The ability to perform fast and accurate 3 dimensional reconstruction of an environment or object is central to many areas of computer vision processing. 3D face recognition, parts inspection, autonomous drivers and a near infinite number of other applications have driven research in 3D reconstruction forward for the last decade. Whilst much of the mathematics of image formation and 3D reconstruction have been comprehensively researched through photometry and multiple view geometry for many years it is only the recent exponential explosion of processing and graphics power that have allowed practical implementations of such work within computer science. Current research is at a stage where, whilst the majority of the basics have been well covered, many practical problems and implementation issues remain.
This thesis proposes a practical framework for 3D reconstruction with versatile and wide ranging applicability to current state-of-the-art reconstruction projects. The development of a framework aims to facilitate the rapid development of novel reconstruction systems. By adhering to the proposed framework researches may gain insight into appropriate algorithmic selection and testing strategies for particular application domains. The modular approach to the framework also encourages modular application design allowing a greater degree of reusability from reconstruction system components.
Further to the proposal of a comprehensive reconstruction framework we demonstrate the applicability of the design by implementing a state-of-the-art reconstruction and 3D face recognition system based on the described framework. During the implementation of the reconstruction and recognition system we propose a number of novel algorithms particularly suited to facial reconstruction under structured light conditions. A number of unique potential applications where 3D reconstruction may be put to use are discussed in addition to how such varied reconstruction scenarios fall within the practical framework defined by this thesis, thus demonstrating the general applicability of the work.