Mobile check deposit
Methods and systems for remote check deposit are disclosed. A check for deposit is processed without the need for a server to receive any image of the check initially. Instead, optical character recognition (OCR) data is received at the server from a mobile device. Verification processing for the check is then performed using the OCR data. If the verification process is successful, a confirmation notification is sent to the mobile device. Subsequently, after sending the confirmation notification, a check image is received, from which the OCR data was determined. The check is, in turn, processed for deposit using the received check image.
1 . A method comprising:
obtaining image data created by an image capture device of a mobile device;
at the mobile device, processing the image data to form a processed image, including:
converting the image data to grayscale image data;
identifying a shadow mask based on shadow regions in the grayscale image data;
refining the shadow mask;
modifying the shadow regions in the grayscale image data using the shadow mask;
reducing noise in the grayscale image data;
enhancing contrast in the grayscale image data; and
adjusting brightness or contrast in the grayscale image data; and
extracting a first snippet from the processed image;
at the mobile device, performing optical character recognition on the first snippet to generate first optical character recognition data;
at the mobile device, verifying the first optical character recognition data; and
only after verifying the first optical character recognition data, providing the processed image or image data based on the processed image from the mobile device to a server.
2 . The method of claim 1 , wherein obtaining the image data includes loading the image data without altering bit depth or color channels of the image data.
3 . The method of claim 1 , wherein identifying the shadow mask includes: applying an inverse binary threshold to the image data such that pixels below a certain intensity are white in the mask and others are black in the mask.
4 . The method of claim 1 , wherein refining the shadow mask includes:
filling in small holes in the mask by applying a dilation morphological operation; and
after performing the dilation morphological operation, applying an erosion morphological operation.
5 . The method of claim 1 , wherein modifying the shadow regions includes filling in at least a portion of the shadow regions using nearby pixel information.
6 . The method of claim 1 , wherein enhancing the contrast in the image data includes applying contrast limited adaptive histogram equalization.
7 . The method of claim 1 , further comprising:
saving the processed image in a TIFF (Tag Image File Format) format using lossless compression.
8 . The method of claim 1 , further comprising:
extracting a second snippet from the processed image;
sending the second snippet to another device for processing;
receiving second optical character recognition data from the another device;
verifying the second optical character recognition data; and
responsive to the verifying, providing the second optical character recognition data to a server for validation processing.
9 . The method of claim 8 , further comprising:
after providing the first and second optical character recognition data, receiving a confirmation notification from the server responsive to the providing;
after receiving the confirmation notification, presenting, on a user interface of the mobile device, a request for confirmation from the user for further processing; and
receiving a user confirmation from the user in response to the request for confirmation; and
only after receiving the user confirmation, providing by the mobile device an image of the entire object to the server for further processing.
10 . The method of claim 1 , wherein the method is performed entirely by the mobile device.
11 . A method comprising:
at a mobile device:
reading image data;
processing the image data to form a processed image, including:
converting the image data to grayscale image data;
identifying a shadow mask based on shadow regions in the grayscale image data;
refining the shadow mask;
modifying the shadow regions in the grayscale image data using the shadow mask;
reducing noise in the grayscale image data;
enhancing contrast in the grayscale image data; and
adjusting brightness or contrast in the grayscale image data; and
saving the processed image.
12 . The method of claim 11 , wherein reading the image data includes loading the image data without altering bit depth or color channels of the image data.
13 . The method of claim 11 , wherein identifying the shadow mask includes:
applying an inverse binary threshold to the image data such that pixels below a certain intensity are white in the mask and others are black in the mask.
14 . The method of claim 11 , wherein refining the shadow mask includes:
filling in small holes in the mask by applying a dilation morphological operation; and
after performing the dilation morphological operation, applying an erosion morphological operation.
15 . The method of claim 11 , wherein modifying the shadow regions includes filling in at least a portion of the shadow regions using nearby pixel information.
16 . The method of claim 11 , wherein enhancing the contrast in the image data includes applying contrast limited adaptive histogram equalization.
17 . The method of claim 11 , wherein saving the processed image includes saving the processed image in a TIFF (Tag Image File Format) format using lossless compression.
18 . The method of claim 11 , further comprising:
extracting a first snippet from the processed image;
extracting a second snippet from the processed image;
performing optical character recognition on the first snippet to generate first optical character recognition data;
sending the second snippet to another device for processing;
receiving second optical character recognition data from the another device;
verifying the first optical character recognition data and the second optical character recognition data; and
responsive to the verifying, providing the first optical character recognition data and the second optical character recognition data to a server for validation processing.
19 . The method of claim 18 , further comprising:
after providing the first and second optical character recognition data, receiving a confirmation notification from the server responsive to the providing;
after receiving the confirmation notification, presenting, on a user interface of a mobile device, a request for confirmation from the user for further processing; and
receiving a user confirmation from the user in response to the request for confirmation; and
only after receiving the user confirmation, providing by the mobile device an image of the entire object to the server for further processing.
20 . The method of claim 11 , further comprising:
obtaining the image data from a camera of the mobile device.