Content-based detection and three dimensional geometric reconstruction of objects in image and video data
Systems, computer program products, and techniques for detecting and/or reconstructing objects depicted in digital image data within a three-dimensional space are disclosed. The concepts utilize internal features for detection and reconstruction, avoiding reliance on information derived from location of edges. The inventive concepts provide an improvement over conventional techniques since objects may be detected and/or reconstructed even when edges are obscured or not depicted in the digital image data. In one aspect, detecting a document depicted in a digital image includes: detecting a plurality of identifying features of the document, wherein the plurality of identifying features are located internally with respect to the object; projecting a location of one or more edges of the document based at least in part on the plurality of identifying features; and outputting the projected location of the one or more edges of the document to a display of a computer, and/or a memory.
1. A computer program product for detecting a document depicted in a digital image, comprising a non-transitory computer readable medium having stored thereon computer readable program instructions configured to cause a hardware processor, upon execution thereof, to:
detect, using the hardware processor, a plurality of identifying features of the document, wherein the plurality of identifying features are located internally with respect to the document, and wherein detecting the document comprises:
determining one or more outlier key points from among a set of key points, each key point corresponding to one of the plurality of identifying features of the document;
identifying, from among each set of corresponding key points, the set of corresponding key points having a lowest number of outlier key points;
defining a set of inlier key points from among the set of corresponding key points having the lowest number of outlier key points, the set of inlier key points excluding the outlier key points determined from among the set of corresponding key points having the lowest number of outlier key points; and
estimating a homography transform H based on the set of inlier key points;
project, using the hardware processor, a location of one or more edges of the document based at least in part on the plurality of identifying features; and
output, at least in part based on the projected location of the one or more edges of the document to a display of a computer, and/or a memory.
2. The computer program product as recited in claim 1 , wherein the document is selected from a group consisting of: a form, a passport, a driver license, a credit card, a business card, a receipt, and a check.
3. The computer program product as recited in claim 2 , wherein the plurality of identifying features correspond to boilerplate content of the check.
4. The computer program product as recited in claim 2 , wherein the plurality of identifying features are selected from the group consisting of: a “MEMO” region of the check, a payee designator, a bank name, a bank address, a payor name, a payor address, one or more MICR characters, an endorsement line, a dollar sign, a padlock icon, a “PAY TO THE ORDER OF” region of the check, and a payment amount region of the check.
5. The computer program product as recited in claim 1 , wherein at least one edge of the document is not depicted in the digital image.
6. The computer program product as recited in claim 1 , wherein detecting the plurality of identifying features comprises analyzing a plurality of feature vectors, each feature vector corresponding to a pixel in the digital image.
7. The computer program product as recited in claim 1 , wherein the plurality of identifying features are characterized by exhibiting a sharp transition in intensity.
8. The computer program product as recited in claim 1 , wherein the projected location of the one or more edges of the document is based at least in part on the estimated homography transform H.
9. A computer-implemented method for detecting a document depicted in a digital image, comprising:
detecting a plurality of identifying features of the document, wherein the plurality of identifying features are located internally with respect to the document, and wherein detecting the document comprises:
determining one or more outlier key points from among a set of key points, each key point corresponding to one of the plurality of identifying features of the document;
identifying, from among each set of corresponding key points, the set of corresponding key points having a lowest number of outlier key points;
defining a set of inlier key points from among the set of corresponding key points having the lowest number of outlier key points, the set of inlier key points excluding the outlier key points determined from among the set of corresponding key points having the lowest number of outlier key points; and
estimating a homography transform H based on the set of inlier key points;
projecting a location of one or more edges of the document based at least in part on the plurality of identifying features; and
outputting the projected location of the one or more edges of the document to a display of a computer, and/or a memory.
10. The method as recited in claim 9 , wherein the document is selected from a group consisting of: a form, a passport, a driver license, a credit card, a business card, a receipt, and a check.
11. The method as recited in claim 10 , wherein the plurality of identifying features correspond to boilerplate content of the check.
12. The method as recited in claim 10 , wherein the plurality of identifying features are selected from the group consisting of: a “MEMO” region of the check, a payee designator, a bank name, a bank address, a payor name, a payor address, one or more MICR characters, an endorsement line, a dollar sign, a padlock icon, a “PAY TO THE ORDER OF” region of the check, and a payment amount region of the check.
13. The method as recited in claim 9 , wherein at least one edge of the document is not depicted in the digital image.
14. The method as recited in claim 9 , wherein detecting the plurality of identifying features comprises analyzing a plurality of feature vectors, each feature vector corresponding to a pixel in the digital image.
15. The method as recited in claim 9 , wherein the plurality of identifying features are characterized by exhibiting a sharp transition in intensity.
16. The method as recited in claim 9 , wherein the projected location of the one or more edges of the document is based at least in part on the estimated homography transform H.