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

1. An image processing apparatus comprising:

a processor comprising hardware, the processor being configured to

obtain a plurality of images that are temporally continuous, the plurality of images being generated by continuously imaging a subject illuminated with illumination light;

calculate a correction coefficient on the basis of a correction target frame among the plurality of images;

revise the correction coefficient of the correction target frame on the basis of the correction coefficient of each of a plurality of frames within a predetermined time set beforehand from a shooting time of the correction target frame; and

create a display image on the basis of the correction target frame and the correction coefficient.

2. The image processing apparatus according to claim 1 , wherein the plurality of images includes at least one of an image of the subject, the image being generated by imaging the subject under illumination of the illumination light having a predetermined wavelength band, and an image generated by imaging a living body lumen.

3. The image processing apparatus according to claim 1 ,

wherein the processor is further configured to

set the plurality of frames to be used for calculating a representative value of the correction coefficient; and

calculate the representative value of the correction coefficient on the basis of the correction coefficient of the correction target frame and the correction coefficient of each of the plurality of frames, and

set the representative value as a revised correction coefficient of the correction target frame.

4. The image processing apparatus according to claim 3 ,

wherein the processor is further configured to calculate deviation of the correction coefficient of the correction target frame or one or more correction coefficients of the plurality of frames, with respect to the correction coefficient of a frame in a specific time-series section.

5. The image processing apparatus according to claim 4 , wherein the processor is further configured to calculate a difference between the correction coefficient of the correction target frame and the one or more correction coefficients of the plurality of frames, as the deviation.

6. The image processing apparatus according to claim 4 , wherein the processor is further configured to calculate the deviation from a distribution state of the correction coefficients based on the correction coefficient of each of the plurality of frames.

7. The image processing apparatus according to claim 6 , wherein the processor is further configured to

calculate one of median, an average value, and a Mahalanobis distance from the distribution state, and

calculate a difference between the median or the average value and the correction coefficient of the correction target frame, as the deviation, or calculate the Mahalanobis distance, as the deviation.

8. The image processing apparatus according to claim 4 ,

wherein the processor is further configured to calculate the representative value of the correction coefficient of the correction target frame on the basis of the deviation.

9. The image processing apparatus according to claim 8 , wherein the processor is further configured to calculate weight of the correction target frame and weight of each of the plurality of frames with respect to the correction coefficient on the basis of the deviation, and calculate the representative value on the basis of the calculated weight.

10. The image processing apparatus according to claim 8 , wherein the processor is further configured to calculate the representative value on the basis of the correction coefficient of each of the plurality of frames in a case where the deviation is greater than a predetermined value, and calculate a maximum value of the correction coefficients in the plurality of frames used for calculating the deviation, as the representative value, when the deviation is the predetermined value or less.

11. The image processing apparatus according to claim 3 ,

wherein the processor is further configured to

determine one of an acquisition timing of the image used for correction, and ease of acquisition of the correction coefficient, and

calculate the representative value on the basis of a determination result by the determining.

12. The image processing apparatus according to claim 11 , wherein the processor is further configured to determine an acquisition status of the image to be used for correction.

13. The image processing apparatus according to claim 12 , wherein the processor is further configured to calculate the representative value on the basis of a determination result by the determining.

14. The image processing apparatus according to claim 13 , wherein the processor is further configured to calculate weight of the correction target frame and weight of each of the plurality of frames with respect to the correction coefficient on the basis of a determination result by the determining, and calculate the representative value on the basis of the calculated weight.

15. The image processing apparatus according to claim 14 , wherein processor is further configured to calculate the representative value with increased weight for the correction coefficient of each of the plurality of frames with respect to the correction coefficient, in accordance with a degree or possibility of being any one of a frame close to a shooting time of the correction target frame, a frame in which the image as a correction target has been updated, and a frame having an image in which information regarding the correction object appears in high contrast has been updated.

16. The image processing apparatus according to claim 11 ,

wherein the processor is configured to calculate a misalignment amount between images used for correction.

17. The image processing apparatus according to claim 16 ,

wherein the processor is further configured to calculate weight of the correction target frame and weight of each of the plurality of frames with respect to the correction coefficient on the basis of the misalignment amount, and calculate the representative value on the basis of the calculated weight.

18. The image processing apparatus according to claim 1 , wherein the correction coefficient is a coefficient in enhancement of any one or more of tissues, mucosa, and a blood vessel in a living body, or a coefficient for combining images.

19. An image processing method to be executed by an image processing apparatus, the method comprising:

obtaining a plurality of images that are temporally continuous, the plurality of images being generated by continuously imaging a subject illuminated with illumination light;

calculating a correction coefficient for correcting each of the plurality of images on the basis of a correction target frame among the plurality of images;

revising the correction coefficient of the correction target frame on the basis of the correction coefficient of each of a plurality of frames within a predetermined time set beforehand from a shooting time of the correction target frame; and

creating a display image on the basis of the correction target frame and the correction coefficient.

20. A non-transitory computer readable recording medium storing a program that causes a computer to execute a process, the process comprising:

obtaining a plurality of images that are temporally continuous, the plurality of images being generated by continuously imaging a subject illuminated with illumination light;

calculating a correction coefficient for correcting each of the plurality of images on the basis of a correction target frame among the plurality of images;

revising the correction coefficient of the correction target frame on the basis of the correction coefficient of each of a plurality of frames within a predetermined time set beforehand from a shooting time of the correction target frame; and

creating a display image on the basis of the correction target frame and the correction coefficient.