Geometry-Based Skin Colour Estimation for Bare Torso Surface Reconstruction

• Type: Article in International Conference Proceedings Book
• Date: 2019

Authors

Monteiro, JP (Author) Other; Zolfagharnasab, H (Author) Other; Oliveira, HP (Author) FCUP

Conference proceedings International

Title: IMAGE ANALYSIS AND PROCESSING - ICIAP 2019, PT II

Pages: 595-606

20th International Conference on Image Analysis and Processing (ICIAP)

Univ Trento, Fac Law, Trento, ITALY, SEP 09-13, 2019

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 0 Citations

Other information

Authenticus ID: P-00R-4FZ

DOI: 10.1007/978-3-030-30645-8_54

Abstract (EN): Three-dimensional imaging techniques have been endeavouring at reaching affordable ubiquity. Nevertheless, its use in clinical practice can be hampered by less than naturally looking surfaces that greatly impact its visual inspection. This work considers the task of surface reconstruction from point clouds of non-rigid scenes acquired through structured-light-based methods, wherein the reconstructed surface contains some level of imperfection to be inpainted before visualized by experts in a clinically oriented context. Appertain to the topic, the recovery of colour information for missing or damaged partial regions is considered. A local geometry-based interpolation method is proposed for the reconstruction of the bare human torso and compared against a reference differential equations based inpainting method. Widely used perceptual distance-based metrics, such as PSNR, SSIM and MS-SSIM, and the evaluation from a panel of experienced breast cancer surgeons is presented for the discussion on inpainting quality assessment.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 12