Automatic image inspector inspects the quality of printed circuit boards using image-processing technology. In this study, we change an automatic inspection problem into a problem for detecting the signal singularities. Based on the wavelet theory that the wavelet transform can focus on localized signal structures with a zooming procedure, a novel singularity detection and measurement algorithm is proposed. Singularity positions are detected with the local wavelet transform modulus maximum (WTMM) line, and the Lipschitz exponent is estimated at each singularity from the decay of the wavelet transform amplitude along the WTMM line. According to the theoretical analysis and computer simulation results, the proposed algorithm is shown to be successful for solving the automatic inspection problem and calculating the Lipschitz exponents of signals. These Lipschitz exponents successfully characterize singular behavior of signals at singularities.

In medical fields, detecting traumatic bleedings has always been a difficult task due to the small size, low contrast of targets and large number of images. In this work we propose an automatic traumatic bleeding detection approach from contrast enhanced CT images via deep CNN networks, containing segmentation process and classification process. CT values of DICOM images are extracted and processed via three different window settings first. Small 3D patches are cropped from processed images and segmented by a 3D CNN network. Then segmentation results are converted to point cloud data format and classified by a classifier. The proposed pre-processing approach makes the segmentation network be able to detect small and low contrast targets and achieve a high sensitivity. The additional classification network solves the boundary problem and short-sighted problem generated during the segmentation process to further decrease false positives. The proposed approach is tested with 3 CT cases containing 37 bleeding regions. As a result, a total of 34 bleeding regions are correctly detected, the sensitivity reaches 91.89%. The average false positive number of test cases is 1678. 46.1% of false positive predictions are decreased after being classified. The proposed method is proved to be able to achieve a high sensitivity and be a reference of medical doctors.