Visual appearance based document image classification

In the paper, we present a new method for classifying documents with rigid geometry. Our approach is based on the fast and robust Viola-Jones object detection algorithm. The advantages of our proposed method are high speed, the possibility of automatic model construction using a training set, and pr...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2010 IEEE International Conference on Image Processing s. 2133 - 2136
Hlavní autoři: Usilin, Sergey, Nikolaev, Dmitry, Postnikov, Vassili, Schaefer, Gerald
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.09.2010
Témata:
Algorithm design and analysis
Classification algorithms
Document classification
Face detection
form identification
Insurance
Object detection
Pensions
Training
ISBN:9781424479924, 1424479924
ISSN:1522-4880
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In the paper, we present a new method for classifying documents with rigid geometry. Our approach is based on the fast and robust Viola-Jones object detection algorithm. The advantages of our proposed method are high speed, the possibility of automatic model construction using a training set, and processing of raw source images without any pre-processing steps such as draft recognition, layout analysis or binarisation. Furthermore, our algorithm allows not only to classify documents, but also to detect the placement and orientation of documents within an image.
ISBN:9781424479924
1424479924
ISSN:1522-4880
DOI:10.1109/ICIP.2010.5652024