%0 Journal Article
%@ 14248220
%A Anwer, A.
%A Ainouz, S.
%A Saad, M.N.M.
%A Ali, S.S.A.
%A Meriaudeau, F.
%D 2022
%F scholars:16415
%I MDPI
%J Sensors
%K Large dataset; Pixels; Textures, Condition; False positive; Highlights detection; Images segmentations; Modern techniques; Multiple objects; Network-based; Non trivial problems; Real-world image; Specular highlight, Image segmentation, article; false positive result; image segmentation
%N 17
%R 10.3390/s22176552
%T SpecSeg Network for Specular Highlight Detection and Segmentation in Real-World Images
%U https://khub.utp.edu.my/scholars/16415/
%V 22
%X 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. © 2022 by the authors.
%Z cited By 4