Title :
An integrated preprocessing method on real estate file images recognition
Author :
Kuan Lin ; Jian-Qiao Yu ; Wen-Lan Geng ; Bin Liao
Author_Institution :
Sch. of Comput. & Inf. Sci., Southwest Univ., Chongqing, China
Abstract :
This paper proposes an effective image preprocessing chain for estate electron file to eliminate most of the effect of noise and enhance the recognition performance. Owing to its´ diversity and particularity, the processing of real estate file images is extremely significant compared with the general images´, so a integrated preprocessing chain is firstly applied for images of estate file .It includes image graying and binarization, the smoothing of the images, the removing of separate noise, image correcting and the effective image segmentation. The experimental result shows that this presented chain can effectively process the real estate file images according to its characteristic and achieve a high average precision.
Keywords :
document image processing; image recognition; image segmentation; real estate data processing; estate electron file; image binarization; image correction; image graying; image preprocessing chain; image recognition; image segmentation; image smoothing; real estate file image; separate noise removal; Feature extraction; Filtering; Image color analysis; Image recognition; Image segmentation; Noise; Transforms; Image Preprocessing; Image-Adjusting; Image-Correction; Image-Segmentation; Real Estate File;
Conference_Titel :
Mechatronic Science, Electric Engineering and Computer (MEC), 2011 International Conference on
Conference_Location :
Jilin
Print_ISBN :
978-1-61284-719-1
DOI :
10.1109/MEC.2011.6025951