Image processing apparatus for generating a combined image from plural captured images having been subjected to position alignment, and image processing method
An image processing apparatus includes one or more processors including hardware. The one or more processors are configured to: divide, regarding a plurality of images acquired by capturing images of an imaging subject over time, the respective images into a plurality of regions; calculate, for the respective divided regions, motion vectors by detecting movements of the imaging subject; detect luminances and contrasts of the respective regions and detect specific regions where the detected luminances and contrasts satisfy determination conditions, the determination conditions being that the luminances are equal to or greater than a first threshold and that the contrasts are equal to or less than a second threshold; select the motion vectors to be used by excluding the motion vectors of the detected specific regions from the calculated motion vectors; and generate a combined image by performing position alignment of the plurality of images by using the selected motion vectors.
1. An image processing apparatus comprising at least one processor comprising hardware, the at least one processor being configured to:
divide, regarding a plurality of images acquired by capturing images of an imaging subject over time, each of the respective images into a plurality of regions, a size, shape, and layout of the divided regions being the same in all of the respective images;
calculate, for each of the divided regions in all of the respective images, a motion vector by detecting movements of the imaging subject in the divided region;
detect a luminance and a contrast of each of the divided regions, and detect specific regions among the divided regions whose detected luminances and contrasts satisfy determination conditions, the determination conditions including a condition that the luminances are equal to or greater than a first threshold and a condition that the contrasts are equal to or less than a second threshold;
select motion vectors to be used by excluding motion vectors of the detected specific regions from the calculated motion vectors; and
generate a combined image by performing position alignment of the plurality of images by using the selected motion vectors.
2. The image processing apparatus according to claim 1 , wherein the detecting of the specific regions comprises detecting the specific regions by using positions thereof in their corresponding images as a condition.
3. The image processing apparatus according to claim 1 , wherein the detecting of the specific regions comprises detecting one of the divided regions as a specific region in a case in which other divided regions disposed so as to flank the one of the divided regions have luminances and contrasts that satisfy the determination conditions.
4. The image processing apparatus according to claim 1 , wherein the detecting of the specific regions comprises detecting one of the divided regions as a specific region only in a case in which a number of the divided regions that satisfy the determination conditions is greater than a number of the divided regions that do not satisfy the determination conditions in a prescribed area centered on the one of the divided regions.
5. The image processing apparatus according to claim 1 , wherein the detecting of the specific regions comprises performing expansion processing on the divided regions that do not satisfy the determination conditions and subsequently performing contraction processing thereon, thus re-determining whether or not the divided regions having been subject to the expansion and contraction processing satisfy the determination conditions.
6. The image processing apparatus according to claim 1 ,
wherein the at least one processor is further configured to determine an image-capturing scene by processing the images, and
wherein, in a case in which the determined image-capturing scene is a specific scene, the selecting of the motion vectors excludes the motion vectors of the detected specific regions.
7. An image processing method comprising:
dividing, regarding a plurality of images acquired by capturing images of an imaging subject over time, each of the respective images into a plurality of regions, a size, shape, and layout of the divided regions being the same in all of the respective images;
calculating, for each of the divided regions in all of the respective images, a motion vector by detecting movements of the imaging subject in the divided region;
detecting a luminance and a contrast of each of the divided regions;
detecting specific regions among the divided regions whose detected luminances and contrasts satisfy determination conditions, the determination conditions including a condition that the luminances are equal to or greater than a first threshold and a condition that the contrasts are equal to or less than a second threshold;
selecting motion vectors to be used by excluding motion vectors of the detected specific regions from the calculated motion vectors; and
generating a combined image by performing position alignment of the plurality of images by using the selected motion vectors.