A Method of Construction Invariant Features for AI Image Analysis Systems

Abstract

The invariant recognition of shapes under affine distortion and translation requires the use of invariant descriptors under these distortions. This paper is concerned with the definition of classes of such features which are appropriate for the description of 2D shapes and could be used for problems like character recognition, even for cases where the characters are very complex like Chinese characters, for example. As we are concerned with the problem of classes of features as opposed to individual features themselves, we are in position to propose very large numbers of features that belong to these classes. These features do not necessarily have a straight forward geometric interpretation as they are derived algebraically. Therefore it is difficult to investigate their usefulness theoretically , so they have to be analyzed by AI systems before being used for Pattern Recognition.