Image Classification Applied to the Problem of Conformity Check in Industry

Nour Islam Mokhtari (1) , Igor Jovančević (1, 2) , Hamdi Ben Abdallah (3) , Jean-José Orteu (3)

1 DIOTASOFT
2 UCG - University of Montenegro
3 ICA - Institut Clément Ader

This paper shows the application of several learning-based image classification techniques to conformity check, which is a common problem in industrial visual inspection. The approaches are based on processing 2D images. First, a classification pipeline has been developed. An effort has been invested into choosing an appropriate classifier. First experiment was performed with HoG features (Histogram Of Gradient) and Support Vector Machine (SVM). Further, to improve accuracy, we employed a bag of visual words (BoVW) and ORB detector for extracting features that we further use to build our dictionary of visual words. The final solution uses features extracted by passing an image through a pre-trained deep convolutional neural network Inception. Using these features a SVM classifier was trained and high accuracy was obtained. To augment our image data set, different transformations such as zoom and shearing were applied. Promising results were obtained which shows that state-of-the-art deep learning classification techniques can be successfully employed in the visual industrial inspection field.

Domaines: Sciences de l'ingénieur [physics]

Nour Islam Mokhtari, Igor Jovančević, Hamdi Ben Abdallah, Jean-José Orteu. Image Classification Applied to the Problem of Conformity Check in Industry. SOCO 2022 - 17th International Conference on Soft Computing Models in Industrial and Environmental Applications, Sep 2022, Salamanque, Spain. p. 340-349, ⟨10.1007/978-3-031-18050-7_33⟩. ⟨hal-03813066⟩