Intelligent recognition method of colour multidimensional image boundary feature based on improved neural network

2019 ◽  
Vol 10 (2) ◽  
pp. 115
Author(s):  
Chunping Li ◽  
Huibing Hao ◽  
Jie Ding ◽  
Guotao Zhao
Keyword(s):  
Neural Network ◽  
Recognition Method ◽  
Feature Based ◽  
Intelligent Recognition

scholarly journals Deep Learning-Based Classification of Weld Surface Defects

2019 ◽  
Vol 9 (16) ◽  
pp. 3312 ◽  
Author(s):  
Zhu ◽  
Ge ◽  
Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Random Forest ◽  
Convolutional Neural Network ◽  
Surface Defects ◽  
Recognition Method ◽  
High Level ◽  
Intelligent Recognition ◽  
Non Destructive

In order to realize the non-destructive intelligent identification of weld surface defects, an intelligent recognition method based on deep learning is proposed, which is mainly formed by convolutional neural network (CNN) and forest random. First, the high-level features are automatically learned through the CNN. Random forest is trained with extracted high-level features to predict the classification results. Secondly, the weld surface defects images are collected and preprocessed by image enhancement and threshold segmentation. A database of weld surface defects is established using pre-processed images. Finally, comparative experiments are performed on the weld surface defects database. The results show that the accuracy of the method combined with CNN and random forest can reach 0.9875, and it also demonstrates the method is effective and practical.

Image Recognition and Counting for the Bacilli Cell Based on the Microscopic Image

2014 ◽  
Vol 651-653 ◽  
pp. 2318-2321
Author(s):  
Min Tan ◽  
Ji Kang Zhong ◽  
Guo Zhao Zhang ◽  
Zhi Xiang Hu
Keyword(s):  
Neural Network ◽  
Small Area ◽  
Object Segmentation ◽  
Single Layer ◽  
Difficult Problem ◽  
Microscopic Image ◽  
Neural Network Classifier ◽  
Recognition Method ◽  
Accurate Identification ◽  
Intelligent Recognition

In order to automatically detect bacilli in sputum image with microscopy, an intelligent recognition method based on machine vision is presented. Firstly, a novel background filter was designed based on the single layer perceptron to realize object segmentation from background. After eliminating the short twig and small area noise, the suspicious goals and the image noise are separated. In the feature extraction, besides the base features of single bacillus two important features are presented to solve the difficult problem of identification and counting for the overlapping and winding bacilli cells. Finally, an EBP neural network classifier is designed for the accurate identification and counting of the bacilli cells. Experimental results verified the effectiveness of the presented method.

Research on visual recognition intelligent system of city brand image based on fuzzy theory and regional culture

2021 ◽  
pp. 1-9
Author(s):  
Lin Han ◽  
Lu Han
Keyword(s):  
Neural Network ◽  
Visual Recognition ◽  
Intelligent System ◽  
Brand Image ◽  
Fuzzy Theory ◽  
Recognition System ◽  
Market Competitiveness ◽  
Visual Identity ◽  
Fuzzy Neural ◽  
Intelligent Recognition

With the rapid development of China’s market economy, brand image is becoming more and more important for an enterprise to enhance its market competitiveness and occupy a favorable market share. However, the brand image of many established companies gradually loses with the development of society and the improvement of people’s aesthetic pursuit. This has forced it to change its corporate brand image and regain the favor of the market. Based on this, this article combines the related knowledge and concepts of fuzzy theory, from the perspective of visual identity design, explores the development of corporate brand image visual identity intelligent system, and aims to design a set of visual identity system that is different from competitors in order to shape the enterprise. Distinctive brand image and improve its market competitiveness. This article first collected a large amount of information through the literature investigation method, and made a systematic and comprehensive introduction to fuzzy theory, visual recognition technology and related theoretical concepts of brand image, which laid a sufficient theoretical foundation for the later discussion of the application of fuzzy theory in the design of brand image visual recognition intelligent system; then the fuzzy theory algorithm is described in detail, a fuzzy neural network is proposed and applied to the design of the brand image visual recognition intelligent system, and the design experiment of the intelligent recognition system is carried out; finally, through the use of the specific case of KFC brand logo, the designed intelligent recognition system was tested, and it was found that the visual recognition intelligent system had an overall accuracy rate of 96.08% for the KFC brand logo. Among them, the accuracy rate of color recognition was the highest, 96.62%; comparing the changes in the output value of the training sample and the test sample, the output convergence effect of the color network is the best; through the comparison test of the BP neural network, the recognition effect of the fuzzy neural network is better.

scholarly journals Intelligent Recognition Method of Low-Altitude Squint Optical Ship Target Fused with Simulation Samples

2021 ◽  
Vol 13 (14) ◽  
pp. 2697
Author(s):  
Bo Liu ◽  
Qi Xiao ◽  
Yuhao Zhang ◽  
Wei Ni ◽  
Zhen Yang ◽  
...  
Keyword(s):  
Feature Recognition ◽  
Spectral Characteristics ◽  
Transmission Model ◽  
Sample Type ◽  
Recognition Method ◽  
Atmospheric Transmission ◽  
K Nearest Neighbors ◽  
Imaging Simulation ◽  
Low Altitude ◽  
Intelligent Recognition

To address the problem of intelligent recognition of optical ship targets under low-altitude squint detection, we propose an intelligent recognition method based on simulation samples. This method comprehensively considers geometric and spectral characteristics of ship targets and ocean background and performs full link modeling combined with the squint detection atmospheric transmission model. It also generates and expands squint multi-angle imaging simulation samples of ship targets in the visible light band using the expanded sample type to perform feature analysis and modification on SqueezeNet. Shallow and deeper features are combined to improve the accuracy of feature recognition. The experimental results demonstrate that using simulation samples to expand the training set can improve the performance of the traditional k-nearest neighbors algorithm and modified SqueezeNet. For the classification of specific ship target types, a mixed-scene dataset expanded with simulation samples was used for training. The classification accuracy of the modified SqueezeNet was 91.85%. These results verify the effectiveness of the proposed method.

Machine-Printed Invoice Number Based on Fuzzy Recognition

2012 ◽  
Vol 214 ◽  
pp. 705-710 ◽  
Author(s):  
Xiao Ping Xian
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Recognition Rate ◽  
Real System ◽  
Recognition Method ◽  
Recognition Time ◽  
Recognition Ability ◽  
System Requirements ◽  
Fuzzy Recognition ◽  
Detection And Separation

A new fuzzy recognition method of machine-printed invoice number based on neural network is presented. This method includes ten links: invoice number detection and separation of right on top of invoice, binarization, denoising, incline correction, extraction of invoice code numerals, window scaling, location standardization, thinning, extraction of numeral feature and fuzzy recognition based on BP neural network. Through testing, the recognition rate of this method can be over 99%.The recognition time of characters for character is less than 1 second, which means that the method is of more effective recognition ability and can better satisfy the real system requirements.

Sign in / Sign up

Export Citation Format

Share Document