Candidate Character Research Articles

License Plate Recognition Using Three-Dimensional Rotated Character Recognition and Instance Segmentation by Deep Learning

License plate recognition is currently used in various situations, such as parking lot vehicle management and the tracking of wanted vehicles. These applications require recognition from all possible camera angles. Therefore, we propose a method for license plate recognition in images captured from various camera angles. First, the license plate area is detected from the input image using the YOLOv5 object detection method. The subsequent process can be performed in two manners: by rotating the license plate to the front using projective transformation and trapezoidal correction, or by using graph matching. The first method performs Hough transforms or linear approximations as preprocessing, and then calculates the rectangle surrounding the license plate from the YOLOv5 output. After performing trapezoidal correction, the maximally stable extremal regions (MSER) are used to detect character candidates, and characters are recognized using 3D rotated character recognition. The second method performs character candidate detection and recognition without trapezoidal correction, followed by graph matching. These methods are versatile because they do not depend on the layout of license plates, which varies among countries and regions. Two types of datasets were used: a set of images containing Japanese license plates collected by ourselves, and a set of publicly available images containing Taiwanese license plates. Two recognition rates were evaluated: the license plate character recognition rate and license plate recognition rate in which all characters in one plate are recognized. The license plate character recognition rates using graph matching were 91.9% for the Japanese license plates and 89.3% for the Taiwanese license plates. The license plate recognition rates were 84.0% and 84.5%, respectively.

Loving a good fight: personality traits and reactions to conflict in TV debates

AbstractThis article seeks to contribute to our understanding of media influence on political behaviour by investigating the ways in which people with different personality types react to candidates’ conflicting rhetoric in televised debates during election campaigns. It analyses responses along three reaction types: evaluations of candidate character, debate performance, and voting intentions in two debate clips from the 2019 UK general election and 2022 Australian federal election. The study uses semi-structured interviews with respondents in the UK and relies on deductive, flexible thematic analysis. The findings show that respondents’ personality traits are associated with different reactions to conflict in televised debates, which are sometimes mediated by the nature of attack, partisanship and preconceptions about candidates especially in the UK debate.

Image Text Detection and Conversion into Text Form

We are purposing a system by which we can detect the image text and convert into the text form for which we firstly apply MSER (Maximally Stable External Region) which is used as a method of blob detection in images, or to detect character candidates. After that some text features by which the text can be recognized. To recognize the text feature we apply some geometric filtration by which we can easily identified the character from the image. This is why all the character is formed by combination of geometric figures. After recognizing the text, reject the false positives i.e. background, figures, and many things expect character. Performing all these we apply OCR function by which Segmenting out the text from a cluttered scene helps with related tasks. Lastly after finding all these we have the text which is in text form which is easily modified and editable. Key Words: Image Processing, OCR

SMART HIRE BASED SYSTEM

An efficient and effective hiring process is a step-by-step process for hiring a new employee, whereby an organization identifies its talent needs, recruits from its talent pool and eventually hires the most qualified candidates. Most companies have their own hiring processes. What follows are the most common steps in the hiring process across industry and regardless of company size. Keep in mind, however, that the specific details of the hiring process are unique to each company. Our model is to Automate the interview process by using Machine learning in order to simplify the process by selecting the key words, skills, passions from the profile and sending the mails to the applicants. In most organisations, recruitment is a complex and time-consuming process, since they get a large number of job applications for openings that are called. managing those process applications manually would want a great amount of labour, time, and cash. further, the hr personnel or the recruitment group ought to manually shortlist the incoming candidates and time table interviews for them as a result. this lengthy technique makes the organization's operations inefficient. therefore, we deliberate to build a web-software with an aim to automate the interview system. the software consists of following capabilities which includes candidate character prediction the use of device gaining knowledge of, computerized resume parser, coping with of the scheduling of interviews, video recording in browser, test self assurance degree and other character trends of the candidate the use of video (eye movements and face feelings) and tone (speech) evaluation, hold track of the recruitment data and send mail to chose/rejected candidates robotically in one-click. this machine will as a consequence make the hiring technique plenty faster & smoother, allow recruitments in larger numbers, generate concise insights and offer summary of the candidate's profile with a purpose to encompass the resume, responses to questions, technical competencies, character traits, video and tone evaluation end result.

MLSL-Spell: Chinese Spelling Check Based on Multi-Label Annotation

Chinese spelling errors are commonplace in our daily lives, which might be caused by input methods, optical character recognition, or speech recognition. Due to Chinese characters’ phonetic and visual similarities, the Chinese spelling check (CSC) is a very challenging task. However, the existing CSC solutions cannot achieve good spelling check performance since they often fail to fully extract the contextual information and Pinyin information. In this paper, we propose a novel CSC framework based on multi-label annotation (MLSL-Spell), consisting of two basic phases: spelling detection and correction. In the spelling detection phase, MLSL-Spell uses the fusion vectors of both character-based pre-trained context vectors and Pinyin vectors and adopts the sequence labeling method to explicitly label the type of misspelled characters. In the spelling correction phase, MLSL-Spell uses Masked Language Mode (MLM) model to generate candidate characters, then performs corresponding screenings according to the error types, and finally screens out the correct characters through the XGBoost classifier. Experiments show that the MLSL-Spell model outperforms the benchmark model. On SIGHAN 2013 dataset, the spelling detection F1 score of MLSL-Spell is 18.3% higher than that of the pointer network (PN) model, and the spelling correction F1 score is 10.9% higher. On SIGHAN 2015 dataset, the spelling detection F1 score of MLSL-Spell is 11% higher than that of Bert and 15.7% higher than that of the PN model. And the spelling correction F1 of MLSL-Spell score is 6.8% higher than that of PN model.

An approach for handwritten Chinese text recognition unifying character segmentation and recognition

Text line recognition methods can be categorized into explicit segmentation based and implicit segmentation based ones. Explicit segmentation based methods require character-level annotation during training, while implicit segmentation based methods, trained on line-level annotated data, face alignment drift challenges. Though some methods have been proposed to address these challenges using weakly supervised object detection, they often rely on cumbersome pseudo-box generation processes and complex decoding. In this paper, we propose a unified framework to overcome these challenges, achieving high accuracy in text recognition and character segmentation. To eliminate the need of character-level annotated real text line data in training, we introduce a novel training paradigm that utilizes character-level annotated synthetic data and line-level annotated real data jointly. For synthetic data, candidate characters are explicitly aligned with labeled characters to generate hard labels for supervising model training. For real data, implicit alignment is produced by Connectionist Temporal Classification (CTC) mapping to provide soft labels for weakly-supervised model training. And for inference, we propose two decoding strategies leveraging the advantages of Non-Maximum Suppression (NMS) and CTC decoding. Extensive experiments on benchmark datasets demonstrate the superior performance of our method in text recognition and character localization, even with minimal amounts of character-level annotated line data.

Hybrid Arabic handwritten character segmentation using CNN and graph theory algorithm

Arabic handwritten words segmentation is considered a challenging step in Arabic optical character recognition. In this work, we propose a convolutional neural network-based segmentation of handwritten Arabic words. After generating candidate segmentation points, we applied a graph theory-based technique to divide the word into sub-words. Our approach reached a 96% correct sub-word segmentation rate. Additionally, we develop a Segmentation Hypothesis Graph (SHG) to generate candidate characters for each sub-word. We employ both a manually designed convolutional neural network and a transfer learning-based CNN using the pretrained AlexNet model. The accuracy, 96.97%, of the pretrained model outperformed the manually and state of the art models trained on the same dataset. Finally, we used recognition confidence to validate the segmentation points. Hence, our approach correctly segments 88% of the words into characters and successfully resolves 100% of the overlapping cases.

Detection and Recognition of Tilted Characters on Railroad Wagon Wheelsets Based on Deep Learning.

The quality of railroad wheelsets is an important guarantee for the safe operation of wagons, and mastering the production information of wheelsets plays a vital role in vehicle scheduling and railroad transportation safety. However, when using objection detection methods to detect the production information of wheelsets, there are situations that affect detection such as character tilting and unfixed position. Therefore, this paper proposes a deep learning-based method for accurately detecting and recognizing tilted character information on railroad wagon wheelsets. It covers three parts. Firstly, we construct a tilted character detection network based on Faster RCNN for generating a wheelset's character candidate regions. Secondly, we design a tilted character correction network to classify and correct the orientation of flipped characters. Finally, a character recognition network is constructed based on convolutional recurrent neural network (CRNN) to realize the task of recognizing a wheelset's characters. The result shows that the method can quickly and effectively detect and identify the information of tilted characters on wheelsets in images.

A Tree-Structure Analysis Network on Handwritten Chinese Character Error Correction

Existing researches on handwritten Chinese characters are mainly based on recognition network designed to solve the complex structure and numerous amount characteristics of Chinese characters. In this paper, we investigate Chinese characters from the perspective of error correction, which is to diagnose a handwritten character to be right or wrong and provide a feedback on error analysis. For this handwritten Chinese character error correction task, we define a benchmark by unifying both the evaluation metrics and data splits for the first time. Then we design a diagnosis system that includes decomposition, judgement and correction stages. Specifically, a novel tree-structure analysis network (TAN) is proposed to model a Chinese character as a tree layout. Using the predicted tree layout for judgement, if the character is wrongly written, correction operation is needed for error analysis. The correction stage mainly consists of three steps: fetch the ideal character, correct the errors and locate the errors. Computing the distance between the model output and all candidate characters can generate ideal characters. With the decomposition ability of TAN, edit distance computing between predicted tree and ideal tree can lead to correction operations. By using attention visualization, we can even provide the approximate error location. Through quantitative analysis, we prove that TAN captures more accurate spatial position information than regular encoder-decoder models. Additionally, we propose a novel bucketing mining strategy to apply triplet loss at radical level to alleviate feature dispersion. Experiments on handwritten character dataset demonstrate that our proposed TAN shows great superiority on all three metrics comparing with other state-of-the-art models.

Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition.

Leveraging the advances of natural language processing, most recent scene text recognizers adopt an encoder-decoder architecture where text images are first converted to representative features and then a sequence of characters via 'sequential decoding'. However, scene text images suffer from rich noises of different sources such as complex background and geometric distortions which often confuse the decoder and lead to incorrect alignment of visual features at noisy decoding time steps. This paper presents I2C2W, a novel scene text recognition technique that is tolerant to geometric and photometric degradation by decomposing scene text recognition into two inter-connected tasks. The first task focuses on image-to-character (I2C) mapping which detects a set of character candidates from images based on different alignments of visual features in an non-sequential way. The second task tackles character-to-word (C2W) mapping which recognizes scene text by decoding words from the detected character candidates. The direct learning from character semantics (instead of noisy image features) corrects falsely detected character candidates effectively which improves the final text recognition accuracy greatly. Extensive experiments over nine public datasets show that the proposed I2C2W outperforms the state-of-the-art by large margins for challenging scene text datasets with various curvature and perspective distortions. It also achieves very competitive recognition performance over multiple normal scene text datasets.

Penalties for Going Against Type: How Sexism Shapes Voters’ Perceptions of Candidate Character

Although women are increasingly represented in elected office, little is known about how a female candidate's gender influences voter approval when her messaging emphasizes her strong leadership ability—a character trait generally regarded as masculine. Drawing from theories of social cognition and gender stereotypes, we examine in this article how citizens react to male and female politicians who emphasize particular character traits. After synthesizing relevant literature, we report on a study conducted to see whether women lose public support for emphasizing their leadership ability—thus “going against type.” In a survey of more than 800 American adults, we found that respondents penalized a fictional woman running for Congress when her messaging to voters emphasized the core character trait of leadership, as opposed to compassion (a trait traditionally associated with women) or no character trait at all. In contrast, respondents viewed a fictional man more favorably when his messaging to voters went against type by highlighting compassion than when he emphasized leadership. These findings suggest that female candidates have fewer options than men do when selecting which personal characteristics to present in their messaging to gain the approval of the voting public. This result underscores the need for policies and programs that promote female leadership in all walks of life, thereby leading the public to associate leadership skill with both genders equally.

Dominating set based arbitrary oriented bilingual scene text localization

<p>Localizing and recognizing arbitrarily oriented text in natural scene images is the biggest challenge. It is because scene texts are often erratic in shapes. This paper presents a simple and effective graph representational algorithm for detecting arbitrary-oriented text location to smoothen the text recognition process because of its high impact and simplicity of representation. An arbitrarily oriented text can be horizontal, vertical, perspective, curved (diagonal/off-diagonal), or even a combination. As a pre-processing step, image enhancement is performed in the frequency domain to improve the representation of images that are invariant to intensity. It is necessary to draw bounding boxes for each candidate character in the scene images to extract text regions. This step is carried out by utilizing the advantage of the region-based approach called maximally stable extremal regions. A typical problem with curved text localization is that non-text objects may occur within localized text regions. Our method is the first in the literature that searches for dominating sets to solve this problem. This dominating set method outperforms several traditional methods, including deep learning methods used for arbitrary text localization, on challenging datasets like 13<sup>th</sup> international conference on document analysis and recognition (ICDAR 2015), multi-script robust reading competition (MRRC), CurvedText 80 (CUTE80), and arbitrary text (ArT).</p>

Exploring the association between character strengths and moral functioning

ABSTRACT We explored the relationship between 24 character strengths measured by the Global Assessment of Character Strengths (GACS), which was revised from the original VIA instrument, and moral functioning comprising postconventional moral reasoning, empathic traits and moral identity. Bayesian Model Averaging (BMA) was employed to explore the best models, which were more parsimonious than full regression models estimated through frequentist regression, predicting moral functioning indicators with the 24 candidate character strength predictors. Our exploration was conducted with a dataset collected from 666 college students at a public university in the Southern United States. Results showed that character strengths as measured by GACS partially predicted relevant moral functioning indicators. Performance evaluation results demonstrated that the best models identified by BMA performed significantly better than the full models estimated by frequentist regression in terms of AIC, BIC, and cross-validation accuracy. We discuss theoretical and methodological implications of the findings for future studies addressing character strengths and moral functioning.

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.

Strategi Pemenangan Partai Golongan Karya Pada Pemilihan Kepala Daerah Kabupaten Seram Bagian Timur Tahun 2020

This study is a descriptive qualitative research that aims to know the winning strategy of the Golkar Party in the 2020 Seram Bagian Timur Regency Election. The study results showed that the realization of the Party's programs offered to the community is more inclined to the people's economy, such as in infrastructure, education, and health. The placement of figures was very influential in winning the 2020 Pilkada. The political behavior of the community tends to choose Mukti and Idris because of the candidate's character, vision, and mission on the collective expectations of the community. In the Adat leadership, Pak Mukti supports and develops local wisdom and inaugurates Adat leaders in Seram Bagian Timur Regency. Pak Mukti's leadership always tends to represent the interests of Adat.

Think Twice: A Post-Processing Approach for the Chinese Spelling Error Correction

Chinese Spelling Error Correction is a hot subject in the field of natural language processing. Researchers have already produced many great solutions, from the initial rule-based solution to the current deep learning method. At present, SpellGCN, proposed by Alibaba’s team, achieves the best results of which character level precision over SIGHAN2013 is 98.4%. However, when we apply this algorithm to practical error correction tasks, it produces many false error correction results. We believe that this is because the corpus used for model training contains significantly more errors than the text used for model correcting. In response to this problem, we propose performing a post-processing operation on the error correction tasks. We employ the initial model’s output as a candidate character, obtain various features of the character itself and its context, and then use a classification model to filter the initial model’s false error correction results. The post-processing idea introduced in this paper can apply to most Chinese Spelling Error Correction models to improve their performance over practical error correction tasks.

Indonesian Plate Number Identification Using YOLACT and Mobilenetv2 in the Parking Management System

A vehicle registration plate is used for vehicle identity. In recent years, technology to identify plate numbers automatically or known as Automatic License Plate Recognition (ALPR) has grown over time. Convolutional Neural Network and YOLACT are used to do plate number recognition from a video. The number plate recognition process consists of 3 stages. The first stage determines the coordinates of the number plate area on a video frame using YOLACT. The second stage is to separate each character inside the plat number using morphological operations, horizontal projection, and topological structural. The third stage is recognizing each character candidate using CNN MobileNetV2. To reduce computation time by only take several frames in the video, frame sampling is performed. This experiment study uses frame sampling, YOLACT epoch, MobileNet V2 epoch, and the ratio of validation data as parameters. The best results are with 250ms frame sampling succeed to reduce computational times up to 78%, whereas the accuracy is affected by the MobileNetV2 model with 100 epoch and ratio of split data validation 0,1 which results in 83,33% in average accuracy. Frame sampling can reduce computational time however higher frame sampling value causes the system fails to obtain plate region area.

An Improved Deep Learning Network Structure for Multitask Text Implication Translation Character Recognition

With the rapid development of artificial intelligence technology, multitasking textual translation has attracted more and more attention. Especially after the application of deep learning technology, the performance of multitask translation text detection and recognition has been greatly improved. However, because multitasking contains the interference problem faced by the translated text, there is a big gap between recognition performance and actual application requirements. Aiming at multitasking and translation text detection, this paper proposes a text localization method based on multichannel multiscale detection of the largest stable extreme value region and cascade filtering. This paper selects the appropriate color channel and scale to extract the maximum stable extreme value area as the character candidate area and designs a cascaded filter from coarse to fine to remove false detections. The coarse filter is based on some simple morphological features and stroke width features, and the fine filter is trained by a two-recognition convolutional neural network. The remaining character candidate regions are merged into horizontal or multidirectional character strings through the graph model. The experimental results on the text data set prove the effectiveness of the improved deep learning network character model and the feasibility of the textual implication translation analysis method based on this model. Among them, the text contains translation character recognition results prove that the model has good description ability. The characteristics of the model determine that this method is not sensitive to the scale of the sliding window, so it performs better than the existing typical methods in retrieval tasks.

Political Rhetoric of East Java’s Governor and Deputy Governor Candidates

Public debate is one of the stages in a General Election determined by the Commission of Election (KPU) to present the vision, missions, ideas, and programs of prospective leaders to the public. Political rhetoric is a specific study on how political actors try to persuade or attract public voters’ sympathy. This study aimed to reveal Governor and Deputy Governor candidates’ rhetoric in the 2018 East Java Public Debate, using an interpretative qualitative research method with political rhetorical analysis from Finlayson. This study used documentation techniques of the broadcasted recording of Public Debate I, II, and III by TVRI Surabaya and JTV Surabaya for the data collection. The study results indicated that the two candidates for Governor and Deputy Governor of East Java in 2018 had their respective political rhetoric strategies in persuading prospective voters when the Public Debate took place, started from the context contestation; candidate character in rhetoric; contestation perception; and ideological contestation.

Character Segmentation in Asian Collector's Seal Imprints: An Attempt to Retrieval Based on Ancient Character Typeface

Collector's seals provide important clues about the ownership of a book. They contain much information pertaining to the essential elements of ancient materials and also show the details of possession, its relation to the book, the identity of the collectors and their social status and wealth, amongst others. Asian collectors have typically used artistic ancient characters rather than modern ones to make their seals. In addition to the owner's name, several other words are used to express more profound meanings. A system that automatically recognizes these characters can help enthusiasts and professionals better understand the background information of these seals. However, there is a lack of training data and labelled images, as samples of some seals are scarce and most of them are degraded images. It is necessary to find new ways to make full use of such scarce data. While these data are available online, they do not contain information on the characters' position. The goal of this research is to assist in obtaining more labelled data through user interaction and provide retrieval tools that use only standard character typefaces extracted from font files. In this paper, a character segmentation method is proposed to predict the candidate characters' area without any labelled training data that contain character coordinate information. A retrieval-based recognition system that focuses on a single character is also proposed to support seal retrieval and matching. The experimental results demonstrate that the proposed character segmentation method performs well on Asian collector's seals, with 85% of the test data being correctly segmented.