A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pseudo one pass thinning algorithm
Pattern Recognition Letters
Treatment of Diagrams in Document Image Analysis
Diagrams '00 Proceedings of the First International Conference on Theory and Application of Diagrams
Bar Charts Recognition Using Hough Based Syntactic Segmentation
Diagrams '00 Proceedings of the First International Conference on Theory and Application of Diagrams
Random Subwindows for Robust Image Classification
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Region based image annotation through multiple-instance learning
Proceedings of the 13th annual ACM international conference on Multimedia
Real-time computerized annotation of pictures
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Chart Image Classification Using Multiple-Instance Learning
WACV '07 Proceedings of the Eighth IEEE Workshop on Applications of Computer Vision
Automated analysis of images in documents for intelligent document search
International Journal on Document Analysis and Recognition
The WEKA data mining software: an update
ACM SIGKDD Explorations Newsletter
Recognition and classification of figures in PDF documents
GREC'05 Proceedings of the 6th international conference on Graphics Recognition: ten Years Review and Future Perspectives
Image classification by a two-dimensional hidden Markov model
IEEE Transactions on Signal Processing
Support vector machines for histogram-based image classification
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
Recognition and classification of charts is an important part of analysis of scientific and financial documents. This paper presents a novel model-based method for classifying images of charts. Particularly designed chart edge models reflect typical shapes and spatial layouts of chart elements for different chart types. The classification process consists of two stages. First, chart location and size are predicted based on the analysis of color distribution in the input image. Second, a set of image edges is extracted and matched with the chart edge models in order to find the best match. The proposed approach was extensively tested against the state-of-the-art supervised learning methods and showed high accuracy, comparable to that of the best supervised approaches. The proposed model-based approach has several advantages: it doesn't require supervised learning and it uses the high-level features, which are necessary for further steps of data extraction and semantic interpretation of chart images.