A Survey on Text Detection from Document Images

According to the edge and gradient based algorithm for text information extraction of video image under the multimedia environment, the line structure of the video image is acted as a feature of text information to obtain the change law of line structure in video images. However, pseudo area, large noise and poor adaptability etc., appear during extraction step. Thus, a text information extraction algorithm of video images in multimedia environment is proposed. The shot of multimedia video images is segmented, and video images with text information are detected. The text of segmented video images is located, and the text information is extracted using linear extraction method. The maximum between-class variance method is adopted to optimize extracted text information, so as to achieve text information extraction of video images in multimedia environment. The experimental results show that the method considers the region of extracted text and situation of text noise in multimedia environment, and saves the extraction time compared to general extraction methods, and improves the extraction accuracy and adaptability, which can effectively advance the performance of text extraction.

Scene text information extraction plays an important role in many computer vision applications. Most features in existing text extraction algorithms are only applicable to one text extraction stage (text detection or recognition), which significantly weakens the consistency in an end-to-end system, especially for the complex Chinese texts. To tackle this challenging problem, we propose a novel text structure feature extractor based on a text structure component detector (TSCD) layer and residual network for Chinese texts. Inspired by the three-layer Chinese text cognition model of a human, we combine the TSCD layer and the residual network to extract features suitable for both text extraction stages. The specialized modeling for Chinese characters in the TSCD layer simulates the key structure component cognition layer in the psychological model. And the residual mechanism in the residual network simulates the key bidirectional connection among the layers in the psychological model. Through the organic combination of the TSCD layer and the residual network, the extracted features are applicable to both text detection and recognition, as humans do. In evaluation, both text detection and recognition models based on our proposed text structure feature extractor achieve great improvements over baseline CNN models. And an end-to-end Chinese text information extraction system is experimentally designed and evaluated, showing the advantage of the proposed feature extractor as a unified feature extractor.

Ever increasing volumes of media content and the desire to extract information from media archives motivate the studies into semantic audio information mining. Much research in this filed concerns development of bespoke systems, in which soundtracks are exclusively classified and segmented, and a specific type of sound is recognized and analyzed. This approach however is detrimental to the complete extraction of all relevant semantic information and audio scene analysis. The current study addresses the issues of soundtracks with overlapped music, speech and ambient sounds, and explores how MARSYAS (Music Analysis, Retrieval and Synthesis for Audio Signals) can be extended to mixed and overlapped soundtrack applications. The MARSYAS has been adapted to this application by means of adopting additional speech cleaning algorithms. The proposed new system can analyze arbitrary soundtracks and timestamp the occurrence of music and speech, allowing overlaps, in the form of a “sound score” for further recognition methods to extract music score and text information. Validation tests have shown that the new system handles overlapping cases and is therefore capable of extracting more information than other existing methods.

Since the COVID-19 pandemic, numerous jobs have become necessary, including the storing and sharing of printed material across computers. One simple way to save data from printed papers to a computer system is to scan them first and then save them as images. However, it would be quite challenging to extract or query text or other information from these photo files to reuse this information. As a result, a method for automatically retrieving and storing information, particularly text, from picture files is required. Optical character recognition (OCR) is an ongoing research topic that aims to create a computer system capable of extracting and processing text from images. To accomplish successful automation, certain significant problems must be identified and addressed. The font properties of characters in paper documents, as well as image quality, are only a few of the latest problems. Characters may not be recognized correctly by the computer system because of many complexities. So, in this study, authors look into OCR in four different contexts and apply them to get our results. However, every OCR is further followed by these two steps. First, a comprehensive explanation of the challenges that may develop during the OCR phases is provided. The key phases of an OCR system are then executed, including pre-processing, segmentation, normalization, feature extraction, classification, and post-processing. It can be used with deep learning software to provide OCR data which is very useful for robotic and AI applications.

Handwritten script recognition is a interesting task that has been widely researched in the arena of computer vision and image processing. Tulu language is a Dravidian language spoken in coastal regions of Southern part of India. Recognition of Tulu handwritten scripts is important for preserving cultural heritage, historical documents, and facilitating communication among native speakers. This survey paper provides an overview of the existing tactics for recognition of Tulu scripts. We present a comprehensive review of the literature on various methods such as feature extraction, segmentation, classification, and deep learning techniques used for Tulu script recognition. The paper also discusses the challenges associated with Tulu script recognition and highlights the future research directions in this area. Key Words: Tulu, Handwritten script recognition, Feature extraction, Segmentation, Classification, Deep learning

The expansive growth of information on the Internet has led to new developments in computer vision technology and image processing techniques. Since stone inscriptions are subject to erosion and polishing by the external environment for years, it is difficult to extract image and text information. In this study, the fuzzy control theory is combined with edge detection technology for image edge detection. Firstly, a suitable fuzzy rule and affiliation function are set, then a fuzzy control system is used to extract and detect the image edge information, and then a fuzzy logic rule-based edge detection algorithm is proposed to detect the inscription images. To test the performance of the algorithm, the detection effect of the image is first analyzed from a subjective perspective. The experimental results show that the proposed algorithm has better edge detection for both inscription and lena images, with better noise suppression without excessive distortion, and clearer inscription images. The proposed algorithm has the lowest MSE value of 41.26 when the detection object is the lena image b, and the highest PSNR value of 33.84 when the detection object is the lena image a. The proposed algorithm has the lowest MSE value of 41.26 when the detection object is the lena image b, and the highest PSNR value of 41.26 when the detection object is the lena image b. The proposed algorithm has the highest PSNR value of 33.84 when the detection object is the lena image b. In summary, the analysis of both subjective and objective indicators shows that the inscription image processing algorithm used in this paper has better processing effect, and the processed images become clearer with less distortion, which is helpful for both inscription image and text extraction.

The burgeoning field of natural language processing (NLP) has witnessed exponential growth, captivating researchers due to its diverse practical applications across industries. However, the intricate nature of legal texts poses unique challenges for conventional text extraction methods. To surmount these challenges, this article introduces a pioneering legal text extraction model rooted in fuzzy language processing and metaphor recognition, tailored for the domain of online environment governance. Central to this model is the utilization of a bidirectional long short-term memory (Bi-LSTM) network, adept at delineating illicit behaviors by establishing connections between legal provisions and judgments. Additionally, a self-attention module is integrated into the Bi-LSTM architecture, augmented by L2 regularization, to facilitate the efficient extraction of legal text information, thereby enabling the identification and classification of illegal content. This innovative approach effectively resolves the issue of legal text recognition. Experimental findings underscore the efficacy of the proposed method, achieving an impressive macro-F1 score of 0.8005, precision of 0.8047, and recall of 0.8014. Furthermore, the article delves into an analysis and discussion of the potential application prospects of the legal text extraction model, grounded in fuzzy language processing and metaphor recognition, within the realm of online environment governance.

Automated Image Analysis Pipeline for Standardized Processing, Segmentation, and Feature Extraction in Diffuse Large B-Cell Lymphoma Histological Slides: Towards Enhanced Prediction of Immunotherapy Response and Risk Stratification

International audience

The rapid emergence of technology and big data science opened up a significant amount of work that has been carried out in the field of feature extraction and classification techniques of heart sound using various deep learning methods. Practically, medical practitioners use the same old scientific method and practice to seek out any cardiac disorders and predict any abnormality in the human heart. Heart sound normalization, denoising, segmentation, feature extraction, and classification techniques provide a suitable way of study of phonocardiography (PCG) signal analysis which eventually reduces the cost, makes the system compact, and simultaneously, can work with extensive training data. This paper mainly indulges in two parts feature extraction and classification. The proposed deep learning study for PCG signal used online available heart disease datasets, and time domain features like average energy, power, root mean square (RMS), total harmonic distortion, and zero Crossing rates are used. Statistical features used are kurtosis and skewness. The acoustic features used are Mel-frequency cepstrum coefficients (MFCCs), mel, chroma, contrast, and tonnetz. For the classification of heart sound, the proposed modified CNN-based mobile network is used. The modified CNN-based mobile network is very effective in heart sound analysis as it requires very less computation time and storage. The proposed CNN-based modified Mobile Network model attained an accuracy of 99.04 + 0.07% on the test dataset with a sensitivity of 96.8 + 0.03 % and specificity of 97.2 + 0.09%.

In this paper the classification of hyperspectral images is investigated by using a supervised approach. The spectral feature are extracted with well known decision boundary feature extraction (DBFE) and non-parametric weighted feature extraction (NWFE) techniques. The most informative features are fed to random forest (RF) classifier to perform pixel-wise classification. The experiments are carried out on two benchmark hyperspectral images. The results show that RF classifier generates good classification accuracies for hyperspectral image with smaller execution time. Among feature extraction techniques, DBFE has produced better results than NWFE.

Automatic extraction of text information plays an important role in machine translation, knowledge mapping and other fields. In recent years, with the rapid development of computer technology and the popularization of Internet application, the resources acquired by people through the Internet show explosive growth. Facing the massive information resources, how to extract the required information quickly and effectively and convert it into structured data has become a hot topic of current research. Based on this, this paper proposes a automatic topic-oriented text extraction method combining BiLSTM and CRF models. This method firstly establishes the text extraction topic, then carries on the automatic entity recognition to the data related topic, finally forms the standard structured data, thereby realizes the unstructured text data to the specific structure of the information block, which lays the foundation for knowledge mining. Taking the data collected in ACL 2018 Chinese NER as the test data, the precision of our algorithm is 95.74%. Compared with the traditional neural network method, our text information extraction method can effectively identify more entity information in the text data, and improve its effect in practical application.

The extraction of text information from traffic panels is one of the challenging problems in computer vision. Although the past decade has seen a promising shift and important progress in object detection, few works and a limited number of datasets focus specifically on extracting text from traffic signs. To address the lack of data for text detection in traffic panels, especially those with Arabic scripts, this paper introduces a new multilingual and multipurpose dataset named ASAYAR. It consists of three sub-datasets: Arabic-Latin scene text localization, traffic sign detection, and directional symbol detection. The dataset contains 1763 images collected on different Moroccan highways, and annotated manually, using 16 object categories. The fully annotated ASAYAR images contains more than 20000 bounding box objects. The paper also investigates the usability of the dataset, by evaluating the performance of the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">state-of-the-art</i> algorithms for object and text detection. Experimental results show good detection scores, demonstrating the potential contribution of ASAYAR in the development of methods for text extraction from traffic panels.

The aim of this article to introduces various image processing and machine learning techniques used to identify plant diseases based on images of diseased plants in order to recognize disease in plants from images and necessary in image processing and machine learning as they apply to the identification and categorization of plant diseases. We meticulously review more content and provide important standards. These characteristics include things like the size of the photo collection, preprocessing, segmentation techniques, classifier types, classifier resolution, and other things. To suggest and arrange our work on the classification and identification of plant diseases, we explain our study here. Then, based on the principal technical solution used in the method, each of these groups is split using machine learning techniques. Photos of plant disease samples were processed using support vector (SVM) and k-mean clustering techniques to extract color and texture information. The results show that the SVM classifier is a very good tool for detecting and identifying plant-borne diseases in agricultural crops.

This paper presents a novel geometrical scale and rotation independent feature extraction (FE) technique for multi-lingual character recognition (CR). The performance of any CR techniques mainly depends on the robustness of the proposed FE methods. Currently, there are very few scale and rotation independent FE techniques present in the literature which successfully extract the robust features from characters with noise such as distortion and breaks in the characters. Many FE methods from the literature failed to distinguish the characters which look similar in their appearance. So, in this paper, we have proposed a novel scale and rotation independent geometrical shape FE technique which successfully recognized distorted, broken, and similarly looking characters. Aside from the proposed FE technique, we've used crossing count (CC) features. Finally, we have combined the proposed features with CC features to make as Feature Vector (FV) of the character to be recognized. The proposed CR technique is evaluated using publicly available media-lab license plate (LP), ISI_Bengali, and Chars74K benchmark data sets and achieved encouraging results. To further assess the performance of the proposed FE method, we've used a proprietary data set containing nearly 168000 multi-lingual characters from English, Devanagari, and Marathi scripts and achieved encouraging results. We have observed better classification rates for the proposed FE method using publicly available benchmark data sets as compared to few of the CR FE methods from the literature.