Method and system for sorting and identifying medication via its label and/or package

1. A computer implemented method for building a medication library, comprising,

(a) receiving a plurality of raw images of a blister package of a medication;

(b) juxtaposing two of the plurality of raw images to produce a juxtaposed image, in which the two raw images are different from each other;

(c) processing the juxtaposed image to produce a reference image; and

(d) establishing the medication library with the aid of the reference image,

wherein the step (b) comprises,

(b-1) respectively processing the plurality of raw images to produce a plurality of first processed images respectively having defined contours,

(b-2) identifying the corners of each defined contours of the first processed images to determine the coordinates thereof;

(b-3) rotating each of the first processed images of the step (b-1) based on the determined coordinates of the step (b-2) to produce a plurality of second processed images; and

(b-4) juxtaposing any two of the second processed images to produce the juxtaposed image of the step (b); and

wherein the juxtaposed image produced in the step (b) fits a fixed template.

2. The computer implemented method of claim 1 , further comprising capturing the plurality of raw images of the blister package of the medication simultaneously prior to the step (a).

3. The computer implemented method of claim 1 , wherein each of the plurality of raw images of step (b-1) are subjected to treatments of, (i) a grayscale-converting treatment, (ii) a noise-reduction treatment, (iii) an edge-identification treatment, (iv) a convex hull treatment, and (v) a contouring treatment.

4. The computer implemented method of claim 1 , wherein the step (b-2) is carried out by a line transforming algorithm or a centroid algorithm.

5. The computer implemented method of claim 1 , wherein the juxtaposed image comprises the image of both sides of the blister package of the medication.

6. The computer implemented method of claim 1 , wherein the step (c) is carried out by a machine learning algorithm.

7. A computer implemented method for identifying a medication via its blister package, comprising,

(a) obtaining the front and back images of the blister package of the medication simultaneously;

(b) juxtaposing the front and back images of the step (a) to produce a candidate image that fits the fixed template;

(c) comparing the candidate image with a reference image of a medication library established by the method of claim 1 ; and

(d) outputting the result of the step (c).

8. The computer implemented method of claim 7 , wherein the step comprises,

(b-1) respectively processing the front and back images of the step (a) to produce two first processed images respectively having defined contours;

(b-2) identifying the corners of each defined contours of the two first processed images to determine the coordinates thereof;

(b-3) rotating each of the two first processed images of the step (b-1) based on the determined coordinates of the step (b-2) to produce two second processed images; and

(b-4) combining the two second processed images of the step (b-3) to produce the candidate image of the step (b).

9. The computer implemented method of claim 8 , wherein the front and back images of the step (b-1) are respectively subjected to treatments of, (i) a grayscale-converting treatment, (ii) a noise-reduction treatment, (iii) an edge-identification treatment, (iv) a convex hull treatment, and (v) a contouring treatment.

10. The computer implemented method of claim 8 , wherein the step (b-2) is carried out by a line transforming algorithm or a centroid algorithm.

11. The computer implemented method of claim 7 , wherein the step (c) is carried out by a machine learning algorithm.

12. The computer implemented method of claim 7 , further comprising transferring the candidate image into the medication library prior to the step (c).

13. A pharmaceutical management system, comprising,

an image capturing device configured to capture a plurality of images of a package of a medication;

an image processor programmed with instructions to execute a method for producing a candidate image, wherein the method comprises,

(1) respectively processing the plurality of images of the package of the medication to produce a plurality of first processed images respectively having defined contours;

(2) identifying the corners of each defined contours of the first processed images to determine the coordinates thereof;

(3) rotating each of the first processed images based on the identified coordinates of the step (2) to produce a plurality of second processed images; and

(4) juxtaposing two of the second processed images of the step (3) to produce the candidate image, in which the two second processed images are different from each other; and

a machine learning processor programmed with instructions to execute a method for comparing the candidate image with a reference image of a medication library established by the method of claim 1 .

14. The system of claim 13 , wherein the image capturing device comprises,

a transparent board on which the medication is placed; and

two image-capturing units individually disposed above each side of the transparent board.

15. The system of claim 13 , wherein each of the plurality of images of step (1) are subjected to treatments of, (i) a grayscale-converting treatment, (ii) a noise-reduction treatment, (iii) an edge-identification treatment, (iv) a convex hull treatment, and (v) a contouring treatment.

16. The system of claim 13 , wherein the step (2) is carried out by a line transforming algorithm or a centroid algorithm.

17. The system of claim 13 , wherein the method for comparing the candidate image with a reference image of a medication library is carried out by a machine learning algorithm.