Title :
Postal address block location by contour clustering
Author :
Govindaraju, Venu ; Tulyakov, Sergey
Author_Institution :
Dept. of Comput. Sci. & Eng., UB Commons, Amherst, NY, USA
Abstract :
We have developed a well performing algorithm for locating address blocks in postal parcel images. Both machine printed and handwritten addresses are processed by the algorithm. The algorithm is invariant to the image orientation and scale, and it works with high noise images. It could also serve as an additional step after other address block location algorithms.
Keywords :
algorithm theory; feature extraction; grammars; handwritten character recognition; image denoising; mailing systems; optical character recognition; postal services; connected components; contour clustering; feature extraction; handwritten address; machine printed address; mail delivery; mail sorting; noise images; postal address block location; postal parcel images; Algorithm design and analysis; Character recognition; Clustering algorithms; Feature extraction; Graphics; Image analysis; Image segmentation; Postal services; Text analysis; Venus;
Conference_Titel :
Document Analysis and Recognition, 2003. Proceedings. Seventh International Conference on
Print_ISBN :
0-7695-1960-1
DOI :
10.1109/ICDAR.2003.1227703
