Gradient-based Hough transform for the detection and characterization of defects during non-destructive inspection

摘要: Summary form only given, substantially as follows. Ultrasonic non-destructive inspection is today a routine method in industries for the detection, localization and sizing of surface buried defects engineering structures. However, analysis huge amount data obtained during an ultrasonic not simple task usually time consuming. This why are displayed images order to take advantage power visual representation information image processing tools used so speed up problem. In mainly three types known B-SCAN, C-SCAN D-SCAN displays. Our work concerned with application algorithm on B-SCAN displays detect crack thick based Hough transform which gradient performed computation space. decide whether defect present structure or we need set threshold analyze Any maximum space greater than represents structure. Due diversity may contain defects, fixed one depends obtained.