Three-dimensional pattern recognition with a single two-dimensional synthetic reference function

Review of three-dimensional holographic imaging by multiple-viewpoint-projection based methods

Methods of generating multiple viewpoint projection holograms of three-dimensional (3-D) realistic objects illuminated by incoherent white light are reviewed in this paper. Using these methods, it is possible to obtain holograms with a simple digital camera, operating in regular light conditions. Thus, most disadvantages characterizing conventional digital holography, namely the need for a powerful, highly coherent laser and extreme stability of the optical system, are avoided. The proposed holographic processes are composed of two stages. In the first stage, regular intensity-based images of the 3-D scene are captured from multiple points of view by a simple digital camera. In the second stage, the acquired projections are digitally processed to yield the complex digital hologram of the 3-D scene, where no interference is involved in the process. For highly reflecting 3-D objects, the resulting hologram is equivalent to an optical hologram of the objects recorded from the central point of view. We first review various methods to acquire the multiple viewpoint projections. These include the use of a microlens array and a macrolens array, as well as digitally generated projections that are not acquired optically. Next, we show how to digitally process the acquired projections to Fourier, Fresnel, and image holograms. Additionally, to obtain certain advantages over the known types of holograms, the proposed hybrid optical-digital process can yield novel types of holograms such as the modified Fresnel hologram and the protected correlation hologram. The prospective goal of these methods is to facilitate the design of a simple and portable digital holographic camera that can be useful for a variety of practical applications, including 3-D video acquisition and various types of biomedical imaging. We review several of these applications to signify the advantages of multiple viewpoint projection holography.

Nonlinear filter for pattern recognition invariant to illumination and to out-of-plane rotations

Automatic target recognition in uncontrolled conditions is a difficult task because many parametersare involved. This study deals with the recognition of targets under limited out-of-plane rotations while maintaining invariance to ambient light illumination. Contrast invariance is achieved by using the recently developed locally adaptive contrast-invariant filter, a method that yields correlation peaks whose values are invariant under any linear transformation of intensity. To reduce the sensitivity to the orientation of the object we replace the reference in the nonlinear filter by a synthetic discriminant filter. The range used for out-of-plane rotations was 40 degrees with a depression angle of 20 degrees. We present results for unsegmented targets on complex backgrounds with the presence of false targets.

Scale-invariant recognition of three-dimensional objects by use of a quasi-correlator

A method of scale-invariant recognition of three-dimensional (3-D) objects is presented. Several images of the observed scene are recorded under white-light illumination from several different points of view and compressed into a single complex two-dimensional matrix. After filtering with a single scale-invariant filter, the resultant function is then coded into a computer-generated hologram (CGH). When this CGH is coherently illuminated, a correlation space is reconstructed in which light peaks indicate the existence and location of true targets in the tested 3-D scene. The light peaks are detectable for different sizes of the true objects, as long as they are within the invariance range of the filter. Experimental results in a complete electro-optical system are presented, and comparisons with other systems are investigated by use of computer simulation.

Object recognition using three-dimensional optical quasi-correlation

A novel method of three-dimensional (3-D) object recognition is proposed. Several projections of a 3-D target are recorded under white-light illumination and fused into a single complex two-dimensional function. After proper filtering, the resulting function is coded into a computer-generated hologram. When this hologram is coherently illuminated, a correlation space is reconstructed such that light peaks indicate the existence and locations of true targets in the observed 3-D scene. Experimental results and comparisons with results of another 3-D object recognition technique are presented.

Three-dimensional optical correlator with general complex filters

A new type of electro-optical three-dimensional (3-D) correlator is proposed and demonstrated. A 3-D object scene, observed by multiple cameras from several points of view, is correlated with a 3-D complex computer-generated function. This correlator is a hybridization of the joint transform and the VanderLugt correlators, and, as such, it allows correlations to be made between 3-D real-world objects and 3-D general complex functions. Experimental results are presented.