Granted Patent B2

US 10,223,584 · App. 15/335,565 · Granted Mar 5, 2019

Abstract

Claims (33)

1. A method, comprising:

retaining frames of a video as document images for a document in a buffer;

obtaining a still image of the document;

selecting a best image from the still image and the document images, including identifying an area of interest included within or surrounded by edges of each document image retained within the buffer;

wherein identifying includes removing noise pixels from each of the areas of interest;

wherein removing includes calculating a focus score for each of the areas of interest having the noise pixels removed;

wherein calculating includes selecting a candidate document image from the document images based on the focus scores;

wherein selecting further includes increasing a resolution of the candidate document image to match a resolution for the still image;

wherein increasing includes calculating a new focus score for an increased resolution candidate document image and a still image focus score for the still image and selecting the best image as the image that has a higher focus score; and

providing the best image for Optical Character Recognition processing to derive document information represented in the best image for the document.

2. A method, comprising:

automatically activating a camera of a device to begin recording frames, each frame representing a document image of a document;

determining when video is being recorded to activate the camera to take a higher resolution document image;

selecting a subset of the document images and discarding remaining document images;

calculating a focus score for each of the subset of document images;

picking a particular one of the subset of document images based on the calculated focus scores for the subset of document images;

increasing a current resolution of the particular document image to match a resolution of the higher resolution document image;

identifying a best document image from the particular document image and the higher resolution document image; and

providing the best document image to perform Optical Character Recognition (OCR) processing and obtaining document information represented in the best document image.

3. The method of claim 2 , wherein automatically activating further includes activating the camera when a user selects an option for processing relevant to processing the document.

4. The method of claim 2 , wherein determining further includes automatically activating the camera for taking the higher resolution document image when a predefined percentage of the document images are congruent with one another.

5. The method of claim 2 , wherein determining further includes activating an interface to request that a user activate the camera after an elapsed period of time has passed without having determined that a predefined percentage of the document images are congruent with one another.

6. A method, comprising:

retaining frames of a video as document images for a document in a buffer;

obtaining a still image of the document;

identifying an area of interest included within or surrounded by edges of each document image retained within the buffer;

removing noise pixels from each of the areas of interest of each document image;

calculating a focus score for each of the areas of interest having the noise pixels removed;

selecting candidate document images from the document images having the highest focus scores;

increasing resolutions of the candidate document images to match a resolution for the still image;

calculating new focus scores for increased resolution candidate document images and a still image focus score for the still image; and

selecting a best image as the increased resolution candidate document image that has a highest new focus score; and

providing the best image for Optical Character Recognition processing to derive document information represented in the best image for the document.

Assignments (10)