A proposal of smart means to retrieve impressively-referred document-page

Author(s):  
Toyohide Watanabe
Keyword(s):  
1981 ◽  
Vol 86 ◽  
pp. 248-273 ◽  
Author(s):  
Michel Korzec ◽  
Martin King Whyte

These reading notes are based upon an initial close reading of an important compilation of documents on the Chinese wage and fringe benefit system previously unavailable in the west and entitled Laodong Gongzi Wenjian Xuanbian (Selected Documents on Labour Wages; cited hereafter as LGWX: date of original document: page number). This volume is over 700 pages long, contains more than 390 documents and regulations on wages and fringe benefits spanning the years 1949 to 1973, and was published in 1973 by the Planning Commission of the Fujian Provincial Revolutionary Committee. The introduction states that some of the documents were included for historical reference only, but most were still being applied in 1973 and thereafter. In this respect it is interesting to note that over half of the documents included were issued in the years 1962–65. Furthermore, although published in Fujian, the great majority of the documents (over 300) were not issued in that province, but by national authorities, particularly the State Council, the Ministry of Labour and the Ministry of Internal Affairs. Some of the documents included, such as those on the 1956 wage reforms, labour insurance regulations, and holidays and holiday travel leaves, have previously been available in openly-published documents.


Author(s):  
X. Dong ◽  
P. Majewicz ◽  
G. McNutt ◽  
C. Bouman ◽  
J. Allebach ◽  
...  

Author(s):  
SANJOY PRATIHAR ◽  
PARTHA BHOWMICK ◽  
SHAMIK SURAL ◽  
JAYANTA MUKHOPADHYAY

Skew correction of a scanned document page is an important preprocessing step in document image analysis. We propose here a fast and robust skew estimation algorithm based on rank analysis in Farey sequence. Our target document class comprises two major Indian scripts with headlines, namely Devnagari and Bangla. At the beginning, straight edge segments from the edge map of the document page are detected by our algorithm using properties of digital straightness. Straight edges derived in this manner are binned by Farey ranks in correspondence with their slopes. The principal bin, identified from these bins using the strength of accumulated edge points, represents the principal direction along the direction of headlines, from which the gross skew angle is estimated. A fast refinement algorithm is then applied with a finer tuning of Farey ranks, to detect the skew up to the desired level of precision. The algorithm has been tested on a diverse set of document images, containing Bangla and Devnagari scripts. Experimental results are quite encouraging in terms of accuracy, sensitivity to non-textual objects, effectiveness in dealing with unrestricted layouts, and computational efficiency.


Sign in / Sign up

Export Citation Format

Share Document