Using a neural net to instantiate a deformable model

Christopher K.I. Williams, Michael Revow, Geoffrey E Hinton

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Deformable models are an attractive approach to recognizing nonrigid objects which have considerable within class variability. However, there are severe search problems associated with fitting the models to data. We show that by using neural networks to provide better starting points, the search time can be significantly 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 fitting each model to an image is very computationally intensive, because there is no efficient 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 fitting models to data to obtain better starting points that significantly reduce the search time. 
Original languageEnglish
Title of host publicationAdvances in neural information processing systems
Number of pages8
Publication statusPublished - 1995


Dive into the research topics of 'Using a neural net to instantiate a deformable model'. Together they form a unique fingerprint.

Cite this