Mobile check deposit system and method
A computer-implemented method is provided for a mobile device to detect, by a camera of the mobile device, a plurality of checks; determine, by a processing unit of the mobile device, that the image of the plurality of checks is of sufficient quality; instruct, by a display of the mobile device, a user to take a photograph of the plurality of checks; crop, by the processing unit, the photograph of the plurality of checks into a plurality of images, wherein each of the plurality of images contains one of the plurality of checks; and transmit, by a transmitter of the mobile device, the plurality of images to a server via a network. The plurality of images may be transmitted individually (i.e., one at time), or alternatively, collectively and in one payload.
1. A computer-implemented method implemented by a mobile device for remote deposit, the computer-implemented method comprising:
detecting, by a camera of a mobile device registered to a first user, a digital image of a plurality of objects;
determining, via object detection and object localization, and using a machine learning model trained on a training dataset of check images by a processing unit of the mobile device prior to a photograph of the plurality of objects being taken using the mobile device, (1) that the plurality of objects in the digital image comprise a plurality of checks and (2) respective locations of individual checks of the plurality of checks in the digital image;
determining, by the processing unit, that the digital image of the plurality of checks as detected is of sufficient quality;
in response to determining that the digital image of the plurality of checks is of the sufficient quality, generating, by the processing unit, an instruction for a photograph of the plurality of checks to be taken;
causing, by the processing unit, the instruction to be presented on a display of the mobile device;
cropping, using the machine learning model, by the processing unit, and based upon the respective locations of the individual checks as determined, the photograph of the plurality of checks into a plurality of cropped images, wherein each of the plurality of cropped images contains one of the plurality of checks;
determining, by the processing unit and based on biometric data collected via a sensor of the mobile device, that a current user of the mobile device is a second user different from the first user;
based on determining that the current user is different from the first user, creating, by the processing unit, an association between the plurality of cropped images and a financial account of the second user; and
transmitting, by a transmitter of the mobile device, the plurality of cropped images, and an identifier uniquely identifying the financial account of the second user, to a server via a network.
2. The computer-implemented method of claim 1 , further comprising:
detecting, by the processing unit, an outline of the plurality of checks using an edge-detection algorithm, wherein the cropping of the photograph is performed along the outline of the plurality of checks.
3. The computer-implemented method of claim 1 , further comprising:
determining, by the processing unit, an orientation of each of the plurality of checks;
determining, by the processing unit, at least one of the plurality of checks that is not oriented upright; and
reorienting, by the processing unit after cropping the photograph of the plurality of checks into the plurality of cropped images, an orientation of at least one cropped image of the at least one of the plurality of checks that is not oriented upright.
4. The computer-implemented method of claim 1 , wherein determining that the digital image of the plurality of checks is of the sufficient quality comprises performing edge-detection algorithm.
5. The computer-implemented method of claim 1 , wherein determining that the digital image of the plurality of checks is of the sufficient quality comprises performing sharpness analysis algorithm.
6. The computer-implemented method of claim 1 , wherein determining that the digital image of the plurality of checks is of the sufficient quality comprises determining, by a proximity sensor of the mobile device, a distance between the plurality of checks and the camera of the mobile device.
7. The computer-implemented method of claim 1 , further comprising:
performing, by the processing unit, character recognition on the plurality of cropped images to recognize information printed or written on the plurality of checks; and
attaching, by the processing unit, the recognized information to the plurality of cropped images when the plurality of cropped images are transmitted to the server.
8. The computer-implemented method of claim 1 , wherein determining the plurality of objects comprise the plurality of checks and determining the respective locations of the plurality of checks occur simultaneously with detecting the digital image.
9. The computer-implemented method of claim 1 , further comprising:
establishing, by the processing unit, an association between the plurality of cropped images and a financial account of the first user.
10. The computer-implemented method of claim 1 , wherein determining that the current user of the mobile device is the second user is further based at least in part on a passcode.
11. A check depositing system for remote deposit via a mobile device, the system comprising:
a network;
a server operatively connected to the network; and
a mobile device operatively connected to the network, the mobile device registered to a first user and comprising:
a camera configured to detect a digital image of a plurality of objects,
a sensor configured to collect biometric data;
a processing unit configured to:
determine, using a machine learning model trained on a training dataset of check images prior to a photograph of the plurality of objects being taken using the mobile device, (1) that the plurality of objects in the digital image comprise a plurality of checks and (2) respective locations of individual checks of the plurality of checks in the digital image, and determine that the digital image of the plurality of checks as detected is of sufficient quality; and
in response to the processing unit determining that the digital image of the plurality of checks is of the sufficient quality, generate an instruction for a photograph of the plurality of checks to be taken;
a display configured to present the instruction, wherein the photograph of the plurality of checks is cropped using the machine learning model by the processing unit into a plurality of cropped images based upon the respective locations of the individual checks as determined, wherein each of the plurality of cropped images contains one of the plurality of checks,
the processing unit further configured to (1) determine, based on biometric data collected via the sensor of the mobile device, that a current user of the mobile device is a second user different from the first user, and (2) based on determining that the current user is different from the first user, creating an association between the plurality of cropped images and a financial account of the second user; and
a transmitter configured to transmit the plurality of cropped images to the server via the network.
12. The check depositing system of claim 11 , wherein the processing unit is configured to detect an outline of the plurality of checks using an edge-detection algorithm, wherein the cropping is performed along the outline of the plurality of checks.
13. The check depositing system of claim 11 , wherein the processing unit is configured to:
determine an orientation of each of the plurality of checks;
determine at least one of the plurality of checks that is not oriented upright; and
reorient, after cropping the photograph of the plurality of checks into the plurality of cropped images, an orientation of at least one cropped image of the at least one of the plurality of checks that is not oriented upright.
14. The check depositing system of claim 11 , wherein the processing unit is configured to perform edge-detection algorithm to determine that the digital image of the plurality of checks is of the sufficient quality.
15. The check depositing system of claim 11 , wherein the processing unit is configured to perform sharpness analysis algorithm to determine that the digital image of the plurality of checks is of the sufficient quality.
16. The check depositing system of claim 11 , wherein the mobile device further comprises a proximity sensor to determine a distance between the plurality of checks and the camera of the mobile device, wherein the processing unit is configured to determine that the digital image of the plurality of checks is of the sufficient quality based upon the distance determined by the proximity sensor.
17. The check depositing system of claim 11 , wherein the processing unit is further configured to:
perform character recognition on the plurality of cropped images to recognize information printed or written on the plurality of checks; and
attach the recognized information to the plurality of cropped images when the plurality of cropped images are transmitted to the server.
18. The check depositing system of claim 11 , wherein determining the plurality of objects comprise the plurality of checks, and the respective locations of the plurality of checks are determined simultaneously with detection of the digital image.
19. The check depositing system of claim 11 , wherein determining that the current user of the mobile device is the second user is further based at least in part on a passcode.
20. The check depositing system of claim 17 , wherein performing the character recognition comprises performing handwritten character recognition of handwritten text.