Granted Patent B2

US 9,602,793 · App. 12/634,078 · Granted Mar 21, 2017

Abstract

Claims (59)

1. A method for processing sensor data in an image processor that implements at least one image enhancement process, the method comprising:

receiving sensor data from an image sensor;

performing a skin tone detection operation to identify skin tone areas in the sensor data in pre-capture processing;

selectively modifying at least one image enhancement process for the identified skin tone areas prior to image capture;

applying the at least one modified image enhancement process to the identified skin tone areas in the sensor data to generate modified sensor data;

feeding the modified sensor data back to the image sensor, thereby enabling the image sensor to capture an image using the modified sensor data; wherein each step is performed in the image processor;

dividing the sensor data into blocks of pixels and calculating a percentage of the skin tone area within each block of pixels; and

determining a weighting scheme, wherein the weighting scheme assigns weights to the at least one image enhancement process based on the percentage of the skin tone area within each block of pixels, and wherein the at least one image enhancement process is modified based on the weights assigned.

2. The method of claim 1 , wherein the image enhancement process is selected from a group consisting of Auto Focus, Auto Exposure, and Auto White Balance.

3. The method of claim 1 , wherein performing the skin tone detection operation comprising classifying the sensor data as one of a skin tone data and a non skin tone data.

4. The method of claim 3 , wherein classifying the sensor data comprising classifying a pixel in the sensor data as a skin tone pixel if the pixel's chrominance components U and V in a YUV colorspace satisfy each of the following conditions:

90<= U component<=125;

133<= V component<=171; and

270<= V component+1.1875 U component<=291.

5. The method of claim 3 , wherein classifying the sensor data comprising:

dividing the sensor data into blocks of pixels;

calculating an average color for each block of pixels; and

classifying each block of pixels as one of a skin tone pixel block and a non skin tone pixel block, the skin tone pixel block is one for which chrominance components U and V in a YUV colorspace satisfy each of the following conditions:

90<= U component<=125;

133<= V component<=171; and

270 V component+1.1875 U component<=291.

6. The method of claim 1 , further comprising performing post-capture processing on the image captured by the image sensor using the modified sensor data, to thereby generate a processed image as the output of the image processor.

7. An image processor for processing sensor data, the image processor implements at least one image enhancement process, the image processor comprises:

a skin tone detector capable of receiving sensor data from an image processor and performing a skin tone detection operation to identify skin tone areas in the sensor data in pre-capture processing; dividing the sensor data into blocks of pixels and calculating a percentage of the skin tone area within each block of pixels; and determining a weighting scheme, wherein the weighting scheme assigns weights to the at least one image enhancement process based on the percentage of the skin tone area within each block of pixels, and wherein the at least one image enhancement process is modified based on the weights assigned;

an image enhancement module capable of selectively modifying at least one image enhancement process for the identified skin tone areas prior to image capture;

control circuitry capable of applying the at least one modified image enhancement process to the identified skin tone areas in the sensor data to generate modified sensor data and to feed the modified sensor data back to the image sensor, thereby enabling the image sensor to capture an image using the modified sensor data; and

a post-capture processing module configured to perform post-capture processing on the captured image using the modified sensor data, to thereby generate a processed image as the output of the image processor.

8. The image processor of claim 7 , wherein the image enhancement process is selected from a group consisting of Auto Focus, Auto Exposure, and Auto White Balance.

9. The image processor of claim 7 , wherein the skin tone detector classifies the sensor data as one of a skin tone data and a non skin tone data.

10. The image processor of claim 9 , wherein the skin tone detector classifies a pixel in the sensor data as a skin tone pixel if the pixel's chrominance components U and V in a YUV colorspace satisfy each of the following conditions:

90<= U component<=125;

133<= V component<=171; and

270<= V component+1.1875 U component<=291.

11. The image processor of claim 9 , wherein the skin tone detector classifies the sensor data by:

dividing the sensor data into blocks of pixels;

calculating an average color for each block of pixels; and

classifying each block of pixels as one of a skin tone pixel block and a non skin tone pixel block, the skin tone pixel block is one for which chrominance components U and V in a YUV colorspace satisfy each of the following conditions:

90<= U component<=125;

133<= V component<=171; and

270<= V component+1.1875 U component<=291.

12. A non-transitory computer readable medium containing a computer program product for processing a sensor by an image processor, the computer program product comprising:

program code for receiving sensor data from an image sensor and performing a skin tone detection operation to identify skin tone areas in the sensor data in pre-capture processing;

program code for selectively modifying at least one image enhancement process for the identified skin tone areas prior to image capture;

program code for applying the at least one modified image enhancement process to the identified skin tone areas in the sensor data to generate modified sensor data;

program code to feed the modified sensor data back to the image sensor, thereby enabling the image sensor to capture an image using the modified sensor data;

program code for dividing the sensor data into blocks of pixels and calculating a percentage of the skin tone area within each block of pixels; and

program code for determining a weighting scheme, wherein the weighting scheme assigns weights to the at least one image enhancement process based on the percentage of the skin tone area within each block of pixels, and wherein the at least one image enhancement process is modified based on the weights assigned.

13. The computer program product of claim 12 , wherein the program code for performing the skin tone detection operation comprising program code for classifying the sensor data as one of a skin tone data and a non skin tone data.

14. The computer program product of claim 13 , wherein classifying the sensor data comprising program code for classifying a pixel in the sensor data as a skin tone pixel if the pixel's chrominance components U and V in a YUV colorspace satisfy each of the following conditions:

90<= U component<=125;

133<= V component<=171; and

270<= V component+1.1875 U component<=291.

15. The computer program product of claim 13 , wherein the program code for classifying the sensor data comprising:

program code for dividing the sensor data into blocks of pixels;

program code for calculating an average color for each block of pixels; and

program code for classifying each block of pixels as one of a skin tone pixel block and a non skin tone pixel block, the skin tone pixel block is one for which chrominance components U and V in a YUV colorspace satisfy each of the following conditions:

90<= U component<=125;

133<= V component<=171; and

270<= V component+1.1875 U component<=291.

Assignments (6)