Postal Envelope Segmentation by 2-D Histogram Clustering through Watershed Transform

Authors:
Eduardo Akira Yonekura;Jacques Facon
Affiliations:
-;-
Venue:
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Year:
2003

Citing 6
Cited 1

Automatic thresholding of gray-level pictures using two-dimensional entropy

Computer Vision, Graphics, and Image Processing
On the color image segmentation algorithm based on the thresholding and the fuzzy C-means techniques

Pattern Recognition
A color clustering technique for image segmentation

Computer Vision, Graphics, and Image Processing
Multiresolution Color Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Abnormality Detection in Automated Mass Screening System of Diabetic Retinopathy

CBMS '01 Proceedings of the Fourteenth IEEE Symposium on Computer-Based Medical Systems
Histogram-based segmentation in a perceptually uniform color space

IEEE Transactions on Image Processing

Segmentation of Chinese Postal Envelope Images for Address Block Location

ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a new postal envelope segmentationmethod based on 2-D histogram clustering and watershedtransform. Segmentation task consists in detectingthe modes associated with homogeneous regions in envelopeimages such as handwritten address block, postmarks,stamps and background. The homogeneous modes in 2-Dhistogram are segmented through the morphological watershedtransform. Our approach is applied to complex Brazilianpostal envelopes. Very little a priori knowledge of theenvelope images is required. The advantages of this approachwill be described and illustrated with tests carriedout on 300 different images where there are no fixed positionfor the handwritten address block, postmarks and stamps.