A method for solving the stereo correspondence problem transforms the problem into a maximum-flow problem. Once solved, the minimum-cut associated to the maximum-flow results in a disparity surface for the entire image at once. This global approach to stereo analysis provides a more accurate and coherent depth map than the traditional line-by-line stereo method. Moreover, the optimality of the depth surface is guaranteed and can be shown to be a generalization of the dynamic programming approach that is widely used in standard stereo. Results show improved depth estimation as well as better handling of depth discontinuities. While the worst case running time is O(n.sup.3 d.sup.3), the observed average running time is O(n d.sup.1.4) for an image size of n pixels and depth resolution d.

The present invention is embodied in a system and method for curve matching multiple images of a scene. The curve matching produces a geometrical representation of the scene from the images, which can be used for any suitable application, such as computer and stereo vision applications. In general, first, multiple images depicting a scene are digitally received by the system. The images are graphical images digitally received and processed as two dimensional image data, such as bitmap or raster image data. Curve matching of the images is then performed to correlate the two images of the scene for creating three dimensional (3D) curve information, such as 3D vector information, of the scene. This 3D vector information can then be used in any suitable manner, for example, to digitally reconstruct the scene for stereo vision applications.

Whether or not an object to be rendered in stereo images is inside of a fusional area is determined on the basis of a focus point and positions of eyes of a viewer. By using characteristics of a view sight of a human in which an object in a fusional area of human eyes can be clearly recognized as a single solid, however, if an object is not in the fusional area, the object is recognized as vague overlapped images, an object which is inside of the fusional area is rendered by using an image generating algorithm capable expressing in high precision. In contrast, an object which is outside of the fusional area is rendered by using an image generating algorithm which requires lighter calculation load than the former image generating algorithm.

A system for processing stereo matching of a video image sequence in a real-time mode. The system includes a signal converter for converting an image input from a first camera and a second camera into a digital signal; and an image matching clip for calculating a determined matching cost based on a pair of pixels in one scan line of the first and second digital image signals, tracing the decision value which determines the minimum matching cost, and outputting the decided value as an estimated disparity according to determined activation information; and a display for displaying the output from the image matching. According to the system, real-time stereo matching is enabled by parallel processing or video image sequences using an algorithm which is based on a new dynamic trellis based method and is optimal in the Bayesian sense.

Dynamic histogram warping is performed on histograms extracted from an image pair of a scene. The warped histograms are remapped to the image pair and the resulting remapped image pair is subsequently subjected to image processing.