scholarly journals Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4939
Author(s):  
Weidong Zhao ◽  
Hancheng Huang ◽  
Dan Li ◽  
Feng Chen ◽  
Wei Cheng
Keyword(s):  
Transfer Learning ◽  
Defect Detection ◽  
Detection Rate ◽  
Surface Defects ◽  
Average Precision ◽  
The Common ◽  
Visual Characteristics ◽  
Few Data ◽  
Common Defect

To meet the practical needs of detecting various defects on the pointer surface and solve the difficulty of detecting some defects on the pointer surface, this paper proposes a transfer learning and improved Cascade-RCNN deep neural network (TICNET) algorithm for detecting pointer defects. Firstly, the convolutional layers of ResNet-50 are reconstructed by deformable convolution, which enhances the learning of pointer surface defects by feature extraction network. Furthermore, the problems of missing detection caused by internal differences and weak features are effectively solved. Secondly, the idea of online hard example mining (OHEM) is used to improve the Cascade-RCNN detection network, which achieve accurate classification of defects. Finally, based on the fact that common pointer defect dataset and pointer defect dataset established in this paper have the same low-level visual characteristics. The network is pre-trained on the common defect dataset, and weights are transferred to the defect dataset established in this paper, which reduces the training difficulty caused by too few data. The experimental results show that the proposed method achieves a 0.933 detection rate and a 0.873 mean average precision when the threshold of intersection over union is 0.5, and it realizes high precision detection of pointer surface defects.

scholarly journals Plastic Gasket Defect Detection Based on Transfer Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Xieyi Chen ◽  
Dongyun Wang ◽  
Jinjun Shao ◽  
Jun Fan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Defect Detection ◽  
Data Augmentation ◽  
Surface Defects ◽  
Visual Detection ◽  
Training Data

To automatically detect plastic gasket defects, a set of plastic gasket defect visual detection devices based on GoogLeNet Inception-V2 transfer learning was designed and established in this study. The GoogLeNet Inception-V2 deep convolutional neural network (DCNN) was adopted to extract and classify the defect features of plastic gaskets to solve the problem of their numerous surface defects and difficulty in extracting and classifying the features. Deep learning applications require a large amount of training data to avoid model overfitting, but there are few datasets of plastic gasket defects. To address this issue, data augmentation was applied to our dataset. Finally, the performance of the three convolutional neural networks was comprehensively compared. The results showed that the GoogLeNet Inception-V2 transfer learning model had a better performance in less time. It means it had higher accuracy, reliability, and efficiency on the dataset used in this paper.

scholarly journals Research on Recognition Technology of Aluminum Profile Surface Defects Based on Deep Learning

2019 ◽  
Author(s):  
Ruofeng Wei ◽  
Yunbo Bi
Keyword(s):  
Deep Learning ◽  
Machine Vision ◽  
Defect Detection ◽  
Visual Inspection ◽  
Surface Defects ◽  
Average Precision ◽  
Saliency Maps ◽  
Aluminum Profile ◽  
Safety And Reliability ◽  
Aluminum Profiles

Aluminum profile surface defects can greatly affect the performance, safety and reliability of products. Traditional human-based visual inspection is low accuracy and time consuming, and machine vision-based methods depend on hand-crafted features which need to be carefully designed and lack robustness. To recognize the multiple types of defects with various size on aluminum profiles, a multiscale defect detection network based on deep learning is proposed. Then, the network is trained and evaluated using aluminum profile surface defects images. Results show 84.6%, 48.5%, 96.9%, 97.9%, 96.9%, 42.5%, 47.2%, 100%, 100%, 43.3% average precision(AP) for the ten defect categories, respectively, with a mean AP of 75.8%, which illustrate the effectiveness of the network in aluminum profile surface defects detection. In addition, saliency maps also show the feasibility of the proposed network.

scholarly journals Hot-Rolled Steel Strip Surface Inspection Based on Transfer Learning Model

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Hao Wu ◽  
Quanquan Lv
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Defect Detection ◽  
Surface Defects ◽  
Learning Model ◽  
Strip Surface ◽  
Neural Network Method ◽  
Steel Strips ◽  
Network Method

In the production process of steel strips, the detection of surface defects is very important. However, traditional methods of defect detection bring problems of low detection accuracy and dependence on subjective judgment. In this study, the surface defects of steel strips are detected by a classic convolutional neural network method that is improved by the use of a transfer learning model. This model has the advantages of shorter training time, faster convergence, and more accurate weight parameters. The transfer learning model obtained through experiments secures better results in defect detection than the classic convolutional neural network method, as its accuracy of training and testing has reached about 98%. Finally, a model based on a full convolutional neural network (FCN) is proposed for segmenting the defective areas of steel strips.

scholarly journals Trend Review Related To Defects Detection from Fruits and Vegetables

2021 ◽  
Author(s):  
Anjali N ◽  
Rajkumar Kannan ◽  
Frederic Andres ◽  
Georgeghita Ghinea
Keyword(s):  
Defect Detection ◽  
Fruits And Vegetables ◽  
Surface Defects ◽  
Morphological Characteristics ◽  
Local Market ◽  
Indian Agriculture ◽  
Detection And Identification ◽  
Rgb Images ◽  
Vegetables And Fruits

Defect detection and identification from fruits and vegetables are particularly challenging for Indian agriculture. Defect Detection is a process to identify the defects or damages in vegetables and fruits, based on the shapes, colors and textures. The local market finds it difficult to cope with the defects and other infections in fruits and vegetables as quality evaluations and classification of vegetables and fruits have become tedious process. Recently, several approaches based on Image processing, Machine Learning and Artificial Intelligence methods have been proposed for the purpose of defect detection. On the basis of classifying the types of defects, related pathogens, and physical and morphological characteristics descriptors, we review the different approaches based on a corpus of 57 articles between 2016 and 2021. In the process of describing the defect analysis, steps from the target articles, algorithms, and methods including qualitative and quantitative evaluation are mainly summarized. The aim of this current review work is to present-day novel images and collects recent defective area calculation methods to detect surface defects of fruits and vegetables using RGB images and to classify whether the fruit is defected or fresh. A rigorous evaluation of many new algorithms provided for quality assurance by researcher’s probes of vegetables and fruits have been conducted in this work. This review work conveys that using the recent identification features will help to decrease the disadvantages in fruit storeroom owing to storage of the affected vegetables and fruits, ie. Preventing the spread of defects and other infections from the infected fruits and vegetables to the fresh ones.

scholarly journals Defect Classification of Green Plums Based on Deep Learning

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6993
Author(s):  
Haiyan Zhou ◽  
Zilong Zhuang ◽  
Ying Liu ◽  
Yang Liu ◽  
Xiao Zhang
Keyword(s):  
Deep Learning ◽  
Defect Detection ◽  
Surface Defects ◽  
Recognition Accuracy ◽  
Economic Value ◽  
Recognition Rate ◽  
Cost Effective ◽  
Test Time ◽  
Training Set

The green plum is rich in amino acids, lipids, inorganic salts, vitamins, and trace elements. It has high nutritional value and medicinal value and is very popular among Chinese people. However, green plums are susceptible to collisions and pests during growth, picking, storage, and transportation, causing surface defects, affecting the quality of green plums and their products and reducing their economic value. In China, defect detection and grading of green plum products are still performed manually. Traditional manual classification has low accuracy and high cost, which is far from meeting the production needs of green plum products. In order to improve the economic value of green plums and their products and improve the automation and intelligence level of the product production process, this study adopted deep learning methods based on a convolutional neural network and cost-effective computer vision technology to achieve efficient classification of green plum defects. First, a camera and LEDs were used to collect 1240 green plum images of RGB, and the green plum experimental classification standard was formulated and divided into five categories, namely, rot, spot, scar, crack, and normal. Images were randomly divided into a training set and test set, and the number of images of the training set was expanded. Then, the stochastic weight averaging (SWA) optimizer and w-softmax loss function were used to improve the VGG network, which was trained and tested to generate a green plum defect detection network model. The average recognition accuracy of green plum defects was 93.8%, the test time for each picture was 84.69 ms, the recognition rate of decay defect was 99.25%, and the recognition rate of normal green plum was 95.65%. The results were compared with the source VGG network, resnet18 network, and green lemon network. The results show that for the classification of green plum defects, the recognition accuracy of the green plum defect detection network increased by 9.8% and 16.6%, and the test speed is increased by 1.87 and 6.21 ms, respectively, which has certain advantages.

scholarly journals Research on Recognition Technology of Aluminum Profile Surface Defects Based on Deep Learning

Materials ◽  
2019 ◽  
Vol 12 (10) ◽  
pp. 1681 ◽  
Author(s):  
Ruofeng Wei ◽  
Yunbo Bi
Keyword(s):  
Deep Learning ◽  
Machine Vision ◽  
Defect Detection ◽  
Visual Inspection ◽  
Surface Defects ◽  
Average Precision ◽  
Saliency Maps ◽  
Aluminum Profile ◽  
Safety And Reliability ◽  
Aluminum Profiles

Aluminum profile surface defects can greatly affect the performance, safety, and reliability of products. Traditional human-based visual inspection has low accuracy and is time consuming, and machine vision-based methods depend on hand-crafted features that need to be carefully designed and lack robustness. To recognize the multiple types of defects with various size on aluminum profiles, a multiscale defect-detection network based on deep learning is proposed. Then, the network is trained and evaluated using aluminum profile surface defects images. Results show 84.6%, 48.5%, 96.9%, 97.9%, 96.9%, 42.5%, 47.2%, 100%, 100%, and 43.3% average precision (AP) for the 10 defect categories, respectively, with a mean AP of 75.8%, which illustrate the effectiveness of the network in aluminum profile surface defects detection. In addition, saliency maps also show the feasibility of the proposed network.

Philosophcal review of h. white̕s tropological theory in the context of the new philosophy of history

2020 ◽  
Vol 3 (152) ◽  
pp. 92-99
Author(s):  
S. M. Geiko ◽  
◽  
O. D. Lauta
Keyword(s):  
Modern Science ◽  
Historical Knowledge ◽  
Text Organization ◽  
The Social ◽  
History Of ◽  
Actual Material ◽  
The Common ◽  
Historical Nature ◽  
Selection Of

The article provides a philosophical analysis of the tropological theory of the history of H. White. The researcher claims that history is a specific kind of literature, and the historical works is the connection of a certain set of research and narrative operations. The first type of operation answers the question of why the event happened this way and not the other. The second operation is the social description, the narrative of events, the intellectual act of organizing the actual material. According to H. White, this is where the set of ideas and preferences of the researcher begin to work, mainly of a literary and historical nature. Explanations are the main mechanism that becomes the common thread of the narrative. The are implemented through using plot (romantic, satire, comic and tragic) and trope systems – the main stylistic forms of text organization (metaphor, metonymy, synecdoche, irony). The latter decisively influenced for result of the work historians. Historiographical style follows the tropological model, the selection of which is determined by the historian’s individual language practice. When the choice is made, the imagination is ready to create a narrative. Therefore, the historical understanding, according to H. White, can only be tropological. H. White proposes a new methodology for historical research. During the discourse, adequate speech is created to analyze historical phenomena, which the philosopher defines as prefigurative tropological movement. This is how history is revealed through the art of anthropology. Thus, H. White’s tropical history theory offers modern science f meaningful and metatheoretically significant. The structure of concepts on which the classification of historiographical styles can be based and the predictive function of philosophy regarding historical knowledge can be refined.

Sign in / Sign up

Export Citation Format

Share Document