Surface inspection is a critical step in ensuring the product quality in the steel-making industry. In order to relieve inspectors of laborious work and improve the consistency of inspection, much effort has been dedicated to the automated inspection using computer vision approaches over the past decades. However, due to non-uniform illumination conditions and similarity between the surface textures and defects, the present methods are usually applicable to very specific cases. In this paper a new framework for surface inspection has been proposed to overcome these limitations. By investigating the image formation process, a quantitative model characterizing the impact of illumination on the image quality is developed, based on which the non-uniform brightness in the image can be effectively removed. Then a simple classifier is designed to identify the defects among the surface textures. The significance of this approach lies in its robustness to illumination changes and wide applicability to different inspection scenarios. The proposed approach has been successfully applied to the real-time surface inspection of round billets in real manufacturing. Implemented on a conventional industrial PC, the algorithm can proceed at 12.5 frames per second with the successful detection rate being over 90% for turned and skinned billets.
Motivated by the statistical and computational challenges of computing Wasserstein distances in high-dimensional contexts, machine learning researchers have defined modified Wasserstein distances based on computing distances between one-dimensional projections of the measures. Different choices of how to aggregate these projected distances (averaging, random sampling, maximizing) give rise to different distances, requiring different statistical analyses. We define the Sliced Wasserstein Process, a stochastic process defined by the empirical Wasserstein distance between projections of empirical probability measures to all one-dimensional subspaces, and prove a uniform distributional limit theorem for this process. As a result, we obtain a unified framework in which to prove distributional limit results for all Wasserstein distances based on one-dimensional projections. We illustrate these results on a number of examples where no distributional limits were previously known.
For adaptive ultrasound imaging, a reliable estimation of the covariance matrix has a decisive influence on the performance of beamformers. In this paper, we propose a new cross subaperture averaging generalized sidelobe canceler approach (GSC-CROSS) for medical ultrasound imaging, which uses the cross-covariance matrix instead of the traditional covariance matrix estimation. By using the more stable and accurate estimation of the covariance matrix, GSC-CROSS performs well in both lateral resolution and contrast. Experiments are conducted based on the simulated echo data of scattering points and a cyst target. Beamforming responses of scattering points show that GSC-CROSS can improve the lateral resolution by 76.9%, 68.8%, and 17.1% compared with delay-and-sum (DS), synthetic aperture (SA), and the traditional generalized sidelobe canceler (GSC), respectively. Also, imaging of the cyst target shows that compared with DS, SA, and GSC, the contrast increases by 101%, 32.6%, and 63.5%, respectively. Finally, the actual echo data collected from a medical ultrasonic imaging system is applied to reconstruct the image. Results show that the proposed method has a good performance on lateral resolution and contrast. Both the simulated and experimental data demonstrate the effectiveness of the proposed method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.