Byoungho Lee;Jae-Hyeung Park;Heejin Choi;
Three-dimensional image recognition is an important issue in the field of information optics. There have been many researches in the 3D object recognition. Recently much attention has been focused on integral imaging, which used to be called integral photography in the past. In this paper, we will discuss our recent works on the 3D image capture, processing and correlation using the integral imaging technique. By using a lens array, we capture different perspectives of a 3D object at one time. Then, the information can be processed to figure out the original 3D image based on multi- baseline stereoscopy techniques. A composite lens array that consists of different-focal-length lenses can be more efficient for this purpose. The captured images can be used for multiple joint transform correlation with reference images. From the results, we can obtain the correlation between the 3D object and the reference object. And also, we can figure out both transverse and longitudinal shift information of the 3D object with respect to the reference 3D object. Both theoretical discussion and experimental proof are provided.
Three-dimensional correlation, integral imaging, integral photography, three-dimensional recognition, joint transform correlation
To explore the background and basis of the node document
Documents that have the similar content to the node document