Scratch Detection Algorithm of Car Surface Based on Directional Color SUSAN Operator

The car surface scratch detection adopts the traditional manual detection with poor efficiency and high missing rate.Because of the gray mark and the background of car surface scratches,the traditional edge detection algorithm cannot meet the needs of car surface scratch detection.Therefore,the directional SUSAN algorithm based on CIELab color space is adopted in this paper.The direction template and the circle template to calculate the color difference of the color image are used in the algorithm which has been converted to the CIELab space.The edges and scratches are eliminated by matching and contrasting the detected image with the edge template.Experimental results show that the algorithm can effectively detect scratches on the surface of cars,improve the detection speed and reduce the undetected rate.

Classification-Detection of Metal Surfaces under Lower Edge Sharpness Using a Deep Learning-Based Approach Combined with an Enhanced LoG Operator

Metal flat surface in-line surface defect detection is notoriously difficult due to obstacles such as high surface reflectivity,pseudo-defect interference,and random elastic deformation.This study evaluates the approach for detecting scratches on a metal surface in order to address a problem in the detection process.This paper proposes an improved Gauss-Laplace(LoG)operator combined with a deep learning technique for metal surface scratch identification in order to solve the difficulties that it is challenging to reduce noise and that the edges are unclear when utilizing existing edge detection algorithms.In the process of scratch identification,it is challenging to differentiate between the scratch edge and the interference edge.Therefore,local texture screening is utilized by deep learning techniques that evaluate and identify scratch edges and interference edges based on the local texture characteristics of scratches.Experiments have proven that by combining the improved LoG operator with a deep learning strategy,it is able to effectively detect image edges,distinguish between scratch edges and interference edges,and identify clear scratch information.Experiments based on the six categories of meta scratches indicate that the proposedmethod has achieved rolled-in crazing(100%),inclusion(94.4%),patches(100%),pitted(100%),rolled(100%),and scratches(100%),respectively.

A Novel Method for Detection and Removal of Line Scratch in High Resolution Digital Film

With increasing need of high quality movie, more and more standard resolution films are upconverted to the high-resolution films. After this operation, the defects exist in the old movie are more obvious because they are enlarged in size, therefore, an efficient artifacts detection method with more precise result and lower computational complexity is in need. This paper provided a line scratch mathematical model, which derives from the Kokaram model and Bruni model, and then gave a detection method to meet the requirements of the high-resolution video application.

Dark-field detection method of shallow scratches on the super-smooth optical surface based on the technology of adaptive smoothing and morphological differencing

In recent years, modern optical processing technologies, such as single point diamond turning, ion beam etching, and magneto-theological finishing, arc getting break- throughs. Machining precisions of super-smooth optics have also been significantly improved. However, with increasing demands for the optical surface quality,