Laboratoire d'Informatique, du Traitement de l'Information et des Systèmes (LITIS), Normandie Université, UNIROUEN, UNIHAVRE, INSA Rouen, 76000 Rouen, France.
Centre for Intelligent Signal& Imaging Research (CISIR), Electrical and Electronic Engineering Department, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Malaysia.
Sensors (Basel). 2022 Aug 30;22(17):6552. doi: 10.3390/s22176552.
Specular highlights detection and removal in images is a fundamental yet non-trivial problem of interest. Most modern techniques proposed are inadequate at dealing with real-world images taken under uncontrolled conditions with the presence of complex textures, multiple objects, and bright colours, resulting in reduced accuracy and false positives. To detect specular pixels in a wide variety of real-world images independent of the number, colour, or type of illuminating source, we propose an efficient Specular Segmentation (SpecSeg) network based on the U-net architecture that is expeditious to train on nominal-sized datasets. The proposed network can detect pixels strongly affected by specular highlights with a high degree of precision, as shown by comparison with the state-of-the-art methods. The technique proposed is trained on publicly available datasets and tested using a large selection of real-world images with highly encouraging results.
镜面高光的检测和去除是一个基本但具有挑战性的问题。大多数现有的技术在处理在非受控条件下拍摄的真实世界图像时效果不佳，这些图像存在复杂的纹理、多个物体和明亮的颜色，导致准确性降低和误报增加。为了在不受光照源数量、颜色或类型影响的情况下，在各种真实世界图像中检测镜面像素，我们提出了一种基于 U-net 架构的高效镜面分割（SpecSeg）网络，该网络可以在标称大小的数据集上快速训练。所提出的网络可以高精度地检测受到镜面高光强烈影响的像素，这一点通过与最先进的方法进行比较得到了证明。所提出的技术是在公开数据集上进行训练的，并使用大量真实世界图像进行测试，结果非常令人鼓舞。
