Affine-Invariant Recognition of Gray-Scale Characters Using Global Affine Transformation Correlation
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
This paper introduces a new technique of affine-invariant correlation of gray-scale characters by reinforcing correlation-based matching in two ways. First is the use of normalized cross-correlation as matching measure based on definite canonicalization to realize robustness against image degradation. Second is the application of iterative global affine transformation (GAT) to the input image so as to realize the maximal affine-invariant correlation with the target image. The advantages and effectiveness of the proposed method are both shown theoretically and demonstrated through preliminary experiments using gray-scale images of numerals subject to a wide range of affine transformation and random Gaussian noise.