Visual Control of Robots with Delayed Images

This research develops a control scheme for visual servoing that explicitly takes into account the delay introduced by image acquisition and processing. For this purpose, a predictor block, i.e., an estimator that predicts several samples ahead of time, is properly included in the scheme. The proposed approach is analytically analyzed in terms of dynamics and steady-state errors, and compared to previous approaches. Furthermore, several simulations are comparatively shown in order to illustrate the benefits and limitations of the proposed control scheme. Finally, some experimental results using a turntable and a 3-d.o.f. Cartesian robot are provided in order to validate the analytical and simulation results.     

Gabor filtering for feature extraction on complex images: application to defect detection on semiconductors

Abstract

This paper is an extension of previous work on the image segmentation of electronic structures on patterned wafers to improve the defect detection process on optical inspection tools. Die-to-die wafer inspection is based upon the comparison of the same area on two neighbourhood dies. The dissimilarities between the images are a result of defects in this area of one of the dies. The noise level can vary from one structure to the other, within the same image. Therefore, segmentation is needed to create a mask and apply an optimal threshold in each region. Contrast variation on the texture can affect the response of the parameters used for the segmentation. This paper shows a method of anticipating these variations with a limited number of training samples and modifying the classifier accordingly to improve the segmentation results.