Method and system for detecting defects on surface of object

Abstract

Method and system for detecting defects on surface of object are presented. An imaging device captures images of surface of object under ambient and dark field illumination conditions. The images are processed with a plurality of image operations to detect area of potential defect at location on surface of object based on predictable pattern consisting of bright and shadow regions. Kernels are defined corresponding to configurations of dark field illumination sources to enhance detecting potential defect. Areas of potential defect are cut from processed images to sub images. Sub images are stitched together to generate hypothesis of potential defect at location on surface of object. The hypothesis is classified with a classifier to determine whether the potential defect is true defect. The classifier is trained with training data having characteristics of true defect. The method provides efficient automated detection of micro defects on surface of object.

Description

TECHNICAL FIELD[0001]This invention relates generally to a method and a system for detecting a defect on a surface of an object.DESCRIPTION OF RELATED ART[0002]Defect detection is an important aspect of industrial production quality assurance process which may provide an important guarantee for quality of products. Defects may be cracks on a surface of an object. Defects may be very small. Scale of the defects may be as small as micrometers.[0003]Traditional methods of micro defect detection involve significant manual process which may not guarantee consistent quality of detection. Due to small scale of the micro defects, it may require a considerably long detection time to achieve certain accuracy using traditional methods. Some traditional detection methods may require applying certain chemicals which may damage the object. Methods currently being used in industry for detecting defects on surface of object are time consuming and may not provide consistent quality of detection.SUMM...

AI Technical Summary

Benefits of technology

This patent describes a method and system for detecting defects on the surface of an object using a platform for supporting the object and a plurality of illumination sources for illuminating the surface. The system captures images of the surface of the object under illumination conditions and processes them with image operations to detect potential defects. The system then cuts the detected areas from the images and stitches them together to create a hypothesis of the potential defect, which is then classified using a classifier trained with training data to determine whether it is a true defect. The system generates an output of the classification, which includes the detected true defect and its location on the surface of the object. The technical effect of this patent is that it provides a reliable and effective means for detecting defects on the surface of an object, which can help improve manufacturing processes and product quality.

Problems solved by technology

Defects may be cracks on a surface of an object.

Traditional methods of micro defect detection involve significant manual process which may not guarantee consistent quality of detection.

Due to small scale of the micro defects, it may require a considerably long detection time to achieve certain accuracy using traditional methods.

Methods currently being used in industry for detecting defects on surface of object are time consuming and may not provide consistent quality of detection.

Images