Character Segmentation Research Articles

Newton Algorithm Based DELM for Enhancing Offline Tamil Handwritten Character Recognition

Numerous research based on offline Tamil recognition deals only with few Tamil characters since it becomes extremely complicated in distinguishing small variations in large handwritten document. The writer’s complexity affects the overall formation of the characters. Such types of complexities are due to discontinuation of structures, unnecessary over loops, variation in shapes as well as irregular curves. This complex issue results in enhanced error value rate. Therefore, to conquer such issues, this paper proposes a novel approach to enhance the offline Tamil handwritten character recognition by utilizing four principal steps: pre-processing, segmentation, feature extraction and classification. For optimal segmentation of Tamil characters, this paper utilizes the Tsallis entropy approach-based atom search (TEAS) optimization algorithm. Then a Newton algorithm based deep convolution extreme learning (DELM) approach is utilized for the extraction and classification of input images. Finally, experiments are carried out for numerous Tamil handwritten recognition-based approaches. The proposed Tamil character recognition utilizes the datasets of isolated Tamil handwritten characters established by HP lab India to evaluate the efficiency of the system.

Libyan Vehicle License Plate Recognition with Support Vector Machine

Computer vision has become widely used in many aspects of our daily lives. There are a great number of applications that consider computer vision as a core part of them, such as those associated with law enforcement. This paper presents the design and implementation of a model for a vehicle building entrance, using a license plate recognition algorithm for Libyan vehicles. In addition, a small dataset of Libyan vehicles was created for research purposes. As with most recognition systems, there are mainly three stages to be distinguished: plate detection using vertical and horizontal histograms, character segmentation is performed through a connected-component labeling algorithm, and finally, optical character recognition (OCR) by using support vector machines (SVMs). An Arduino board was used to control the gate opening and closing processes according to the authorized vehicles stored in the database. Ultrasonic sensors were used to detect a vehicle stop at the gate. The system was programmed with MATLAB executed on a 2.20GHz Core i7 CPU, 8 GB RAM, Windows 10. Despite the limited size of the vehicle images dataset, the experiments showed promising performance in terms of average accuracy estimated at 83.3%, and the computation time was 5 seconds.

Character Segmentation and Recognition of Variable-Length License Plates Using ROI Detection and Broad Learning System

Variable-length license plate segmentation and recognition has always been a challenging barrier in the application of intelligent transportation systems. Previous approaches mainly concern fixed-length license plates, lacking adaptability for variable-length license plates. Although objection detection methods can be used to address the issue, they face a series of difficulties: cross class problem, missing detections, and recognition errors between letters and digits. To solve these problems, we propose a machine learning method that regards each character as a region of interest. It covers three parts. Firstly, we explore a transfer learning algorithm based on Faster-RCNN with InceptionV2 structure to generate candidate character regions. Secondly, a strategy of cross-class removal of character is proposed to reject the overlapped results. A mechanism of template matching and position predicting is designed to eliminate missing detections. Moreover, a twofold broad learning system is designed to identify letters and digits separately. Experiments performed on Macau license plates demonstrate that our method achieves an average 99.68% of segmentation accuracy and an average 99.19% of recognition rate, outperforming some conventional and deep learning approaches. The adaptability is expected to transfer the developed algorithm to other countries or regions.

Legal Text Recognition Using LSTM-CRF Deep Learning Model.

In legal texts, named entity recognition (NER) is researched using deep learning models. First, the bidirectional (Bi)-long short-term memory (LSTM)-conditional random field (CRF) model for studying NER in legal texts is established. Second, different annotation methods are used to compare and analyze the entity recognition effect of the Bi-LSTM-CRF model. Finally, other objective loss functions are set to compare and analyze the entity recognition effect of the Bi-LSTM-CRF model. The research results show that the F1 value of the model trained on the word sequence labeling corpus on the named entity is 88.13%, higher than that of the word sequence labeling corpus. For the two types of entities, place names and organization names, the F1 values obtained by the Bi-LSTM-CRF model using word segmentation are 67.60% and 89.45%, respectively, higher than the F1 values obtained by the model using character segmentation. Therefore, the Bi-LSTM-CRF model using word segmentation is more suitable for recognizing extended entities. The parameter learning result using log-likelihood is better than that using the maximum interval criterion, and it is ideal for the Bi-LSTM-CRF model. This method provides ideas for the research of legal text recognition and has a particular value.

Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence

Automated monitoring of dark web (DW) platforms on a large scale is the first step toward developing proactive Cyber Threat Intelligence (CTI). While there are efficient methods for collecting data from the surface web, large-scale dark web data collection is often hindered by anti-crawling measures. In particular, text-based CAPTCHA serves as the most prevalent and prohibiting type of these measures in the dark web. Text-based CAPTCHA identifies and blocks automated crawlers by forcing the user to enter a combination of hard-to-recognize alphanumeric characters. In the dark web, CAPTCHA images are meticulously designed with additional background noise and variable character length to prevent automated CAPTCHA breaking. Existing automated CAPTCHA breaking methods have difficulties in overcoming these dark web challenges. As such, solving dark web text-based CAPTCHA has been relying heavily on human involvement, which is labor-intensive and time-consuming. In this study, we propose a novel framework for automated breaking of dark web CAPTCHA to facilitate dark web data collection. This framework encompasses a novel generative method to recognize dark web text-based CAPTCHA with noisy background and variable character length. To eliminate the need for human involvement, the proposed framework utilizes Generative Adversarial Network (GAN) to counteract dark web background noise and leverages an enhanced character segmentation algorithm to handle CAPTCHA images with variable character length. Our proposed framework, DW-GAN, was systematically evaluated on multiple dark web CAPTCHA testbeds. DW-GAN significantly outperformed the state-of-the-art benchmark methods on all datasets, achieving over 94.4% success rate on a carefully collected real-world dark web dataset. We further conducted a case study on an emergent Dark Net Marketplace (DNM) to demonstrate that DW-GAN eliminated human involvement by automatically solving CAPTCHA challenges with no more than three attempts. Our research enables the CTI community to develop advanced, large-scale dark web monitoring. We make DW-GAN code available to the community as an open-source tool in GitHub.

An Enhanced Approach for Number Plate Detection and Recognition

Introduction: The number of vehicles is increasing day by day in our life. The vehicle may violate traffic rules and cause accidents. The automatic number plate detection system (ANPR) plays a significant role to identify these vehicles. Number plate detection is very difficult sometimes because each country has its own format for representing the number plate and font types and sizes may also vary for different vehicles. The number of ANPR systems is available nowadays but still, it is a big problem to detect the number plate correctly in various scenarios like high-speed vehicle, number plate language, etc. Methods: In the development of this method, we mainly used wiener filter for noise removal, morphological operations for number plate localization, connected component algorithm for character segmentation, and template based matching for character recognition. Results: Our proposed methodology is providing promising results in terms of detection accuracy. Discussion: The automatic number plate detection system (ANPR) has wide range of applications because the license number is the crucial, commonly putative and essential identifier of motor vehicles. These applications include ticketless parking fee management, parking access automation, car theft prevention, security guide assistance, Motorway Road Tolling, Border Control, Journey Time Measurement, Law Enforcement and many more. Conclusion: In this paper, an enhanced approach of automatic number plate detection system is proposed using some different techniques which not only detect the number plate of the vehicle but also recognize each character present in the detected number plate image.

Deep Neural Networks Algorithm for Vietnamese Word Segmentation

Traditional Vietnamese word segmentation methods do not perform well in the face of Vietnamese ambiguity, in response to the enormous challenge posed by the scarcity of the Vietnamese corpus to language processing. We first investigated the most advanced deep neural network method. According to the ambiguity problem of Vietnamese word segmentation, we then proposed a Vietnamese word segmentation processing technology based on an improved long short-term memory neural network (LSTM), which is made up of an LSTM encoding and a CNN feature extraction portion. The previous important information is kept in the memory unit; the word segmentation processing task is refined into a classification problem and a sequence labeling problem, which can gain the useful features of the word segmentation character and word level automatically. The limitation of the local context window size is avoided, and the word segmentation processing task is refined into a classification problem and a sequence labeling problem. Finally, validated by a homemade Vietnamese news website crawler dataset, the experimental results show that, compared with the single LSTM, single CNN methods, and traditional methods, the performance improvement of our proposed method is more obvious. In the Vietnamese word separation task, the accuracy reaches 96.6%, the recall reaches 95.2%, and the F1 value reaches 96.3%, which is significantly better than the traditional methods CNN and LSTM.

Chinese Character Learning Information Platform Based on Multimedia Information Technology

MIT (multimedia information technology) has brought profound changes to education, and MIT teaching has become an effective teaching method. Based on the teaching concept of MIT and curriculum integration, the connotation and goal of MIT Chinese and the Chinese character learning information platforms are clarified. In this paper, the design of a Chinese character learning information platform based on MIT is chosen as the study object. Starting with the investigation and analysis of the application of multimedia teaching resources by teachers in oral Chinese teaching, the problems in the construction of Chinese teaching resources are summarized. This paper combines the characteristics of domain ontology with those in the process of word segmentation to disambiguate ambiguous fields by calculating the strength of semantic association, so as to maximize the speed of ambiguity identification and resolution without losing AR (accuracy rate). After experiments, the system found a balance between RR (recall rate), AR, and the speed of Chinese character segmentation.

Character segmentation and restoration of Qin-Han bamboo slips using local auto-focus thresholding method

Character segmentation and restoration of Qin-Han bamboo slips using local auto-focus thresholding method

Application of Artificial Intelligence Recognition Technology in Digital Image Processing

Synthetic Artificial Intelligence technique is a science and technique derived and developed on the basis of calculator application technology. Image recognition is a special image processing step that plays an important role. Only after image recognition can it enter the stage of picture analysis and understanding. With the development of various computer technologies, images have gradually become and have become an important source of information for people. The use of calculator artificial intelligence is becoming increasingly widespread; therefore, understanding its application and related research is more conducive to pointing out the direction of research and learning for us. The goal of this paper is to discuss the emergence and development of synthetic intelligence identification technology and analyze the application bottlenecks of various types of synthetic intelligence identification technology, so as to increase our understanding of Synthetic Artificial Intelligence technique and provide reference for the research in related fields. This article simply introduces the technology of artificial intelligence type and its new development trend, and by combining concrete images of public facilities, the application of different computer artificial recognition methods of image recognition processing on the basis of the traditional method is improved, and through the corresponding simulation software of processing and identification methods for the analysis and comparison, the main application of two methods, the image processing recognition error rate is less than 0.5; improving computer artificial intelligence identification technique for the analysis of its application in image processing has certain help. The preprocessing process generally includes image digitization, grayscale, binarization, noise removal, and character segmentation. In terms of image recognition, algorithms mainly include statistical recognition, syntax recognition, and template matching. In recent years, with the development of neural networks and support vector machine technology, image recognition technology has a new and higher level of development.

Deep Segmentation of Corrupted Glyphs

Historical documents and archaeological artifacts are hard to process due to natural degradation, fading, spills, tears, overlaid data,, and so on. In this work, we focus on the task of recovering characters and symbols from images of corrupted archaeological artifacts where data is partially erased, occluded, or overwritten by other data. Such phenomena can be widely observed in image datasets of palimpsests and petroglyphs consisting of erased, overwritten, and in general heavily degraded data. Segmentation and binarization are typically applied to such images to detect and recover characters and symbols from their background. However, these methods mainly focus on the visible data while in our case, due to large corruption, both visible and invisible information should be considered. For example, computing the segmentation mask of an occluded character requires also labeling invisible pixels and missing parts. In this work, we introduce a deep neural network that computes character segmentation in palimpsests and petroglyphs while overcoming occlusions, missing parts, and degradation. Our network has inference abilities, thus, not only segmenting the symbol’s foreground pixels but also inferring and completing missing and corrupted parts. Since palimpsests and petroglyphs have very limited annotated ground-truth data, we also introduce data augmentation tools to properly train our network. We demonstrate both qualitative and quantitative performance of our method also including a user study involving expert evaluation.

Automatic Receipt Recognition System Based on Artificial Intelligence Technology

In this study, an automatic receipt recognition system (ARRS) is developed. First, a receipt is scanned for conversion into a high-resolution image. Receipt characters are automatically placed into two categories according to the receipt characteristics: printed and handwritten characters. Images of receipts with these characters are preprocessed separately. For handwritten characters, template matching and the fixed features of the receipts are used for text positioning, and projection is applied for character segmentation. Finally, a convolutional neural network is used for character recognition. For printed characters, a modified You Only Look Once (version 4) model (YOLOv4-s) executes precise text positioning and character recognition. The proposed YOLOv4-s model reduces downsampling, thereby enhancing small-object recognition. Finally, the system produces recognition results in a tax declaration format, which can upload to a tax declaration system. Experimental results revealed that the recognition accuracy of the proposed system was 80.93% for handwritten characters. Moreover, the YOLOv4-s model had a 99.39% accuracy rate for printed characters; only 33 characters were misjudged. The recognition accuracy of the YOLOv4-s model was higher than that of the traditional YOLOv4 model by 20.57%. Therefore, the proposed ARRS can considerably improve the efficiency of tax declaration, reduce labor costs, and simplify operating procedures.

Study of Handwriting Recognition Implementation in Data Entry of Survei Angkatan Kerja Nasional (SAKERNAS) using CNN

The use of Paper and Pencil Interviewing (PAPI) at BPS requires manual data entry that cannot be separated from the human ability to recognize handwriting. For computers, handwriting recognition is complex work that requires complex algorithms. Convolutional Neural Network (CNN) is an algorithm that can accommodate the complexity of handwriting recognition. This research intends to conduct a study on the implementation of the handwriting recognition model using CNN in recognizing handwriting on the PAPI questionnaire in data entry activities. Handwriting recognition model was built using the EMNIST dataset separately according to its character type and provides 89% accuracy for characters in the form of letters and numbers, 95% for characters in the form of letters, and 99% for characters in the form of numbers. Implementation of the handwriting recognition on the questionnaire image shows good results with 83.33% accuracy. However, there are problems found in the process of character segmentation where characters are not segmented correctly because the line of writing continues on the character that should be separated and disconnected characters when they should be joined. The result obtained in this study is expected to be a consideration regarding the entry method data used by BPS later.

Character Detection and Segmentation of Historical Uchen Tibetan Documents in Complex Situations

Tibetan is a low-resource language, and Tibetan culture carried by historical Tibetan documents is an important part of Chinese civilization. The study of historical Tibetan documents is of great significance to the protection of Tibetan culture and the promotion of Chinese culture. Character segmentation is an important step in image analysis and recognition of historical Tibetan documents. However, the following three challenges prevent solving problems of character segmentation in historical Tibetan documents: 1) the text lines have different degrees of tilt and twist; 2) there are many complex situations such as overlapping, crossing, touching and breaking character strokes; and 3) these documents are written by different people with different stroke styles. To resolve these problems, we propose a character segmentation method based on key feature information for historical Tibetan documents. The proposed method consists of three parts: 1) projection and syllable point location information are used to shorten the text lines of historical Tibetan documents and establish a character block database; 2) the local baseline of the character block is detected by using the location information of syllable points or combined with horizontal projection and straight line detection, and the character block is divided into two areas above and below the baseline, and different segmentation methods are adopted; and 3) in view of the large difference in stroke styles, three stroke attribution distances are used to complete the attribution. The experimental results show that the method proposed in this paper can effectively solve the problem of character segmentation of historical Tibetan documents and achieve a better character segmentation effect, which also provides a reference for the relevant document character segmentation.

The Trend of Segmentation for Arabic Handwritten Touching Characters

The paper is a comprehensive study of existing research trends in the sector of Arabic language, with a focus on state-of-the-art methods to illustrate the existing condition of various theory in that sector, with the goal of facilitating the adaptation and extension of prior ones into new systems and applications. In the Arabic alphabet, there are 28 letters. Depending on its place in the word, every Arabic letter has over one shape; a single character may have from one to four shapes. The Touching between character and the Overlapping occurred in the handwritten. Historical documents contained a massive knowledge and culture. There are many old books that need to be converted into readable format. Which would take a long time if humans converted it. However, the main problem is the lack of research in Arabic Handwritten especially for segmentation of touching characters. Thus, current trends of the segmentation techniques are investigated to identify the current state-of-the art of segmenting touching characters in other domains for constructing enhance techniques for Arabic touching characters. In this paper, it reviewed approaches for the segmentation of the touching characters. This paper presents the trend of approaches for the recognition process and segmentation of Arabic handwritten touching characters. In this paper, it highlighted the strength of each technique, the method used, and the drawback of the techniques. Based on the outcome, this will provide a good foundation for constructing a better technique for segmentation of Arabic touching characters, especially from the degraded documents.

Convolutional Neural Network Based Intelligent Handwritten Document Recognition

This paper presents a handwritten document recognition system based on the convolutional neural network technique. In today’s world, handwritten document recognition is rapidly attaining the attention of researchers due to its promising behavior as assisting technology for visually impaired users. This technology is also helpful for the automatic data entry system. In the proposed system prepared a dataset of English language handwritten character images. The proposed system has been trained for the large set of sample data and tested on the sample images of user-defined handwritten documents. In this research, multiple experiments get very worthy recognition results. The proposed system will first perform image pre-processing stages to prepare data for training using a convolutional neural network. After this processing, the input document is segmented using line, word and character segmentation. The proposed system get the accuracy during the character segmentation up to 86%. Then these segmented characters are sent to a convolutional neural network for their recognition. The recognition and segmentation technique proposed in this paper is providing the most acceptable accurate results on a given dataset. The proposed work approaches to the accuracy of the result during convolutional neural network training up to 93%, and for validation that accuracy slightly decreases with 90.42%.

Characters Segmentation from Arabic Handwritten Document Images: Hybrid Approach

Characters Segmentation from Arabic Handwritten Document Images: Hybrid Approach

Research on Car License Plate Recognition Based on Improved YOLOv5m and LPRNet

The application of license plate recognition technology is becoming more and more extensive. In view of the current practical requirements for the recognition accuracy and real-time performance of license plate recognition system in complex scenes, the existing target detection methods and license plate recognition methods are studied, and a car license plate recognition method based on improved YOLOv5m and LPRNet model is proposed. On the basis of studying the YOLOv5m algorithm and the image features of the car license plate, the YOLOv5m algorithm is improved from three aspects: the K-means++ algorithm is used to improve the matching degree between the anchor frame and the detection target, the DIOU loss function is used to improve the NMS method, and the feature map with 20×20 is removed to reduce the number of detection layers. A lightweight LPRNet network is used to realize license plate character recognition without character segmentation. Combining the improved YOLOv5m algorithm with LPRNet network, a license plate recognition system based on IYOLOv5m-LPRNet model is designed. The experimental results show that the average recognition accuracy of license plates in front, tilt, night and strong light interference scenes is more than 98%; Compared with the models of YOLOv3-LPRNet, YOLOv4-LPRNet, YOLOv5s-LPRNet and YOLOv5m-LPRNet, the recognition accuracy and recall rate of this method are improved, reaching 99.49% and 98.79% respectively; The mAP of this method is also the highest, reaching 98.56%; In terms of recognition speed, this method is also faster than the other four methods, and the number of pictures processed per second is increased by 5 compared with the YOLOv5m-LPRNet model. Therefore, the improved license plate recognition method in this paper performs well in robustness and speed.

Character Level Segmentation and Recognition using CNN Followed Random Forest Classifier for NPR System

The number plate recognition system must be able to quickly and accurately identify the plate in both low and noisy lighting conditions, as well as within the specified time limit. This study proposes automated authentication, which would minimize security and individual workload while eliminating the requirement for human credential verification. The four processes that follow the acquisition of an image are pre-processing, number plate localization, character segmentation, and character identification. A human error during the affirmation and the enrolling process is a distinct possibility since this is a manual approach. Personnel at the selected location may find it difficult and time-consuming to register and compose information manually. Due to the printed edition design, it is impossible to communicate the information. Character segmentation breaks down the number plate region into individual characters, and character recognition detects the optical characters. Our approach was tested using genuine license plate images under various environmental circumstances and achieved overall recognition accuracy of 91.54% with a single license plate in an average duration of 2.63 seconds.

DKNet: Deep Kuzushiji Characters Recognition Network

Kuzushiji, a cursive writing style, had been extensively utilized in Japan for over a thousand years starting from the 8^<i>th</i> century. In 1900, Kuzushiji was not included in regular school curricula due to the change in the Japanese writing system. Nowadays Japanese natives are unable to read historical books that were written using Kuzushiji language. Therefore, libraries and museums have decided to build digital copies of the documents and books that were written in Kuzushiji language. Due to a limited number of trained experts, researchers have utilized machine and deep learning models to convert historical documents and books into a modern script that can be easily read by human beings. However, the existing deep learning techniques suffer from over-fitting and gradient vanishing problems. To overcome these problems, an efficient deep Kuzushiji characters recognition network (DKNet) is proposed. Initially, to remove noise from the training images, a trilateral joint filter is applied. Contrast limited adaptive histogram equalization (CLAHE) is then applied to enhance the visibility of filtered images. Thereafter, a pre-trained MobileNet is utilized to extract the features of Kuzushiji characters. MobileNet&#x2019;s final layers are removed, including the fully connected layer and softmax. The flatten layer is then applied to the input. A fully connected classification layer is then used with Rectified linear units (ReLUs) and dropouts. Dropouts are used to generalize the model, thus preventing the over-fitting problem. Finally, the softmax activation function is employed to provide the recognition results. To test the proposed model, actual documents are first segmented by using the proposed Maximally stable extremal regions (MSERs) and convexhull-based segmentation approach. Segmented characters are then recognized using the trained DKNet. Extensive comparative analyses reveal that DKNet achieves better performance than the competitive models in terms of various performance metrics. An efficient Application Programming Interface (API) is also designed for Japanese Kuzushiji ancient heritage character recognition to help the end-users.