IMAGE DATA NORMALIZATION FOR A MONITORING SYSTEM

• US 20080294017A1
• Filed: 05/22/2007
• Published: 11/27/2008
• Est. Priority Date: 05/22/2007
• Status: Active Grant

• Current Assignee: Eastman Kodak Company
• Original Assignee: Eastman Kodak Company
• Inventors: Kurtz, Andrew F., Gobeyn, Kevin M., Olson, Donald E., Madden, Thomas E.
• Granted Patent: US 7,972,266 B2
• Time in Patent Office: Days
• US Class Current: 600/301
• CPC Class Codes: A61B 3/113 for determining or recording eye movement
• CPC Class Codes: A61B 5/0088 for oral or dental tissue
• CPC Class Codes: A61B 5/411 Detecting or monitoring allergy or intolerance reactions to an allergenic agent or substance
• CPC Class Codes: A61B 5/442 Evaluating skin mechanical properties, e.g. elasticity, hardness, texture, wrinkle assessment
• CPC Class Codes: A61B 5/444 Evaluating skin marks, e.g. mole, nevi, tumour, scar
• CPC Class Codes: A61B 5/445 Evaluating skin irritation or skin trauma, e.g. rash, eczema, wound, bed sore
• CPC Class Codes: A61B 5/4547 Evaluating teeth
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A method for providing normalized physiological monitoring data of an individual with a measure of the quality of the normalization, including providing a reference feature based on a physiological attribute of the individual for which an attribute value can be determined; unobtrusively capturing physiological monitoring data for the individual during a series of capture events and determining the capture conditions present during each capture event; detecting the presence of the reference feature in the series of captured physiological monitoring data and determining associated attribute values for each capture event; normalizing the captured physiological monitoring data from each capture event according to differences in the attribute values associated with each event and previously calculated attribute values; and calculating normalization confidence values for the individual at the series of capture events, based on capture conditions, normalization transforms, or semantic data, wherein the confidence values statistically measure the quality of the normalization.

Claims

1. A method for providing normalized physiological monitoring data of an individual with a measure of the quality of the normalization, comprising;

providing a reference feature based on a physiological attribute of the individual for which an attribute value can be determined;

unobtrusively capturing physiological monitoring data for the individual during a series of capture events and determining the capture conditions present during each capture event;

detecting the presence of the reference feature in the series of captured physiological monitoring data and determining associated attribute values for each capture event;

normalizing the captured physiological monitoring data from each capture event according to differences in the attribute values associated with each event and previously calculated attribute values; and

calculating normalization confidence values for the individual at the series of capture events, based on capture conditions, normalization transforms, or semantic data, wherein the confidence values statistically measure the quality of the normalization.

2. The method as in claim 1 wherein the semantic data related to the individual, that can affect the quality of the normalization, includes the time of day of a capture event, the use of cosmetics, or the tiredness of the individual.

3. The method as in claim 1 wherein the normalization confidence values are tracked over multiple capture events to monitor changes in normalization quality over time.

4. The method as in claim 1 wherein normalization confidence values are used to determine if valid wellness parameters can be derived, wherein the wellness parameters are associated with the physiological attributes being monitored.

5. The method as in claim 1 wherein the attribute values or normalization transforms are obtained by RGB or spectral color measurements of:

the sclera, the skin, the tongue, the ambient light, or the capture light.

6. The method as in claim 1 wherein the physiological monitoring data is obtained by image capture, audio capture or multi-spectral capture.

7. The method as in claim 6 wherein the capture conditions are derived as capture parameters from one or more captured images acquired during a capture event.

8. The method as in claim 6 wherein the face of the individual in the captured images are normalized according to color attributes of one or more facial reference features of the individual.

9. The method as in claim 6 wherein the face of the individual in the captured images are normalized based on the spatial disparity between two or more facial reference features of the individual.

10. The method as in claim 9 wherein the captured images of the individual are normalized based on the spatial disparity between corresponding features of both eyes of the individual.

11. The method as in claim 6 wherein the captured images of the individual are normalized to provide changes in the size or orientation or combinations thereof of the image of the individual.

12. The method as in claim 6 wherein the audio capture is normalized to reduce the noise associated with voice capture under variable capture conditions.

13. The method as in claim 1 wherein the physiological attributes and associated reference features include color, size, weight, posture, gait, motion, or voice.

14. The method as in claim 1 wherein the reference features are related to physiological attributes of one or both eyes, the skin, the tongue, one or more teeth or combinations thereof.

15. A method for providing normalized images of an individual from a physiological monitoring system comprising;

providing a reference feature based on the sclera of one or more eyes of the individual from which color attribute values can be determined

capturing an image of the individual during a first capture event and determining the presence of a reference feature in the captured image and determining a first attribute value;

capturing an image of the individual during a second capture event and determining the presence of the reference feature in the second captured image and determining a second attribute value; and

normalizing the second captured image according to differences between the first and second attribute values.

16. The method of claim 15 wherein the sclera feature is the average color value excluding the blood vessels of at least one eye of the individual.

17. The method of claim 15 wherein the differences in sclera color are due to changes in the capture lighting conditions at the time of capture.