Feature-based detection and context discriminate classification for digital images

• US 6,999,625 B1
• Filed: 07/12/2002
• Issued: 02/14/2006
• Est. Priority Date: 07/12/2002
• Status: Expired due to Fees

• Current Assignee: the united states of america as represented by the secretary of the navy
• Original Assignee: the united states of america as represented by the secretary of the navy
• Inventors: Nelson, Susan
• Primary Examiner(s): Wu, Jingge
• Assistant Examiner(s): MACKOWEY, ANTHONY M
• Application Number:
  US10/196,388
• Time in Patent Office: 1,313 Days
• Field of Search: 382/103, 382/132, 382/224, 382/228
• US Class Current: 382/224
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/30068 Mammography; Breast
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 10/421 by analysing segments intersecting the pattern

Abstract

Detection and classification of targets in a digital image is accomplished by evaluating windowed portions of the image. A feature set is generated for each of a plurality of overlapping windowed portions, a weighted sum is formed for each portion based upon its feature set, and a context matrix is defined for each window. A score is formed from each context matrix and is normalized for each window. A threshold criteria is compared to a maximum score for each window. Each window having its maximum score satisfy the threshold criteria is classified as a possible target window and is assigned to a group based on location of the possible target window and its maximum score. A group score is formed for each group and compared to a group threshold criteria. Each group having its corresponding group score satisfying the group threshold criteria is classified as a target.

Claims

1. A method of detecting and classifying targets in a digital image, comprising the steps of:

generating a feature set for each of a plurality of overlapping windowed portions of said image, each feature in said feature set defined by a value indicative of a mathematical measure of a corresponding one of said plurality of overlapping windowed portions;

forming a weighted sum for each of said plurality of overlapping windowed portions using said feature set corresponding thereto;

normalizing each feature in said feature set and said weighted sum for each of said plurality of overlapping windowed portions across said plurality of overlapping windowed portions, wherein a context matrix is defined by a normalized feature set and a normalized weighted sum for each of said plurality of overlapping windowed portions;

forming a score using said context matrix for each of said plurality of overlapping windowed portions;

normalizing said score for each of said plurality of overlapping windowed portions across said plurality of overlapping windowed portions, wherein a normalized score is defined for each of said plurality of overlapping windowed portions;

comparing a threshold criteria to a maximum score defined as the maximum of said normalized weighted sum and said normalized score for each of said plurality of overlapping windowed portions, wherein each of said plurality of overlapping windowed portions having said maximum score satisfying said threshold criteria is classified as a possible target window and wherein said maximum score is indicative of a target classification;

assigning each said possible target window to a group based on location of said possible target window in said image and said maximum score associated with said possible target window;

forming a group score for each said group using said maximum score associated with each said possible target window in said group; and

comparing each said group score to a group threshold criteria, wherein each said group having its corresponding said group score satisfying said group threshold criteria is classified as a target and wherein said group score is indicative of a target classification.

2. A method according to claim 1 wherein said step of forming said weighted sum includes the step of adjusting weight values for each said feature based on said value thereof.

3. A method according to claim 1 wherein said step of forming said score comprises the step of summing values in said context matrix for each of said plurality of overlapping windowed portions.

4. A method according to claim 1 wherein said step of forming said group score comprises the step of forming an average using said maximum score for each said possible target window in said group.

5. A method according to claim 1 wherein said step of forming said group score comprises the step of selecting a median from said maximum score for each said possible target window in said group.

6. A method according to claim 1 wherein said step of forming said group score comprises the steps of:

forming an average using said maximum score for each said possible target window in said group;

selecting a maximum from said maximum score for each said possible target window in said group;

selecting a median from said maximum score for each said possible target window in said group; and

calculating said group score using said average, said maximum and said median.

7. A method according to claim 1 wherein said step of forming said group score comprises the steps of:

forming an average using said maximum score for each said possible target window in said group;

selecting a maximum from said maximum score for each said possible target window in said group;

selecting a minimum from said maximum score for each said possible target window in said group;

selecting a median from said maximum score for each said possible target window in said group; and

calculating said group score using said average, said maximum, said minimum and said median.

8. A method according to claim 1 wherein each said feature set associated with a corresponding one of said plurality of overlapping windowed portions includes first order statistical features associated with said corresponding one of said plurality of overlapping windowed portions, second order statistical features associated with said corresponding one of said plurality of overlapping windowed portions, and combinations of said first order statistical features and said second order statistical features associated with said corresponding one of said plurality of overlapping windowed portions.

9. A system for detecting and classifying targets in a digital image, comprising:

means for generating a feature set for each of a plurality of overlapping windowed portions of said image, each feature in said feature set being defined by a value indicative of a mathematical measure of a corresponding one of said plurality of overlapping windowed portions;

a processor for

i) forming a weighted sum for each of said plurality of overlapping windowed portions using said feature set corresponding thereto,

ii) normalizing each feature in said feature set and said weighted sum for each of said plurality of overlapping windowed portions across said plurality of overlapping windowed portions, wherein a context matrix is defined by a normalized feature set and a normalized weighted sum for each of said plurality of overlapping windowed portions,

iii) forming a score using said context matrix for each of said plurality of overlapping windowed portions,

iv) normalizing said score for each of said plurality of overlapping windowed portions across said plurality of overlapping windowed portions, wherein a normalized score is defined for each of said plurality of overlapping windowed portions,

v) comparing a threshold criteria to a maximum score defined as the maximum of said normalized weighted sum and said normalized score for each of said plurality of overlapping windowed portions, wherein each of said plurality of overlapping windowed portions having said maximum score satisfying said threshold criteria is classified as a possible target window and wherein said maximum score is indicative of a target classification,

vi) assigning each said possible target window to a group based on location of said possible target window in said image and said maximum score associated with said possible target window,

vii) forming a group score for each said group using said maximum score associated with each said possible target window in said group, and

viii) comparing each said group score to a group threshold criteria, wherein each said group having its corresponding said group score satisfying said group threshold criteria is classified as a target and wherein said group score is indicative of a target classification; and

at least one output device coupled to said processor for providing an indication that said group score satisfies said group threshold criteria.

10. A system as in claim 9 wherein said at least one output device is selected from the group consisting of an image display, a printer and an audio device.

11. A system as in claim 9 wherein said processor further adjusts weight values used in said weighted sum in accordance with said value of each said feature.

12. A system as in claim 9 wherein said processor forms said score by summing values in said context matrix for each of said plurality of overlapping windowed portions.

13. A system as in claim 9 wherein said processor forms said group score by forming an average using said maximum score for each said possible target window in said group.

14. A system as in claim 9 wherein said processor forms said group score by selecting a median from said maximum score for each said possible target window in said group.

15. A system as in claim 9 wherein said processor forms said group score by forming said group score comprises the steps of:

forming an average using said maximum score for each said possible target window in said group;

selecting a maximum from said maximum score for each said possible target window in said group;

selecting a median from said maximum score for each said possible target window in said group; and

calculating said group score using said average, said maximum and said median.

16. A system as in claim 9, wherein said processor forms said group score by forming said group score comprises the steps of:

forming an average using said maximum score for each said possible target window in said group;

selecting a maximum from said maximum score for each said possible target window in said group;

selecting a minimum from said maximum score for each said possible target window in said group;

selecting a median from said maximum score for each said possible target window in said group; and

calculating said group score using said average, said maximum, said minimum and said median.

17. A system as in claim 9 wherein said feature set associated with a corresponding one of said plurality of overlapping windowed portions includes first order statistical features associated with said corresponding one of said plurality of overlapping windowed portions, second order statistical features associated with said corresponding one of said plurality of overlapping windowed portions, and combinations of said first order statistical features and said second order statistical features associated with said corresponding one of said plurality of overlapping windowed portions.