Title :
WISDOM++: an interactive and adaptive document analysis system
Author :
Altamura, Oronzo ; Esposito, Floriana ; Malerba, Donato
Author_Institution :
Dipt. di Inf., Bari Univ., Italy
Abstract :
WISDOM++ is a document analysis system whose main design requirements are real-time user interaction and adaptivity. This paper presents the two-phased skew estimation algorithm and the adaptive document block segmentation and classification techniques. An evaluation of the performance of some of these tasks is also conducted according to a benchmarking procedure
Keywords :
adaptive systems; document image processing; image classification; image segmentation; optical character recognition; real-time systems; software performance evaluation; text analysis; WISDOM++; adaptive document analysis system; adaptive document block classification; adaptive document block segmentation; benchmarking procedure; interactive document analysis system; performance evaluation; real-time user adaptivity; real-time user interaction; two-phased skew estimation algorithm; Adaptive systems; Classification tree analysis; Decision trees; Graphics; Machine learning; Optical character recognition software; Performance analysis; Real time systems; Text analysis; Text recognition;
Conference_Titel :
Document Analysis and Recognition, 1999. ICDAR '99. Proceedings of the Fifth International Conference on
Conference_Location :
Bangalore
Print_ISBN :
0-7695-0318-7
DOI :
10.1109/ICDAR.1999.791800
