Skip to main content
SpringerLink
Log in

Correcting for variable skew in document images

  • Published:
Document Analysis and Recognition Aims and scope Submit manuscript

Abstract.

The proliferation of inexpensive sheet-feed scanners, particularly in fax machines, has led to a need to correct for the uneven paper feed rates during digitization if the images produced by these scanners are to be further analyzed. We develop a technique for detecting and compensating for this type of image distortion. This technique relies on the detection of multiple prominent skew angles in the document image along with their vertical position on the page, rotating the image by each of those angles and sampling the rotated images to allow reconstruction of the entire page image.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Antonacopoulos A (1997) Local skew angle estimation from background space in text regions. Proceedings of the international conference on document analysis and recognition, Ulm, Germany, 18-20 Aug 1997, pp 684-688

  2. Bagdanov AD, Kanai J (1996) Evaluation of document image skew estimation techniques. SPIE, San Jose, 29-30 January 1996, pp 343-353

  3. Baird HS (1987) The skew angle of printed documents. Proceedings of the SPSE symposium on hybrid imaging systems, Rochester, NY, pp 21-24

  4. Baird HS (1992) Document image defect models. In: Baird HS, Bunke H, Yamamoto K (eds) Structured document image analysis. Springer, Berlin Heidelberg New York, pp 546-556

  5. Hunter R, Robinson AH (1980) International digital facsimile coding standards. Proc IEEE 68(7):854-867

    Google Scholar 

  6. Kanungo T, Haralick R, Phillips I (1993) Global and local document degradation models. Proceedings of the international conference on document analysis and recognition, Tsukuba Science City, Japan, 20-22 October 1993, pp 730-734

  7. Paeth AW (1986) A fast algorithm for general raster rotation. Graphics Interface ‘86, May 1986, pp 77-81

  8. Spitz AL (1998) Analysis of compressed document images for dominant skew, multiple skew and logotype detection. Comput Vis Image Understand 70(3):321-334

    Google Scholar 

  9. Spitz AL (1992) Skew determination in CCITT Group 4 compressed images. Proceedings of the symposium on document analysis and information retrieval, Las Vegas, 16-18 March 1992, pp 11-25

Download references

Author information

Authors and Affiliations

  1. DocRec Ltd, 34 Strathaven Place, 7001, New Zealand

    A. Lawrence Spitz

Authors
  1. A. Lawrence Spitz
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to A. Lawrence Spitz.

Additional information

Received: 28 November 2002, Accepted: 16 April 2003, Published online: 12 September 2003

Correspondence to: A. Lawrence Spitz

Rights and permissions

Reprints and permissions

About this article

Cite this article

Spitz, A.L. Correcting for variable skew in document images. IJDAR 6, 192–200 (2003). https://doi.org/10.1007/s10032-003-0109-9

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10032-003-0109-9

Keywords:

Search

Navigation