Using a neural net to instantiate a deformable model

Deformable models are an attractive approach to recognizing nonrigid objects which have considerable within class variability. However, there are severe search problems associated with tting the models to data. We show that by using neural networks to provide better starting points, the search time can be signi cantly reduced. The method is demonstrated on a character recognition task. In previous work we have developed an approach to handwritten character recognition based on the use of deformable models Hinton, Williams and Revow, 1992a; Revow, Williams and Hinton, 1993. We have obtained good performance with this method, but a major problem is that the search procedure for tting each model to an image is very computationally intensive, because there is no e cient algorithm like dynamic programming for this task. In this paper we demonstrate that it is possible to compile down" some of the knowledge gained while tting models to data to obtain better starting points that signi c...

• Type: Conference
• Year: 1994
• Where: NIPS
• Authors: Christopher K. I. Williams, Michael Revow, Geoffrey E. Hinton
• Keywords: Better Starting Points, Character Recognition, Deformable Models, NIPS 1994, NIPS 2007