This paper demonstrates a new approach towards object recognition founded on the development of Neural Network classifiers and Bayesian Networks. The mapping from segmented image region descriptors to semantically meaningful class membership terms is achieved using Neural Networks. Bayesian Networks are then employed to probabilistically detect objects within an image by means of relating region class labels and their surrounding environments. Furthermore, it makes use of an intermediate level of image representation and demonstrates how object recognition can be achieved in this way.
|Title of host publication||Vision, video, and graphics 2005: University of Edinburgh July 7-8th, 2005|
|Place of Publication||Aire-la-Ville|
|Publisher||Eurographics: European Association for Computer Graphics|
|Number of pages||8|
|Publication status||Published - 2005|
|Event||2nd International Conference on Video, Vision and Graphics, VVG 2005 - Edinburgh, UK United Kingdom|
Duration: 7 Jul 2005 → 8 Jul 2005
|Conference||2nd International Conference on Video, Vision and Graphics, VVG 2005|
|Country||UK United Kingdom|
|Period||7/07/05 → 8/07/05|
Song, Y. Z., & Town, C. P. (2005). Visual recognition of man-made materials and structures in an office environment. In Vision, video, and graphics 2005: University of Edinburgh July 7-8th, 2005 (pp. 159-166). Eurographics: European Association for Computer Graphics.