On-device partial recognition systems and methods
AssigneeOpen Text Corporation
InventorsMikhail Yurievitch Zakharov, Kirill Vaniukov, Christopher Dale Lund
Life of this patent
Estimating the term…
Abstract
Disclosed is an approach of on-device partial recognition that includes performing partial recognition on an image of a document captured by a mobile device to detect and/or recognize a specific area (e.g., barcodes, non-relevant text, etc.) and filling the recognized area with a solid color. Because the solid color area has a maximum compression ratio, this approach can lead to image size reduction and increased network throughput for client-server based data recognition where further processing such as advanced data extraction is performed at the server side. The approach can be enforced with neural network algorithms to exclude non-relevant information (e.g., logos, phrases, words, etc.).
Claims20
A method for on-device partial recognition, the method comprising:
- examining, by an on-device partial recognition module running on a user device, an image of a document for partial recognition, wherein the document comprises a non-text portion, wherein the examining comprises applying image recognition to the non-text portion of the document, and wherein the applying generates partially recognized image data;
- cutting, by the on-device partial recognition module, the partially recognized image data from the non-text portion of the image;
- filling, by the on-device partial recognition module, the non-text portion of the image with pixels of a single color in place of the partially recognized image data, wherein the filling results in modified image data;
- compressing, by the on-device partial recognition module, the modified image data, wherein the compressing produces compressed modified image data;
- and
- communicating the compressed modified image data to a recognition server computer.
An apparatus for on-device partial recognition, the apparatus comprising:
- a processor;
- a non-transitory computer-readable medium;
- and
- stored instructions translatable by the processor for:
- examining an image of a document for partial recognition, wherein the document comprises a non-text portion, wherein the examining comprises applying image recognition to the non-text portion of the document, and wherein the applying generates partially recognized image data;
- cutting the partially recognized image data from the non-text portion of the image;
- filling the non-text portion of the image with pixels of a single color in place of the partially recognized image data, wherein the filling results in modified image data;
- compressing the modified image data, wherein the compressing produces compressed modified image data;
- and
- communicating the compressed modified image data to a recognition server computer.
A computer program product for on-device partial recognition, the computer program product comprising a non-transitory computer-readable medium storing instructions translatable by a processor for:
- examining an image of a document for partial recognition, wherein the document comprises a non-text portion, wherein the examining comprises applying image recognition to the non-text portion of the document, and wherein the applying generates partially recognized image data;
- cutting the partially recognized image data from the non-text portion of the image;
- filling the non-text portion of the image with pixels of a single color in place of the partially recognized image data, wherein the filling results in modified image data;
- compressing the modified image data, wherein the compressing produces compressed modified image data;
- and
- communicating the compressed modified image data to a recognition server computer.
Dependencies are inferred from the claim text.