Abstract
The goal of computer vision is to derive descriptive information about a scene by computer analysis of images of the scene. Vision algorithms can often serve as computational models for biological visual processes, and they also have many practical uses; but this paper treats computer vision as a subject in its own right. Vision problems are often ill-defined, ill-posed, or computationally intractable; nevertheless, successes have been achieved in many specific areas — document processing and industrial inspection, for example. We suggest that by limiting the domain of application, carefully choosing the task, using redundant data (multi-sensor, multi-frame), and applying adequate computing power, useful solutions to many vision problems can be obtained. Methods of designing such solutions are the subject of the emerging discipline ofvision engineering. With projected advances in sensor and computing technologies, the domains of applicability and ranges of problems that can be solved will gradually expand.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aloimonos J, Shulman D 1989Integration of visual modules: An extension of the Marr paradigm (Boston: Academic Press)
Aloimonos J, Weiss I, Bandhopadhay A 1987 Active vision.Int. J. Comput. Vision 1: 333–356
Dickmanns E D, Graefe V 1988a Dynamic monocular machine vision.Mach. Vision Appl. 1: 223–240
Dickmanns E D, Graefe V 1988b Applications of dynamic monocular machine vision.Machine Vision Appl. 1: 241–261
Grimson W E L 1990Object recognition by computer Cambridge, ma: (Mit Press) chap. 10
Jain R 1988 Perception engineering.Mach. Vision Appl. 1: 73–74
Kirousis L M, Papadimitriou C H 1988 The complexity of recognizing polyhedral scenes.J. Comput. Syst. Sci. 37: 14–38
Leclerc Y C 1989 Constructing simple stable descriptions for image partitioning.Int. J. Comput. Vision 3: 73–102
Mead C 1989Analog VLSI and neural systems (Reading, MA: Addison-Wesley)
Nandhakumar N, Aggarwal J K 1988 Integrated analysis of thermal and visual images for scene interpretations.IEEE Trans. Pattern Anal. Mach. Intell. PAMI-10: 469–481
Okutomi M, Kanade T 1991 A multiple-baseline stereo.Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, (Miami) (New York: IEEE Press
Oliensis J 1991 Uniqueness in shape from shading.Int. J. Comput. Vision 6: 75–104
Oliensis J 1992 Direct method for reconstructing shape from shading.Proc. DARPA Image Understanding Workshop, (San Diego)
Poggio T, Torre V, Koch C 1985 Computational vision and regularization theory.Nature (London) 317: 214–319
Prasanna Kumar V K 1991Parallel architectures and algorithms for image understanding (New York: Academic Press)
Schick J, Dickmanns E D 1991 Simultaneous estimation of 3D shape and motion of objects by computer vision.IEEE Workshop on Visual Motion, (Princeton) (New York: IEEE Press
Sharma R, Aloimonos J 1991 Robust detection of independent motion: An active and purposive solution, Center for Automation Research Technical Report CAR-tr-354, University of Maryland, College Park, md
Terzopoulos D 1986 Regularization of inverse visual problems involving discontinuities.IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8: 413–426
Tikhonov A N, Arsenin V Y 1977Solution of ill-posed problems (New York: Winston)
Wildey R L 1984 Topography from a single radar image.Science 224: 153–156
Woodham R J 1989 Photometric method for determining surface orientation from multiple images. InShape from shading (eds) B K P Horn, M J Brooks (Cambridge, MA): MIT Press
Zheng Q, Chellappa R 1991 Estimation of illuminant direction, albedo and shape from shading.IEEE Trans. Pattern Anal. Mach. Intell. PAMI-13: 680–702
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Chellappa, R., Rosenfeld, A. Current issues in computer vision. Sadhana 18, 149–158 (1993). https://doi.org/10.1007/BF02742655
Issue Date:
DOI: https://doi.org/10.1007/BF02742655