Image processing apparatus, image processing method, and non-transitory computer readable medium

1 . An image processing apparatus configured to perform recognition processing for a target object in an input image, comprising:

at least one memory storing a program; and

at least one processor which, by executing the program, causes the image processing apparatus to:

perform the recognition processing for the target object in a first image having a first resolution acquired based on the input image and acquire a first recognition result;

determine whether or not a reliability of the first recognition result satisfies a predetermined standard; and

perform the recognition processing for the target object in a second image which has a higher resolution than the first resolution acquired based on the input image, and acquire a second recognition result, in a case where it is determined that the reliability of the first recognition result does not satisfy the predetermined standard, wherein

the first recognition result and the second recognition result indicate likelihood to which the target object belongs to a predetermined classification type, and

the at least one processor causes the image processing apparatus to determine that the reliability of the first recognition result satisfies the predetermined standard in a case where the likelihood indicated by the first recognition result is a predetermined likelihood or more, or in a case where the likelihood difference between the classification types using the likelihood indicated by the first recognition result is a predetermined likelihood difference or more.

2 . The image processing apparatus according to claim 1 , wherein

the at least one processor causes the image processing apparatus to acquire a third recognition result based on at least one of the first recognition result and the second recognition result, depending on the reliability of the first recognition result and/or the reliability of the second recognition result.

3 . The image processing apparatus according to claim 1 , wherein

the at least one processor causes the image processing apparatus to acquire a third recognition result by integrating the first recognition result and the second recognition result, based on the reliability of the first recognition result and the reliability of the second recognition result.

4 . The image processing apparatus according to claim 1 , wherein

the at least one processor further causes the image processing apparatus to output the first recognition result in a case where it is determined that the reliability of the first recognition result satisfies a predetermined standard.

5 . The image processing apparatus according to claim 1 , wherein

the at least one processor causes the image processing apparatus to output one of the first recognition result and the second recognition result having a higher reliability, as the recognition result, in a case where it is determined that the reliability of the first recognition result does not satisfy the predetermined standard.

6 . The image processing apparatus according to claim 1 , wherein

the at least one processor causes the image processing apparatus to integrate the first recognition result and the second recognition result, in a case where it is determined that the reliability of the first recognition result does not satisfy the predetermined standard.

7 . The image processing apparatus according to claim 1 , wherein

the at least one processor causes the image processing apparatus to perform recognition processing for the target object in the second image and acquire the second recognition result, in a case where it is determined that the reliability of the first recognition result satisfies the predetermined standard.

8 . An image processing apparatus configured to perform recognition processing for a target object in an input image, comprising:

at least one memory storing a program; and

at least one processor which, by executing the program, causes the image processing apparatus to:

perform the recognition processing for the target object in a first image having a first resolution acquired based on the input image and acquire a first recognition result;

determine whether or not a reliability of the first recognition result satisfies a predetermined standard;

perform the recognition processing for the target object in a second image which has a higher resolution than the first resolution acquired based on the input image, and acquire a second recognition result, in a case where it is determined that the reliability of the first recognition result does not satisfy the predetermined standard; and

determine a coefficient to reduce a resolution of the input image, wherein

the first image is an image having a resolution that is acquired by using a first coefficient determined by the image processing apparatus, and

the second image is an image having a resolution that is acquired by using a second coefficient that generates a higher resolution than the first coefficient determined by the image processing apparatus.

9 . An image processing apparatus configured to perform recognition processing for a target object in an input image, comprising:

at least one memory storing a program; and

at least one processor which, by executing the program, causes the image processing apparatus to:

perform the recognition processing for the target object in a first image having a first resolution acquired based on the input image and acquire a first recognition result;

determine whether or not a reliability of the first recognition result satisfies a predetermined standard; and

perform the recognition processing for the target object in a second image which has a higher resolution than the first resolution acquired based on the input image, and acquire a second recognition result, in a case where it is determined that the reliability of the first recognition result does not satisfy the predetermined standard, wherein

the first recognition result and the second recognition result are recognition results of recognition processing using coordinate values of a landmark that indicates a position of a feature of the target object in the input image, and

the at least one processor causes the image processing apparatus to determine that the reliability of the first recognition result satisfies the predetermined standard in a case where the landmark exists at a predetermined position based on brightness of the input image in the first recognition result.

10 . The image processing apparatus according to claim 9 , wherein

the at least one processor causes the image processing apparatus to acquire a third recognition result based on at least one of the first recognition result and the second recognition result, depending on the reliability of the first recognition result and/or the reliability of the second recognition result.

11 . The image processing apparatus according to claim 9 , wherein

the at least one processor causes the image processing apparatus to acquire a third recognition result by integrating the first recognition result and the second recognition result, based on the reliability of the first recognition result and the reliability of the second recognition result.

12 . The image processing apparatus according to claim 9 , wherein

the at least one processor further causes the image processing apparatus to output the first recognition result in a case where it is determined that the reliability of the first recognition result satisfies a predetermined standard.

13 . The image processing apparatus according to claim 9 , wherein

the at least one processor causes the image processing apparatus to output one of the first recognition result and the second recognition result having a higher reliability, as the recognition result, in a case where it is determined that the reliability of the first recognition result does not satisfy the predetermined standard.

14 . The image processing apparatus according to claim 9 , wherein

the at least one processor causes the image processing apparatus to integrate the first recognition result and the second recognition result, in a case where it is determined that the reliability of the first recognition result does not satisfy the predetermined standard.

15 . The image processing apparatus according to claim 9 , wherein

the at least one processor causes the image processing apparatus to perform recognition processing for the target object in the second image and acquire the second recognition result, in a case where it is determined that the reliability of the first recognition result satisfies the predetermined standard.

16 . An image processing apparatus configured to perform recognition processing for a target object in an input image, comprising:

at least one memory storing a program; and

at least one processor which, by executing the program, causes the image processing apparatus to:

perform the recognition processing for the target object in a first image having a first resolution acquired based on the input image and acquire a first recognition result;

determine whether or not a reliability of the first recognition result satisfies a predetermined standard; and

perform the recognition processing for the target object in a second image which has a higher resolution than the first resolution acquired based on the input image, and acquire a second recognition result, in a case where it is determined that the reliability of the first recognition result does not satisfy the predetermined standard, wherein

the first image is at least one first patch image having the first resolution, which is part extracted from the input image,

the second image is at least one second patch image having a second resolution higher than the first resolution, which is a part extracted from the input image, and

each of the first recognition result and the second recognition result indicates a likelihood that a target cross section is included in the first patch image or the second patch image respectively.

17 . The image processing apparatus according to claim 16 , wherein

the at least one processor causes the image processing apparatus to determine that the reliability of the first recognition result satisfies the predetermined standard in a case where a number of first patch images, of which likelihood indicated in the first recognition result is a predetermined likelihood or more, satisfies a predetermined condition.

18 . An image processing method comprising steps of:

performing recognition processing for a target object in an input image;

performing the recognition processing for the target object in a first image having a first resolution acquired based on the input image, and acquiring a first recognition result;

determining whether or not a reliability of the first recognition result satisfies a predetermined standard; and

performing the recognition processing for the target object in a second image which has a higher resolution than the first resolution acquired based on the input image and acquiring a second recognition result, in a case where it is determined that the reliability of the first recognition result does not satisfy the predetermined standard, wherein

the first recognition result and the second recognition result indicate likelihood to which the target object belongs to a predetermined classification type, and

the determining determines that the reliability of the first recognition result satisfies the predetermined standard in a case where the likelihood indicated by the first recognition result is a predetermined likelihood or more, or in a case where the likelihood difference between the classification types using the likelihood indicated by the first recognition result is a predetermined likelihood difference or more.

19 . A non-transitory computer readable medium that stores a program, wherein the program causes a computer to execute steps of:

performing recognition processing for a target object in an input image;

performing the recognition processing for the target object in a first image having a first resolution acquired based on the input image, and acquiring a first recognition result;

determining whether or not a reliability of the first recognition result satisfies a predetermined standard; and

performing the recognition processing for the target object in a second image which has a higher resolution than the first resolution acquired based on the input image and acquiring a second recognition result, in a case where it is determined that the reliability of the first recognition result does not satisfy the predetermined standard, wherein

the first recognition result and the second recognition result indicate likelihood to which the target object belongs to a predetermined classification type, and

the determining determines that the reliability of the first recognition result satisfies the predetermined standard in a case where the likelihood indicated by the first recognition result is a predetermined likelihood or more, or in a case where the likelihood difference between the classification types using the likelihood indicated by the first recognition result is a predetermined likelihood difference or more.