The High-Speed Extraction of Interest Region in the Parcel Image of Large Size 


Vol. 11,  No. 3, pp. 691-702, Jun.  2004
10.3745/KIPSTD.2004.11.3.691


PDF
  Abstract

In this paper, we propose a sequence of method which extracts ROIs (Region of Interests) rapidly from the parcel image of large size. In the proposed method, original image is split into the small masks, and the meaningful masks, the ROIs, are extracted by two criterions sequentially. The first criterion is difference of pixel value between inner points, and the second is deviation of it. After processing, some informational ROIs-the areas of bar code, characters, label and the outline of object-are acquired. Using diagonal axis of each ROI and the feature of various 2D bar code, the area of 2D bar code can be extracted from the ROIs. From an experiment using above methods, various ROIs are extracted less than 200msec from large-size parcel image, and 2D bar code region is selected by the accuracy of 100%.

  Statistics


  Cite this article

[IEEE Style]

M. S. Park, S. E. Bak, I. S. Kim, H. K. Kim, H. K. Jung, "The High-Speed Extraction of Interest Region in the Parcel Image of Large Size," The KIPS Transactions:PartD, vol. 11, no. 3, pp. 691-702, 2004. DOI: 10.3745/KIPSTD.2004.11.3.691.

[ACM Style]

Moon Sung Park, Sang Eun Bak, In Soo Kim, Hye Kyu Kim, and Hoe Kyung Jung. 2004. The High-Speed Extraction of Interest Region in the Parcel Image of Large Size. The KIPS Transactions:PartD, 11, 3, (2004), 691-702. DOI: 10.3745/KIPSTD.2004.11.3.691.