Refrigerator, server, and object recognition method of refrigerator

1. An object recognition method of a refrigerator with an image capturing device, a memory to store images and a processor, the method comprising:

obtaining by the image capturing device, a captured image of a storage compartment of the refrigerator;

based on a change of the captured image compared to an original image that is stored being identified by the processor, identifying whether a change has occurred in an image capturing direction of the image capturing device through which the captured image of the storage compartment is captured;

determining whether to perform an object recognition operation based on the identifying of whether the change has occurred in the image capturing direction of the image capturing device; and

based on no change in the image capturing direction being determined, performing, by the processor, the object recognition operation according to the captured image to thereby obtain information associated with an item in the storage compartment of the refrigerator.

2. The object recognition method according to claim 1 , further comprising:

based on the change in the image capturing direction being identified, storing the captured image by replacing with the original image.

3. The object recognition method according to claim 1 , wherein the identifying whether the change has occurred in the image capturing direction comprises

identifying the change in the image capturing direction by using an artificial intelligence model set to identify the change in the image capturing direction, and

wherein the artificial intelligence model is at least one of a convolutional neural network (CNN), a recurrent neural network (RNN), and a convolutional recurrent neural network (CRNN).

4. The object recognition method according to claim 1 , wherein the identifying whether the change has occurred in the image capturing direction comprises:

detecting a pixel value change region by comparing each of pixels between the original image and the captured image; and

based on an area of the pixel value change region being larger than a predetermined size, identifying the change has occurred in the image capturing direction.

5. The object recognition method according to claim 4 , wherein the identifying whether the change has occurred in the image capturing direction comprises:

detecting a plurality of second feature points corresponding to a plurality of first feature points in the original image from the captured image; and

calculating movement distances and movement directions of the plurality of second feature points by comparing a pixel coordinate value of each of the plurality of first feature points and the plurality of second feature points, and identifying the change in the image capturing direction based on the calculated movement distances and movement directions.

6. The object recognition method according to claim 5 , wherein the identifying the change in the image capturing direction based on the movement distances and the movement directions comprises:

based on the movement distances and the movement directions of the plurality of second feature points coinciding within a predetermined error range, determining that the image capturing direction is changed; and

based on a movement distance or a movement direction of at least one second feature point from among the plurality of second feature points being different from movement distances or movement directions of the remaining second feature points beyond the predetermined error range, determining that the image capturing direction is maintained.

7. The object recognition method according to claim 5 , wherein the identifying whether the change has occurred in the image capturing direction comprises:

based on a change ratio between a number of the plurality of second feature points and a number of the plurality of first feature points exceeding a predetermined threshold ratio, determining that the image capturing direction is maintained.

8. A refrigerator comprising:

a storage compartment configured to store an item;

an image capturing device configured to capture an image of the storage compartment;

a memory configured to store an original image previously captured by the image capturing device; and

a processor configured to,

obtain a captured image by controlling the image capturing device to capture an image of the storage compartment,

based on a change of the captured image compared to the original image being identified, identify whether an image capturing direction of the image capturing device is changed,

determine whether to perform an object recognition operation based on the identifying of whether the change has occurred in the image capturing direction of the image capturing device, and

based on no change in the image capturing direction being determined, perform the object recognition operation according to the captured image to thereby obtain information associated with the item in the storage compartment of the refrigerator.

9. The refrigerator according to claim 8 , wherein the processor is configured to, based on the change in the image capturing direction being identified, store the captured image in the memory by replacing with the original image.

10. The refrigerator according to claim 8 , wherein the processor is configured to identify the change in the image capturing direction by using an artificial intelligence model set to identify the change in the image capturing direction, and

wherein the artificial intelligence model is at least one of a convolutional neural network (CNN), a recurrent neural network (RNN), and a convolutional recurrent neural network (CRNN).

11. The refrigerator according to claim 8 , wherein the processor is configured to:

detect a pixel value change region by comparing pixels of the each of the original image and the captured image; and

based on an area of the pixel value change region being larger than a predetermined size, identify the change in the image capturing direction.

12. The refrigerator according to claim 11 , wherein the processor is configured to:

detect a plurality of second feature points corresponding to a plurality of first feature points in the original image from the captured image, calculate movement distances and movement directions of the plurality of second feature points by comparing a pixel coordinate value of each of the plurality of first feature points and the plurality of second feature points, and identify the change in the image capturing direction based on the calculated movement distances and movement directions.

13. The refrigerator according to claim 12 , wherein the processor is configured to:

based on the movement distances and the movement directions of the plurality of second feature points coinciding within a predetermined error range, determine that the image capturing direction is changed; and

based on a movement distance or a movement direction of at least one second feature point from among the plurality of second feature points being different from movement distances or movement directions of the remaining second feature points beyond the predetermined error range, determine that the image capturing direction is maintained.

14. The refrigerator according to claim 12 , wherein the processor is configured to:

based on a change ratio between a number of the plurality of second feature points and a number of the plurality of first feature points exceeding a predetermined threshold ratio, determine that the image capturing direction is maintained.

15. A server comprising:

a memory configured to store an original image obtained by capturing an image of a storage compartment of a refrigerator;

a communication device configured to receive a captured image obtained by capturing the storage compartment of the refrigerator from the refrigerator; and

wherein, based on whether a change has occurred in the captured image compared to the original image being confirmed, identify whether an image capturing direction of the captured image is changed,

based on the identifying of whether the change has occurred in the image capturing direction of an image capturing device, determine whether to perform an object recognition operation; and

based on no change of the image capturing direction being determined, perform, by a processor, the object recognition operation according to the captured image to thereby obtain information associated with an item in the storage compartment of the refrigerator.