A Robust Method for Shape from Shading Using Genetic Algorithm Based on Matrix Code

R. F. Mansour

doi:10.5923/j.ajcam.20110101.07

Abstract

In this paper, a method for reconstructing a 3-D shape of an object from a 2-D shading image using a Genetic Algorithm (GA), which is an optimizing technique based on mechanisms of natural selection. The 3D-shape is recovered through the analysis of the gray levels in a single image of the scene. This problem is ill-posed except if some additional assumptions are made. In the proposed method, shape from shading is addressed as an energy minimization problem. The traditional deterministic approach provides efficient algorithms to solve this problem in terms of time but reaches its limits since the energy associated with shape from shading can contain multiple deep local minima. Genetic Algorithm is used as an alternative approach which is efficient at exploring the entire search space. The Algorithm is tested in both synthetic and real image and is found to perform accurate and efficient results.

Highlights

shape-from shading (SFS) deals with the recovery of surface orientation and surface shape from the gradual variation of shading in images
Marr identified shape-from shading (SFS) as providing one of the key routes to understanding 3D surface structure via the 21⁄2D sketch[4]
A new method for solving the Shape from Shading problem using GA based on matrix code has been developed

Summary

Introduction

SFS deals with the recovery of surface orientation and surface shape (highlight) from the gradual variation of shading in images. Indirect methods determine the relative depth by cues extracted from gray level images of observed object Since the direct or active techniques usually involve many complex external component setup, they may As a result these techniques can only be applied to the object surface that satisfies the constraints. Tsai and Shah[8] applied the discrete approximation of the gradient first, employed the linear approximation of the reflectance function in terms of the depth directly Their algorithm recovered the depth at each point using a Jacobi iterative scheme. The proposed method can be categorized as a linear shape from shading method, which linearizes the reflectance function for symmetric objects using the symmetry cues of the shape and the albedo, and iteratively computes the depth values. The reconstructed shapes are compared with shapes reconstructed by the conventional method of obtaining a shape from shading[13]

Related Works

Problem Formulation

Reconstruction Using GA

Shape From Shading Using GA

Experimental

Conclusions