APPARATUS AND METHOD FOR CLASSIFYING IMAGES

• US 20100238316A1
• Filed: 02/11/2010
• Published: 09/23/2010
• Est. Priority Date: 02/23/2009
• Status: Active Grant

• Current Assignee: INHA Industry Partnership Institute, Samsung Electronics Co. Ltd. (Samsung Group)
• Original Assignee: INHA Industry Partnership Institute, Samsung Electronics Co. Ltd. (Samsung Group)
• Inventors: KIM, Ji-Hye, Cho, Sung-Dae, Kim, Jin-Ho, Oh, Yun-Je, Park, Hee-Chan, Park, Min-Kyu, Kim, Kyoung-Tae, Jang, Seul-Ki, Kim, Choon-Woo
• Granted Patent: US 8,704,910 B2
• Time in Patent Office: Days
• US Class Current: 348/223.100
• CPC Class Codes: H04N 23/88 for colour balance, e.g. white-balance circuits or colour temperature control

Abstract

An image classification apparatus and method for Automatic White Balance (AWB) are provided. An input image is divided into blocks including pluralities of pixels. A hue value and a chroma value are calculated for each of the blocks. A color-changed block is detected by calculating, for each one of the blocks, differences between the hue and chroma values calculated for all blocks adjacent to the one of the blocks and the hue and chroma values calculated for the one of the blocks. A hue variance and a chroma variance are calculated for the entire input image if a number of the detected color-changed blocks is greater than or equal to a first threshold. The input image is determined as a non-monochromatic image, if the hue variance is greater than or equal to a second threshold or the chroma variance is greater than or equal to a third threshold.

Claims

1. An apparatus for classifying an image, comprising:

an image divider for dividing an input image into blocks, wherein each block includes a plurality of pixels; and

an image type determiner for calculating a hue value and a chroma value for each of the blocks, determining, for each one of the blocks, whether the one of the blocks is a color-changed block by calculating differences between the hue value and chroma value calculated for all blocks adjacent to the one of the blocks and the hue value and chroma value calculated for the one of the blocks, calculating a hue variance and a chroma variance for the entire input image if a number of determined color-changed blocks is greater than or equal to a first preset threshold, and determining that the input image is a non-monochromatic image if the hue variance is greater than or equal to a second preset threshold or the chroma variance is greater than or equal to a third preset threshold.

2. The apparatus of claim 1, wherein the image type determiner determines that the input image is a monochromatic image, if the number of the determined color-changed blocks is less than the first preset threshold.

3. The apparatus of claim 1, wherein the image type determiner determines the input image as a monochromatic image, if the hue variance is less than the second preset threshold and the chroma variance is less than the third preset threshold.

4. The apparatus of claim 1, wherein the image type determiner determines that the one of the blocks is a color-changed block when a difference between the hue value calculated for all the blocks adjacent to the one block and the hue value calculated for the one of the blocks is greater than or equal to a preset fourth preset threshold, or a difference between the chroma value calculated for all the blocks adjacent to the one of the blocks and the chroma value calculated for the one of the blocks is greater than or equal to a preset fifth preset threshold.

5. The apparatus of claim 4, wherein the image type determiner determines that the one of the blocks is a non-color-changed block when the difference between the hue value calculated for all the blocks adjacent to the one of the blocks and the hue value calculated for the one of the blocks is less than the fourth preset threshold, and the difference between the chroma value calculated for all the blocks adjacent to the one of the blocks and the chroma value calculated for the one of the blocks is less than the fifth preset threshold.

6. The apparatus of claim 1, further comprising an Automatic White Balance (AWB) applier for applying white balance to the input image, upon determining that the input image is a non-monochromatic image.

7. A method for classifying an image, comprising:

dividing an input image into blocks, wherein each block includes a plurality of pixels;

calculating a hue value and a chroma value for all the blocks, and a hue value and a chroma value for each of the blocks;

determining, for each one of the blocks, whether the one of the blocks is a color-changed block by calculating differences between the hue value and the chroma value calculated for all blocks adjacent to the one of the blocks and the hue value and the chroma value calculated for the one of the blocks;

calculating a number of the detected color-changed blocks and comparing the number of the detected color-changed blocks with a first preset threshold;

calculating a hue variance and a chroma variance for the entire input image if the number of the determined color-changed blocks is greater than or equal to the first preset threshold, and determining whether the hue variance is greater than or equal to a second preset threshold and the chroma variance is greater than or equal to a third preset threshold; and

determining that the input image is a non-monochromatic image, if the hue variance is greater than or equal to the second preset threshold or the chroma variance is greater than or equal to the third preset threshold.

8. The method of claim 7, further comprising determining that the input image is a monochromatic image, if a number of the determined color-changed blocks is less than the first preset threshold.

9. The method of claim 7, further comprising determining that the input image is a monochromatic image, if the hue variance is less than the second preset threshold and the chroma variance is less than the third preset threshold.

10. The method of claim 9, wherein determining whether the one of the blocks is a color-changed block comprises:

comparing a difference between the hue values calculated for all the blocks adjacent to the one of the blocks and the hue value calculated for the one of the blocks with a preset fourth threshold, and comparing a difference between the chroma value calculated for all the blocks adjacent to the one of the blocks and the chroma value calculated for the one of the blocks with a preset fifth preset threshold; and

determining that the one of the blocks is a color-changed block, when the differences between the hue values calculated for all the blocks adjacent to the one of the blocks and the hue value calculated for the one of the blocks is greater than or equal to the fourth preset threshold, or the difference between the chroma value calculated for all the blocks adjacent to the one of the blocks and the chroma value calculated for the one of the blocks is greater than or equal to the fifth preset threshold.

11. The method of claim 10, further comprising determining that the one of the blocks is a non-color-changed block when the difference between the hue value calculated for all the blocks adjacent to the one of the blocks and the hue value calculated for the one of the blocks is less than the fourth preset threshold, and the difference between the chroma value calculated for all the blocks adjacent to the one of the blocks and the chroma value calculated for the one of the blocks is less than the fifth preset threshold.

12. The method of claim 7, further comprising applying white balance to the input image after determining the input image as a non-monochromatic image.