Image processing apparatus and computer program product

1. An image processing apparatus comprising:

a control unit configured with a microcomputer, the control unit includes:

a feature-quantity calculating unit that calculates feature quantities of target regions each indicating a tracking object in respective target images, the target images being obtained by capturing the tracking object at a plurality of time points;

a provisional-tracking processing unit that performs provisional tracking of the target region by associating the target regions of the target images with each other using the calculated feature quantities; and

a final-tracking processing unit that acquires a final tracking result of the target region based on a result of the provisional tracking, wherein

the provisional-tracking processing unit includes an origin-image setting unit that sets the target images at a plurality of time points within a time range for which the provisional tracking is performed as origin images each being an origin of the provisional tracking, and the provisional-tracking processing unit performs the provisional tracking for each of the origin images that are set by the origin-image setting unit, and

the final-tracking processing unit acquires the final tracking result of the target region by totaling a plurality of results of the provisional tracking performed for the respective origin images.

2. The image processing apparatus according to claim 1 , wherein the provisional-tracking processing unit performs the provisional tracking toward earlier time and later time in a time series.

3. The image processing apparatus according to claim 1 , wherein the provisional-tracking processing unit performs the provisional tracking by associating the target regions of the target images having different time intervals with each other.

4. The image processing apparatus according to claim 1 , wherein the provisional-tracking processing unit includes

a provisional ID assigning unit that assigns a provisional ID for identifying the target region, to each of the target regions in the target images;

a correspondence-index calculating unit that calculates a correspondence index value that indicates a degree of correspondence of the target regions of the target images at different time points; and

a provisional ID propagating unit that associates the target regions of the target images with each other by sequentially propagating a provisional ID of the target region, the correspondence index value of which is highest, to the target region in the target image at a time point earlier or later in a time series from the target region in the origin image.

5. The image processing apparatus according to claim 4 , wherein the provisional ID assigning unit assigns, when the provisional ID propagating unit determines that the target images have no target region, the correspondence index value of which is higher than a predetermined threshold, a new provisional ID to the target region.

6. The image processing apparatus according to claim 4 , wherein the correspondence index value is a value calculated based on a distance between the target regions in a feature space that is defined by at least one of feature quantities of a position, a size, a shape, a luminance, and a color of the target region.

7. The image processing apparatus according to claim 4 , wherein the correspondence index value is a value that is obtained by normalizing an area in which the target regions are overlapped with each other by a sum of areas of the target regions.

8. The image processing apparatus according to claim 1 , wherein the feature quantity includes a feature quantity of at least one of a position, a size, a shape, a luminance, and a color of the target region.

9. The image processing apparatus according to claim 1 , wherein the target region indicating the tracking object is a region indicating a cell.

10. A non-transitory computer program medium having stored thereon programmed instructions for tracking a target area indicating a tracking object present in target images obtained by capturing a tracking object at a plurality of time points in a time series, wherein the instructions, when executed by a computer, cause the computer to perform:

calculating feature quantities of target regions each indicating a tracking object in respective target images, the target images being obtained by capturing the tracking object at a plurality of time points;

performing provisional tracking of the target region by associating the target regions of the target images with each other using the calculated feature quantities; and

acquiring a final tracking result of the target region based on a result of the provisional tracking, wherein

the instructions further causing the computer to perform setting the target images at a plurality of time points within a time range for which the provisional tracking is performed, as origin images each being an origin of the provisional tracking,

the provisional-tracking is performed for each of the origin images that are set at the setting the target images, and

the acquiring the final tracking result includes acquiring the final tracking result of the target region by totaling a plurality of results of the provisional tracking performed for the respective origin images.

11. The medium according to claim 10 , wherein the provisional-tracking is performed toward earlier time and later time in a time series.

12. The medium according to claim 10 , wherein the provisional-tracking is performed by associating the target regions of the target images having different time intervals with each other.

13. The medium according to claim 10 , wherein the instructions further causing the computer to perform:

assigning a provisional ID for identifying the target region, to each of the target regions in the target images;

calculating a correspondence index value that indicates a degree of correspondence of the target regions of the target images at different time points; and

associating the target regions of the target images with each other by sequentially propagating a provisional ID of the target region, the correspondence index value of which is highest, to the target region in the target image at a time point earlier or later in a time series from the target region in the origin image.

14. The medium according to claim 13 , wherein the assigning the provisional ID includes assigning, when it is determined that the target images have no target region, the correspondence index value of which is higher than a predetermined threshold, a new provisional ID to the target region.

15. The medium according to claim 13 , wherein the correspondence index value is a value calculated based on a distance between the target regions in a feature space that is defined by at least one of feature quantities of a position, a size, a shape, a luminance, and a color of the target region.

16. The medium according to claim 13 , wherein the correspondence index value is a value that is obtained by normalizing an area in which the target regions are overlapped with each other by a sum of areas of the target regions.

17. The medium according to claim 10 , wherein the feature quantity includes a feature quantity of at least one of a position, a size, a shape, a luminance, and a color of the target region.

18. The medium according to claim 10 , wherein the target region indicating the tracking object is a region indicating a cell.