses an explicit, indirect character segmentation method. The presented segmentation method is baseline dependent and employs a hybrid, three-steps character segmentation algorithm to handle the problem of character overlapping. Besides, it uses a set of topological features that are designed and generalized to make the segmentation approach font independent. The segmented characters are fed as an input to a convolutional neural network for feature extraction and recognition. The APTID-MF data set has been used for testing and evaluation. The average accuracy of the proposed segmentation stage is 95%, while the average accuracy of the recognition stage is 99.97%. The whole approach achieves an average accuracy of 95% without using font-type recognition or any post-processing techniques.

Recent advances in complex automated handwriting identification systems have led to a lack of understandability of these systems' computational processes and features by the forensic handwriting examiners that they are designed to support. To mitigate this issue, this research studied the relationship between two systems: FLASH ID® , an automated handwriting/black box system that uses measurements extracted from a static image of handwriting, and MovAlyzeR® , a system that captures kinematic features from pen strokes. For this study, 33 writers each wrote 60 phrases from the London Letter using cursive writing and handprinting, which led to thousands of sample pairs for analysis. The dissimilarities between pairs of samples were calculated using two score functions (one for each system). The observed results indicate that dissimilarity scores based on kinematic spatial-geometric pen stroke features (e.g., amplitude and slant) have a statistically significant relationship with dissimilarity scores obtained using static, graph-based features used by the FLASH ID® system. Similar relationships were observed for temporal features (e.g., duration and velocity) but not pen pressure, and for both handprinting and cursive samples. These results strongly imply that both the current implementation of FLASH ID® and MovAlyzeR® rely on similar features sets when measuring differences in pairs of handwritten samples. These results suggest that studies of biometric discrimination using MovAlyzeR® , specifically those based on the spatial-geometric feature set, support the validity of biometric matching algorithms based on FLASH ID® output.

Multi-oriented handwritten documents require additional preprocessing for segmentation and subsequent phases to work accurately in handwritten recognition systems. Skew correction is one such additional phase. Appearance of skew in multi-oriented Indian language based handwritten document is higher due to the presence of cursive nature. In the current work, we utilise a salient feature present in Indian scripts called $m\bar {a}$ tr $\bar {a}$ (also known as headline), extract a group of eligible pixels, and employ linear curve fitting for detecting and correcting skew in handwritten words. The proposed method is capable of correcting skew in four distinct Indian languages, viz. Bangla, Hindi, Marathi, and Punjabi. It is capable of efficiently handling skewed word images to an extent of ± 55∘ and delivers precise result even when the $m\bar {a}$ tr $\bar {a}$ is mostly absent or discontinuous.

Signboard detection and recognition is an important task in automated context-aware marketing. Recently many scripting languages like Latin, Japanese, and Chinese have been effectively detected by several machine learning algorithms. As compared to other languages, outdoor Urdu text needs further attention in detection and recognition due to its cursive nature. Urdu detection and recognition are also difficult due to a wide variety of illuminations, low resolution, inconsistent font styles, color, and backgrounds. To overcome the deficiency of Urdu text detection from the outdoor environment, we have proposed a new Urdu-text signboard dataset with 467 ligature categories, containing a 30 + K images for recognition and 700 base images with annotation are created for detection. We also propose a methodology, that consists of 3-phases. In first phase text regions containing Urdu ligatures from shop-signboard images are detected by a faster regional convolutional neural network (FasterRCNN) using pre-trained CNNs like Alexnet and Vgg16. In the second phase detected regions from the first phase are clustered to identify unique ligatures in a dataset. Lastly in the third phase, all detected regions are recognized by 18-layer convolutional neural network trained model. The proposed system has successfully achieved the precision and recall of 87% and 96% respectively using vgg16 model for detection. For the classification of ligatures, a recognition rate of 97.50% is achieved. Recognition of ligatures was also evaluated using bilingual evaluation understudy (BLEU), and achieved an encouraging score of 0.96 on the newly developed Urdu-Signboard dataset.

This study focuses on cursive text recognition appearing in videos, using a complete framework of deep neural networks. While mature video optical character recognition systems (V-OCRs) are available for text in non-cursive scripts, recognition of cursive scripts is marked by many challenges. These include complex and overlapping ligatures, context-dependent shape variations and presence of a large number of dots and diacritics. The authors present an analytical technique for recognition of cursive caption text that relies on a combination of convolutional and recurrent neural networks trained in an end-to-end framework. Text lines extracted from video frames are preprocessed to segment the background and are fed to a convolutional neural network for feature extraction. The extracted feature sequences are fed to different variants of bi-directional recurrent neural networks along with the ground truth transcription to learn sequence-to-sequence mapping. Finally, a connectionist temporal classification layer is employed to produce the final transcription. Experiments on a data set of more than 40,000 text lines from 11,192 video frames of various News channel videos reported an overall character recognition rate of 97.63%. The proposed work employs Urdu text as a case study but the findings can be generalised to other cursive scripts as well.

In this paper, we propose integrated adaptive sensitivity and robustness terms for the cost function of a convolutional neural network (CNN). The sensitivity term considers the slight variations and high frequency components of the input image samples. It distinguishes between images that look similar but belong to different classes. This regularizer is designed to enhance the between-class distance which is a biological definition for the simple cells of the visual system. On the other hand, the robustness term is used to develop a more stable CNN structure against disturbances and perturbations. The robust term provides better within-class features because it recognizes images that look different but are actually from the same class. The robust term symbolizes the complex cell characteristics of the visual system. The coefficients of the sensitivity and robustness regularization terms are adaptively tuned along with the network parameters using gradient descent. Two optimizers are assigned to tune the parameters: one for tuning the model parameters and the other one to adjust the sensitivity and robustness coefficients. This approach is applied to Korean traditional documents for character classification. The results show better within- and between-class classification ability for highly complex character styles with imbalanced number of samples.

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.

The accuracy of current natural scene text recognition algorithms is limited by the poor performance of character recognition methods for these images. The complex backgrounds, variations in the writing, text size, orientations, low resolution and multi-language text make recognition of text in natural images a complex and challenging task. Conventional machine learning and deep learning-based methods have been developed that have achieved satisfactory results, but character recognition for cursive text such as Arabic and Urdu scripts in natural images is still an open research problem. The characters in the cursive text are connected and are difficult to segment for recognition. Variations in the shape of a character due to its different positions within a word make the recognition task more challenging than non-cursive text. Optical character recognition (OCR) techniques proposed for Arabic and Urdu scanned documents perform very poorly when applied to character recognition in natural images. In this paper, we propose a multi-scale feature aggregation (MSFA) and a multi-level feature fusion (MLFF) network architecture to recognize isolated Urdu characters in natural images. The network first aggregates multi-scale features of the convolutional layers by up-sampling and addition operations and then combines them with the high-level features. Finally, the outputs of the MSFA and MLFF networks are fused together to create more robust and powerful features. A comprehensive dataset of segmented Urdu characters is developed for the evaluation of the proposed network models. Synthetic text on the patches of images with real natural scene backgrounds is generated to increase the samples of infrequently used characters. The proposed model is evaluated on the Chars74K and ICDAR03 datasets. To validate the proposed model on the new Urdu character image dataset, we compare its performance with the histogram of oriented gradients (HoG) method. The experimental results show that the aggregation of multi-scale and multilevel features and their fusion is more effective, and outperforms other methods on the Urdu character image and Chars74K datasets.

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.

Although numerous research studies have been conducted concerning automatic vehicle number plate detection and recognition, various presented automated number plate recognition systems are devised for specific countries where number plates follow standard patterns. However, such systems cannot be applied in Afghanistan because of the different designs and the language. Moreover, due to the cursive nature, writing direction, and shape variation of the Pashto characters, the segmentation of words into isolated characters is a more complicated task. Hence, the Pashto optical character recognition is a less developed area. To date, no research study has been conducted for Afghanistan number plate detection and recognition. The details on the Afghanistan number plate include character, numbers, and each province's name. The paper presents the study of its type attempting to detect the number plate from the vehicle image and then recognize the province's name, characters, and numbers on the number plate. In particular, the new method incorporating four core steps. The first step is number plate detection applying canny edge detection based on user-defined thresholding and extracts the number plate involving several image processing techniques. The second phase is number plate adjustment using Randon transform-based techniques. The third stage is number plate segmentation isolating each character, number, and province name on the number plate using a scanning approach. The final step employs a convolutional neural network to classify the number plate's alphanumeric characters and provinces' names. In addition, two datasets have been created: the dataset for alphanumeric characters contains 2800 images of 14 classes, and the dataset for provinces' names contains 6800 images of 34 classes. The proposed models present 99.93 percent accuracy for provinces' names classification and 98.93 percent for alphanumeric characters' classification.

One of the major research areas in data science is deep learning. Convolutional Neural Networks play a huge role in the recent success of the artificial intelligence-based applications. Cursive character recognition is still an active research problem from many years. This paper deals with recognition of offline handwritten Marathi documents written in MODI script using deep learning convolutional neural network model. The algorithm explained in this paper makes use of Rectified Linear Unit neuron activation function in the convolutional layers as it gives better performance and computationally least expensive and softmax neuron activation function in its fully connected layer. The max pooling layer is used for feature detection. The model designed uses 32 convolutional filters of size 3 × 3 × 1. The model developed is trained by using more than 40000-character samples belonging to 31 different class labels. The trained neural network is tested on more than 10000-character samples from 31 different class labels, giving an accuracy of more than 60%.

In this paper, a robust character segmentation approach for cursive handwritten Modi script touching character cluster is presented. Prior to segmentation, the middle text region of the touching character cluster is separated by examining the location of Shirorekha and baseline. The middle text region is scrutinized for the estimation of ligature between two characters. Two different strategies are employed to find the location of the ligature. The selection of the strategy is based on the degree of connected component overlapratio. The foreground pixel intensity and vertical projection profile is scrutinized to segment the touching characters. The performance of the system is tested using the touching character clusters of the original archaic handwritten Modi documents. The proposed approach yields efficient touching characters cluster segmentation output and it is feasible to tackle most of the challenges in touching character cluster segmentation.

Handwritten character recognition (HCR) is presently gaining much popularity due to its wide range of applications. Bangla language comprises many unique characters of complex shapes, cursive nature, and resemblance among different characters. This nature of the script makes Bangla Handwritten character recognition (BHCR) a very challenging task. Very few HCR models can classify all types of Bangla characters with respectable accuracy. The current work proposes a hybrid BHCR model combining the Convolutional Neural Network (CNN) with stacked Bidirectional Long Short-Term Memory (Bi-LSTM). The experimental model used CNN for feature extraction and stacked Bidirectional LSTM for classification purposes. An augmented version of the CMATER dB dataset was implemented for training and evaluating the model. The model could recognize 243 individual classes of Bangla handwritten characters with 96.07% accuracy. No other proposed models are found to classify such a high number of classes with high accuracy.

Due to the nature of Arabic handwriting, segmenting words into characters/graphemes is the most difficult and critical task of the recognition system. The present paper proposes an approach to segment handwritten Arabic words into graphemes based on a directed Convolutional Neural Network (CNN) and Mathematical Morphology Operations (MMO). Arabic script is cursive, which means that almost all graphemes are connected via horizontal links; therefore, a technique to remove links will facilitate the segmentation of graphemes. In general, an MMO such as erosion seems suitable for getting the job done, but since Arabic handwriting is difficult, MMOs cause information loss and suffer from many issues such as diacritics and over-traces, which lead to over/under/bad segmentations. To overcome limitations, the present paper addresses these issues in the following order: the over-traces issue is addressed for the first time in the literature; a robust algorithm for diacritics extraction is provided; and finally, the main segmentation algorithm adopts a strategy based on a Partial Dilation (PD)-Global Erosion (GE) technique to combat the information loss issue. The PD phase amplifies important regions, while GE eliminates links between graphemes. The complementarity between PD and GE facilitates the extraction of graphemes and creates resistance against information loss. To properly tackle these difficult problems, this article exploits the robustness of CNNs, so a new directed CNN model is suggested. The idea is to draw the model's attention to certain targeted features, which are selected according to the nature of the problem addressed. The proposed directed CNN is used in all phases of the segmentation process. The experimental results are very encouraging and show that the proposed directed CNN model outperformed basic CNN in many experiments. The results also reveal that the followed strategy improved the ability of MMOs to perform segmentation and to compete with other approaches in this research area.

Handwritten character recognition is increasingly important in a variety of automation fields, for example, authentication of bank signatures, identification of ZIP codes on letter addresses, and forensic evidence. Despite improved object recognition technologies, Pashto&rsquo, s hand-written character recognition (PHCR) remains largely unsolved due to the presence of many enigmatic hand-written characters, enormously cursive Pashto characters, and lack of research attention. We propose a convolutional neural network (CNN) model for recognition of Pashto hand-written characters for the first time in an unrestricted environment. Firstly, a novel Pashto handwritten character data set, &ldquo, Poha&rdquo, for 44 characters is constructed. For preprocessing, deep fusion image processing techniques and noise reduction for text optimization are applied. A CNN model optimized in the number of convolutional layers and their parameters outperformed common deep models in terms of accuracy. Moreover, a set of benchmark popular CNN models applied to Poha is evaluated and compared with the proposed model. The obtained experimental results show that the proposed model is superior to other models with test accuracy of 99.64 percent for PHCR. The results indicate that our model may be a strong candidate for handwritten character recognition and automated PHCR applications.

Recognition of ancient Korean–Chinese cursive character (Hanja) is a challenging problem mainly because of large number of classes, damaged cursive characters, various hand-writing styles, and similar confusable characters. They also suffer from lack of training data and class imbalance issues. To address these problems, we propose a unified Regularized Low-shot Attention Transfer with Imbalance τ -Normalizing ( R E L A T I N ) framework. This handles the problem with instance-poor classes using a novel low-shot regularizer that encourages the norm of the weight vectors for classes with few samples to be aligned to those of many-shot classes. To overcome the class imbalance problem, we incorporate a decoupled classifier to rectify the decision boundaries via classifier weight-scaling into the proposed low-shot regularizer framework. To address the limited training data issue, the proposed framework performs Jensen–Shannon divergence based data augmentation and incorporate an attention module that aligns the most attentive features of the pretrained network to a target network. We verify the proposed RELATIN framework using highly-imbalanced ancient cursive handwritten character datasets. The results suggest that (i) the extreme class imbalance has a detrimental effect on classification performance; (ii) the proposed low-shot regularizer aligns the norm of the classifier in favor of classes with few samples; (iii) weight-scaling of decoupled classifier for addressing class imbalance appeared to be dominant in all the other baseline conditions; (iv) further addition of the attention module attempts to select more representative features maps from base pretrained model; (v) the proposed ( R E L A T I N ) framework results in superior representations to address extreme class imbalance issue.

the problems which arise in the system of automatic recognition of the handwritten Arabic script shows that the morphology complexity of the Arabic script and its cursivity remains a very vast subject of research. This research subject has known in recent years a great progress especially in the automation of postal mail sorting, check processing and form processing. Generally, there are two main types of approaches namely the analytical approach and the global approach. In this paper, we have exploited the global approach, which is based on a single description of the image of the word, seen as an indivisible entity. Our work is devoted to offline handwritten Arabic word recognition based on the global limited vocabulary approach using the IFN/ENIT database, which contains handwritten Arabic words featuring handwritten Tunisian city/village names. In the feature extraction phase, we studied three types of descriptors; the oriented gradient histogram, the local binary pattern and the Gabor filter for feature extraction. We evaluate the performance of our models by calculating some common metrics. Among the performances of three descriptors, the model based on the Gabor filter achieves an extreme precision of 99.90%.

Handwriting recognition is the process of recognizing handwritten or printed alphabets in various documents and even old manuscript. This method also helps in preserving the texts and writings of ancient times. This paper aims to represent the work related to recognition of cursive handwriting of different languages. Cursive handwritings are connected to each other, hence segmentation is required. Segmentation is used for extraction: line segmentation to extract sentence, word segmentation to extract words and character segmentation to extract individual letters. The segmentation involves dividing based on contours by setting different kernel size. For classification, we have used classifiers—convolution neural networks. We carried our experiment using datasets collected from E-MNIST, UCI. The experimental accuracy for the E-MNIST dataset is 79.3% and for UCI Devanagari dataset is 93%.

With the increment of computation power, recognizing handwritten Character has become popular and significant improvement has been achieved for most of the major languages. But Bengali character recognition system is not well enough because of the presence of perplexing character and excessive cursive in its characters. Although several research works have been conducted for recognizing the Bengali characters, an efficient procedure is yet to discover. As the number of datasets is inadequate, most of these studies could not achieve a satisfactory level. So we propose here to train a Convolution Neural Network (CNN) and tune the parameters for better accuracy. This procedure is applied to CMATERDB 3.1.2 dataset with 15000.

Despite decades of research, developing optical character recognition (OCR) systems with capabilities comparable to that of a human remains an open challenge. A large scale of documents in the form of the image is needed to be entered into computer databases which takes a lot of memory as compared to editable text and there can be errors while interpretation of data from an image. This project aims to use OCR to convert handwritten or printed documents into editable text. Documents are scanned to image format as an input to a doc_class_net which is a full-size image classifier that classifies the input image into four different classes viz. printed, semi-printed, handwritten discrete, and handwritten cursive. The OCR model predicts and then decodes the text in the image and gives the output as an editable text. We have applied OCR to printed text images using the Pytesseract. For handwritten text images, the text is predicted using a self-developed convolutional recurrent neural network (CRNN) named CL-9 (7 CNN layers and 2 LSTM layers). The accuracy of the doc_class_net classifier and line_class_net classifier(line-wise classifier) was 88.03 % and 82.1 % respectively. The overall accuracy for printed, handwritten discrete and handwritten cursive obtained is 94.79 %, 75.2 %, and 65.7 % respectively. OCR has real-time applications in various fields like medical prescriptions, smart libraries, and tax returns. Using this method books, magazines, and any other form of documents can be digitized and made accessible very efficiently.

Arabic language contains a multiple set of features which complete the process of embedding and extracting text from the compressed image. In specific, the Arabic language covers numerous textual styles and shapes of the Arabic letter. This paper investigated Arabic cursive steganography using complex edge detection techniques via compressed image, which comprises several characteristics (short, medium and Long sentence) as per the research interest. Sample of images from the Berkeley Segmentation Database (BSD) was utilized and compressed with a diverse number of bits per pixel through Least Significant Bit (LSB) technology. The method presented in this paper was evaluated based on five complex edge detectors (Roberts, Prewitt, Sobel, LoG, and Canny) via MATLAB. Canny edge detector has been demonstrated to be the most excellent solution when it is vital to perform superior edge discovery over-compressed image with little several facts, but Sobel appears to be better in term of the execution time for Long sentence contents.

In this paper we present a system for offline recognition cursive Arabic handwritten text based on Hidden Markov Models (HMMs). The system is analytical without explicit segmentation used embedded training to perform and enhance the character models. Extraction features preceded by baseline estimation are statistical and geometric to integrate both the peculiarities of the text and the pixel distribution characteristics in the word image. These features are modelled using hidden Markov models and trained by embedded training. The experiments on images of the benchmark IFN/ENIT database show that the proposed system improves recognition. Keywords: Recognition, Handwriting, Arabic text, HMMs, Embedded training

The cursive nature, Nastaliq writing style and a large number of different ligatures make ligature recognition very difficult in Urdu. In this paper, we present a segmentation-free approach to holistically recognize Urdu ligatures. We first generate a rich dataset which contains 17,010 ligatures with different orientation and different degrees of noise. Secondly, the ligatures are clustered (categorized) in order to reduce the search space and make the learning robust. Finally, we employ a deep neural network with dropout regularization to classify ligatures. The detailed experiments show that a deep neural network with dropout regularization and clustering of ligatures significantly enhances the classification accuracy.

Due to the cursive nature, segmentation of handwritten Bangla words into characters and also recognition of the same sometimes become a very challenging problem to the researchers. Presence of comparatively large character set along with modifiers, ascendants, descendants, and compound characters makes the segmentation task more complex. As holistic method avoids such character-level segmentation, it is generally useful for the recognition of words written in any such complex scripts. In the present work, a holistic handwritten word recognition method is developed using a feature descriptor, designed by combining different Elliptical, Tetragonal and Vertical pixel density histogram-based features. Recognition process is carried out separately using two classifiers, namely multi-layer perceptron (MLP) and support vector machine (SVM). For evaluation of the proposed method, a database of 18,000 handwritten Bangla word images, having 120 word classes, is prepared. The proposed system performs comparatively better with SVM than MLP for the prepared dataset. It has achieved 83.64% accuracy at best case and 79.38% accuracy on an average using fivefold cross-validation. The current method has also outperformed some recently reported holistic word recognition technique tested on the developed dataset. In addition to that the database, prepared in this work, is made freely available to fill the absence of a publicly available standard database for holistic Bangla word recognition.

Recent developments in recognition of cursive scripts rely on implicit feature extraction methods that provide better results as compared to traditional hand-crafted feature extraction approaches. We present a hybrid approach based on explicit feature extraction by combining convolutional and recursive neural networks for feature learning and classification of cursive Urdu Nastaliq script. The first layer extracts low-level translational invariant features using Convolutional Neural Networks (CNN) which are then forwarded to Multi-dimensional Long Short-Term Memory Neural Networks (MDLSTM) for contextual feature extraction and learning. Experiments are carried out on the publicly available Urdu Printed Text-line Image (UPTI) dataset using the proposed hierarchical combination of CNN and MDLSTM. A recognition rate of up to 98.12% for 44-classes is achieved outperforming the state-of-the-art results on the UPTI dataset.

Optical character recognition (OCR) system holds great significance in human-machine interaction. OCR has been the subject of intensive research especially for Latin, Chinese and Japanese script. Comparatively, little work has been done for Urdu OCR, due to the complexities and segmentation errors associated with its cursive script. This paper proposes an Urdu OCR system which aims at ligature-level recognition of Urdu text. This ligature based recognition approach overcomes the character-levelsegmentation problems associated with cursive scripts. A newly developed OCR algorithm is introduced that uses a semi-supervised multi-level clustering for categorization of the ligatures. Classification is performed using four machine learning techniques i.e. decision trees, linear discriminant analysis, naive Bayes and k-nearest neighbor (K-NN). The system was implemented and the results show 62, 61, 73 and 90% accuracy for decision tree, linear discriminant analysis, naive Bayes and K-NN respectively.

Document layout analysis is a key step in the process of converting document images into text. Arabic language script is cursive and written in different styles which cause some challenges in the analysis of Arabic text documents. In this paper, we introduce an approach for Arabic documents layout analysis. In that approach, the document is segmented into set of zones using morphological operations. The segmented zones are classified as text or non-text ones using a support vector machine classifier. Features used in zone classification are combination between texture-based features and connected component-based features. The textural-based feature vector size is reduced using genetic algorithm. Classified text zones are clustered, using adaptive sample set clustering algorithm, into lines. Each segmented line is segmented into words by clustering inter- and intra-spaces. The proposed system was evaluated against two other systems that represent the best available tools for the Arabic documents analysis, and evaluation results show that the proposed system works well on multi-font and multi-size documents with a variety of layouts even on some historical documents.

The Arabic Optical Characters Recognition (AOCR) is one of the challenging recognition tasks nowadays, as Arabic handwriting is cursive and contains many dots. Dots are a big challenge for Arabic recognizers, as writers sometimes connect them. Moreover, Dots are prone to be considered noise. This paper proposes a new divide and conquers based approach that tries to conquer dots problems. The novelty of the proposed approach is in its feature extraction method. The extracted features are used to train Artificial Neural Network (ANN) Feed-forward. The result is interesting and shows that this method should be further investigated.

Hidden Markov Model (HMM) based offline cursive manually written word segmentation technique is proposed in this strategy. In this paper, we are utilizing a classification technique to perceive the written by hand word which is SVM. Dataset collection comprises handwritten words which are in the cursive configuration images are taken as input and these pictures comprise of noise and these noises are expelled by preprocessing strategy. The preprocessing technique incorporates word picture acquisition which is an RGB image; for additional steps, the RGB image is changed over to gray image. Later, thresholding is applied to the gray image. Thinning and skeletonization is connected to the thresholded image. At that point, noise is expelled from the manually written word image and a preprocessed binary matrix appears as a matrix. Over-segmented words are partitioned by potentially segmented column (PSC) and the HMM technique. At last, the character is perceived by utilizing SVM Method.

This paper proposes a character segmentation method using a fully convolutional network (FCN) and a post-processing phase. The network is trained with five-channel images that indicate five kinds of zones within the bounding box for each character—the top half, bottom half, left half, right half, and center. The post-processing step reconstructs the bounding boxes for characters from the five-channel image of the FCN output. The proposed method possesses the following advantages: (1) It is possible to process input images including multiple text lines directly; in other words, a text line segmentation process is unnecessary. (2) It does not rely upon character recognition. (3) It is robust to variations in the sizes of characters and the gaps between characters and also to cursive characters or character overlap. In the experiment of character segmentation, the accuracy ratio was 95% for real images of historical handwritten official documents written in Japanese.

Handwritten documents recognition is a challenging task in the field of pattern recognition. It has an array of applications wherein recognition of words, alphabets, digits and other characters are the mandate. This review article mainly focuses review on Convolutional Neural Network (CNN) based handwritten documents recognition system. Basically, the handwritten recognition is divided into two different types: online and offline recognition. The difficulty of this system is dealing with huge variety of handwritten styles written by different writers. The system wants to recognize and identify such characters in effective manner. The scope of this review paper is to represent the merits and limitations of different techniques used in the development of recognition system. This paper definitely helps the researcher to get new idea to develop a new technique with good environment and architecture to propose more accuracy and less error rate. The major bottlenecks in this system are the issues of recognizing unconstrained handwritings like cursive, block, and tilt that cause huge variation in writing styles, the overlapping and the interconnections between characters. These systems are designed to assure high accuracy and reliability. This article summarizes different strategies in handwritten recognition system, which may help the researchers interested in this area to spot the research gap. The Future work of this paper is to implement a robust technique providing more accuracy and less error rate.

Despite many advances in optical character recognition in general, there are still serious challenges remaining in recognizing Farsi text. The main reason is the cursive nature of the letters in written Farsi, i.e., depending on the position of a letter within a word, it might join to its neighboring letters, which consequently changes the shape of the character. As a result, each letter can have up to four different character shapes. In addition to the problem of segmenting the characters, the increased number of characters makes the recognition task even more challenging. This paper introduces a complete framework for character recognition, including a method for segmenting the characters and one for classifying the resulting separated characters. Character segmentation is performed using a new sliding-window algorithm with a high accuracy rate of 98.23%. With a total of 32 Farsi letters resulting in 114 character shapes, an almost perfect character recognition rate of 99.94% is achieved using the proposed Fisher characters method. The final system, including segmentation and recognition modules, achieves a recognition rate of 98.17% and is robust against the scale and rotation of the image, and the font size of the written text.

In Cursive languages like Urdu, segmentation of handwritten text lines is such a problem because of context sensitivity, diagonality of text etc. In this work, we presented a simple and robust line segmentation algorithm for Urdu handwritten and printed text. In the proposed line segmentation algorithm, modified header and baseline detection method are used. This technique purely depends on the counting pixels approach. Which efficiently segment Urdu handwritten and printed text lines along with skew detection. Handwritten and printed Urdu text dataset is manually generated for evaluating algorithm. Dataset consists of 80 pages having 687 handwritten Urdu text lines and printed dataset consist of 48 pages having 495 printed text lines. The algorithm performed significantly well on printed documents and handwritten Urdu text documents with well-separated lines and moderately well on a document containing overlapping words.

We present an off-line handwritten word recognition system.The system is based on extraction of directional features.Arnold transform followed by Hough transform is used to extract directional feature.A multi-class linear SVM is employed to recognize handwritten cursive words.Experiments are done on CENPERMI database of legal amounts written in English. This paper presents a holistic off-line handwriting recognition system based on extraction of directional features which depends on the stroke orientation distribution of cursive word. This stroke orientation distribution is estimated using Arnold transform followed by Hough transform. Besides this feature some other directional shape features are also used to form feature vector. Finally, a multi-class linear SVM is employed to recognize cursive word. Experiments are carried out on CENPARMI database of legal amount written in English and an overall accuracy of 87.19% is achieved. We have also compared our proposed method with the state-of-the-art methods for handwritten character recognition using C-Cube data-set.

Optical Character Recognition of cursive scripts remains a challenging task due to a large number of character shapes, inter- and intra-word overlaps, context sensitivity and diagonality of text. This paper presents an implicit segmentation based recognition system for Urdu text lines in Nastaliq script. The proposed technique relies on sliding overlapped windows on lines of text and extracting a set of statistical features. The extracted features are fed to a multi-dimensional long short term memory recurrent neural network (MDLSTM RNN) with a connectionist temporal classification (CTC) output layer that labels the character sequences. Experimental study of the proposed technique is carried out on the standard Urdu Printed Text-line Images (UPTI) database which comprises 10,000 text lines in Nastaliq font. Evaluations under different experimental settings realize promising recognition rates with a highest character recognition rate of 96.40%.

Handwritten document analysis is a scientific technique for identifying and understanding the personality of a writer through the strokes and patterns revealed by writer's handwriting. This research proposed an off-line handwritten document analysis through segmentation, skew recognition and writing pressure detection for cursive handwritten document. The proposed segmentation method is based on modified horizontal and vertical projection that can segment the text lines and words even if the presence of overlapped and multi-skewed text lines. Proposed work also present orthogonal projection based baseline recognition and normalization method as well as writing pressure detection method that can predict the personality of a writer from the baseline and writing pressure. The proposed method was tested on more than 550 text images of IAM database and sample handwriting image which are written by the different writer on the different background. The proposed method also provides a comparative study of the details analysis of the proposed method with other existing methods.

Over the past decades, text recognition technologies have focused immensely on noncursive isolated scripts. A text recognition system for the cursive Pashto script will serve as a great contribution, allowing the traditional, cultural, and educational Pashto literature to be converted into machine-readable form. We propose the use of deep learning architectures based on the transfer learning for the recognition of Pashto ligatures. For recognition analysis and evaluation, the ligature images in the dataset are preprocessed by data augmentation techniques, i.e., negatives, contours, and rotated to increase the variation of each sample and size of the original dataset. Rich feature representations are automatically extracted from the Pashto ligature images using deep convolution layers of the convolution neural network (CNN) architectures using fine-tuned approach. Pretrained CNN architectures: AlexNet, GoogleNet, and VGG (VGG-16 and VGG-19) are used for classification by feeding the extracted features to a fully connected layer and a softmax layer. The proposed deep transfer-based learning has achieved phenomenal recognition rates for Pashto ligatures on benchmark FAST-NU Pashto dataset. An accuracy of 97.24%, 97.46%, and 99.03% is achieved using AlexNext, GoogleNet, and VGGNet architectures, respectively.

Arabic script is inherently cursive in nature; therefore, optical character recognition (OCR) techniques developed for other scripts are generally inappropriate for Arabic. We present an OCR system for the recognition of handwritten Arabic words. Several original contributions have been made. First, we have proposed a novel feature vector to represent handwritten Arabic words based on the ellipsoid approximation of maximally stable extremal regions (MSERs). This feature vector is compact, robust, and well suited to handle writer-induced variation in handwritten script. Second, we present a new database, Saudi Arabian city name (SACN) database consisting of handwritten Saudi Arabian city names, which is the first such publicly available database. Finally, we present promising experimental results on two databases. One of the main experiments compares the proposed MSER feature vector with several well-established feature extraction methods using the proposed SACN database. The proposed feature vector performed better than all the standardized methods, with 100% correct identification rate. Another experiment is designed to compare our system to other recent studies on handwritten Arabic text recognition using the extensively employed IFN/ENIT database. Using the standard experimental protocol, our system outperformed all others with 92.64% correct identification rate.

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.

International audience; We propose an original approach for characterizing early Alzheimer, based on the analysis of online handwritten cursive loops. Unlike the literature, we model the loop velocity trajectory (full dynamics) in an unsupervised way. Through a temporal clustering based on K-medoids, with Dynamic Time Warping as dissimilarity measure, we uncover clusters that give new insights on the problem. For classification, we consider a Bayesian formalism that aggregates the contributions of the clusters, by probabilistically combining the discriminative power of each. On a dataset consisting of two cognitive profiles, Early-stage Alzheimer Disease and Healthy persons, each comprising 27 persons collected at Broca Hospital in Paris, our classification performance significantly outperforms the state of the art, based on global kinematic features

Handwritten script identification and converting it to printed electronic document as vast application. It helps to translate humanly readable to machine-readable text. This paper presents a technique to identify non cursive scanned, handwritten English script to digital document in notepad/MS-Office format using neural networks. Initially preprocessing of the input document image as conversion from RGB image to 8 bit gray scale, nonlinear contrast enhancement and mean normalization for correcting non uniform illumination and binarization are performed. Further the lines, words and characters of the input documents are localized in the preprocessed image and extracted from gray input image. Each extracted character of the gray input image is resized, normalized and used as input to the neural network for classification. The network consists of two layers feedforward network with sigmoid output neurons. The error back propagation algorithm is used for training. The proposed technique is tested on sample images from publically available CEDAR database as well as self created database with 1600 images for training and 620 images for testing purpose belonging to 62 classes. Overall Recognition accuracy of 95% is obtained. The performance of the proposed technique is also compared with the other existing technique.

It presents our recent study on segmentation-free recognition of unconstrained cursive online handwriting of Devanagari and Bangla, the two most popular Indic scripts. Here, we have devised an efficient algorithm for obtaining the core region of a handwritten word sample and compute a robust feature set which includes certain measures based on the knowledge of this core region. It also includes first and second order discrete derivatives which estimate certain geometric properties of discrete curves along the pen trajectory of the input online handwritten word sample. The proposed feature vector is obtained at each point on the trajectory of the preprocessed word sample based on a window (called vicinity) centered at the point. A hybrid deep neural network architecture consisting of a convolutional neural network (CNN), a bidirectional recurrent neural network (BiRNN) having Long Short Term Memory (LSTM) cells and a connectionist temporal classification (CTC) layer receives this high level feature vector as input for labelling the character sequence in the online word sample. This study shows that the proposed hybrid architecture recognizes online handwriting more efficiently than a BLSTM network alone.

In this paper we investigate the challenging problem of cursive text recognition in natural scene images. In particular, we have focused on isolated Urdu character recognition in natural scenes that could not be handled by tradition Optical Character Recognition (OCR) techniques developed for Arabic and Urdu scanned documents. We also present a dataset of Urdu characters segmented from images of signboards, street scenes, shop scenes and advertisement banners containing Urdu text. A variety of deep learning techniques have been proposed by researchers for natural scene text detection and recognition. In this work, a Convolutional Neural Network (CNN) is applied as a classifier, as CNN approaches have been reported to provide high accuracy for natural scene text detection and recognition. A dataset of manually segmented characters was developed and deep learning based data augmentation techniques were applied to further increase the size of the dataset. The training is formulated using filter sizes of 3x3, 5x5 and mixed 3x3 and 5x5 with a stride value of 1 and 2. The CNN model is trained with various learning rates and state-of-the-art results are achieved.

In this research work, classification and recognition methods are presented and compared for Urdu characters in natural scenes. Urdu text is a type of cursive text, and the detection or recognition of cursive text in natural scenes is a more complex and challenging task than for non-cursive text. Character classification is a fundamental step in the process of automatic text extraction from natural scenes. Accurate detection and recognition of characters for an end-to-end system heavily depends upon the efficiency of the character classifier. Furthermore, character classification of cursive languages is difficult due to the problems of complexity and character diversity. We propose a framework with image processing operations and a feature extraction technique to handle the problem of Urdu character recognition in natural scene images. In this paper, features are extracted using the Histogram of Oriented Gradient (HOG) method and are fed into five classifiers: Support Vector Machine (SVM), k Nearest Neighbors (kNN), Random Forest Classifier (RFC), Extra Tree Classifier (ETC) and Multi-Layer Perceptron (MLP). To evaluate the proposed system, as no dataset for Urdu natural scene text exists, we manually segmented characters from images and have developed a dataset of 18000 cropped Urdu characters. Experimental results show the efficiency of each classification method for segmented Urdu characters in natural scene images.

In this paper we present a system for offline recognition cursive Arabic handwritten text which is analytical without explicit segmentation based on Hidden Markov Models (HMMs). Extraction features preceded by baseline estimation are statistical and geometric to integrate both the peculiarities of the text and the pixel distribution characteristics in the word image. These features are modelled using hidden Markov models. The HMM-based classifiercontains a training module and a recognition module. The training module estimates the parameters of each of the character HMMs uses the Baum-Welchalgorithm. In the recognition phase, feature vectors extracted from an image are passed to a network of word lexicon entries formed of character models. The character sequence providing the maximumlikelihood identifies the recognized entry. If required, the recognition can generate N best output hypotheses rather than just the single best one. To determine the best output hypotheses, the Viterbi algorithm is used.The experiments on images of the benchmark IFN/ENIT database show that the proposed system improves recognition.

Urdu language uses cursive script which results in connected characters constituting ligatures. For identifying characters within ligatures of different scales (font sizes), Convolution Neural Network (CNN) and Long Short Term Memory (LSTM) Network are used. Both network models are trained on formerly extracted ligature thickness graphs, from which models extract Meta features. These thickness graphs provide consistent information across different font sizes. LSTM and CNN are also trained on raw images to compare performance on both forms of inputs. For this research, two corpora, i.e. Urdu Printed Text Images (UPTI) and Centre for Language Engineering (CLE) Text Images are used. Overall performance of networks ranges between 90% and 99.8%. Average accuracy on Meta features is 98.08% while using raw images, 97.07% average accuracy is achieved.

Text detection in natural and video scene images is still considered to be challenging due to unpredictable nature of scene texts. This paper presents a new method based on Cloud of Line Distribution (COLD) and Random Forest Classifier for text detection in both natural and video images. The proposed method extracts unique shapes of text components by studying the relationship between dominant points such as straight or cursive over contours of text components, which is called COLD in polar domain. We consider edge components as text candidates if the edge components in Canny and Sobel of an input image share the COLD property. For each text candidate, we further study its COLD distribution at component level to extract statistical features and angle oriented features. Next, these features are fed to a random forest classifier to eliminate false text candidates, which results representatives. We then perform grouping using representatives to form text lines based on the distances between edge components in the edge image. The statistical and angle orientated features are finally extracted at word level for eliminating false positives, which results in text detection. The proposed method is tested on standard database, namely, SVT, ICDAR 2015 scene, ICDAR2013 scene and video databases, to show its effectiveness and usefulness compared with the existing methods.

The camera captured images have various aspects to investigate. Generally, the emphasis of research depends on the interesting regions. Sometimes the focus could be on color segmentation, object detection or scene text analysis. The image analysis, visibility and layout analysis are the tasks easier for humans as suggested by behavioural trait of humans, but in contrast when these same tasks are supposed to perform by machines then it seems to be challenging. The learning machines always learn from the properties associated to provided samples. The numerous approaches are designed in recent years for scene text extraction and recognition and the efforts are underway to improve the accuracy. The convolutional approach provided reasonable results on non-cursive text analysis appeared in natural images. The work presented in this manuscript exploited the strength of linear pyramids by considering each pyramid as a feature of the provided sample. Each pyramid image process through various empirically selected kernels. The performance was investigated by considering Arabic text on each image pyramid of EASTR-42k dataset. The error rate of 0.17% was reported on Arabic scene text recognition.