• 반도체디스플레이기술학회지
• /
• 제20권2호
• /
• pp.109-114
• /
• 2021

When we inspect scaffold defect using sight, inspecting performance is decrease and inspecting time is increase. We need for automatically scaffold defect detection method to increase detection accuracy and reduce detection times. In this paper. We produced scaffold defect classification models using densenet, alexnet, vggnet algorithms based on CNN. We photographed scaffold using multi dimension camera. We learned scaffold defect classification model using photographed scaffold images. We evaluated the scaffold defect classification accuracy of each models. As result of evaluation, the defect classification performance using densenet algorithm was at 99.1%. The defect classification performance using VGGnet algorithm was at 98.3%. The defect classification performance using Alexnet algorithm was at 96.8%. We were able to quantitatively compare defect classification performance of three type algorithms based on CNN.

• 반도체디스플레이기술학회지
• /
• 제19권3호
• /
• pp.77-81
• /
• 2020

In this paper, we create scaffold defect classification models using machine learning based data. We extract the characteristic from collected scaffold external images using USB camera. SVM, KNN, MLP algorithm of machine learning was using extracted features. Classification models of three type learned using train dataset. We created scaffold defect classification models using test dataset. We quantified the performance of defect classification models. We have confirmed that the SVM accuracy is 95%. So the best performance model is using SVM.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.4028-4042
• /
• 2021

Aiming at the problem of software defect prediction difficulty caused by insufficient software defect marker samples and unbalanced classification, a semi-supervised software defect prediction model based on a tri-training algorithm was proposed by combining feature normalization, over-sampling technology, and a Tri-training algorithm. First, the feature normalization method is used to smooth the feature data to eliminate the influence of too large or too small feature values on the model's classification performance. Secondly, the oversampling method is used to expand and sample the data, which solves the unbalanced classification of labelled samples. Finally, the Tri-training algorithm performs machine learning on the training samples and establishes a defect prediction model. The novelty of this model is that it can effectively combine feature normalization, oversampling techniques, and the Tri-training algorithm to solve both the under-labelled sample and class imbalance problems. Simulation experiments using the NASA software defect prediction dataset show that the proposed method outperforms four existing supervised and semi-supervised learning in terms of Precision, Recall, and F-Measure values.

• 소성∙가공
• /
• 제31권4호
• /
• pp.229-239
• /
• 2022

Convolution Neural Network(CNN) is a class of deep learning algorithms and can be used for image analysis. In particular, it has excellent performance in finding the pattern of images. Therefore, CNN is commonly applied for recognizing, learning and classifying images. In this study, the surface defect classification performance of Al 6061 extruded material using CNN-based algorithms were compared and evaluated. First, the data collection criteria were suggested and a total of 2,024 datasets were prepared. And they were randomly classified into 1,417 learning data and 607 evaluation data. After that, the size and quality of the training data set were improved using data augmentation techniques to increase the performance of deep learning. The CNN-based algorithms used in this study were VGGNet-16, VGGNet-19, ResNet-50 and DenseNet-121. The evaluation of the defect classification performance was made by comparing the accuracy, loss, and learning speed using verification data. The DenseNet-121 algorithm showed better performance than other algorithms with an accuracy of 99.13% and a loss value of 0.037. This was due to the structural characteristics of the DenseNet model, and the information loss was reduced by acquiring information from all previous layers for image identification in this algorithm. Based on the above results, the possibility of machine vision application of CNN-based model for the surface defect classification of Al extruded materials was also discussed.

• 한국멀티미디어학회논문지
• /
• 제24권8호
• /
• pp.1026-1034
• /
• 2021

Tire wear and defect are important factors for safe driving condition. These defects are generally inspected by some specialized experts or very expensive equipments such as stereo depth camera and depth gauge. In this paper, we propose tire safety vision inspector based on deep neural network (DNN). The status of tire wear is categorized into three: 'safety', 'warning', and 'danger' based on depth of tire tread. We propose an attention mechanism for emphasizing the feature of tread area. The attention-based feature is concatenated to output feature maps of the last convolution layer of ResNet-101 to extract more robust feature. Through experiments, the proposed tire wear classification model improves 1.8% of accuracy compared to the existing ResNet-101 model. For detecting the tire defections, the developed tire defect detection model shows up-to 91% of accuracy using the Mask R-CNN model. From these results, we can see that the suggested models are useful for checking on the safety condition of working tire in real environment.

• 한국전자통신학회논문지
• /
• 제17권4호
• /
• pp.577-586
• /
• 2022

철강 표면 결함의 검출 및 분류는 철강 산업의 제품 품질 관리에 중요하다. 그러나 정확도가 낮고 속도가 느리기 때문에 기존 방식은 생산 라인에서 효과적으로 사용할 수 없다. 현재 널리 사용되는 알고리즘(딥러닝 기반)은 정확도 문제가 있으며 아직 개발의 여지가 있다. 본 논문에서는 이미지 분류를 위한 EfficientNetV2와 물체 검출기로 YOLOv5를 결합한 강철 표면 결함 검출 방법을 제안한다. 이 모델의 장점은 훈련 시간이 짧고 정확도가 높다는 것이다. 먼저 EfficientNetV2 모델에 입력되는 이미지는 결함 클래스를 분류하고 결함이 있을 확률을 예측한다. 결함이 있을 확률이 0.3보다 작으면 알고리즘은 결함이 없는 샘플로 인식한다. 그렇지 않으면 샘플이 YOLOv5에 추가로 입력되어 금속 표면의 결함 감지 프로세스를 수행한다. 실험에 따르면 제안된 모델은 NEU 데이터 세트에서 98.3%의 정확도로 우수한 성능을 보였고, 동시에 평균 훈련 속도는 다른 모델보다 단축된 것으로 나타났다.

• 한국산학기술학회논문지
• /
• 제19권3호
• /
• pp.61-68
• /
• 2018

공동주택 하자는 유지보수에 막대한 비용이 들어가게 되며, 발주자, 시공자 그리고 입주자 등에게 심각한 피해를 입힌다. 이에 따라 하자분쟁을 최소화하고 철저한 품질관리를 통한 체계적이고 효율적인 하자관리를 위한 토대를 마련할 필요가 있다. 본 연구에서는 하자분쟁사례를 활용하여 공동주택의 공종/부위/현상에 따른 하자분류체계를 도출하고, 이를 기반으로 하자유형별 하자위험을 평가할 수 있는 방안을 제시하였다. 이를 위하여 본 논문에서는 경과년수 10년 이상 공동주택 하자분쟁사례 34건, 약 6000여개의 하자항목 자료를 토대로 분석을 실시하였다. 분석 결과를 정리하면, 하자분류체계는 하자 공종, 하자부위 및 하자현상으로 크게 분류한 후 세부적으로 총 157개 항목으로 세분화하였다. 하자분류체계를 토대로 하자 빈도, 하자비용 및 하자위험을 분석한 결과, RC공사 및 마감공사에 하자위험이 상당히 집중되어 있는 것으로 확인되었다. 이에 따라 이러한 하자위험에 대한 하자예방 활동이 우선적으로 고려되어야 할 것으로 판단된다. 본 연구를 토대로 하자위험을 관리할 수 있는 방안에 대한 추가적인 연구가 필요할 것으로 판단된다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제2권1호
• /
• pp.1-6
• /
• 2013

소프트웨어의 결함 경향 모듈 예측을 위해 SVM 분류기가 우수한 성능을 보인다는 연구들이 많지만, SVM에서 필요한 파라미터 선정 시 매 커널마다 다르게 선정해야 하고, 파라미터의 변경에 따른 결과예측을 위해 알고리즘을 반복적으로 수행해야 하는 불편함이 있다. 따라서 본 논문에서는 SVM의 파라미터 선정 시 유전알고리즘을 이용하여 스스로 찾게 하는 GA-SVM 모델을 구현하였다. 그리고 분류 성능 비교를 위해 신경망의 역전파알고리즘을 이용하여 분류했던 기존 논문과 비교 분석한 결과, GA-SVM 모델의 성능이 더 우수함을 확인하였다.

• Smart Structures and Systems
• /
• 제33권1호
• /
• pp.55-64
• /
• 2024

This paper proposes a fusion imaging-based coating-defect classification method for steel structures that uses zero-shot learning. In the proposed method, a halogen lamp generates heat energy on the coating surface of a steel structure, and the resulting heat responses are measured by an infrared (IR) camera, while photos of the coating surface are captured by a charge-coupled device (CCD) camera. The measured heat responses and visual images are then analyzed using zero-shot learning to classify the coating defects, and the estimated coating defects are visualized throughout the inspection surface of the steel structure. In contrast to older approaches to coating-defect classification that relied on visual inspection and were limited to surface defects, and older artificial neural network (ANN)-based methods that required large amounts of data for training and validation, the proposed method accurately classifies both internal and external defects and can classify coating defects for unobserved classes that are not included in the training. Additionally, the proposed model easily learns about additional classifying conditions, making it simple to add classes for problems of interest and field application. Based on the results of validation via field testing, the defect-type classification performance is improved 22.7% of accuracy by fusing visual and thermal imaging compared to using only a visual dataset. Furthermore, the classification accuracy of the proposed method on a test dataset with only trained classes is validated to be 100%. With word-embedding vectors for the labels of untrained classes, the classification accuracy of the proposed method is 86.4%.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2012년도 한국컴퓨터종합학술대회논문집 Vol.39 No.1(B)
• /
• pp.522-524
• /
• 2012

For exact classification of the defect, good feature selection and classifier is necessary. In this paper, various features such as brightness features, shape features and statistical features are stated and Bayes classifier using Gaussian mixture model is used as classifier. Also feature extraction method based on spectral graph theory is presented. Experimental result shows that feature extraction method using graph Laplacian result in better performance than the result using PCA.