Testing Visual Abilities of Machines - Visual Intelligence Tests

Authors: Zbigniew Les, Magdalena Les

Abstract:

Intelligence tests are series of tasks designed to measure the capacity to make abstractions, to learn, and to deal with novel situations. Testing of the visual abilities of the shape understanding system (SUS) is performed based on the visual intelligence tests. In this paper the progressive matrices tests are formulated as tasks given to SUS. These tests require good visual problem solving abilities of the human subject. SUS solves these tests by performing complex visual reasoning transforming the visual forms (tests) into the string forms. The experiment proved that the proposed method, which is part of the SUS visual understanding abilities, can solve a test that is very difficult for human subject.

Keywords: Shape understanding, intelligence test, visual concept, visual reasoning.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1062264

References:

[1] Colaruso, R., and Hammil, D., Motor Free Visual Perception Test. 2003, New York: Academic Therapy Publications.
[2] Gardener, M.F., Test of Visual-Perceptual Skills. 1996: Psychological and Educational Publicatios.
[3] Bhanu, B., and Faugeras, O.D., Shape Matching of Two-Dimensional Objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984. 6(2): p. 137-156.
[4] Lu, C.H., and Dunham, J.G., Shape Matching Using Polygon Approximation and Dynamic Alignment. Pattern Recognition Letters, 1993. 14: p. 945-949.
[5] He, Y., and Kundu, A., 2-D Shape Classification Using Hidden Markov Model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991. 13(11): p. 1172-1184.
[6] Kartikeayan, B., and Sarkar, A., Shape Description by Time Series. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989. 11(9): p. 977-984.
[7] Pal, N.R., Pal, P., and Basu, A.K., A New Shape Representation Scheme and Its Application to Shape Discrimination Using a Neural Network. Pattern Recognition, 1993. 26(4): p. 543-551.
[8] Pope, A.R., Model-based Object Recognition, a Survey of Recent Research. 1994, Department of Computer Science, The University of British Columbia.
[9] Les, Z., and Les, M., Shape Understanding System: Visual Intelligence Tests. International Journal of Intelligent Systems, 2005. 20(6): p. 1-28.
[10] Les, Z., Shape Understanding System: Understanding the thin object. An International Journal Computers and Graphics, 2002. 26(6): p. 951- 970.
[11] Les, Z., and Les, M., Shape Understanding system: Understanding of the Convex Objects. The Journal of Electronic Imaging, 2003. 12(2): p. 327-341.
[12] Les, Z., and Les, M., Understanding of a Concave Polygon Object in Shape Understanding System. Journal of Computer and Graphics, 2005. 29(3): p. 365-378.
[13] Les, Z., and Les, M., Shape Understanding System: Understanding of the Complex Object. The Journal of Electronic Imaging (in print), 2005. 14(2).
[14] Les, Z., and Les, M., Shape Understanding System-the System of Experts. International Journal of Intelligent Systems, 2004. 19(10): p. 949-978.