Abstract | ||
---|---|---|
The existing skew estimation techniques usually assume that the input image is of high resolu- tion and that the detectable angle range is limited. We present a more generic solution for this task that over- comes these restrictions. Our method is based on deter- mination of the rst eigenvector of the data covariance matrix. The solution comprises image resolution reduc- tion, connected component analysis, component classi- cation using a fuzzy approach, and skew estimation. Experiments on a large set of various document images and performance comparison with two Hough transform- based methods show a good accuracy and robustness for our method. |
Year | DOI | Venue |
---|---|---|
1999 | 10.1007/s100320050043 | IJDAR |
Keywords | Field | DocType |
image resolution,eigenvectors,hough transform,covariance matrix,image processing,connected component | Pattern recognition,Computer science,Fuzzy logic,Hough transform,Image processing,Robustness (computer science),Artificial intelligence,Covariance matrix,Connected-component labeling,Image resolution,Eigenvalues and eigenvectors | Journal |
Volume | Issue | Citations |
2 | 2-3 | 14 |
PageRank | References | Authors |
1.22 | 29 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Oleg Okun | 1 | 308 | 28.56 |
Matti Pietikäinen | 2 | 14779 | 739.80 |
Jaakko J. Sauvola | 3 | 451 | 44.31 |