Text characters embedded in images represent a rich source of information for content-based indexing and retrieval applications. However, these text characters are difficult to be detected and recognized due to their ...Text characters embedded in images represent a rich source of information for content-based indexing and retrieval applications. However, these text characters are difficult to be detected and recognized due to their various sizes, grayscale values, and complex backgrounds. Existing methods cannot handle well those texts with different contrast or embedded in a complex image background. In this paper, a set of sequential algorithms for text extraction and enhancement of image using cellular automata are proposed. The image enhancement includes gray level, contrast manipulation, edge detection, and filtering. First, it applies edge detection and uses a threshold to filter out for low-contrast text and simplify complex background of high-contrast text from binary image. The proposed algorithm is simple and easy to use and requires only a sample texture binary image as an input. It generates textures with perceived quality, better than those proposed by earlier published techniques. The performance of our method is demonstrated by presenting experimental results for a set of text based binary images. The quality of thresholding is assessed using the precision and recall analysis of the resultant text in the binary image.展开更多
In the context of constructing an embedded system to help visually impaired people to interpret text,in this paper,an efficient High-level synthesis(HLS)Hardware/Software(HW/SW)design for text extraction using the Gam...In the context of constructing an embedded system to help visually impaired people to interpret text,in this paper,an efficient High-level synthesis(HLS)Hardware/Software(HW/SW)design for text extraction using the Gamma Correction Method(GCM)is proposed.Indeed,the GCM is a common method used to extract text from a complex color image and video.The purpose of this work is to study the complexity of the GCM method on Xilinx ZCU102 FPGA board and to propose a HW implementation as Intellectual Property(IP)block of the critical blocks in this method using HLS flow with taking account the quality of the text extraction.This IP is integrated and connected to the ARM Cortex-A53 as coprocessor in HW/SW codesign context.The experimental results show that theHLS HW/SW implementation of the GCM method on ZCU102 FPGA board allows a reduction in processing time by about 89%compared to the SW implementation.This result is given for the same potency and strength of SW implementation for the text extraction.展开更多
To promote behavioral change among adolescents in Zambia, the National HIV/AIDS/STI/TB Council, in collaboration with UNICEF, developed the Zambia U-Report platform. This platform provides young people with improved a...To promote behavioral change among adolescents in Zambia, the National HIV/AIDS/STI/TB Council, in collaboration with UNICEF, developed the Zambia U-Report platform. This platform provides young people with improved access to information on various Sexual Reproductive Health topics through Short Messaging Service (SMS) messages. Over the years, the platform has accumulated millions of incoming and outgoing messages, which need to be categorized into key thematic areas for better tracking of sexual reproductive health knowledge gaps among young people. The current manual categorization process of these text messages is inefficient and time-consuming and this study aims to automate the process for improved analysis using text-mining techniques. Firstly, the study investigates the current text message categorization process and identifies a list of categories adopted by counselors over time which are then used to build and train a categorization model. Secondly, the study presents a proof of concept tool that automates the categorization of U-report messages into key thematic areas using the developed categorization model. Finally, it compares the performance and effectiveness of the developed proof of concept tool against the manual system. The study used a dataset comprising 206,625 text messages. The current process would take roughly 2.82 years to categorise this dataset whereas the trained SVM model would require only 6.4 minutes while achieving an accuracy of 70.4% demonstrating that the automated method is significantly faster, more scalable, and consistent when compared to the current manual categorization. These advantages make the SVM model a more efficient and effective tool for categorizing large unstructured text datasets. These results and the proof-of-concept tool developed demonstrate the potential for enhancing the efficiency and accuracy of message categorization on the Zambia U-report platform and other similar text messages-based platforms.展开更多
Natural scene recognition has important significance and value in the fields of image retrieval,autonomous navigation,human-computer interaction and industrial automation.Firstly,the natural scene image non-text conte...Natural scene recognition has important significance and value in the fields of image retrieval,autonomous navigation,human-computer interaction and industrial automation.Firstly,the natural scene image non-text content takes up relatively high proportion;secondly,the natural scene images have a cluttered background and complex lighting conditions,angle,font and color.Therefore,how to extract text extreme regions efficiently from complex and varied natural scene images plays an important role in natural scene image text recognition.In this paper,a Text extremum region Extraction algorithm based on Joint-Channels(TEJC)is proposed.On the one hand,it can solve the problem that the maximum stable extremum region(MSER)algorithm is only suitable for gray images and difficult to process color images.On the other hand,it solves the problem that the MSER algorithm has high complexity and low accuracy when extracting the most stable extreme region.In this paper,the proposed algorithm is tested and evaluated on the ICDAR data set.The experimental results show that the method has superiority.展开更多
Text representation is a key aspect in determining the success of various text summarizing techniques.Summarization using pretrained transformer models has produced encouraging results.Yet the scope of applying these ...Text representation is a key aspect in determining the success of various text summarizing techniques.Summarization using pretrained transformer models has produced encouraging results.Yet the scope of applying these models in medical and drug discovery is not examined to a proper extent.To address this issue,this article aims to perform extractive summarization based on fine-tuned transformers pertaining to drug and medical domain.This research also aims to enhance sentence representation.Exploring the extractive text summarization aspects of medical and drug discovery is a challenging task as the datasets are limited.Hence,this research concentrates on the collection of abstracts collected from PubMed for various domains of medical and drug discovery such as drug and COVID,with a total capacity of 1,370 abstracts.A detailed experimentation using BART(Bidirectional Autoregressive Transformer),T5(Text-to-Text Transfer Transformer),LexRank,and TexRank for the analysis of the dataset is carried out in this research to perform extractive text summarization.展开更多
Retrieving information from evolving digital data collection using a user’s query is always essential and needs efficient retrieval mechanisms that help reduce the required time from such massive collections.Large-sc...Retrieving information from evolving digital data collection using a user’s query is always essential and needs efficient retrieval mechanisms that help reduce the required time from such massive collections.Large-scale time consumption is certain to scan and analyze to retrieve the most relevant textual data item from all the documents required a sophisticated technique for a query against the document collection.It is always challenging to retrieve a more accurate and fast retrieval from a large collection.Text summarization is a dominant research field in information retrieval and text processing to locate the most appropriate data object as single or multiple documents from the collection.Machine learning and knowledge-based techniques are the two query-based extractive text summarization techniques in Natural Language Processing(NLP)which can be used for precise retrieval and are considered to be the best option.NLP uses machine learning approaches for both supervised and unsupervised learning for calculating probabilistic features.The study aims to propose a hybrid approach for query-based extractive text summarization in the research study.Text-Rank Algorithm is used as a core algorithm for the flow of an implementation of the approach to gain the required goals.Query-based text summarization of multiple documents using a hybrid approach,combining the K-Means clustering technique with Latent Dirichlet Allocation(LDA)as topic modeling technique produces 0.288,0.631,and 0.328 for precision,recall,and F-score,respectively.The results show that the proposed hybrid approach performs better than the graph-based independent approach and the sentences and word frequency-based approach.展开更多
This paper presents a new method for text detection, location and binarization from natural scenes. Several morphological steps are used to detect the general position of the text, including English, Chinese and Japan...This paper presents a new method for text detection, location and binarization from natural scenes. Several morphological steps are used to detect the general position of the text, including English, Chinese and Japanese characters. Next bonnding boxes are processed by a new “Expand, Break and Merge” （EBM） method to get the precise text areas. Finally, text is binarized by a hybrid method based on Otsu and Niblack. This new approach can extract different kinds of text from complicated natural scenes. It is insensitive to noise, distortedness, and text orientation. It also has good performance on extracting texts in various sizes.展开更多
In the era of Big Data,we are faced with an inevitable and challenging problem of“overload information”.To alleviate this problem,it is important to use effective automatic text summarization techniques to obtain th...In the era of Big Data,we are faced with an inevitable and challenging problem of“overload information”.To alleviate this problem,it is important to use effective automatic text summarization techniques to obtain the key information quickly and efficiently from the huge amount of text.In this paper,we propose a hybrid method of extractive text summarization based on deep learning and graph ranking algorithms(ETSDG).In this method,a pre-trained deep learning model is designed to yield useful sentence embeddings.Given the association between sentences in raw documents,a traditional LexRank algorithm with fine-tuning is adopted fin ETSDG.In order to improve the performance of the extractive text summarization method,we further integrate the traditional LexRank algorithm with deep learning.Testing results on the data set DUC2004 show that ETSDG has better performance in ROUGE metrics compared with certain benchmark methods.展开更多
This investigation has presented an approach to Extractive Automatic Text Summarization (EATS). A framework focused on the summary of a single document has been developed, using the Tf-ldf method (Frequency Term, Inve...This investigation has presented an approach to Extractive Automatic Text Summarization (EATS). A framework focused on the summary of a single document has been developed, using the Tf-ldf method (Frequency Term, Inverse Document Frequency) as a reference, dividing the document into a subset of documents and generating value of each of the words contained in each document, those documents that show Tf-Idf equal or higher than the threshold are those that represent greater importance, therefore;can be weighted and generate a text summary according to the user’s request. This document represents a derived model of text mining application in today’s world. We demonstrate the way of performing the summarization. Random values were used to check its performance. The experimented results show a satisfactory and understandable summary and summaries were found to be able to run efficiently and quickly, showing which are the most important text sentences according to the threshold selected by the user.展开更多
Assembly process documents record the designers'intention or knowledge.However,common knowl-edge extraction methods are not well suitable for assembly process documents,because of its tabular form and unstructured...Assembly process documents record the designers'intention or knowledge.However,common knowl-edge extraction methods are not well suitable for assembly process documents,because of its tabular form and unstructured natural language texts.In this paper,an assembly semantic entity recognition and relation con-struction method oriented to assembly process documents is proposed.First,the assembly process sentences are extracted from the table through concerned region recognition and cell division,and they will be stored as a key-value object file.Then,the semantic entities in the sentence are identified through the sequence tagging model based on the specific attention mechanism for assembly operation type.The syntactic rules are designed for realizing automatic construction of relation between entities.Finally,by using the self-constructed corpus,it is proved that the sequence tagging model in the proposed method performs better than the mainstream named entity recognition model when handling assembly process design language.The effectiveness of the proposed method is also analyzed through the simulation experiment in the small-scale real scene,compared with manual method.The results show that the proposed method can help designers accumulate knowledge automatically and efficiently.展开更多
Visual question answering(VQA)has attracted more and more attention in computer vision and natural language processing.Scholars are committed to studying how to better integrate image features and text features to ach...Visual question answering(VQA)has attracted more and more attention in computer vision and natural language processing.Scholars are committed to studying how to better integrate image features and text features to achieve better results in VQA tasks.Analysis of all features may cause information redundancy and heavy computational burden.Attention mechanism is a wise way to solve this problem.However,using single attention mechanism may cause incomplete concern of features.This paper improves the attention mechanism method and proposes a hybrid attention mechanism that combines the spatial attention mechanism method and the channel attention mechanism method.In the case that the attention mechanism will cause the loss of the original features,a small portion of image features were added as compensation.For the attention mechanism of text features,a selfattention mechanism was introduced,and the internal structural features of sentences were strengthened to improve the overall model.The results show that attention mechanism and feature compensation add 6.1%accuracy to multimodal low-rank bilinear pooling network.展开更多
The robust guarantee of train control on-board equipment is inextricably linked to the safe functioning of a high-speed train.A fault diagnostic model of on-board equipment is built utilizing the integrated learning X...The robust guarantee of train control on-board equipment is inextricably linked to the safe functioning of a high-speed train.A fault diagnostic model of on-board equipment is built utilizing the integrated learning XGBoost(eXtreme Gradient Boosting)algorithm to help technicians assess the malfunction category of high-speed train control on-board equipment accurately and rapidly.The XGBoost algorithm iterates multiple decision tree models to improve the accuracy of fault diagnosis by lifting the predicted residual and adding regular terms.To begin,the text features were extracted using the improved TF-IDF(Term Frequency-Inverse Document Frequency)approach,and 24 fault feature words were chosen and converted into weight word vectors.Secondly,considering the imbalanced fault categories in the data set,the ADASYN(Adaptive Synthetic sampling)adaptive synthetically oversampling technique was used to synthesize a few category fault samples.Finally,the data samples were split into training and test sets based on the fault text data of CTCS-3train control on-board equipment recorded by Guangzhou Railway Group maintenance personnel.The XGBoost model was utilized to realize the automatic fault location of the test set after optimized parameter tuning through grid search.Compared with other methods,the evaluation index of the XGBoost model was significantly improved.The diagnostic accuracy reached 95.43%,which verifies the effectiveness of the method in text fault diagnosis.展开更多
文摘Text characters embedded in images represent a rich source of information for content-based indexing and retrieval applications. However, these text characters are difficult to be detected and recognized due to their various sizes, grayscale values, and complex backgrounds. Existing methods cannot handle well those texts with different contrast or embedded in a complex image background. In this paper, a set of sequential algorithms for text extraction and enhancement of image using cellular automata are proposed. The image enhancement includes gray level, contrast manipulation, edge detection, and filtering. First, it applies edge detection and uses a threshold to filter out for low-contrast text and simplify complex background of high-contrast text from binary image. The proposed algorithm is simple and easy to use and requires only a sample texture binary image as an input. It generates textures with perceived quality, better than those proposed by earlier published techniques. The performance of our method is demonstrated by presenting experimental results for a set of text based binary images. The quality of thresholding is assessed using the precision and recall analysis of the resultant text in the binary image.
文摘In the context of constructing an embedded system to help visually impaired people to interpret text,in this paper,an efficient High-level synthesis(HLS)Hardware/Software(HW/SW)design for text extraction using the Gamma Correction Method(GCM)is proposed.Indeed,the GCM is a common method used to extract text from a complex color image and video.The purpose of this work is to study the complexity of the GCM method on Xilinx ZCU102 FPGA board and to propose a HW implementation as Intellectual Property(IP)block of the critical blocks in this method using HLS flow with taking account the quality of the text extraction.This IP is integrated and connected to the ARM Cortex-A53 as coprocessor in HW/SW codesign context.The experimental results show that theHLS HW/SW implementation of the GCM method on ZCU102 FPGA board allows a reduction in processing time by about 89%compared to the SW implementation.This result is given for the same potency and strength of SW implementation for the text extraction.
文摘To promote behavioral change among adolescents in Zambia, the National HIV/AIDS/STI/TB Council, in collaboration with UNICEF, developed the Zambia U-Report platform. This platform provides young people with improved access to information on various Sexual Reproductive Health topics through Short Messaging Service (SMS) messages. Over the years, the platform has accumulated millions of incoming and outgoing messages, which need to be categorized into key thematic areas for better tracking of sexual reproductive health knowledge gaps among young people. The current manual categorization process of these text messages is inefficient and time-consuming and this study aims to automate the process for improved analysis using text-mining techniques. Firstly, the study investigates the current text message categorization process and identifies a list of categories adopted by counselors over time which are then used to build and train a categorization model. Secondly, the study presents a proof of concept tool that automates the categorization of U-report messages into key thematic areas using the developed categorization model. Finally, it compares the performance and effectiveness of the developed proof of concept tool against the manual system. The study used a dataset comprising 206,625 text messages. The current process would take roughly 2.82 years to categorise this dataset whereas the trained SVM model would require only 6.4 minutes while achieving an accuracy of 70.4% demonstrating that the automated method is significantly faster, more scalable, and consistent when compared to the current manual categorization. These advantages make the SVM model a more efficient and effective tool for categorizing large unstructured text datasets. These results and the proof-of-concept tool developed demonstrate the potential for enhancing the efficiency and accuracy of message categorization on the Zambia U-report platform and other similar text messages-based platforms.
基金This work is supported by State Grid Shandong Electric Power Company Science and Technology Project Funding under Grant Nos.520613180002,62061318C002the Fundamental Research Funds for the Central Universities(Grant No.HIT.NSRIF.201714)+1 种基金Weihai Science and Technology Development Program(2016DX GJMS15)Key Research and Development Program in Shandong Provincial(2017GGX90103).
文摘Natural scene recognition has important significance and value in the fields of image retrieval,autonomous navigation,human-computer interaction and industrial automation.Firstly,the natural scene image non-text content takes up relatively high proportion;secondly,the natural scene images have a cluttered background and complex lighting conditions,angle,font and color.Therefore,how to extract text extreme regions efficiently from complex and varied natural scene images plays an important role in natural scene image text recognition.In this paper,a Text extremum region Extraction algorithm based on Joint-Channels(TEJC)is proposed.On the one hand,it can solve the problem that the maximum stable extremum region(MSER)algorithm is only suitable for gray images and difficult to process color images.On the other hand,it solves the problem that the MSER algorithm has high complexity and low accuracy when extracting the most stable extreme region.In this paper,the proposed algorithm is tested and evaluated on the ICDAR data set.The experimental results show that the method has superiority.
文摘Text representation is a key aspect in determining the success of various text summarizing techniques.Summarization using pretrained transformer models has produced encouraging results.Yet the scope of applying these models in medical and drug discovery is not examined to a proper extent.To address this issue,this article aims to perform extractive summarization based on fine-tuned transformers pertaining to drug and medical domain.This research also aims to enhance sentence representation.Exploring the extractive text summarization aspects of medical and drug discovery is a challenging task as the datasets are limited.Hence,this research concentrates on the collection of abstracts collected from PubMed for various domains of medical and drug discovery such as drug and COVID,with a total capacity of 1,370 abstracts.A detailed experimentation using BART(Bidirectional Autoregressive Transformer),T5(Text-to-Text Transfer Transformer),LexRank,and TexRank for the analysis of the dataset is carried out in this research to perform extractive text summarization.
文摘Retrieving information from evolving digital data collection using a user’s query is always essential and needs efficient retrieval mechanisms that help reduce the required time from such massive collections.Large-scale time consumption is certain to scan and analyze to retrieve the most relevant textual data item from all the documents required a sophisticated technique for a query against the document collection.It is always challenging to retrieve a more accurate and fast retrieval from a large collection.Text summarization is a dominant research field in information retrieval and text processing to locate the most appropriate data object as single or multiple documents from the collection.Machine learning and knowledge-based techniques are the two query-based extractive text summarization techniques in Natural Language Processing(NLP)which can be used for precise retrieval and are considered to be the best option.NLP uses machine learning approaches for both supervised and unsupervised learning for calculating probabilistic features.The study aims to propose a hybrid approach for query-based extractive text summarization in the research study.Text-Rank Algorithm is used as a core algorithm for the flow of an implementation of the approach to gain the required goals.Query-based text summarization of multiple documents using a hybrid approach,combining the K-Means clustering technique with Latent Dirichlet Allocation(LDA)as topic modeling technique produces 0.288,0.631,and 0.328 for precision,recall,and F-score,respectively.The results show that the proposed hybrid approach performs better than the graph-based independent approach and the sentences and word frequency-based approach.
文摘This paper presents a new method for text detection, location and binarization from natural scenes. Several morphological steps are used to detect the general position of the text, including English, Chinese and Japanese characters. Next bonnding boxes are processed by a new “Expand, Break and Merge” （EBM） method to get the precise text areas. Finally, text is binarized by a hybrid method based on Otsu and Niblack. This new approach can extract different kinds of text from complicated natural scenes. It is insensitive to noise, distortedness, and text orientation. It also has good performance on extracting texts in various sizes.
文摘In the era of Big Data,we are faced with an inevitable and challenging problem of“overload information”.To alleviate this problem,it is important to use effective automatic text summarization techniques to obtain the key information quickly and efficiently from the huge amount of text.In this paper,we propose a hybrid method of extractive text summarization based on deep learning and graph ranking algorithms(ETSDG).In this method,a pre-trained deep learning model is designed to yield useful sentence embeddings.Given the association between sentences in raw documents,a traditional LexRank algorithm with fine-tuning is adopted fin ETSDG.In order to improve the performance of the extractive text summarization method,we further integrate the traditional LexRank algorithm with deep learning.Testing results on the data set DUC2004 show that ETSDG has better performance in ROUGE metrics compared with certain benchmark methods.
文摘This investigation has presented an approach to Extractive Automatic Text Summarization (EATS). A framework focused on the summary of a single document has been developed, using the Tf-ldf method (Frequency Term, Inverse Document Frequency) as a reference, dividing the document into a subset of documents and generating value of each of the words contained in each document, those documents that show Tf-Idf equal or higher than the threshold are those that represent greater importance, therefore;can be weighted and generate a text summary according to the user’s request. This document represents a derived model of text mining application in today’s world. We demonstrate the way of performing the summarization. Random values were used to check its performance. The experimented results show a satisfactory and understandable summary and summaries were found to be able to run efficiently and quickly, showing which are the most important text sentences according to the threshold selected by the user.
文摘Assembly process documents record the designers'intention or knowledge.However,common knowl-edge extraction methods are not well suitable for assembly process documents,because of its tabular form and unstructured natural language texts.In this paper,an assembly semantic entity recognition and relation con-struction method oriented to assembly process documents is proposed.First,the assembly process sentences are extracted from the table through concerned region recognition and cell division,and they will be stored as a key-value object file.Then,the semantic entities in the sentence are identified through the sequence tagging model based on the specific attention mechanism for assembly operation type.The syntactic rules are designed for realizing automatic construction of relation between entities.Finally,by using the self-constructed corpus,it is proved that the sequence tagging model in the proposed method performs better than the mainstream named entity recognition model when handling assembly process design language.The effectiveness of the proposed method is also analyzed through the simulation experiment in the small-scale real scene,compared with manual method.The results show that the proposed method can help designers accumulate knowledge automatically and efficiently.
基金This work was supported by the Sichuan Science and Technology Program(2021YFQ0003).
文摘Visual question answering(VQA)has attracted more and more attention in computer vision and natural language processing.Scholars are committed to studying how to better integrate image features and text features to achieve better results in VQA tasks.Analysis of all features may cause information redundancy and heavy computational burden.Attention mechanism is a wise way to solve this problem.However,using single attention mechanism may cause incomplete concern of features.This paper improves the attention mechanism method and proposes a hybrid attention mechanism that combines the spatial attention mechanism method and the channel attention mechanism method.In the case that the attention mechanism will cause the loss of the original features,a small portion of image features were added as compensation.For the attention mechanism of text features,a selfattention mechanism was introduced,and the internal structural features of sentences were strengthened to improve the overall model.The results show that attention mechanism and feature compensation add 6.1%accuracy to multimodal low-rank bilinear pooling network.
基金supported by the Science and Tec hnology Research and Development Plan Contract of China National Railway Group Co.,Ltd(Grant No.N2022G012)the Railway Science and Technology Research and Development Center Project(Project No.SYF2022SJ004).
文摘The robust guarantee of train control on-board equipment is inextricably linked to the safe functioning of a high-speed train.A fault diagnostic model of on-board equipment is built utilizing the integrated learning XGBoost(eXtreme Gradient Boosting)algorithm to help technicians assess the malfunction category of high-speed train control on-board equipment accurately and rapidly.The XGBoost algorithm iterates multiple decision tree models to improve the accuracy of fault diagnosis by lifting the predicted residual and adding regular terms.To begin,the text features were extracted using the improved TF-IDF(Term Frequency-Inverse Document Frequency)approach,and 24 fault feature words were chosen and converted into weight word vectors.Secondly,considering the imbalanced fault categories in the data set,the ADASYN(Adaptive Synthetic sampling)adaptive synthetically oversampling technique was used to synthesize a few category fault samples.Finally,the data samples were split into training and test sets based on the fault text data of CTCS-3train control on-board equipment recorded by Guangzhou Railway Group maintenance personnel.The XGBoost model was utilized to realize the automatic fault location of the test set after optimized parameter tuning through grid search.Compared with other methods,the evaluation index of the XGBoost model was significantly improved.The diagnostic accuracy reached 95.43%,which verifies the effectiveness of the method in text fault diagnosis.
