Abstract. Defects detection on images is a current task in quality control and is often integrated in partially or fully automated systems. Assessing the performances of defects detection algorithms is thus of great interest. However, being application and context dependent, it remains a difficult task. This paper describes a methodology to measure the performances of such algorithms on large size images in a semi-automated defect inspection situation. Considering standard problems occurring on real cases, a comparison of typical performance evaluation methods is made. This analysis leads to the construction of a simple and practical ROC-based method. This method extends the pixel-level ROC analysis to an object-based approach by dilating the ground-truth and the set of detected pixels before calculating true positive and false positive rates. These dilations are computed thanks to the a priori knowledge of a human defined ground-truth and gives to true positive and false positive rates more consistent values in the semi-automated inspection context. Moreover, dilation process is designed to be automatically suited to the objects shape in order to be applied on all types of defects.

No abstract

Sextant Avionique and Thomson LCD developped a 6"x8" portrait AMLCD for avionic cockpit display applications. Main features of the display are : 504x672 resolution in RGGB quad, wide viewing angle (± ±60°) and low reflectivity (0.8%). In addition, the mechanical design of the display module allows low maintenance costs and withstanding of harsh environmental conditions.

We present in this letter a noniterative learning rule for classification and neural networks, which allows to eliminate the drawback of overfitting of the pseudo-inverse (PI) solution and to preserve good learning performances. This solution, which is obtained by artificially increasing the number of patterns in the learning set, is a parametric form between the pseudo-inverse and the Hebb solutions. The results are compared to each other and with those of a gradient descent iterative procedure on two very different examples. We show that the proposed solution is near to the one of the iterative procedure.

Defect detection in images is a current task in quality control and is often integrated in partially or fully automated systems. Assessing the performances of defect detection algorithms is thus of great interest. However, because this is application-and context-dependent, it remains a difficult task. We describe a methodology to measure the performances of such algorithms on large images in a semi-automated defect inspection situation. Considering standard problems occurring in real cases, we compare typical performance evaluation methods. This analysis leads to the construction of a simple and practical receiver operating characteristic (ROC) based method. This method extends the pixel-level ROC analysis to an object-based approach by dilating the ground truth and the set of detected pixels before calculating the true-positive and false-positive rates. These dilations are computed thanks to the a priori knowledge of a human-defined ground truth and gives to true-positive and false-positive rates more consistent values in the semi-automated inspection context. Moreover, the dilation process is designed to be automatically suited to the object's shape in order to be applied on all types of defects without any parameter to be tuned.