Automated visual inspection algorithm for the reflection detection and removing in image sequences

Abstract

Specular reflections are undesirable phenomena that can impair overall perception and subsequent image analysis. In this paper, we propose a modern solution to this problem, based on the latest achievements in this field. The proposed method includes three main steps: image enhancement, detection of specular reflections, and reconstruction of damaged areas. To enhance and equalize the brightness characteristics of the image, we use the alpha-rooting method with adaptive choice of the optimal parameter-alpha. To detect specular reflections, we apply morphological filtering in the HSV color space. At the final stage there is a reconstruction of damaged areas using adversarial neural networks. This combination makes it possible to quickly and effectively detect and remove specular reflections, which is confirmed by a series of experiments given by the experimental section of this work.

SpecReFlow: an algorithm for specular reflection restoration using flow-guided video completion

“…[11][12][13] In addition, conventional methods for SR restorations largely depend on empirical parameter setting, which can lead to slow runtimes and inaccurate feature appearance such as blurriness, structural inaccuracy, and poor color blending with the surrounding non-SR region. 6,[11][12][13][14][15][16][17] Many single-frame methods use deep learning approaches, such as convolutional neural networks (CNNs) 18,19 or generative adversarial networks, 4,5,[20][21][22] to directly inpaint the region for restoration. Although learned methods may lead to fast and high-quality restorations, the generated regions may not be truly representative of the ground-truth tissue, as they only inpaint the missing SR region using local spatial information obtained from a single perspective.…”

“…Many single-frame methods use deep learning approaches, such as convolutional neural networks (CNNs) 18 , 19 or generative adversarial networks, 4 , 5 , 20 – 22 to directly inpaint the region for restoration. Although learned methods may lead to fast and high-quality restorations, the generated regions may not be truly representative of the ground-truth tissue, as they only inpaint the missing SR region using local spatial information obtained from a single perspective.…”