Optical character recognition quality evaluation and optimization
AssigneeIntuit Inc.
InventorsSameeksha Khillan, Prajwal Prakash Vasisht
Life of this patent
Estimating the term…
Abstract
A processor may receive an image and determine a number of foreground pixels in the image. The processor may obtain a result of optical character recognition (OCR) processing performed on the image. The processor may identify at least one bounding box surrounding at least one portion of text in the result and overlay the at least one bounding box on the image to form a masked image. The processor may determine a number of foreground pixels in the masked image and a decrease in the number of foreground pixels in the masked image relative to the number of foreground pixels in the image. Based on the decrease, the processor may modify an aspect of the OCR processing for subsequent image processing.
Claims20
A method comprising:
- receiving, by a processor, an image;
- determining, by the processor, a number of foreground pixels in the image;
- receiving, by the processor, a masked image comprising text recognized in the image by optical character recognition (OCR) processing and at least one bounding box surrounding at least one portion of the text;
- determining, by the processor, a number of foreground pixels in the masked image;
- determining, by the processor, a decrease in the number of foreground pixels in the masked image relative to the number of foreground pixels in the image;
- and
- based on the decrease, modifying, by the processor, an aspect of the OCR processing for subsequent image processing.
A system comprising:
- a processor;
- and
- a non-transitory memory in communication with the processor storing instructions that, when executed by the processor, cause the processor to perform processing comprising:
- receiving an image;
- determining a number of foreground pixels in the image;
- receiving a masked image comprising text recognized in the image by optical character recognition (OCR) processing and at least one bounding box surrounding at least one portion of the text;
- determining a number of foreground pixels in the masked image;
- determining a decrease in the number of foreground pixels in the masked image relative to the number of foreground pixels in the image;
- and
- based on the decrease, modifying an aspect of the OCR processing for subsequent image processing.
A method comprising:
- receiving, by a processor, an image being processed by a computerized workflow;
- determining, by the processor, a number of foreground pixels in the image;
- forming, by the processor, a masked image comprising text recognized in the image by optical character recognition (OCR) processing and at least one bounding box surrounding at least one portion of the text;
- determining, by the processor, a number of foreground pixels in the masked image;
- determining, by the processor, a decrease in the number of foreground pixels in the masked image relative to the number of foreground pixels in the image;
- and
- based on the decrease, modifying, by the processor, the workflow for subsequent image processing, the modifying comprising at least one of changing a customizable OCR parameter and replacing a first OCR processing service with a second OCR processing service.
Dependencies are inferred from the claim text.