Yazar "Varjovi, Mahdi Hatami" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    CNN-Based Fabric Defect Detection System on Loom Fabric Inspection
    (E.U. Printing And Publishing House, 2022) Talu, Muhammed Fatih; Hanbay, Kazim; Varjovi, Mahdi Hatami
    Fabric defect detection is generally performed based on human visual inspection. This method is not effective and it has various difficulties such as eye delusion and labor cost. To deal with these problems, machine learning and computer vision-based intelligent systems have been developed. In this paper, a novel real-time fabric defect detection system is proposed. The proposed industrial vision system has been operated in real-time on a loom. Firstly, two fabric databases are constructed using real fabric images and new defective patch capture (DPC) algorithm. One of the main objectives in this study is to develop a CNN architecture that focuses only on fabric defect detection. One of the most unique aspects of the study is to detect defective pixel regions of fabric images with Fourier analysis on a patch-based and integrate it with deep learning Thanks to the novel developed fast Fourier transform-based DPC algorithm, defective texture areas become visible and defect-free areas are suppressed, even on complex denim fabric textures. Secondly, an appropriate convolution neural networks (CNN) model is developed. Thus the new dataset dataset is refined using negative mining method and CNN model. However, traditional feature extraction and classification approaches are also used to compare classification performances of deep models and traditional models. Experimental results show that our proposed CNN model integrated with negative mining can classify the defected images with high accuracy. Also, the proposed CNN model has been tested in real-time on a loom, and it achieves 96.5% detection accuracy. The proposed model obtains better accuracy and speed performance in terms of detection accuracy with a much smaller model size.
  • Küçük Resim Yok
    Öğe
    Fabric Defect Detection Using Customized Deep Convolutional Neural Network for Circular Knitting Fabrics
    (2022) Varjovi, Mahdi Hatami; Talu, Muhammed Fatih; Hanbay, Kazım
    Visual inspection is a main stage of quality assurance process in many applications. In this paper, we propose a new network architecture for detecting the fabric defects based on convolutional neural network. Four different pre-trained and customized model network architectures have compared in terms of performance. Results has been evaluated on a fabric defect dataset of 13.800 images. Among the existing Inception V3, MobileNetV2, Xception and ResNet50 methods, the InceptionV3 model has achieved 78% classification success. Our designed deep network model could achieve 97% success. The experimental works show that the designed deep model is effective in detecting the fabric defects.
  • Küçük Resim Yok
    Öğe
    Genetic Algorithm Based Tree Segmentation
    (Ieee, 2018) Varjovi, Mahdi Hatami; Altun, Sara; Talu, Muhammed Fatih; Yeroglu, Celaleddin
    Segmentation of tree images are used in agricultural applications such as harvest estimation. The accuracy of the segmentation process influences the success of such applications. Many methods are used for image segmentation such as thresholding, clustering, edge-based, region-based methods. The region growing algorithm is a very robust and easy to implement method, but the disadvantage of this method is that the threshold value is sensitive to critical and environmental noise. In this study, it is aimed to increase the segmentation quality of tree images. In tree segmentation; the optimum threshold values differ because of the camera's characteristics, the amount of light, the color of the leaf, the type of the fruity, the shadow of the branches and the other greens on the background. The starting point is automatically optimized with the help of genetic algorithms for the threshold values used in the determined region growing method.
  • Küçük Resim Yok
    Öğe
    Performance Comparison of Different Optimization Methods under the Same Conditions
    (Ieee, 2018) Altun, Sara; Varjovi, Mahdi Hatami; Karci, Ali
    There are many probing solutions in the literature. Optimization methods performances are compared and the best one is chosen and the problem is executed on it. In this study, Benchmark functions consisting of simple mathematical functions are used and it is aimed to use same media, same method, same starting population and same problem to get the most accurate result. Optimization algorithms Genetic Algorithm (GA), Differential Evolution Algorithm (DGA), Ant Colony (ACR), Artificial Atom Algorithm (A(3)) and Clonal Selection Algorithm (CLONALG) was used. Performance measures of these optimization algorithms are calculated on three different benchmarking algorithms.