Abstract | ||
---|---|---|
In order to increase the performance of document analysis systems a detailed quality evaluation of the achieved results is required. By focussing on segmentation algorithms, we point out that the results produced by the module under consideration should be evaluated directly; we will show that the text-based evaluation method which is often used in the document analysis domain does not accomplish the purpose of a detailed quality evaluation. Therefore, we propose a general evaluation approach for the comparison of segmentation results which is based on the segments directly. This approach is able to handle both algorithms that produce complete segmentations (partition) and algorithms that only extract objects of interest (extraction). Classes of errors are defined in a systematic way, and frequencies for each class can be computed. The evaluation approach is applicable to segmentation or extraction algorithms in a wide range. We have chosen the character segmentation task as an example in order to demonstrate the applicability of our evaluation approach, and we suggest to apply our approach to other segmentation tasks. |
Year | DOI | Venue |
---|---|---|
1998 | 10.1007/3-540-48172-9_5 | Document Analysis Systems |
Keywords | Field | DocType |
segmentation algorithm,general approach,segmentation task,character segmentation task,evaluation approach,detailed quality evaluation,document segmentation results,segmentation result,general evaluation approach,quality evaluation,complete segmentation,document analysis domain,text-based evaluation method | Document analysis,Scale-space segmentation,Computer science,Document Structure Description,Handwriting recognition,Segmentation-based object categorization,Image segmentation,Real-time computing,Artificial intelligence,Computer vision,Pattern recognition,Segmentation,Ground truth | Conference |
Volume | ISSN | ISBN |
1655 | 0302-9743 | 3-540-66507-2 |
Citations | PageRank | References |
9 | 1.42 | 9 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael Thulke | 1 | 14 | 3.45 |
Volker Märgner | 2 | 295 | 29.02 |
Andreas Dengel | 3 | 1926 | 280.42 |