Novel Image-Based 3D Reconstruction of the Human Jaw using Shape from Shading and Feature Descriptors

Abstract

In this paper, we propose a novel approach for 3D surface reconstruction of the human jaw. Due to the difficulties of setting up a data acquisition system inside the mouth, we use an intra-oral camera to capture a sequence of calibrated images. These images are registered together to build a panoramic view of the jaw. We incorporate a shape from shading(SFS) algorithm that benefits from camera calibration parameters to build a 3D model from the panoramic image obtained from the previous stage. Our approach results in a 3D surface which has more fine details compared with those resulting from other literature techniques. We will demonstrate different artificial jaws surfaces reconstruction to show the efficiency of our system.

Shape from Shading for Rough Surfaces: Analysis of the Oren-Nayar Model

“…Having many interesting applications such as astronomy [17], terrain reconstruction [4], endoscopy [21,27] or dentistry [1], the goal of SfS is to recover the surface of an object from a single input image under the assumption that a reflectance model and the light information are available. For a long time, the research in SfS was mainly dominated c 2012.…”

Three-dimensional modeling of the human jaw/teeth using optics and statistics.

“…Focused on generalization of the SFS solution to various object characteristics as stated above [12,26], and deployed newer cameras with various light sources and motion sensors. From algorithmic point of view we introduced a new stitching algorithm [20], which enabled registration of the image segments covering the human jaw, then applying SFS vs. applying SFS on individual segments and then register the results. Equally significant is that we examined the roughness of the jaw material using profiler microscopes available at the University of Louisville MEMS facility, in order to calibrate the albedo parameters in the SFS using realistic measures.…”

“…Currently, the database having 224 teeth with the following statistics: anterior (20), mandibular 3rd molar (119), maxillary deciduous (27), maxillary Molars (38) and premolars (20). They are automatically preprocessed to generate triangular meshes, see Figure 15.…”

“…• Chapter V proposed a novel approach for 3D surface reconstruction of the human jaw [20]. Due to the difficulties of setting up a data acquisition system inside the mouth, an intraoral camera is used to capture a sequence of calibrated images.…”

“…Computer Vision and Image Processing laboratory (CVIP lab.) research group have been interested in this SFS paradigm for jaw/teeth reconstruction from an intraoral image for several years (see for example [6,[18][19][20][21]) due to the significant shading cue in an image of a tooth. In addition, other 3D reconstruction methods, such as Shape from Stereo, will have little success when applied on the textureless tooth surfaces [19].…”