DSpace Repository

Deep Learning Models for Handling Specularity in Face Image Intrinsic Decomposition

Show simple item record

dc.contributor.advisor N. Dailey, Matthew
dc.contributor.author Muhammad, Siraj
dc.contributor.other Ekpanyapong, Mongkol
dc.contributor.other Anutariya, Chutiporn
dc.date.accessioned 2020-01-17T07:51:19Z
dc.date.available 2020-01-17T07:51:19Z
dc.date.issued 2020-01-17
dc.identifier.other https://doi.org/10.1016/j.imavis.2019.11.001
dc.identifier.uri http://www.cs.ait.ac.th/xmlui/handle/123456789/963
dc.description.abstract The process of splitting an image into specular and diffuse components is a fundamental problem in computer vision, because most computer vision al- gorithms, such as image segmentation and tracking, assume diffuse surfaces, so existence of specular reflection can mislead algorithms to make incorrect decisions. Existing decomposition methods tend to work well for images with low specularity and high chromaticity, but they fail in cases of high inten- sity specular light and on images with low chromaticity. In this paper, we address the problem of removing high intensity specularity from low chro- maticity images (faces). We introduce a new dataset, Spec-Face, comprising face images corrupted with specular lighting and corresponding ground truth diffuse images. We also introduce two deep learning models for specularity removal, Spec-Net and Spec-CGAN. Spec-Net takes an intensity channel as input and produces an output image that is very close to ground truth, while Spec-CGAN takes an RGB image as input and produces a diffuse image very similar to the ground truth RGB image. On Spec-Face, with Spec-Net, we obtain a peak signal to noise ratio (PSNR) of 3.979, a local mean squared error (LMSE) of 0.000071, a structural similarity index (SSIM) of 0.899, and a Fréchet Inception Distance (FID) of 20.932. With Spec-CGAN, we obtain a PSNR of 3.360, a LMSE of 0.000098, a SSIM of 0.707, and a FID of 31.699. With Spec-Net and Spec-CGAN, it is now feasible to perform specularity re- moval automatically prior to other critical complex vision processes for real world images, i.e., faces. This will potentially improve the performance of algorithms later in the processing stream, such as face recognition and skin cancer detection. en_US
dc.language.iso en_US en_US
dc.publisher ELSEVIER en_US
dc.subject Specularity, Dichromatic Reflection Model, Deep Learning, Convolutional Neural Networks en_US
dc.title Deep Learning Models for Handling Specularity in Face Image Intrinsic Decomposition en_US
dc.type Dissertation en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account