Automated acquisition of facial images

Patent metadata

Field	Value
Publication number	US-9536046-B2
Application number	US-68568610-A
Country	US
Kind code	B2
Filing date	Jan 12, 2010
Priority date	Jan 12, 2010
Publication date	Jan 3, 2017
Grant date	Jan 3, 2017

Abstract

Described is a technology by which medical patient facial images are acquired and maintained for associating with a patient's records and/or other items. A video camera may provide video frames, such as captured when a patient is being admitted to a hospital. Face detection may be employed to clip the facial part from the frame. Multiple images of a patient's face may be displayed on a user interface to allow selection of a representative image. Also described is obtaining the patient images by processing electronic documents (e.g., patient records) to look for a face pictured therein.

First claim

What is claimed is:

1. In a computing environment, a computer-implemented method performed on at least one processor, the method comprising:
determining that data associated with a patient does not have an image representative of the patient assigned to the data;
based on determining that data associated with a patient does not have an image of the patient assigned to the data, automatically acquiring a patient image from documents associated with the patient;
obtaining information for the image that indicates a bounded region indicative of where the patient's face appears within a frame of the patient image;
clipping the bounded region from the patient image to obtain a patient facial image;
maintaining the patient facial image in association with the data associated with the patient; and
printing patient facial image data corresponding to the image to a medical item associated with the patient.

2. The computer-implemented method of claim 1 further comprising:
automatically acquiring an additional image of the patient by sampling frames of images of the patient provided by a camera;
obtaining information for the additional image that indicates a bounded region indicative of where-the patient's face appears within a frame of the additional image;
clipping the bounded region from the additional image to obtain an additional patient facial image;
assigning the additional patient facial image to a current patient visit; and
maintaining the additional patient facial image in association with the data associated with the patient.

3. The computer-implemented method of claim 1 further comprising:
receiving at least one other image of the patient;
obtaining information for the other image that indicates a bounded region indicative of where the patient's face appears within the other image;
clipping the bounded region from the image to obtain another patient facial image; and
presenting both the patient facial image and the other patient facial image for selection via a user interface.

4. The computer-implemented method of claim 1 further comprising automatically processing electronic documents for images of the patient.

5. The computer-implemented method of claim 1 further comprising outputting the patient facial image to a user interface that shows data of the patient in association with the patient facial image.

6. The computer-implemented method of claim 5 further comprising outputting one or more of the following: a previously saved patient facial image on the user interface, and a current camera shot on the user interface.

7. The computer-implemented method of claim 1 further comprising outputting the patient facial image to a user interface along with a patient facial image of a different patient, patient facial images being accompanied by data by which the patients are able to be differentiated from one another.

8. In a computing environment, a system comprising:
an acquisition mechanism coupled to a source of patient images, the acquisition mechanism further coupled to a face detection algorithm that automatically locates a facial image of a patient within an image of a document based on a determination that data associated with the patient does not have a patient facial image representative of the patient assigned to the data, the acquisition mechanism configured to automatically acquire a patient image from documents associated with the patient and clip the patient facial image from the patient image based upon data received from the face detection algorithm, and maintain patient facial image in a data store in association with information about the patient; and
a printing device configured to print facial image data corresponding to the patient facial image to a medical item associated with the patient.

9. The system of claim 8 wherein the source of patient images comprises a data store of electronic documents.

10. The system of claim 8 wherein the source of patient images comprises a camera.

11. The system of claim 10 further comprising a user interface that displays a plurality of available facial images for the patient captured by the camera, and detects interaction to select one of the available facial images as a selected patient facial image for maintaining in the data store.

12. The system of claim 11 wherein the user interface further includes at least one interactive control for recapturing at least one new patient facial image.

13. The system of claim 11 wherein the user interface shows medical data of the patient in association with the patient facial image.

14. The system of claim 8 further comprising a user interface that shows the patient facial image in association with medical information associated with that patient facial image, and further shows at least one other patient facial image in association with medical information associated with other patient facial images.

15. The system of claim 14 wherein the patient facial image and the at least one other patient facial image are arranged in a column in different rows of a grid, the rows containing the medical information in other columns.

16. The system of claim 8 wherein the printing device comprises means for printing the patient facial image to an item associated with the patient.

17. One or more computer-readable storage devices having computer-executable instructions, which upon execution perform operations comprising:
determining that data associated with a patient does not have an image representative of the patient assigned to the data;
based on determining that data associated with a patient does not have an image of the patient assigned to the data, automatically acquiring a patient image from documents associated with the patient;
obtaining a plurality of camera shots of the patient;
obtaining information for the camera shots that indicates a bounded region indicative of where a face of the patient appears within respective frames of the camera shots;
clipping the bounded region from the camera shots to obtain facial images of the patient;
displaying the facial images in association with medical information of the patient;
detecting interaction to select a facial image from among the displayed facial images as a selected facial image;
maintaining the selected facial image in association with data by which the patient is identifiable; and
printing the selected facial image and locating the selected image onto one or more medical items associated with the patient including a drug bottle or device associated with the patient to help prevent patient misidentification with respect to the medical item or items.

18. The one or more computer-readable storage devices of claim 17 having further computer-executable instructions comprising providing the camera shots to a face detection algorithm, and receiving information from the face detection algorithm by which the images are clipped from the camera shots.

19. The one or more computer-readable storage devices of claim 17 having further computer-executable instructions comprising adding additional medical data of the patient in association with the facial images.

20. The one or more computer-readable storage devices of claim 17 having further computer-executable instructions comprising storing the selected image with previously saved facial images of the patient in association with medical information of the patient, the saved images and the selected image being used as candidate images for identifying the patient.

Assignees

• Gillam Michael
• Gillotte John Christopher
• Feied Craig Frederick
• Handler Jonathan Alan
• Cazangi Renato Reder
• Hegde Rajesh Kutpadi
• Zhang Zhengyou
• Zhang Cha
• Microsoft Technology Licensing Llc

Inventors

• Gillam Michael
• Gillotte John Christopher
• Feied Craig Frederick
• Handler Jonathan Alan
• Cazangi Renato Reder
• Hegde Rajesh Kutpadi
• Zhang Zhengyou
• Zhang Cha

Classifications

• G07C9/253

  visually · CPC title

• G16H10/60 Primary

  for patient-specific data, e.g. for electronic patient records · CPC title

• G07C9/00079

  Physics · mapped topic

• G06F19/322 Primary

  Physics · mapped topic

• G07C9/00103

  Physics · mapped topic