A word shape coding method for camera-based document images

ABSTRACT

This paper reports a word shape coding method to facilitate retrieval of camera-based document images without OCR. Due to perspective distortion, many reported word shape coding methods fail on camera-based images. In this paper, the problem is addressed by approximating the perspective transformation with an affine transformation, and employing an affine invariant, namely length ratio, to represent the connected components. Components in a document image are classified into a few clusters, each of which is assigned with a representative symbol. Retrieval are based on "words" comprising of symbols. The experiment results showed that the proposed method achieved an average retrieval precision of 93.43% and recall of 94.22%.

REFERENCES

• 1: David Doermann, The indexing and retrieval of document images: a survey, Computer Vision and Image Understanding, v.70 n.3, p.287-298, June 1, 1998 [doi>10.1006/cviu.1998.0692]
• 2: C. Gope , N. Kehtarnavaz, Affine invariant comparison of point-sets using convex hulls and hausdorff distances, Pattern Recognition, v.40 n.1, p.309-320, January, 2007 [doi>10.1016/j.patcog.2006.04.026]
• 3: L. O'Gorman, The Document Spectrum for Page Layout Analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.15 n.11, p.1162-1173, November 1993 [doi>10.1109/34.244677]
• 4: Yue Lu , Chew Lim Tan, Information Retrieval in Document Image Databases, IEEE Transactions on Knowledge and Data Engineering, v.16 n.11, p.1398-1410, November 2004 [doi>10.1109/TKDE.2004.76]
• 5: Chew Lim Tan , Weihua Huang , Zhaohui Yu , Yi Xu, Imaged Document Text Retrieval Without OCR, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.24 n.6, p.838-844, June 2002 [doi>10.1109/TPAMI.2002.1008389]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.1 Content Analysis and Indexing

General Terms:
Algorithms

Keywords:
document image retrieval, perspective distortion