scholarly journals Research on Methods of English Text Detection and Recognition Based on Neural Network Detection Model

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Chunlan Li

With the rapid development of computer science, a large number of images and an explosive amount of information make it difficult to filter and effectively extract information. This article focuses on the inability of effective detection and recognition of English text content to conduct research, which is useful for improving the application of intelligent analysis significance. This paper studies how to improve the neural network model to improve the efficiency of image text detection and recognition under complex background. The main research work is as follows: (1) An improved CTPN multidirectional text detection algorithm is proposed, and the algorithm is applied to the multidirectional text detection and recognition system. It uses the multiangle rotation of the image to be detected, then fuses the candidate text boxes detected by the CTPN network, and uses the fusion strategy to find the best area of the text. This algorithm solves the problem that the CTPN network can only detect the text in the approximate horizontal direction. (2) An improved CRNN text recognition algorithm is proposed. The algorithm is based on CRNN and combines traditional text features and depth features at the same time, making it possible to recognize occluded text. The algorithm was tested on the IC13 and SVT data sets. Compared with the CRNN algorithm, the recognition accuracy has been improved, and the detection and recognition accuracy has increased by 0.065. This paper verifies the effectiveness of the improved algorithm model on multiple data sets, which can effectively detect various English texts, and greatly improves the detection and recognition performance of the original algorithm.

2022 ◽  
Vol 2022 ◽  
pp. 1-11
Author(s):  
Bin Zhao ◽  
WenYing Li ◽  
Qian Guo ◽  
RongRong Song

For the accuracy requirements of commodity image detection and classification, the FPN network is improved by DPFM ablation and RFM, so as to improve the detection accuracy of commodities by the network. At the same time, in view of the narrowing of channels in the application of traditional MWI-DenseNet network, a new GTNet network is proposed to improve the classification accuracy of commodities.The results show that at different levels of evaluation indexes, the dpFPN-Netv2 algorithm improved by DPFM + RFM fusion has higher target detection accuracy than RetinaNet-50 algorithm and other algorithms. And the detection time is 52 ms, which is significantly lower than 90 ms required for RetinaNet-50 detection. In terms of target recognition, compared with the traditional MWI-DenseNet neural network, the computation amount of the improved MWI DenseNet neural network is significantly reduced under different shunt ratios, and the recognition accuracy is significantly improved. The innovation of this study lies in improving the algorithm from the perspective of target detection and recognition, so as to change the previous improvement that only can be made in a single way.


2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Qunjing Ji

With the rapid development of image recognition technology, freehand sketch recognition has attracted more and more attention. How to achieve good recognition effect in the absence of color and texture information is the key to the development of freehand sketch recognition. Traditional nonlearning classical models are highly dependent on manual selection features. To solve this problem, a neural network sketch recognition method based on DSCN structure is proposed in this paper. Firstly, the stroke sequence of the sketch is drawn; then, the feature is extracted according to the stroke sequence combined with neural network, and the extracted image features are used as the input of the model to construct the time relationship between different image features. Through the control experiment on TU-Berlin dataset, the results show that, compared with the traditional nonlearning methods, HOG-SVM, SIFT-Fisher Vector, MKL-SVM, and FV-SP, the recognition accuracy of DSCN network is improved by 15.8%, 10.3%, 6.0%, and 2.9%, respectively. Compared with the classical deep learning model, Alex-Net, the recognition accuracy is improved by 5.6%. The above results show that the DSCN network proposed in this paper has strong ability of feature extraction and nonlinear expression and can effectively improve the recognition accuracy of hand-painted sketches after introducing the stroke order.


Axioms ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 106
Author(s):  
Tinggui Chen ◽  
Xiaohua Yin ◽  
Lijuan Peng ◽  
Jingtao Rong ◽  
Jianjun Yang ◽  
...  

With the rapid development of “We media” technology, netizens can freely express their opinions regarding enterprise products on a network platform. Consequently, online public opinion about enterprises has become a prominent issue. Negative comments posted by some netizens may trigger negative public opinion, which can have a significant impact on an enterprise’s image. From the perspective of helping enterprises deal with negative public opinion, this paper combines user portrait technology and a random forest algorithm to help enterprises identify high-risk users who have posted negative comments and thus may trigger negative public opinion. In this way, enterprises can monitor the public opinion of high-risk users to prevent negative public opinion events. Firstly, we crawled the information of users participating in discussions of product experience, and we constructed a portrait of enterprise public opinion users. Then, the characteristics of the portraits were quantified into indicators such as the user’s activity, the user’s influence, and the user’s emotional tendency, and the indicators were sorted. According to the order of the indicators, the users were divided into high-risk, moderate-risk, and low-risk categories. Next, a supervised high-risk user identification model for this classification was established, based on a random forest algorithm. In turn, the trained random forest identifier can be used to predict whether the authors of newly published public opinion information are high-risk users. Finally, a back propagation neural network algorithm was used to identify users and compared with the results of model recognition in this paper. The results showed that the average recognition accuracy of the back propagation neural network is only 72.33%, while the average recognition accuracy of the model constructed in this paper is as high as 98.49%, which verifies the feasibility and accuracy of the proposed random forest recognition method.


2022 ◽  
pp. 154-176
Author(s):  
Zizhe Gao ◽  
Hao Lin

Entering the 21st century, computer science and biological research have entered a stage of rapid development. With the rapid inflow of capital into the field of significant health research, a large number of scholars and investors have begun to focus on the impact of neural network science on biometrics, especially the study of biological interactions. With the rapid development of computer technology, scientists improve or perfect traditional experimental methods. This chapter aims to prove the reliability of the methodology and computing algorithms developed by Satyajit Mahapatra and Ivek Raj Gupta's project team. In this chapter, three datasets take the responsibility to testify the computing algorithms, and they are S. cerevisiae, H. pylori, and Human-B. Anthracis. Among these three sets of data, the S. cerevisiae is the core subset. The result shows 87%, 87.5%, and 89% accuracy and 87%, 86%, and 87% precision for these three data sets, respectively.


Author(s):  
ARGHA GHOSH ◽  
A. SENTHILRAJAN

Email is the most common as well as the fastest medium for communicating around the globe. But, presently every day we used to get lots of junk emails in the name of “spam”. This “spam” emails mainly used to contain two types of content, those are content like an advertisement, offers and, criminal activity content like a phishing website link, malware, trojan, etc. Those advertisements, offer types of spam or junk emails known as Unsolicited Commercial Emails and, those emails contain phishing website link, malware, trojan used to known as Unsolicited Bulk Emails. Whoever used to send spam emails, they are known as Spammers. Spammers mainly used to get the email address of target user from the websites, junk sites, browsers add on, etc. Naive Bayes algorithm is a probabilistic machine learning algorithm that mainly well-known for classifying spam emails. Naive Bayes algorithm mainly originated from Bayes Theorem. Bayes Theorem mainly used in conditional probability for elaborates the probability of an event in terms of when the probability of other event is true. In this research work, we have been performing Feature Extraction in terms of email characteristics and behavior. In this paper, we have been proposed a detection approach for classifying spam emails using Naïve Bayes classifier. In this research work, we have been used multiple email data-sets for implementing Naïve Bayes classifier. Those data sets are Spam Corpus, Spambase. Based on the results of WEKA (Waikato Environment for Knowledge Analysis) tool, we have been performing Experimental analysis in terms of measuring the performance of Naïve Bayes classifier using parameters like Accuracy, Recall, Precision, F-measure. Based on correctly classified instances of emails and incorrectly classified instances of emails, lastly comparing the performance of Naïve Bayes classifier in multiple data sets.


2014 ◽  
Vol 556-562 ◽  
pp. 2744-2747 ◽  
Author(s):  
Xu De Cheng ◽  
Hong Li Wang ◽  
Bing Xu ◽  
Wei Liu

BP neural network model for state monitoring data tendency prediction is constructed based upon neural network theory, and simulation programming is achieved with MATLAB. In the experiment, multiple data sets are selected for training and testing of the network to prove the validity of algorithm and model.


2016 ◽  
Vol 2 (9) ◽  
Author(s):  
Asit Kumar ◽  
Sumit Kumar

Text plays an significant role in day-to-day life because of its dissimilarities in text size, font, style, orientation and alignment as well as composite background and rich information, as a consequence automatic text detection in natural scenes has several attractive applications. Though, detecting and recognizing such text is all the time a challenging issue. Several text extraction techniques grounded on edge detection, connected component analysis, morphological operators, wavelet transform, texture features, neural network etc. have been established. This paper contributes comparative analysis of different technique which provides efficient performance.


Sign in / Sign up

Export Citation Format

Share Document