3m Innovative Properties Company

Nathaniel S Rowekamp

Steven P Floeder

Jeffrey P Adolf

James A Masterman

Xin Yu

An inspection system includes an inspection device having at least one image capture device. The image capture device captures image data of a sheet part passing through the inspection device. A processing unit of the inspection device provides the image data representative of the sheet part to a plurality of neural networks, where each of the neural networks is trained to identify a corresponding defect in the sheet part and output data indicative of the presence of the corresponding defect. The processing unit determines a quality category of the sheet part based on the data indicative of the presence of the corresponding defect output by each corresponding neural network. The processing unit can further output the quality category of the sheet part to a sorter that can sort the sheet part based on the quality category.

Inspecting sheet goods using deep learning

An example system is described herein. The example system may include an inspection device comprising at least one image capture device, the at least one image capture device configured to capture a reference image of a sheet part. Additionally, the example system may include a processing unit configured to identify at least one primary point in the reference image and identify at least one secondary point in a mask image. The processing unit may transform the mask image based on the at least one primary point and the at least one secondary point. The processing unit may apply the transformed mask image to the reference image to identify an inspection region within the reference image, process the inspection region of the reference image to determine the quality of the sheet part, and output information indicative of the quality of the sheet part.

Growing community of inventors

Maplewood, MN, United States of America

Nathaniel S Rowekamp