Presentation is loading. Please wait.

Presentation is loading. Please wait.

Word Recognition Using Fuzzy Logic 作者: R. Buse, Z. Liu, and J. Bezdek 報告人:余家豪.

Similar presentations


Presentation on theme: "Word Recognition Using Fuzzy Logic 作者: R. Buse, Z. Liu, and J. Bezdek 報告人:余家豪."— Presentation transcript:

1 Word Recognition Using Fuzzy Logic 作者: R. Buse, Z. Liu, and J. Bezdek 報告人:余家豪

2 The offline recognition of handwritten cursive word Segment the word into its character parts. Word-based.

3 Word-based approach ’ s challenges The complexity more greater. Have lower discrimination capabilities. It is usually restricted to few word groups.

4 How to extract word feature ? First step: Slant and Tilt Correction Second step: Using Gabor filter Third step: Word Alignment

5 Two-dimensional (2-D) fuzzy membership function Use to represent both sizes and positions of the extracted word feature.

6 First step: Slant and Tilt Correction Silver Vegas

7 Second step: Using Gabor filter The extracted feature image Angle of Gabor filter Ø=90°

8 Third step: Word Alignment(1) K-means clustering algorithm ( Centroids ) The horizontal and vertical Alignment points Formula

9 Third step: Word Alignment(2) Using alignment points to transform the extracted feature images into a standard data structure of aligned image features.

10 How to form fuzzy membership function ? First step: Composite aligned images Second step: Determine threshold points Third step: Corner point Correspondences Fourth step: Membership Value

11 First step: Composite aligned images Baton (a) (f)(e)(d) (c)(b) (g) - R ij

12 Second step: Determine threshold points C u = 0.25 C l = 0.1 H uij : upper threshold point H lij : lower threshold point Rij Found boundary

13 Third step: Corner point Correspondences C: set of valid combination pairs (i,j) (24 possible combinations) T: top rectangle point B: bottom rectangle point || · || distance between the two corners The side of the Membership function

14 Fourth step: Membership Value 2-D membership function μ(x,y): memebership value at point (x,y)

15 Matching test words to the membership function ( at Ø=90° )


Download ppt "Word Recognition Using Fuzzy Logic 作者: R. Buse, Z. Liu, and J. Bezdek 報告人:余家豪."

Similar presentations


Ads by Google