Image processing method, image processing apparatus, storage medium, image processing system, and manufacturing method of learnt model

1. An image processing method comprising:

acquiring input data including an input image and a noise map representing a noise amount in the input image based on an optical black area corresponding to the input image; and

inputting the input data including (i) the input image and (ii) the noise map representing the noise amount in the input image based on the optical black area corresponding to the input image into a neural network to execute a task of a recognition or regression.

2. The image processing method according to claim 1 , further comprising:

acquiring the optical black area corresponding to the input image;

extracting one or more partial optical black images that are at least part of the optical black area; and

generating the noise map based on the number of pixels of the input image and the partial optical black image.

3. The image processing method according to claim 2 , wherein the noise map is generated by arraying the partial optical black image.

4. The image processing method according to claim 1 , further comprising:

acquiring the optical black area corresponding to the input image;

calculating a dispersion of a signal value in the optical black area; and

generating the noise map based on the dispersion.

5. The image processing method according to claim 2 , wherein the input image and the optical black area are extracted from the same captured image.

6. The image processing method according to claim 1 , wherein the input image and the noise map have the same number of pixels in a single channel.

7. The image processing method according to claim 1 , wherein the input data includes data acquired by connecting the input image and the noise map in a channel direction.

8. The image processing method according to claim 1 , comprising subtracting a black level from a signal value of the input data prior to inputting the input data.

9. The image processing method according to claim 1 , wherein the task is to make higher a resolution or contrast of an image.

10. An image processing apparatus comprising:

an acquirer configured to acquire input data including an input image and a noise map representing a noise amount in the input image based on an optical black area corresponding to the input image; and

a processor configured to input the input data including (i) the input image and (ii) the noise map representing the noise amount in the input image based on the optical black area corresponding to the input image into a neural network to execute a task of a recognition or regression.

11. The image processing apparatus according to claim 10 , further comprising a memory configured to store information on a weight used for the neural network.

12. A non-transitory computer-readable storage medium storing a program for causing a computer to execute an image processing method,

wherein the image processing method includes:

acquiring input data including an input image and a noise map representing a noise amount in the input image based on an optical black area corresponding to the input image; and

inputting the input data including (i) the input image and (ii) the noise map representing the noise amount in the input image based on the optical black area corresponding to the input image into a neural network to execute a task of a recognition or regression.

13. An image processing system comprising a first device and a second device configured to communicate with the first device,

wherein the first device includes a transmitter configured to transmit a request for causing the second device to process a captured image, and

wherein the second device includes:

a receiver configured to receive the request transmitted by the transmitter;

an acquirer configured to acquire input data including the captured image and a noise map representing a noise amount in the captured image based on an optical black area corresponding to the captured image;

a processor configured to input the input data into a neural network to execute a task of a recognition or regression; and

a transmitter configured to transmit a result of the task.

14. An image processing method comprising:

acquiring ground truth data and input data that includes a training image and a noise map representing a noise amount in the training image based on an optical black area corresponding to the training image; and

learning a neural network for executing a task of a recognition or regression using the input data and the ground truth data.

15. A non-transitory computer-readable storage medium storing a program for causing a computer to execute an image processing method,

wherein the image processing method includes:

acquiring ground truth data and input data that includes a training image and a noise map representing a noise amount in the training image based on an optical black area corresponding to the training image; and

learning a neural network for executing a task of a recognition or regression using the input data and the ground truth data.

16. A method for manufacturing a learnt model comprising:

acquiring ground truth data and input data that includes a training image and a noise map representing a noise amount in the training image based on an optical black area corresponding to the training image; and

learning a neural network for executing a task of a recognition or regression using the input data and the ground truth data.

17. An image processing apparatus comprising:

an acquirer configured to acquire ground truth data and input data that includes a training image and a noise map representing a noise amount in the training image based on an optical black area corresponding to the training image; and

a learner configured to learn a neural network for executing a task of a recognition or regression using the input data and the ground truth data.