Automated tattoo recognition techniques
In some implementations, a computer-implemented method is capable of automatically segmenting and detecting a tattoo within an image. An image may be initially obtained. A block coverage pattern that identifies multiple blocks within the obtained image may be determined. A set of processing operations may then be performed for each block. The processing operations may include calculating a plurality of statistical features. A confidence score reflecting a likelihood that at least a portion of the block includes a predetermined graphical attribute associated with tattoos may be calculated. A subset of the multiple blocks of the image that have a respective confidence score greater than a predetermined threshold value may be identified. A portion of the image that includes one or more blocks from among the subset of the multiple blocks may then be determined to correspond to a tattoo.
1. A method performed by one or more processors, the method comprising:
obtaining, by the one or more processors, an image that likely includes a tattoo;
determining, by the one or more processors, a set of one or more segmentation parameters for the image;
identifying, by the one or more processors, a plurality of blocks associated with the tattoo based on the determined set of one or more segmentation parameters for the image, wherein each block corresponds a particular region of the image that (i) likely includes the tattoo and (ii) comprises an overlapping portion included in one or more adjacent blocks;
computing, by the one or more processors, a set of feature statistics for each block included in the plurality of blocks;
generating, by the one or more processors, a segmentation mask for the image based on the set of feature statistics computed for the plurality of blocks; and
providing, by the one or more processors, the segmentation mask for output.
2. The method of claim 1 , wherein the plurality of blocks are arranged in the image as a two-dimensional array of overlapping blocks.
3. The method of claim 2 , further comprising computing a confidence score for each of the plurality of blocks, the confidence scores representing a respective likelihood that at least a portion of a block includes a predetermined graphical attribute associated with a tattoo.
4. The method of claim 3 , further comprising:
identifying a subset of the plurality of blocks that have confidence scores satisfying a predetermined threshold; and
wherein the segmentation mask for the image is generated based on the identified subset of the plurality of blocks.
5. The method of claim 3 , wherein:
the segmentation mask comprises a binary image; and
pixel values of pixels included in the binary image are determined based on the confidence scores computed for the plurality of blocks.
6. The method of claim 1 , wherein generating the segmentation mask for the image comprises:
grouping the plurality of blocks based on the feature statistics computed for the plurality of blocks; and
identifying one or more regions that each include blocks that have been grouped based on the feature statistics computed for the plurality of blocks.
7. The method of claim 1 , wherein the set of feature statistics computed for each block included in the plurality of blocks comprises an order statistic that indicates a median value for a characteristic for the plurality of blocks.
8. A system comprising:
one or more computers; and
one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
obtaining, by the one or more processors, an image that likely includes a tattoo;
determining, by the one or more processors, a set of one or more segmentation parameters for the image;
identifying, by the one or more processors, a plurality of blocks associated with the tattoo based on the determined set of one or more segmentation parameters for the image, wherein each block corresponds a particular region of the image that (i) likely includes the tattoo and (ii) comprises an overlapping portion included in one or more adjacent blocks;
computing, by the one or more processors, a set of feature statistics for each block included in the plurality of blocks;
generating, by the one or more processors, a segmentation mask for the image based on the set of feature statistics computed for the plurality of blocks; and
providing, by the one or more processors, the segmentation mask for output.
9. The system of claim 8 , wherein the plurality of blocks are arranged in the image as a two-dimensional array of overlapping blocks.
10. The system of claim 9 , wherein the operations further comprise computing a confidence score for each of the plurality of blocks, the confidence scores representing a respective likelihood that at least a portion of a block includes a predetermined graphical attribute associated with a tattoo.
11. The system of claim 10 , wherein the operations further comprise:
identifying a subset of the plurality of blocks that have confidence scores satisfying a predetermined threshold; and
wherein the segmentation mask for the image is generated based on the identified subset of the plurality of blocks.
12. The system of claim 10 , wherein:
the segmentation mask comprises a binary image; and
pixel values of pixels included in the binary image are determined based on the confidence scores computed for the plurality of blocks.
13. The system of claim 8 , wherein generating the segmentation mask for the image comprises:
grouping the plurality of blocks based on the feature statistics computed for the plurality of blocks; and
identifying one or more regions that each include blocks that have been grouped based on the feature statistics computed for the plurality of blocks.
14. The system of claim 8 , wherein the set of feature statistics computed for each block included in the plurality of blocks comprises an order statistic that indicates a median value for a characteristic for the plurality of blocks.
15. A non-transitory computer-readable storage device encoded with computer program instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:
obtaining, by the one or more processors, an image that likely includes a tattoo;
determining, by the one or more processors, a set of one or more segmentation parameters for the image;
identifying, by the one or more processors, a plurality of blocks associated with the tattoo based on the determined set of one or more segmentation parameters for the image, wherein each block corresponds a particular region of the image that (i) likely includes the tattoo and (ii) comprises an overlapping portion included in one or more adjacent blocks;
computing, by the one or more processors, a set of feature statistics for each block included in the plurality of blocks;
generating, by the one or more processors, a segmentation mask for the image based on the set of feature statistics computed for the plurality of blocks; and
providing, by the one or more processors, the segmentation mask for output.
16. The device of claim 15 , wherein the plurality of blocks are arranged in the image as a two-dimensional array of overlapping blocks.
17. The device of claim 16 , wherein the operations further comprise computing a confidence score for each of the plurality of blocks, the confidence scores representing a respective likelihood that at least a portion of a block includes a predetermined graphical attribute associated with a tattoo.
18. The device of claim 17 , wherein the operations further comprise:
identifying a subset of the plurality of blocks that have confidence scores satisfying a predetermined threshold; and
wherein the segmentation mask for the image is generated based on the identified subset of the plurality of blocks.
19. The device of claim 17 , wherein:
the segmentation mask comprises a binary image; and
pixel values of pixels included in the binary image are determined based on the confidence scores computed for the plurality of blocks.
20. The device of claim 15 , wherein generating the segmentation mask for the image comprises:
grouping the plurality of blocks based on the feature statistics computed for the plurality of blocks; and
identifying one or more regions that each include blocks that have been grouped based on the feature statistics computed for the plurality of blocks.