Structure-guided image processing and image feature enhancement

• US 6,463,175 B1
• Filed: 12/15/2000
• Issued: 10/08/2002
• Est. Priority Date: 12/15/2000
• Status: Expired due to Term

• Current Assignee: Leica Microsystems Gmbh (Danaher Corporation)
• Original Assignee: Shih-Jong J. Lee
• Inventors: Lee, Shih-Jong J.
• Primary Examiner(s): Lee, Thomas D
• Assistant Examiner(s): Brinich, Stephen
• Application Number:
  US09/738,846
• Publication Number:
  US 20020076105A1
• Time in Patent Office: 662 Days
• Field of Search: 382/191-194, 382/199-200, 382/266-269
• US Class Current: 382/190
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/155 involving morphological operators
• CPC Class Codes: G06V 10/34 Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components

Abstract

A structure guided image processing system uses geometric structure information to guide image feature extraction and enhancement of an input image to produce a weight image output and a mask image output. Geometric structure information may be apparent in the nature of the images, or it can in many cases be derived from CAD information. Idempotent processing and filtering operations minimize image distortion. Directional elongated structuring elements provide structure-guided selective processing and high speed filtering throughput.

Claims

1. A structure-guided image feature enhancement system comprising:

a. an input image;

b. a plurality of structuring elements selected according to feature structures to be enhanced;

c. order the plurality of structuring elements by increasing size;

d. an increasing idempotent processing sequence operates on the input image to enhance features using the ordered plurality of structuring elements.

2. The system of claim 1 wherein the plurality of structuring elements includes directional elongated structuring elements.

3. The system of claim 1 wherein the idempotent processing sequence includes morphological opening followed by closing operations.

4. The system of claim 1 wherein the idempotent processing sequence includes morphological closing followed by opening operations.

5. A structure-guided image processing system comprising:

a. a structure-guided image feature enhancement module having an image input and having a feature enhanced image output, wherein the feature enhancement module uses idempotent processing;

b. a mask generation module that is connected to the enhanced image output having a mask image output;

c. a weight generation module connected to the structure guided image feature enhancement output having a weight image output.

6. A structure-guided image processing system comprising:

a. a structure-guided image feature enhancement module having an image input and having a feature enhanced image output, wherein the feature enhancement module uses nonlinear filtering methods;

b. a mask generation module that is connected to the enhanced image output having a mask image output;

c. a weight generation module connected to the structure guided image feature enhancement output having a weight image output.

7. A structure-guided image processing system comprising:

a. a structure-guided image feature enhancement module having an image input and having a feature enhanced image output;

b. a mask generation module that is connected to the enhanced image output having a mask image output, wherein the mask generation module further comprises;

i. an image thresholding module;

ii. a connected component labeling module

c. a weight generation module connected to the structure guided image feature enhancement output having a weight image output.