Systems and methods for detecting and classifying objects in video captured using mobile devices
View Patent ↗A method includes capturing plural frames of video data using a mobile device. The frames are analyzed to determine whether any depict an object exhibiting one or more defining characteristics, and if so, whether those frame(s) depicting the object also satisfy one or more predetermined quality control criteria. If one or more of the frames depict the object and also satisfy the one or more predetermined quality control criteria, the method further includes automatically capturing an image of the object. Exemplary defining characteristics are specified for various types of object, particularly objects comprising documents. Related systems and computer program products are also disclosed. The presently disclosed techniques and systems represent translational developments across the fields of image processing and business process management. Improved analytical techniques enable processing of image captured using cameras rather than traditional scanner technology, and facilitate distribution, tracking and analysis of documents and information throughout business processes.
1. A method, comprising:
capturing video data using a mobile device, the video data comprising a plurality of frames;
determining whether one or more of the frames depict an object exhibiting one or more defining characteristics;
determining whether one or more of the frame(s) determined to depict the object also satisfy one or more predetermined quality control criteria; and
in response to determining one or more of the frames depict the object and also satisfy the one or more predetermined quality control criteria, automatically capturing an image of the object.
2. The method as recited in claim 1 , further comprising initiating a business process in response to determining the one or more of the frames depict the object and also satisfy the one or more predetermined quality control criteria, wherein the business process relies at least in part on the automatically captured image.
3. The method as recited in claim 1 , wherein the image is characterized by a resolution higher than a resolution of any of the plurality of frames.
4. The method as recited in claim 1 , wherein the defining characteristics comprise one or more of:
an object shape;
an object contour;
one or more object dimensions; and
an object color profile.
5. The method as recited in claim 1 , wherein determining whether one or more of the frames depict the object comprises performing optical character recognition (OCR).
6. The method as recited in claim 1 , wherein the object is a document.
7. The method as recited in claim 6 , wherein the defining characteristics comprise one or more of:
textual information depicted on the document;
a photograph depicted on the document;
a barcode depicted on the document;
a logo depicted on the document;
an emblem depicted on the document;
a seal depicted on the document; and
an aspect ratio of the document.
8. The method as recited in claim 6 , wherein the document corresponds to a loan application.
9. The method as recited in claim 8 , wherein the defining characteristics comprise the document depicting one or more of:
a customer name;
a guarantor name;
a customer address;
a date;
an account number;
a loan number;
a digital signature;
a handwritten signature; and
a photograph.
10. The method as recited in claim 6 , wherein the document comprises one or more of:
a receipt;
an expense report;
a credit card; and
a check.
11. The method as recited in claim 10 , wherein the defining characteristics comprise the document depicting one or more of:
a credit card number;
a name;
an expense amount; and
an order number.
12. The method as recited in claim 6 , wherein the document comprises a medical record.
13. The method as recited in claim 6 , wherein the document corresponds to an insurance claim.
14. The method as recited in claim 13 , wherein the defining characteristics comprise the document depicting one or more of:
a photograph of an automobile;
a photograph of an accident report;
a photograph of a proof of insurance document;
a photograph of a driver's license;
a photograph of a quote; and
a signature.
15. The method as recited in claim 6 , wherein the document corresponds to a delivery.
16. The method as recited in claim 15 , wherein the defining characteristics comprise the document depicting one or more of:
a signature;
a proof of delivery;
a package number;
a photograph of a package; and
a declaration of package contents.
17. The method as recited in claim 6 , wherein the document corresponds to an educational program application.
18. The method as recited in claim 17 , wherein the defining characteristics comprise the document depicting one or more of:
an applicant name;
a photograph of an applicant; and
a student identification document.
19. A system, comprising a processor and logic executable by the processor, the logic being configured to cause the processor to:
capture video data using a mobile device, the video data comprising a plurality of frames;
determine whether one or more of the frames depict an object exhibiting one or more defining characteristics;
determine whether one or more of the frame(s) determined to depict the object also satisfy one or more predetermined quality control criteria; and
in response to determining one or more of the frames depict the object and also satisfy the one or more predetermined quality control criteria, automatically capture an image of the object.
20. A computer program product, comprising a non-transitory computer readable storage medium having embodied therewith compute readable program code configured to cause a processor to:
capture video data using a mobile device, the video data comprising a plurality of frames;
determine whether one or more of the frames depict an object exhibiting one or more defining characteristics;
determine whether one or more of the frame(s) determined to depict the object also satisfy one or more predetermined quality control criteria; and
in response to determining one or more of the frames depict the object and also satisfy the one or more predetermined quality control criteria, automatically capture an image of the object.