In this paper a new method of arc detection based on arithmetic discrete lines is presented. Key points are extracted from such a profile and used for the reconstruction. The used method is fast and easy to implement. Experimental studies on several series of test images show the stability and the robustness of the proposed method.
Ancient graphical documents are invaluable heritages which have been handed down since generations. They possess both intellectual and spiritual worth for humanity. In this context, many digitization processes have been started, producing very large warehouse of images. These huge amount of data raise the problem of indexing the information in order to make easier navigation in the databases. In the context of a French research program, called MADONNE, this paper proposes a set of complementary contributions concerning ancient graphic images indexing.
In this paper a genetic matching scheme is extended to take into account primitive arcs and complex description in the pattern recognition process. Classical ways only focus on segments and are sensitive to over segmentation effect. Our approach allows to improve the recognition by handling more accurate description and also to decrease processing time by limiting the number of vertices to match. Experimental studies using real data attest the robustness of our approach.
This paper deals with a complex symbol recognition process considering a large number of classes and only one training image per class. Furthermore, the response times of recognition system should be short and the interpretation of results must be easy. In this particular case, both statistical and structural methods are not the most suitable. A new composite descriptor and a similarity measure are proposed. Experimental results show the proposed method outperforms two descriptors widely used in symbol recognition with industrial data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.