Systems and methods for assessing standards for mobile image quality

Abstract

Methods and systems are provided for defining and determining a formal and verifiable mobile document image quality and usability (MDIQU) standard, or Standard for short. The Standard ensures that a mobile image can be used in an appropriate mobile document processing application, for example an application for mobile check deposit. In order to quantify the usability, the Standard establishes 5 quality and usability grades. A mobile image capture device can capture images. A mobile device can receive information associated with one or more image quality assurance (IQA) criteria; evaluating the images to select an image satisfying an image quality criteria based on the received information; and in response to the image satisfying the image quality score, sending the selected image to determine a set of image quality assurance (IQA) scores.

What is claimed is: 
     
         1 . A method comprising using at least one hardware processor to:
 receive an image captured by a mobile device;   for each of a plurality of image quality assurance (IQA) tests, execute the IQA test on the image to produce an individual IQA score;   compute at least one compound IQA score based on the individual IQA scores;   when the at least one compound IQA score does not satisfy a threshold, reject the image for further processing; and,   when the at least one compound IQA score satisfies the threshold,
 determine a usability score based on a set of data fields that are extracted from the image, and 
 accept or reject the image for further processing based on the usability score. 
   
     
     
         2 . The method of  claim 1 , wherein the at least one compound IQA score comprises two compound IQA scores. 
     
     
         3 . The method of  claim 2 , wherein the two compound IQA scores comprise a quality score and a crop score. 
     
     
         4 . The method of  claim 1 , wherein the at least one compound IQA score consists of a quality score and a crop score. 
     
     
         5 . The method of  claim 1 , further comprising using the at least one hardware processor to classify the image into one of a plurality of ranks, wherein rejecting the image for further processing comprises classifying the image into a lower one of the plurality of ranks, and wherein accepting the image for further processing comprises classifying the image into a higher one of the plurality of ranks. 
     
     
         6 . The method of  claim 1 , further comprising using the at least one hardware processor to, when accepting the image for further processing, transmit the image to an application server. 
     
     
         7 . The method of  claim 1 , wherein determining the usability score comprises:
 cropping a document snippet from the image, wherein the document snippet represents a document in the image;   extracting the set of data fields from the document snippet; and   computing the usability score based on a confidence level that the set of data fields can be read.   
     
     
         8 . The method of  claim 7 , wherein determining the usability score further comprises:
 determining a category of document in the document snippet; and   identifying the set of data fields to be extracted from the document snipped based on the determined category of document.   
     
     
         9 . The method of  claim 1 , wherein accepting or rejecting the image for further processing based on the usability score comprises:
 when the usability score satisfies a usability threshold, accepting the image for further processing; and,   when the usability score does not satisfy the usability threshold, rejecting the image for further processing.   
     
     
         10 . The method of  claim 1 , wherein each of the plurality of IQA tests outputs an individual IQA score that represents one of a plurality of image deficiencies that is different than the plurality of image deficiencies for which an individual IQA score is output by others of the plurality of IQA tests. 
     
     
         11 . The method of  claim 10 , wherein the plurality of image deficiencies comprises two or more of the image is out-of-focus, the image contains a shadow, the image is too small in size, the image contains a reflection, the image has low internal contrast, the image is too dark, the image has plain skew, the image has view skew, the image has cut corners, the image has warpage, the image has low external contrast, or the image has a busy background. 
     
     
         12 . The method of  claim 1 , wherein one of the plurality of IQA tests comprises:
 generating a grey-scale snippet of the image;   computing a frequency of high-contrast local areas in the grey-scale snippet; and   generating an individual IQA score, based on the computed frequency, that indicates whether the image is out of focus.   
     
     
         13 . The method of  claim 1 , wherein one of the plurality of IQA tests comprises:
 generating a grey-scale snippet of the image;   breaking the grey-scale snippet into two areas of different brightness;   determining a delta in brightness between the two areas and a size of a darker one of the two areas; and   generating an individual IQA score, based on the determined delta and size, that indicates whether the image contains a shadow.   
     
     
         14 . The method of  claim 1 , wherein one of the plurality of IQA tests comprises:
 generating a grey-scale snippet of the image;   generating a histogram representing brightness of pixels in the grey-scale snippet; and   generating an individual IQA score, based on the histogram, that indicates whether the image has low internal contrast.   
     
     
         15 . The method of  claim 1 , wherein one of the plurality of IQA tests comprises:
 generating a grey-scale snippet of the image;   generating a histogram representing brightness of pixels in the grey-scale snippet;   generating a weighted average grey-scale value based on the histogram; and   generating an individual IQA score, based on the weighted average grey-scale value, that indicates a darkness of the image.   
     
     
         16 . The method of  claim 1 , wherein one of the plurality of IQA tests comprises:
 detecting how many corners of a document in the image are not present in the image;   for each corner detected as not present in the image, computing a size of the corner that is missing from the image, and computing a penalty based on the computed size; and   generating an individual IQA score, based on any computed penalties, that indicates a substantiality of missing corners of the document in the image.   
     
     
         17 . The method of  claim 1 , wherein one of the plurality of IQA tests comprises:
 cropping a document snippet from the image, wherein the document snippet represents a document within the image; and   generating an individual IQA score that indicates a ratio between a size of the document snippet and a size of the image.   
     
     
         18 . The method of  claim 1 , wherein one of the plurality of IQA tests comprises:
 cropping a document snippet from the image, wherein the document snippet represents a document within the image;   computing a measure of deviation between sides of the document snippet and ideal straight lines; and   generating an individual IQA score, based on the measure of deviation, that indicates how warped the document is within the image.   
     
     
         19 . A system comprising:
 at least one hardware processor; and   software instructions configured to, when executed by the at least one hardware processor,
 receive an image captured by a mobile device, 
 for each of a plurality of image quality assurance (IQA) tests, execute the IQA test on the image to produce an individual IQA score, 
 compute at least one compound IQA score based on the individual IQA scores, 
 when the at least one compound IQA score does not satisfy a threshold, reject the image for further processing, and, 
 when the at least one compound IQA score satisfies the threshold,
 determine a usability score based on a set of data fields that are extracted from the image, and 
 accept or reject the image for further processing based on the usability score. 
 
   
     
     
         20 . A non-transitory computer-readable medium having instructions stored therein, wherein the instructions, when executed by a processor, cause the processor to:
 receive an image captured by a mobile device;   for each of a plurality of image quality assurance (IQA) tests, execute the IQA test on the image to produce an individual IQA score;   compute at least one compound IQA score based on the individual IQA scores;   when the at least one compound IQA score does not satisfy a threshold, reject the image for further processing; and,   when the at least one compound IQA score satisfies the threshold,
 determine a usability score based on a set of data fields that are extracted from the image, and 
 accept or reject the image for further processing based on the usability score.