Koki Arima, Fusaomi Nagata, Tatsuki Shimizu, Akimasa Otsuka, Hirohisa Kato, Keigo Watanabe, Maki K. Habib
{"title":"YOLOv2使用数据集增强方法提高缺陷区域的检测精度及其置信度","authors":"Koki Arima, Fusaomi Nagata, Tatsuki Shimizu, Akimasa Otsuka, Hirohisa Kato, Keigo Watanabe, Maki K. Habib","doi":"10.1007/s10015-023-00885-9","DOIUrl":null,"url":null,"abstract":"<div><p>Recently, CNN (Convolutional Neural Network) and Grad-CAM (Gradient-weighted Class Activation Map) are being applied to various kinds of defect detection and position recognition for industrial products. However, in training process of a CNN model, a large amount of image data are required to acquire a desired generalization ability. In addition, it is not easy for Grad-CAM to clearly identify the defect area which is predicted as the basis of a classification result. Moreover, when they are deployed in an actual production line, two calculation processes for CNN and Grad-CAM have to be sequentially called for defect detection and position recognition, so that the processing time is concerned. In this paper, the authors try to apply YOLOv2 (You Only Look Once) to defect detection and its visualization to process them at once. In general, a YOLOv2 model can be built with less training images; however, a complicated labeling process is required to prepare ground truth data for training. A data set for training a YOLOv2 model has to be composed of image files and the corresponding ground truth data file named gTruth. The gTruth file has names of all the image files and their labeled information, such as label names and box dimensions. Therefore, YOLOv2 requires complex data set augmentation for not only images but also gTruth data. Actually, target products dealt with in this paper are produced with various kinds and small quantity, and also the frequency of occurrence of the defect is infrequent. Moreover, due to the fixed indoor production line, the valid image augmentation to be applied is limited to the horizontal flip. In this paper, a data set augmentation method is proposed to efficiently generate training data for YOLOv2 even in such a production situation and to consequently enhance the performance of defect detection and its visualization. The effectiveness is shown through experiments.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"28 3","pages":"625 - 631"},"PeriodicalIF":0.8000,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Improvements of detection accuracy and its confidence of defective areas by YOLOv2 using a data set augmentation method\",\"authors\":\"Koki Arima, Fusaomi Nagata, Tatsuki Shimizu, Akimasa Otsuka, Hirohisa Kato, Keigo Watanabe, Maki K. Habib\",\"doi\":\"10.1007/s10015-023-00885-9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Recently, CNN (Convolutional Neural Network) and Grad-CAM (Gradient-weighted Class Activation Map) are being applied to various kinds of defect detection and position recognition for industrial products. However, in training process of a CNN model, a large amount of image data are required to acquire a desired generalization ability. In addition, it is not easy for Grad-CAM to clearly identify the defect area which is predicted as the basis of a classification result. Moreover, when they are deployed in an actual production line, two calculation processes for CNN and Grad-CAM have to be sequentially called for defect detection and position recognition, so that the processing time is concerned. In this paper, the authors try to apply YOLOv2 (You Only Look Once) to defect detection and its visualization to process them at once. In general, a YOLOv2 model can be built with less training images; however, a complicated labeling process is required to prepare ground truth data for training. A data set for training a YOLOv2 model has to be composed of image files and the corresponding ground truth data file named gTruth. The gTruth file has names of all the image files and their labeled information, such as label names and box dimensions. Therefore, YOLOv2 requires complex data set augmentation for not only images but also gTruth data. Actually, target products dealt with in this paper are produced with various kinds and small quantity, and also the frequency of occurrence of the defect is infrequent. Moreover, due to the fixed indoor production line, the valid image augmentation to be applied is limited to the horizontal flip. In this paper, a data set augmentation method is proposed to efficiently generate training data for YOLOv2 even in such a production situation and to consequently enhance the performance of defect detection and its visualization. The effectiveness is shown through experiments.</p></div>\",\"PeriodicalId\":46050,\"journal\":{\"name\":\"Artificial Life and Robotics\",\"volume\":\"28 3\",\"pages\":\"625 - 631\"},\"PeriodicalIF\":0.8000,\"publicationDate\":\"2023-07-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Artificial Life and Robotics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s10015-023-00885-9\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ROBOTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial Life and Robotics","FirstCategoryId":"1085","ListUrlMain":"https://link.springer.com/article/10.1007/s10015-023-00885-9","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ROBOTICS","Score":null,"Total":0}
引用次数: 0
摘要
近年来,CNN(卷积神经网络)和Grad-CAM(梯度加权类激活图)正被应用于工业产品的各种缺陷检测和位置识别。然而,在CNN模型的训练过程中,需要大量的图像数据才能获得期望的泛化能力。此外,Grad CAM不容易清楚地识别作为分类结果基础预测的缺陷区域。此外,当它们部署在实际生产线上时,必须依次调用CNN和Grad-CAM的两个计算过程来进行缺陷检测和位置识别,因此处理时间受到关注。在本文中,作者试图将YOLOv2(You Only Look Once)应用于缺陷检测及其可视化,以一次处理它们。通常,YOLOv2模型可以用较少的训练图像来构建;然而,需要复杂的标记过程来准备用于训练的地面实况数据。用于训练YOLOv2模型的数据集必须由图像文件和名为gTruth的相应地面实况数据文件组成。gTruth文件包含所有图像文件的名称及其标记信息,例如标签名称和框尺寸。因此,YOLOv2不仅需要图像,还需要gTruth数据的复杂数据集扩充。实际上,本文处理的目标产品种类繁多,数量很少,而且缺陷的发生频率也很低。此外,由于固定的室内生产线,要应用的有效图像增强仅限于水平翻转。在本文中,提出了一种数据集扩充方法,即使在这种生产情况下,也能有效地生成YOLOv2的训练数据,从而提高缺陷检测及其可视化的性能。实验证明了该方法的有效性。
Improvements of detection accuracy and its confidence of defective areas by YOLOv2 using a data set augmentation method
Recently, CNN (Convolutional Neural Network) and Grad-CAM (Gradient-weighted Class Activation Map) are being applied to various kinds of defect detection and position recognition for industrial products. However, in training process of a CNN model, a large amount of image data are required to acquire a desired generalization ability. In addition, it is not easy for Grad-CAM to clearly identify the defect area which is predicted as the basis of a classification result. Moreover, when they are deployed in an actual production line, two calculation processes for CNN and Grad-CAM have to be sequentially called for defect detection and position recognition, so that the processing time is concerned. In this paper, the authors try to apply YOLOv2 (You Only Look Once) to defect detection and its visualization to process them at once. In general, a YOLOv2 model can be built with less training images; however, a complicated labeling process is required to prepare ground truth data for training. A data set for training a YOLOv2 model has to be composed of image files and the corresponding ground truth data file named gTruth. The gTruth file has names of all the image files and their labeled information, such as label names and box dimensions. Therefore, YOLOv2 requires complex data set augmentation for not only images but also gTruth data. Actually, target products dealt with in this paper are produced with various kinds and small quantity, and also the frequency of occurrence of the defect is infrequent. Moreover, due to the fixed indoor production line, the valid image augmentation to be applied is limited to the horizontal flip. In this paper, a data set augmentation method is proposed to efficiently generate training data for YOLOv2 even in such a production situation and to consequently enhance the performance of defect detection and its visualization. The effectiveness is shown through experiments.