INFORMys: A Flexible Invoice-Like Form-Reader System
IEEE Transactions on Pattern Analysis and Machine Intelligence
Using Character Shape Coding for Information Retrieval
ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
The Detection of Duplicates in Document Image Databases
ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
Fast Winner-Takes-All Networks for the Maximum Clique Problem
KI '02 Proceedings of the 25th Annual German Conference on AI: Advances in Artificial Intelligence
Document Image Layout Comparison and Classification
ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
Features for Word Spotting in Historical Manuscripts
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
A Segmentation-free Approach for Keyword Search in Historical Typewritten Documents
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
| Hi-index | 0.00 |
This paper presents a new approach which allows similarity measurement between documents using a compact image based feature representation. Various applications, in particular document management systems, require the comparison of scanned documents for their classification. The proposed method focuses on mail piece identification within the postal sorting process. Generally, mail pieces resemble in their structure and differ in text regions. Concentration on structural text region features and text line profiles exploits these differences. An attributed relational graph representation is used to combine detailed local information with rough layout information of a document. This method is designed to comply with the strong requirements for postal sorting machines. In particular this approach is invariant towards document rotation, translation and towards document surface modifications caused by mail piece handling and transportation. Efficient algorithms allow its usage in a real time environment. The quality and applicability for mail piece identification has been proven in various tests.