Methods and systems for efficient image cropping and analysis
View Patent ↗A system and method for cropping a license plate image to facilitate license plate recognition by obtaining an image that includes the license plate image, dividing the image into multiple sub-blocks, computing an activity measure for each sub-block; determining an activity threshold, determining that a sub-block is an active sub-block by comparing the activity measure for the sub-block with the activity threshold, generating a second image of the license plate information, where the second image includes the active sub-block, and obtaining the license plate information based on the second image.
1. A method comprising:
obtaining an image comprising license plate information;
dividing the image into a plurality of sub-blocks;
computing a spatial activity measure for each sub-block of the plurality of sub-blocks, wherein the spatial activity measure includes a two-dimensional discrete cosine transform (DCT);
generating a one-dimensional activity profile for the image based on the spatial activity measure for each sub-block;
determining an activity threshold based on a predetermined percentage;
determining that a sub-block of the plurality of sub-blocks is an active sub-block by comparing the spatial activity measure for the sub-block with the activity threshold;
generating, using one or more processors, a second image of the license plate information, wherein the second image comprises the active sub-block; and
obtaining the license plate information based on the second image.
2. The method of claim 1 , wherein, prior to obtaining the image, the image is generated by vertically cropping a third image comprising the license plate information.
3. The method of claim 1 , wherein, prior to obtaining the image, the image is generated by removing tilt from a third image comprising the license plate information.
4. The method of claim 1 , further comprising performing a frequency analysis on each sub-block of the plurality of sub-blocks, wherein the spatial activity measure for each sub-block is based on the frequency analysis of that sub-block.
5. The method of claim 1 , further comprising determining that a second sub-block of the plurality of sub-blocks is inactive, wherein:
the spatial activity measure of the second sub-block is less than the activity threshold; and
the second sub-block is determined to be inactive based on the second sub-block being between the active sub-block and a third active sub-block in the image.
6. The method of claim 1 , further comprising determining that a second sub-block of the plurality of sub-blocks is an inactive sub-block by comparing the spatial activity measure for the second sub-block with the activity threshold, wherein the second image does not comprise the inactive sub-block.
7. The method of claim 6 , further comprising determining that a third sub-block of the plurality of sub-blocks is an inactive sub-block by determining that the third sub-block is between the inactive sub-block and an edge of the image.
8. The method of claim 1 , further comprising determining that a second sub-block of the plurality of sub-blocks is active, wherein:
the spatial activity measure of the second sub-block is less than the activity threshold; and
the second sub-block is determined to be active based on the second sub-block being between the active sub-block and a third active sub-block in the image.
9. The method of claim 1 , further comprising:
determining a third image of the license plate comprising only active sub-blocks;
determining that the third image is overcropped with respect the license plate information based on comparing a ratio of the third image with an expected license plate ratio; and
wherein, the second image additionally comprises one or more inactive sub-blocks.
10. The method of claim 1 , wherein the spatial activity measure is computed using the formula:
a
ij
=
∑
k
·
l
(
k
+
l
>
0
)
C
kl
2
wherein C kl represents resultant coefficients of a two-dimensional DCT performed on a sub-block B ij , and a ij represents the spatial activity measure for the sub-block B ij .
11. A system comprising:
a processing system comprising one or more processors; and
a memory system comprising one or more computer-readable media, wherein the one or more computer-readable media contain instructions that, when executed by the processing system, cause the processing system to perform operations comprising:
obtaining an image comprising license plate information;
dividing the image into a plurality of sub-blocks;
computing a spatial activity measure for each sub-block of the plurality of sub-blocks, wherein the spatial activity measure includes a two-dimensional discrete cosine transform (DCT);
generating a one-dimensional activity profile for the image based on the spatial activity measure for each sub-block;
determining an activity threshold based on a predetermined percentage;
determining that a sub-block of the plurality of sub-blocks is an active sub-block by comparing the spatial activity measure for the sub-block with the activity threshold;
generating, using one or more processors, a second image of the license plate information, wherein the second image comprises the active sub-block; and
obtaining the license plate information based on the second image.
12. The system of claim 11 , wherein, prior to obtaining the image, the image is generated by vertically cropping a third image comprising the license plate information.
13. The system of claim 11 , wherein, prior to obtaining the image, the image is generated by removing tilt from a third image comprising the license plate information.
14. The system of claim 11 , the operations further comprising performing a frequency analysis on each sub-block of the plurality of sub-blocks, wherein the spatial activity measure for each sub-block is based on the frequency analysis of that sub-block.
15. The system of claim 11 , the operations further comprising determining that a second sub-block of the plurality of sub-blocks is inactive, wherein:
the spatial activity measure of the second sub-block is less than the activity threshold; and
the second sub-block is determined to be inactive based on the second sub-block being between the active sub-block and a third active sub-block in the image.
16. The system of claim 11 , the operations further comprising determining that a second sub-block of the plurality of sub-blocks is an inactive sub-block by comparing the spatial activity measure for the second sub-block with the activity threshold, wherein the second image does not comprise the inactive sub-block.
17. The system of claim 16 , the operations further comprising determining that a third sub-block of the plurality of sub-blocks is an inactive sub-block by determining that the third sub-block is between the inactive sub-block and an edge of the image.
18. The system of claim 11 , the operations further comprising determining that a second sub-block of the plurality of sub-blocks is active, wherein:
the spatial activity measure of the second sub-block is less than the activity threshold; and
the second sub-block is determined to be active based on the second sub-block being between the active sub-block and a third active sub-block in the image.
19. The system of claim 11 , the operations further comprising:
determining a third image of the license plate comprising only active sub-blocks;
determining that the third image is overcropped with respect the license plate information based on comparing a ratio of the third image with an expected license plate ratio; and
wherein, the second image additionally comprises one or more inactive sub-blocks.
20. The system of claim 11 , wherein the spatial activity measure is computed using the formula:
a
ij
=
∑
k
·
l
(
k
+
l
>
0
)
C
kl
2
wherein C kl represents resultant coefficients of a two-dimensional DCT performed on a sub-block B ij , and a ij represents the spatial activity measure for the sub-block B ij .