System for generalizing objects and features in an image

• US 6,404,920 B1
• Filed: 11/13/1997
• Issued: 06/11/2002
• Est. Priority Date: 09/09/1996
• Status: Expired due to Term

• Current Assignee: Shin-Yi Hsu
• Original Assignee: Shin-Yi Hsu
• Inventors: Hsu, Shin-yi
• Primary Examiner(s): Couso, Jose L.
• Assistant Examiner(s): Do, Anh Hong
• Application Number:
  US08/969,986
• Time in Patent Office: 1,671 Days
• Field of Search: 382/190, 382/294
• US Class Current: 382/190
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/143 involving probabilistic approaches, e.g. Markov random field [MRF] modelling
• CPC Class Codes: G06T 7/187 involving region growing; involving region merging; involving connected component labelling
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 10/754 involving a deformation of the sample pattern or of the reference pattern; Elastic matching
• CPC Class Codes: G06V 20/00 Scenes; Scene-specific elements control of digital cameras H04N23/60
• CPC Class Codes: G06V 20/13 Satellite images
• CPC Class Codes: G06V 20/64 Three-dimensional objects

Abstract

The present invention features the use of the fundamental concept of color perception and multi-level resolution to perform scene segmentation and object/feature extraction in the context of self-determining and self-calibration modes. The technique uses only a single image, instead of multiple images as the input to generate segmented images. Moreover, a flexible and arbitrary scheme is incorporated, rather than a fixed scheme of segmentation analysis. The process allows users to perform digital analysis using any appropriate means for object extraction after an image is segmented. First, an image is retrieved. The image is then transformed into at least two distinct bands. Each transformed image is then projected into a color domain or a multi-level resolution setting. A segmented image is then created from all of the transformed images. The segmented image is analyzed to identify objects. Object identification is achieved by matching a segmented region against an image library. A featureless library contains full shape, partial shape and real-world images in a dual library system. The depth contours and height-above-ground structural components constitute a dual library. Also provided is a mathematical model called a Parzen window-based statistical/neural network classifier, which forms an integral part of this featureless dual library object identification system. All images are considered three-dimensional. Laser radar based 3-D images represent a special case.

Claims

1. A self-calibrating, self-determining method of generalizing objects or features in an image, the steps comprising:

a) retrieving an original image in pixel form;

b) generating groups having a set of values indicating a number of regions in each segmented image;

c) monitoring a slope and slope change of a scene characteristic (SC) curve;

d) establishing at least one stopping point; and

e) generating at least one segmented image corresponding to each of said at least one stopping point.

2. The self calibrating, self-determining method of generalizing objects or features in an image in accordance with claim 1, wherein said at least one stopping point occurs when the slope or slope change of said SC curve is greater than zero.

3. The self calibrating, self-determining method of generalizing objects or features in an image in accordance with claim 1, the steps further comprising:

f) processing said segmented images, if necessary; and

g) analyzing regions in said segmented images to identify objects.

4. The self calibrating, self-determining method of generalizing objects or features in an image in accordance with claim 3, the steps further comprising:

h) coordinating said segmented images with independently-generated information to identify features and objects.

5. The self-calibrating, self-determining method of generalizing objects or features in an image in accordance with claim 1, the steps further comprising:

f) providing a library comprising data representative of full images or a combination of portions thereof; and

g) matching said original image with said data stored in said library.

6. The method of generalizing objects or features in an image in accordance with claim 5, wherein said data stored in said library comprises geo-coded information.

7. The self-calibrating, self-determining method of generalizing objects or features in an image in accordance with claim 6, wherein said geo-coded information comprises socio-economic data.

8. The self-calibrating, self-determining method of generalizing objects or features in an image in accordance with claim 3, the steps further comprising:

h) providing a library comprising data representative of full images or a combination of portions thereof; and

i) matching said original image with said data stored in said library.

9. The method of generalizing objects or features in an image in accordance with claim 8, wherein said data stored in said library comprises geo-coded information.

10. The self-calibrating, self-determining method of generalizing objects or features in an image in accordance with claim 9, wherein said geo-coded information comprises socio-economic data.

11. The self-calibrating, self-determining method of generalizing objects or features in an image in accordance with claim 7, the steps further comprising:

h) coordinating said segmented images with independently-generated information to identify features and objects.

12. The self-calibrating, self-determining method of generalizing objects or features in an image in accordance with claim 8, the steps further comprising:

j) coordinating said segmented images with independently-generated information to identify features and objects.

13. The self-calibrating, self-determining method of generalizing objects or features in an image in accordance with claim 1, the steps further comprising:

f) coordinating said composite image with independently-generated information to identify features and objects.

14. The self-calibrating, self-determining method of generalizing objects or features in an image in accordance with claim 8, the steps further comprising:

j) updating said library with models and real world data from an independent source.

15. The self-calibrating, self-determining method of generalizing objects or features in an image in accordance with claim 14, wherein said data from an independent source comprises rule-based information.