Image analysis – Pattern recognition – Feature extraction
Patent
1996-08-01
1999-07-13
Shalwala, Bipin H.
Image analysis
Pattern recognition
Feature extraction
382173, 382199, 382245, 382254, 382276, 382282, G06K 934, G06K 936, G06K 940, G06K 946
Patent
active
059237821
ABSTRACT:
There is provided a method for detecting horizontal and vertical lines of an encoded run length image to identify cells of the image that are formed by the lines. Initially, the method comprises the steps of filtering excess details, such as text, from the image and grouping a portion of the image for analysis. A top profile of the image is generated and, then, points along the top profile are determined where substantial changes in the profile position occur. A horizontal section of the top profile which corresponds to a line completely visible from the top is then extracted from between the points. By repeating the above steps, each horizontal line of the image is detected and extracted from the image. In addition, in order to detect the vertical lines of the image, the image is simply rotated 90.degree. and processed with the vertical lines being positioned horizontally. By identifying the horizontal and vertical lines of the image, the cells of the original image may be identified, and the contents of each cell may be processed by optical character recognition techniques and the like.
REFERENCES:
patent: 3069654 (1962-12-01), Hough
patent: 4821336 (1989-04-01), Roye
patent: 4849911 (1989-07-01), Campian
patent: 5572602 (1996-11-01), Naoi et al.
patent: 5636297 (1997-06-01), Eller et al.
patent: 5680471 (1997-10-01), Kanebako et al.
Manesh, et al "Automatic Vectorization of Scanned Engineering Drawings," IEEE, pp. 320-324, Sep. 1990.
Arias, et al "Efficient Techniques for Telephone Company Line Drawing Interpretation," IEEE, Sep. 1995.
Arias, et al "Information Extraction From Telephone Company Drawings," IEEE, 1994.
"A Benchmark: Performance Evaluation of Dashed-Line Detection Algoritum", by Kong et al.,First Int. Workshop Aug. 10-11, 1995.
"Detection of Horizontal lines in Noisy Run Length Encoded Images," by Chhabra et al, Aug. 10-11, 1995.
"Orthogonal Zig-Zag: An Efficient Method for Extracting Straight Lines From Engineering Drawings" by I.Chai & D.Dori, Visual Form: Analysis and Recognition, pp. 127-136.
"Sparse-pixel Recognition of Primitives in Engineering Drawings"by D.Dori, Y.Liang, J.Dowell, and I.Chai, Machine Vision and Applications, pp. 69-82.
"Fast Detection of Horizontal Lines in Telephone Company Drawings" by A.K. Chhabra, S. Surya and V. Misra, First International Workshop on Graphics Recognition.
"Detection of Horizontal Lines in Noisy Run Length Encoded Images: The Fast Method" by A. Chhabra, V. Misra and Juan Arias, Graphics Recognition: Method & Applications, pp. 35-48.
Chhabra Atul K.
Misra Vishal
Surya Surekha
Mariam Daniel G.
NYNEX Science & Technology, Inc.
Shalwala Bipin H.
LandOfFree
System for detecting and identifying substantially linear horizo does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System for detecting and identifying substantially linear horizo, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System for detecting and identifying substantially linear horizo will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2284520