A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Design and Use of Steerable Filters
IEEE Transactions on Pattern Analysis and Machine Intelligence
An Unbiased Detector of Curvilinear Structures
IEEE Transactions on Pattern Analysis and Machine Intelligence
Content-Based Retrieval of Historical Watermark Images: I-tracings
CIVR '02 Proceedings of the International Conference on Image and Video Retrieval
Content-based retrieval of historical watermark images: II - electron radiographs
CIVR'03 Proceedings of the 2nd international conference on Image and video retrieval
Paper retrieval based on specific paper features: chain and laid lines
MRCS'06 Proceedings of the 2006 international conference on Multimedia Content Representation, Classification and Security
| Hi-index | 0.00 |
A watermark in a piece of paper is an important source of information to determine the dating of artworks. Identical watermarks are used in the same period, that makes watermark research a search problem. In order to automate the search process watermarks should be detected in X-ray images of paper. This is a difficult detection problem, because of the large amount of noise in these images. We propose an integrated framework to detect watermarks by exploiting the following four line properties: line profile, line contrast, spatial connectivity and line length. The parametrization of the framework is trained by minimizing an error definition, which is learnt from seven watermark experts by means of a poll. The proposed approach permits to select the optimal parameters according to the visual perception of watermark experts.