Method for barcode detection, barcode detection system, and program therefor

1. A method for detecting a barcode, comprising:

detecting a plurality of blob regions from an image;

for each detected blob in the blob region, obtaining imaginary lines bisecting the detected blob perpendicular at the middle of the detected blob;

determining at least one cluster of the imaginary lines in a feature space according to slopes and positions of the imaginary lines; and

grouping the blobs in one cluster into a rectangular shape corresponding to the barcode.

2. The method of claim 1 , wherein the method further comprises the step of:

allocating at least one rectangular shape to a blob region corresponding to the barcode and deleting the rectangular shape depending on the size of the barcode before obtaining the imaginary lines.

3. The method of claim 1 , wherein the method further comprises the step of:

refining allocation of the blobs to at least one rectangular shape after the step of grouping by using gaps between the blobs.

4. The method of claim 1 , wherein the step of determining at least one cluster comprises the step of:

applying a Hough transformation to the imaginary lines and generating a feature vector with respect to each of the imaginary lines.

5. The method of claim 1 , wherein the step of determining at least one cluster further comprises the step of:

clustering the feature vectors into at least one cluster depending on distances in the feature space defined in Cartesian coordinate system.

6. A non-transitory computer readable storage medium tangibly embodying a computer readable program code having thereon computer readable instructions which, when implemented, cause a computer device to carry out the steps of a method for detecting a barcode, the method comprising:

detecting a plurality of blob regions from an image;

for each detected blob in the blob region, obtaining imaginary lines bisecting the detected blob perpendicular at the middle of the detected blob;

determining at least one cluster of the imaginary lines in a feature space according to slopes and positions of the imaginary lines; and

grouping the blobs in one cluster to a rectangular shape corresponding to the barcode.

7. The computer readable storage medium according to claim 6 , wherein the method further comprises the step of:

allocating at least one rectangular shape to a blob region corresponding to the barcode and deleting the rectangular shape depending on a size of the barcode before obtaining the imaginary lines.

8. The computer readable storage medium according to claim 6 , wherein the method further comprises the step of:

refining allocation of the blobs to at least one rectangular shape after the step of grouping by using gaps between the blobs.

9. The computer readable storage medium according to claim 6 , wherein the step of determining at least one cluster comprises the step of:

applying a Hough transformation to the imaginary lines and generating a feature vector with respect to each of the imaginary lines.

10. The computer readable storage medium according to claim 6 , wherein the step of determining at least one cluster further comprises the step of:

clustering the feature vectors into at least one cluster depending on distances in the feature space defined in Cartesian coordinate system.

11. A barcode detection system comprising an information processing apparatus, which comprises:

an image storage part comprising a memory, the memory storing an image including at least one barcode;

a blob filtering part for allocating rectangular shapes to the blobs and deleting rectangular shape having height and width ratios depending on a predetermined threshold; and

a clustering part for generating imaginary lines bisecting the blobs by applying Hough transformation to generate feature vectors in a feature space defined in a Cartesian coordinate system and projecting the feature vector to the feature space;

wherein the clustering part clusters the feature vectors depending on a distance in the feature space to cluster the feature vectors into the rectangular shape.

12. The barcode detection system of claim 11 , wherein the information processing apparatus further comprises:

a refining part and the refining part omits the blobs in a particular rectangle shape depending on gaps between the blobs.

13. The barcode detection system of claim 12 , wherein the refining part merges the rectangular shapes into one different rectangular shape depending on minimal and maximal gap lengths of the blobs.

14. The barcode detection system of claim 11 , wherein the image including at least one barcode is received from a network by the information processing apparatus and returned a recognition result to an apparatus connected to the network.