ICDAR 2013 Handwriting Segmentation Contest

ICDAR 2009 Handwriting Segmentation Contest was organized in the context of ICDAR2009 conference in order to record recent advances in off-line handwriting segmentation. The contest includes handwritten document images produced by many writers in several languages (English, French, German and Greek). These images are manually annotated in order to produce the ground truth which corresponds to the correct text line and word segmentation result. For the evaluation, a well-established approach is used based on counting the number of matches between the entities detected by the segmentation algorithm and the entities in the ground truth. This paper describes the contest details including the dataset, the ground truth and the evaluation criteria and presents the results of the 12 participating methods as well as of two state-of-the-art algorithms. A description of the winning algorithms is also given.

Segmentation of text lines is one of the important steps in the Optical Character Recognition system. Text Line Segmentation is pre-processing step of word and character segmentation. Text Line Segmentation can be viewed simple for printing documents which contains distinct spaces between the lines. And it is more complex for the documents where text lines are overlap, touch, curvilinear and variation of space between text lines like in Telugu scripts and skewed documents. The main objective of this project is to investigate different text line segmentation algorithms like Projection Profiles, Run length smearing and Adaptive Run length smearing on low quality documents. These methods are experimented and compare their accuracy and results.

Most of the current word segmentation methods are rule-based and traditional machine learning methods. Universal word segmentation tools do not work well in the field such as metallurgy. Domain-specific Chinese word segmentation is rarely studied. In recent years, with the development of deep learning, the neural network has been proved to be effective in Chinese word segmentation. However, this promising performance relies on large-scale training data. Neural networks with conventional architectures cannot achieve the desired results in low-resource datasets due to the lack of labeled training data. This paper takes the field of metallurgy as an example and proposes a domain-specific Chinese word segmentation based on Bi-directional long-short term memory (Bi-directional LSTM) model in the metallurgical field. First, the word segmentation model is obtained by using the Bi-directional LSTM model to train the internal and external domain knowledge. Then, a series of tuning parameters are carried out and the label probability of the word is combined with the weight. Finally, the result of word segmentation is obtained by label inference layer. The experimental results show that the proposed method can create a better word segmentation effect in the field of metallurgy.

Optical Character Recognition is considered one of the fastest methods of data entry. OCR converts the text image representation of x and y coordinates representing pixel information to be converted into text data in a particular language. OCR as a field of pattern recognition and document image understanding, OCR requires a challenging job once a different language text is available on the image. Difference in language script will pose different challenges for OCR which requires entirely different approaches and algorithms. Latin scripts require a different approach whereas the Arabic adopted language scripts require a different approach. In this regard, various solutions have been proposed for different languages. Segmentation is considered one of the important tasks in the process of OCR. A good segmentation will definitely increase the accuracy of an OCR. Segmentation includes the segmentation of text lines from text images which are further divided into words. These segmented words are further divided into characters which are to be recognized. A single segmentation algorithm to segment various scripts of the languages is proposed in this study which checks the script and then segments the text image for the further processing in OCR. The proposed generalized algorithm will check the style, direction and other properties of the script and then adopts the segmentation process to segment text lines, words and characters of the language. The proposed algorithm segments more than ten languages of three scripts and segments for their OCRs. These images can be further processed for feature extraction and classification further. The process of OCR for selected languages will be made easier to recognize. Multiple scripts, languages and images were experimented, and the proposed algorithm successfully segmented 32,833 images of text line, words and character image. The algorithm provides 97% accuracy while segmenting these images and can be extended to further languages as well as scripts.

Text line segmentation is a necessary preliminary step before most text transcription algorithms are applied. The leading deep learning networks used in this context (ARU-Net, dhSegment, and Doc-UFCN) are based on the U-Net architecture. They are efficient, but fall under the same concept, requiring a post-processing step to perform instance (e.g., text line) segmentation. In the present work, we test the advantages of Mask-RCNN, which is designed to perform instance segmentation directly. This work is the first to directly compare Mask-RCNN- and U-Net-based networks on text segmentation of historical documents, showing the superiority of the former over the latter. Three studies were conducted, one comparing these networks on different historical databases, another comparing Mask-RCNN with Doc-UFCN on a private historical database, and a third comparing the handwritten text recognition (HTR) performance of the tested networks. The results showed that Mask-RCNN outperformed ARU-Net, dhSegment, and Doc-UFCN using relevant line segmentation metrics, that performance evaluation should not focus on the raw masks generated by the networks, that a light mask processing is an efficient and simple solution to improve evaluation, and that Mask-RCNN leads to better HTR performance.

Chinese word segmentation plays an important role in search engine, artificial intelligence, machine translation and so on. There are currently three main word segmentation algorithms: dictionary-based word segmentation algorithms, statistics-based word segmentation algorithms, and understanding-based word segmentation algorithms. However, few people combine these three methods or two of them. Therefore, a Chinese word segmentation model is proposed based on a combination of statistical word segmentation algorithm and understanding-based word segmentation algorithm. It combines Hidden Markov Model (HMM) word segmentation and Bi-LSTM word segmentation to improve accuracy. The main method is to make lexical statistics on the results of the two participles, and to choose the best results based on the statistical results, and then to combine them into the final word segmentation results. This combined word segmentation model is applied to perform experiments on the MSRA corpus provided by Bakeoff. Experiments show that the accuracy of word segmentation results is 12.52% higher than that of traditional HMM model and 0.19% higher than that of BI-LSTM model.

Chinese word segmentation has received extensive attention in recent years. The word segmentation method based on character-based tagging improves the performance of word segmentation greatly. This method transforms the word segmentation problem into a sequence labeling problem, which has become the main word segmentation method. In order to further study the word segmentation performance of this method, we use the maximum entropy sequence labeling model in this paper. We used two different word position sets and three feature templates to compare the experimental results. We have done further research on the unknown words and segmentation ambiguity in the word segmentation results. First we combined N-Gram with cohesion and degree of freedom to solve the problem of unknown words. Then the maximum entropy model is used to train the new participle to eliminate the ambiguity. The closed test was conducted on the Bakeoff 2005 corpus of the international Chinese word segmentation evaluation. Experiments show that the six-tag position combined with the corresponding feature templates can achieve better word segmentation performance. After adding unknown words and disambiguation processing, the word segmentation performance of some data sets can be further improved to optimal results of Bakeoff 2005.

Recognition of old Greek document images containing polytonic (multi accent) characters is a challenging task due to the large number of existing character classes (more than 270) which cannot be handled sufficiently by current OCR technologies. Taking into account that the Greek polytonic system was used from the late antiquity until recently, a large amount of scanned Greek documents still remains without full test search capabilities. In order to assist the progress of relevant research, this paper introduces the first publicly available old Greek polytonic database GRPOLY-DB for the evaluation of several document image processing tasks. It contains both machine-printed and handwritten documents as well as annotation with ground-truth information that can be used for training and evaluation of the most commou document image processing tasks, i.e.. text line and word segmentation, test recognition, isolated character recognition and word spotting. Results using several representative baseline technologies are also presented in order to help researchers evaluate their methods and advance the frontiers of old Greek document image recognition and word spotting.

Segmentation is a very critical stage in the character recognition process as the performance of any character recognition system depends heavily on the accuracy of segmentation. Although segmentation is a well-researched area, segmentation of handwritten text is still difficult owing to several factors like skewed and overlapping lines, the presence of touching, broken and degraded characters, and variations in writing styles. Therefore, researchers in this area are working continuously to develop new techniques for the efficient segmentation and recognition of characters. In the character recognition process, segmentation can be implemented at the line, word, and character level. Text line segmentation is the first step in the text/character recognition process. The line segmentation methods used in the character recognition of handwritten documents are presented in this paper. The various levels of segmentation which include line, word, and character segmentation are discussed with a focus on line segmentation.KeywordsSegmentationOCRPattern recognitionLine segmentationWord segmentationCharacter segmentationTouching lines segmentationOverlapping lines segmentation

Despite recent advances in the field of supervised deep learning for text line segmentation, unsupervised deep learning solutions are beginning to gain popularity. In this paper, we present an unsupervised deep learning method that embeds document image patches to a compact Euclidean space where distances correspond to a coarse text line pattern similarity. Once this space has been produced, text line segmentation can be easily implemented using standard techniques with the embedded feature vectors. To train the model, we extract random pairs of document image patches with the assumption that neighbour patches contain a similar coarse trend of text lines, whereas if one of them is rotated, they contain different coarse trends of text lines. Doing well on this task requires the model to learn to recognize the text lines and their salient parts. The benefit of our approach is zero manual labelling effort. We evaluate the method qualitatively and quantitatively on several variants of text line segmentation datasets to demonstrate its effectivity.

Text line segmentation in unconstrained handwritten documents remains a challenge because handwritten text lines are multi-skewed and not obviously separated. This paper presents a new approach based on the variational Bayes (VB) framework for text line segmentation. Viewing the document image as a mixture density model, with each text line approximated by a Gaussian component, the VB method can automatically determine the number of components. We extend the VB method such that it can both eliminate and split components and control the orientation of text line lines. Experiments on Chinese handwritten documents demonstrated the effectiveness of the approach.

This paper attempts to deal with the problems of query-by-example word spotting in handwritten Arabic document. This operation needs a lot of time and effort to do manual work. For this, we propose a fully non supervised methodology dedicated to the word spotting system, without using any text word or line segmentation step, because any segmentation errors of the document affect the subsequent word representations and matching steps. This work is addressing by using a method that integrates two steps into one. First the interest points are automatically extracted from the images. Then, the matching of the extracted points is established with a correlation technique combined to a relaxation technique. Validation study is conducted under a series of controlled experiments on handwritten Arabic document images.

Due to the presence of high volume of noise in text documents, it becomes very difficult to achieve high accuracy while performing text line segmentation. Hence, approaches which are dependent on the performance of the line segmentation stage, also suffers. Also due to the variability of noise patterns, the text contents get distorted and sometimes it results in broken strokes of a character. Thus, character level recognition becomes a challenging task for noisy documents. Our proposed method is aimed to address the aforesaid challenges. Since, we are considering the input image to be of noisy kind, a convolutional neural network (CNN) architecture is introduced to initially identify whether the input image contains noise or not. We consider this as a two-class problem and try to identify the respective classes, i.e. noisy or clean. Then, we apply the proposed piecewise projection profile feature and an adaptive region growing based two-stage algorithmic approach which initially identifies the text line upper and lower boundaries in a noisy text document image and then try to regroup the broken strokes of a character to enhance the character recognition accuracy. The proposed method has been tested on a large size dataset containing noisy documents and also different quality measures are computed to establish the effectiveness of the proposed method. From the measures, it can be noted that the text line segmentation accuracy is comparable to other similar state-of-the-art results.

There are more than 1000 languages and 14 scripts used by 112 million people in India. All of these scripts divide the document in three parts: Text block, Image block, and Table block. In 21st century, there is a need, obvious reasons, to convert these old printed documents in digital form. Converting them manually is a huge and difficult task. Further it is prone to human errors. Another automated technique is to use Optical character recognition (OCR) system to convert the entire printed document image into editable document. In this paper, an effort has been made to develop OCR technique which converts the printed document into editable document. Firstly a scanned document is preprocessed for noise and skew correction. It is then followed by text-non text classification. Then text line detection has to be performed in the text area. There is no method available which can detect the text line if the image contains the multicolumn text area. In this paper the main contribution is to detect the blocks and detect the text lines in these detected blocks. The technique which can extract the text lines in image document is presented here. After extraction of text lines, word segmentation, character segmentation, and template matching can be performed.

A novel grouping approach to segment text lines from handwritten documents is presented. In this text line segmentation algorithm, for each text line, a text string that connects the center points of the characters in this text line is built. The text lines are then segmented using the resulting text strings. Since the characters of the same text line are situated close together and aligned on a smooth curve, 2D tensor voting is used to reduce the conflicts when building these text strings. First, the text lines are represented by separate connected components. The center points of these connected components are then encoded by second order tensors. Finally, a voting process is applied to extract the curve saliency values and normal vectors, which are used to remove outliers and build the text strings. The experimental results obtained from the test dataset of the ICDAR 2009 Handwriting Segmentation Contest show that the proposed method generates high detection rate and recognition accuracy.