Systems and methods of check detection
View Patent ↗A digital image of a check may be divided into segments. The segments may be processed to determine the edges between the background data and the check data in the segments of the digital image. A histogram of each segment may be determined and used to determine the edges of the check image portions in the segments and thus the edges of the check. The data outside the edges of the check image portions in the segments may be considered to be background data and may be identified and/or removed. The segments, with the background data removed, may be recombined into an image of the check and provided into a digital image file that may be transmitted to an institution system for deposit of the check in an account.
1. A method for feature detection in a digital image, the method comprising:
dividing the digital image into a plurality of segments, wherein the digital image includes a depiction of a document including textual information, each of the plurality of segments including a depiction of a part of the document;
obtaining a histogram for each of the plurality of segments;
determining a threshold for each of the plurality of segments, where the threshold corresponds to a level on the histogram between a first density area corresponding to the depiction of a first portion of the document and a second density area corresponding to a second portion of the document;
identifying a background portion in a segment included in the plurality of segments based on the threshold;
extracting partial textual information from the segment based on the identified background portion in the segment;
recombining the plurality of segments to generate a combined image; and
detecting combined textual information from the combined image.
2. The method of claim 1 , further comprising:
blurring the digital image according to a predetermined amount prior to dividing the digital image into the plurality of segments.
3. The method of claim 1 , further comprising:
detecting corners of the document depicted in the combined image;
applying an image modification on the combined image based on the detected corners of the document; and
storing a modified digital image file based on the image modification applied to the combined image.
4. The method of claim 3 , wherein the image modification is at least one of a warp removal image modification, a cropping image modification, or a rotation image modification.
5. The method of claim 1 , further comprising:
applying a convolution filter to each of the plurality of segments, wherein the convolution filter comprises a convolution matrix formed from a vector.
6. The method of claim 1 , further comprising:
transmitting the combined image to an institution server for processing of the document depicted in the combined image.
7. A computing device comprising:
a machine-readable medium, other than a transitory signal; and
instructions stored on the machine-readable medium, the instructions configured to, when executed by processing circuitry, cause the processing circuitry to:
divide a digital image into a plurality of segments, wherein the digital image includes a depiction of a document including textual information, each of the plurality of segments including a depiction of a part of the document;
obtain a histogram for each of the plurality of segments;
determine a threshold for each of the plurality of segments, where the threshold corresponds to a level on the histogram between a first density area corresponding to the depiction of a first portion of the document and a second density area corresponding to a second portion of the document;
identify a background portion in a segment included in the plurality of segments based on the threshold;
extract partial textual information from the segment based on the identified background portion in the segment;
recombine the plurality of segments to generate a combined image; and
detecting combined textual information from the combined image.
8. The computing device of claim 7 , wherein the instructions are further configured to, when executed by the processing circuitry, cause the processing circuitry to:
blur the digital image according to a predetermined amount prior to dividing the digital image into the plurality of segments.
9. The computing device of claim 7 , wherein the instructions are further configured to, when executed by the processing circuitry, cause the processing circuitry to:
detect corners of the document depicted in the combined image;
apply an image modification on the combined image based on the detected corners of the document; and
store a modified digital image file based on the image modification on the combined image.
10. The computing device of claim 9 , wherein the image modification is at least one of a warp removal image modification, a cropping image modification, or a rotation image modification.
11. The computing device of claim 7 , wherein the instructions are further configured to, when executed by the processing circuitry, cause the processing circuitry to:
apply a convolution filter to each of the plurality of segments, wherein the convolution filter comprises a convolution matrix formed from a vector.
12. The computing device of claim 7 , wherein the instructions are further configured to, when executed by the processing circuitry, cause the processing circuitry to:
transmit the combined image to an institution server for processing of the document depicted in the combined image.
13. A computing device comprising:
a processor; and
a memory configured to store instructions that, when executed by the processor, cause the processor to:
divide a digital image into a plurality of segments, wherein the digital image includes a depiction of a document including textual information, each of the plurality of segments including a depiction of a part of the document;
obtain a histogram for each of the plurality of segments;
determine a threshold for each of the plurality of segments, where the threshold corresponds to a level on the histogram between a first density area corresponding to the depiction of a first portion of the document and a second density area corresponding to a second portion of the document;
identify a background portion in a segment included in the plurality of segments based on the threshold;
extract partial textual information from the segment based on the identified background portion in the segment;
recombine the plurality of segments to generate a combined image; and
detecting combined textual information from the combined image.
14. The computing device of claim 13 , wherein the instructions are further configured to, when executed by the processor, cause the processor to:
blur the digital image according to a predetermined amount prior to dividing the digital image into the plurality of segments.
15. The computing device of claim 13 , wherein the instructions are further configured to, when executed by the processor, cause the processor to:
detect corners of the document depicted in the combined image;
apply an image modification on the combined image based on the detected corners of the document; and
store a modified digital image file based on the image modification on the combined image; and
wherein the image modification is at least one of a warp removal image modification, a cropping image modification, or a rotation image modification.
16. The computing device of claim 13 , wherein the instructions are further configured to, when executed by the processor, cause the processor to:
apply a convolution filter to each of the plurality of segments, wherein the convolution filter comprises a convolution matrix formed from a vector.
17. The computing device of claim 13 , wherein the instructions are further configured to, when executed by the processor, cause the processor to:
transmit the combined image to an institution server for processing of the document depicted in the combined image.