Method and apparatus for acquiring feature data from low-bit image

1. A processor-implemented method of generating feature data, the method comprising:

receiving an input image;

generating N binary images from the input image, wherein N is the number of bits per pixel of the input image, wherein N is an integer equal to or greater than 2; and

generating, using at least one neural network, feature data corresponding to the input image from the N binary images,

wherein the generating N binary images from the input image comprises:

generating M color channel images in response to the input image being a color image including M color channels, wherein each of the M color channel images corresponds to each of the M color channels of the input image and M is an integer equal to or greater than 2; and

generating N binary images from the M color channel images.

2. The method of claim 1 , wherein the generating N binary images from the input image comprises:

generating the N binary images by dividing binary bit values of the pixel value of the input image based on a bit value level.

3. The method of claim 1 , wherein the generating N binary images from the input image comprises:

generating each of the N binary images for each bit value level from a highest bit to a lowest bit of the binary bit values of the pixel value of the input image.

4. The method of claim 1 , wherein the generating N binary images from the input image comprises:

generating the N binary images by applying N different edge filters to the input image.

5. The method of claim 4 , wherein the generating N binary images from the input image comprises:

generating each of the N binary images by applying a corresponding different edge filter of the N different edge filters, respectively.

6. The method of claim 1 , wherein L is the number of bits per color channel of the input image and N=M×L.

7. The method of claim 1 , wherein the generating N binary images from the M color channel images comprises:

generating the M×L binary images by dividing binary bit values of the pixel value of the M color channel images based on a bit value level, or generating the M×L binary images by applying L different edge filters to the M color channel images.

8. A processor-implemented method of generating feature data, the method comprising:

receiving a feature map of an input image including pixels having a plurality of bit value levels;

generating, for each of the bit value levels, a binary feature map including binary pixe l values corresponding to pixels of the feature map that include a bit of the bit value level; and

generating, using a neural network, feature data corresponding to the input image based on the generated binary feature maps,

wherein the generating the binary feature map comprises:

generating M color channel images in response to the input image being a color image including M color channels, wherein each of the M color channel images corresponds to each of the M color channels of the input image and M is an integer equal to or greater than 2; and

generating the binary feature map from the M color channel images.

9. The method of claim 1 , wherein the generating of the feature data comprise s performing convolution operations between one or more image filters and the binary feature maps.

10. The method of claim 1 , further comprising performing an image recognition for the input image based on the generated feature data.

11. An apparatus for generating feature data, the apparatus comprising:

one or more processors configured to:

receive an input image;

generate N binary images from the input image, wherein N is the number of bits per pixel of the input image, wherein N is an integer equal to or greater than 2; and

generate, using at least one neural network, feature data corresponding to the input image from the N binary images,

wherein for the generating N binary images from the input image, the one or more processors are configured to:

generate M color channel images in response to the input image being a color image including M color channels, wherein each of the M color channel images corresponds to each of the M color channels of the input image and M is an integer equal to or greater than 2; and

generate N binary images from the M color channel images.

12. The apparatus of claim 11 , wherein for the generating N binary images from the input image, the one or more processors are configured to:

generate the N binary images by dividing binary bit values of the pixel value of the input image based on a bit value level.

13. The apparatus of claim 12 , wherein for the generating N binary images from the input image, the one or more processors are configured to:

generate each of the N binary images for each bit value level from a highest bit to a lowest bit of the binary bit values of the pixel value of the input image.

14. The apparatus of claim 11 , wherein for the generating N binary images from the input image, the one or more processors are configured to:

generate the N binary images by applying N different edge filters to the input image.

15. The apparatus of claim 14 , wherein for the generating N binary images from the input image, the one or more processors are configured to:

generate each of the N binary images by applying a corresponding different edge filter of the N different edge filters, respectively.

16. The apparatus of claim 11 , wherein L is the number of bits per color channel of the input image and N=M×L, wherein L is an integer equal to or greater than 2.

17. The apparatus of claim 11 , wherein the generating N binary images from the M color channel images, the one or more processors are configured to:

generate the M=L binary images by dividing binary bit values of the pixel value of the M color channel images based on a bit value level, or

generate the M=L binary images by applying L different edge filters to the M color channel images.

18. The apparatus of claim 11 , wherein the apparatus further comprises:

a camera configured for capturing the input image and providing the input image to the one or more processors.