Skin-tone filtering

Claim 3

The method of claim 1 , wherein the specified hue value comprises a value selected from a range of hue values.

Claim 4

The method of claim 1 , wherein the act of determining a distance value is performed in a hue space defined by an angular coordinate such that red corresponds to zero degrees, green corresponds to 120 degrees and blue corresponds to 240 degrees, and wherein the distance value is determined by subtracting a hue value of 25 degrees corresponding to skin-tone orange from the first digital image frame's hue values.

Claim 5

The method of claim 1 , wherein the act of determining a distance value is performed in a two-dimensional (2D) hue space, wherein the distance value is determined by calculating a 2D Cartesian distance value from hue-coordinates that specify the first digital image frame's hue values to a location in 2D color space corresponding to skin-tone orange.

Claim 6

The method of claim 1 , further comprising: receiving a second digital image frame from the series of digital image frames; generating a second orange-distance filtered frame corresponding to the second digital image frame; identifying a second skin-tone orange portion in the second orange-distance filtered frame; determining a change in area between the first skin-tone orange portion and the second skin-tone orange portion; and determining a change in location between the first skin-tone orange portion and the second skin-tone orange portion.

Claim 7

The method of claim 5 further comprising detecting a face within the second skin-tone orange portion when the determined changes in area and location are less than respective predetermined variations.

Claim 8

An appliance comprising: a non-transitory data storage device configured to store rules for acknowledging a detected face; an image capture device configured to acquire color frames, each acquired frame comprising pixels, each pixel having a corresponding hue value; and one or more data processors configured to execute program code stored in the non-transitory data storage device to cause the one or more data processors to: apply an orange-distance filter to a first frame and a second frame acquired by the image capture device to identify skin-tone orange portions of the first and second acquired frames, wherein the orange-distance filter identifies distance values between the acquired frames' hue values and a hue value corresponding to skin-tone orange; determine respective changes in an area and a location between the skin-tone orange portions of the first and second acquired frames; infer, based on the determined changes, a presence of a face substantially at rest when the second frame was acquired; detect a face within the skin-tone orange portion of the second acquired frame in response to the inference and based, at least in part on: accessing shape classifiers generated for detecting shapes corresponding to faces within skin-tone orange portions of orange-distance filtered images, wherein the shape classifiers are generated by: retrieving, from a shape library, images of shapes and shape combinations corresponding to a face depicted in a given color space, wherein the shapes corresponding to the face include at least an eye, a nose, and a mouth, and wherein the shape combinations corresponding to the face include at least eyes, eyes and a nose, and a nose and a mouth; producing orange-distance filtered versions of the retrieved images of shapes and shape combinations; and assembling the orange-distance filtered images of shapes and shape combinations into the generated shape classifiers; and using the accessed shape classifiers; and acknowledge the detected face in accordance with a predetermined rule stored on the non-transitory data storage device of the appliance.

Claim 9

An appliance comprising: a non-transitory data storage device configured to store rules for acknowledging a detected face; an image capture device configured to acquire color frames, each acquired frame comprising pixels, each pixel having a corresponding hue value; and one or more data processors configured to execute program code stored in the non-transitory data storage device to cause the one or more data processors to: apply an orange-distance filter to a first frame and a second frame acquired by the image capture device to identify skin-tone orange portions of the first and second acquired frames, wherein the orange-distance filter identifies distance values between the acquired frames' hue values and a hue value corresponding to skin-tone orange; determine respective changes in an area and a location between the skin-tone orange portions of the first and second acquired frames; infer, based on the determined changes, a presence of a face substantially at rest when the second frame was acquired; detect a face within the skin-tone orange portion of the second acquired frame in response to the inference and based, at least in part on: accessing shape classifiers generated for detecting shapes corresponding to faces within skin-tone orange portions of orange-distance filtered images, wherein the shape classifiers are generated by: retrieving, from a shape library, images of shapes and shape combinations corresponding to a face depicted in a given color space, wherein the shapes corresponding to the face include at least an eye, a nose, and a mouth, and wherein the shape combinations corresponding to the face include at least eyes, eyes and a nose, and a nose and a mouth; producing orange-distance filtered versions of the retrieved images of shapes and shape combinations; and assembling the orange-distance filtered images of shapes and shape combinations into the generated shape classifiers; and using the accessed shape classifiers; and acknowledge the detected face in accordance with a predetermined rule stored on the non-transitory data storage device of the appliance.

Claim 10

The appliance of claim 7 , wherein the program code to cause the one or more processors to apply an orange-distance filter comprises program code to cause the one or more processors to: generate a first orange-distance filtered frame corresponding to the first acquired frame and a second orange-distance filtered frame corresponding to the second acquired frame, wherein the orange-distance filtered frames are generated based on the identified distance values between the acquired frames' hue values and the hue value corresponding to skin-tone orange; and identify a portion of the first and second orange-distance filtered frames within which the identified distance values are less than a threshold distance value as the skin-tone orange portions of the first and second acquired frames.

Claim 11

The appliance of claim 8 , wherein the orange-distance filter is applied in a hue space defined by an angular coordinate such that red corresponds to zero degrees, green corresponds to 120 degrees and blue is corresponds to 240 degrees, and wherein the program code to cause the one or more processors to apply the orange-distance filter comprises program code to cause the one or more processors to identify the distance values between the acquired frames' hue values and the hue value corresponding to skin-tone orange by subtracting a hue value of 25 degrees from the acquired frames' hue values.

Claim 12

The appliance of claim 8 , wherein the orange-distance filter is applied in a two-dimensional (2D) hue space, and wherein the program code to cause the one or more processors to apply the orange-distance filter comprises program code to cause the one or more processors to identify the distance values between the acquired frames' hue values and the hue value corresponding to skin-tone orange by calculating a 2D Cartesian distance from hue-coordinates that specify the acquired frames' hue values to a location in 2D color space corresponding to skin-tone orange.

Claim 13

The appliance of claim 7 , wherein the program code to cause the one or more processors to acknowledge the detected face comprises program code to cause the one or more processors to turn on a display of the appliance located on a same side as the image capture device, wherein the display had been off prior to the face detection.

Claim 14

The appliance of claim 7 , wherein the program code to cause the one or more processors to acknowledge the detected face comprises program code to cause the one or more processors to turn on a transceiver of the appliance which was turned off prior to the face detection.

Claim 17

The system of claim 13 , further comprising program code to cause the one or more processors to: maintain rules to apply the generated shape classifiers to detect faces within skin-tone orange portions of orange-distance filtered images; and update the maintained rules based on feedback collected from the image processing devices that have applied the generated shape classifiers and maintained rules.

Claim 18

The system of claim 13 , wherein the program code to cause the one or more processors to produce orange-distance filtered versions of the retrieved images of shapes and shape combinations comprises program code to cause the one or more processors to: convert the retrieved images of shapes and shape combinations to a hue space defined by an angular coordinate such that red corresponds to zero degrees, green corresponds to 120 degrees and blue corresponds to 240 degrees; and calculate the distance values between the hue value of pixels in the retrieved images and the hue value corresponding to skin-tone orange by subtracting a hue value of 25 degrees corresponding to skin-tone orange from the hue value of the pixels in the retrieved images.

Claim 19

The system of claim 13 , wherein the program code to cause the one or more processors to produce orange-distance filtered versions of the retrieved images of shapes and shape combinations comprises program code to cause the one or more processors to: convert the retrieved images of shapes and shape combinations to a two-dimensional (2D) hue space; and calculate 2D Cartesian distance values from hue-coordinates specifying the hue value of the pixels in the retrieved images to a location in 2D color space corresponding to skin-tone orange.