Face searching and detection in a digital image acquisition device

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 8,923,564
App. No.: 14/177,212
Granted: Dec 30, 2014
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

A method of detecting a face in an image includes performing face detection within a first window of the image at a first location. A confidence level is obtained from the face detection indicating a probability of the image including a face at or in the vicinity of the first location. Face detection is then performed within a second window at a second location, wherein the second location is determined based on the confidence level.

Claims (103)

1. A method comprising:

acquiring data of a digital image which depicts one or more objects;

determining a first size of a first detection window and an initial location of the first detection window in the digital image;

wherein the first detection window encompasses a first portion of the digital image;

determining, for the first detection window, first detection window data that represents the first detection window at a first image resolution level;

determining a first set of face detection tests that are to be applied to the first detection window data;

applying the first set of face detection tests to the first detection window data to determine a first confidence level value that indicates a likelihood that a particular object, of the one or more objects, is included in the first detection window;

in response to determining that the first confidence level value is not greater than a first threshold value:

determining a second size that is greater than the first size;

determining a second detection window that has the second size;

wherein the second detection window encompasses a second portion of the digital image;

determining, for the second detection window, second detection window data that represents the second detection window at a second image resolution level;

determining a second set of face detection tests that are to be applied to the second detection window data; and

applying the second set of face detection tests to the second detection window data to determine a second confidence level value that indicates a likelihood that the particular object, of the one or more objects, is included in the second detection window; and

wherein the method is performed using one or more computing devices.

2. The method of claim 1 , further comprising:

in response to determining that the second confidence level value is greater than a second threshold value, determining that the particular object, of the one or more objects, is depicted in the second detection window.

3. The method of claim 2 , further comprising:

in response to determining that the second confidence level value is not greater than the second threshold value:

determining a second location by rotating the second detection window;

determining a third detection window, wherein the third detection window has the second size and is located at the second location;

determining, for the third detection window, third detection window data;

determining a third set of face detection tests that are to be applied to the third detection window data; and

applying the third set of face detection tests to the third detection window data to determine a third confidence level value that indicates a likelihood that the particular object, of the one or more objects, is included in the third detection window.

4. The method of claim 3 , further comprising:

in response to determining that the third confidence level value is greater than a third threshold value, determining that the particular object, of the one or more objects, is depicted in the third detection window.

5. The method of claim 4 , further comprising:

in response to determining that the first confidence level value is greater than the first threshold value:

determining a fourth set of face detection tests that are to be applied to the first detection window data;

wherein the fourth set of face detection tests comprises a chain of classifiers to be applied to the first detection window data to determine a skin map; and

applying the fourth set of face detection tests to the first detection window data to determine a fourth confidence level value that indicates a likelihood that the particular object, of the one or more objects, included in the first detection window, is a face.

6. The method of claim 5 , wherein the fourth set of face detection tests comprises one or more frontal face detection tests.

7. The method of claim 6 ,

wherein the skin map comprises a map of values computed for each pixel of the first detection window; and

wherein a particular value in the skin map represents a probability that a particular pixel of the first detection window depicts a portion of a human skin.

8. A non-transitory computer-readable storage medium, storing one or more instructions which, when executed by one or more processors, cause the one or more processors to perform: