Nearsighted camera object detection

Abstract

A system and process of nearsighted (myopia) camera object detection involves detecting the objects through edge detection and outlining or thickening them with a heavy border. Thickening may include making the object bold in the case of text characters. The bold characters are then much more apparent and heavier weighted than the background. Thresholding operations are then applied (usually multiple times) to the grayscale image to remove all but the darkest foreground objects in the background resulting in a nearsighted (myopic) image. Additional processes may be applied to the nearsighted image, such as morphological closing, contour tracing and bounding of the objects or characters. The bound objects or characters can then be averaged to provide repositioning feedback for the camera user. Processed images can then be captured and subjected to OCR to extract relevant information from the image.

1 - 47 . (canceled) 
     
     
         48 . A method of generating, during acquisition via a camera of an image of a document, a plurality of pre-processed images of the document, the pre-processed images being used to optimize a capture position of the camera when capturing the image of the document for optical character recognition, the method comprising:
 obtaining a plurality of source images, including a first source image and a second source image, continuously acquired via the camera of a computing device, each of the obtained plurality of source images containing characters associated with the document, wherein the first source image is acquired by the camera at a first capture position, and wherein the second source image is acquired by the camera at a second capture position, wherein the first capture position is different from the second capture position;   for each of the plurality of obtained source images, pre-processing a given obtained source image to generate, by a processor of the computing device, a pre-processed image of the given obtained source image; and   presenting, on a graphical user interface, via a display of the computing device, i) the pre-processed image and ii) a graphical indicator to guide physical repositioning of the camera to capture an image to be used by an optical character recognition operation to determine characters of the image of the document, wherein the graphical widget presents one or more parameters associated with the camera being in an determined appropriate range position.   
     
     
         49 . The method of  claim 48 , wherein the pre-processing emphasizes characters associated with a foreground portion of the image of the document attenuates image objects that are background to the characters associated with the foreground portion. 
     
     
         50 . The method of  claim 48 , wherein the pre-processing comprises:
 detecting edges of the characters in the given obtained source image using an image processing operation,   thickening edges of the characters of the detected edge characters to generate a first intermediate image data using a second image processing operation, and   thresholding the first intermediate image data.   
     
     
         51 . The method of  claim 48 , wherein the appropriate range position is determined when a focal plane associated with the camera is square with the image of the document. 
     
     
         52 . The method of  claim 48 , wherein the appropriate range position is determined at an optimum focal length of the camera to the document. 
     
     
         53 . The method of  claim 48 , wherein the appropriate range position is determined at an acceptable focal length of the camera to the document. 
     
     
         54 . The method of  claim 50 , wherein the operation of detecting and thickening edges of the characters include using a Sobel operator. 
     
     
         55 . The method of  claim 48 , further comprising:
 automatically capturing and storing the pre-processed image when the document is within a range of positions, the range being determined based on the characters associated with the document in the pre-processed image.   
     
     
         56 . The method of  claim 48 , further comprising
 determining an average font height for the characters; and   performing optical character recognition using the determined average font height.   
     
     
         57 . The method of  claim 48 , further comprising performing optical character recognition. 
     
     
         58 . The method of  claim 48 , wherein the computing device comprises a handheld electronic device. 
     
     
         59 . The method of  claim 48 , wherein the plurality of source images are captured as a video feed by the camera of the computing device. 
     
     
         60 . A system of generating, during acquisition via a camera of an image of a document, a plurality of pre-processed images of the document, the pre-processed images being used to optimize a capture position of the camera when capturing the image of the document for optical character recognition, the system comprising:
 a camera;   a processor; and   a memory operatively coupled to the processor, the memory having instructions stored thereon, wherein execution of the instructions by the processor, cause the processor to:   obtain a plurality of source images, including a first source image and a second source image, continuously acquired via the camera, each of the obtained plurality of source images containing characters associated with the document, wherein the first source image is acquired by the camera at a first capture position, and wherein the second source image is acquired by the camera at a second capture position, wherein the first capture position is different from the second capture position;   for each of the plurality of obtained source images, pre-process a given obtained source image to generate a pre-processed image of the given obtained source image; and   present, on a graphical user interface, via a display, i) the pre-processed image and ii) a graphical indicator to guide physical repositioning of the camera to capture an image to be used by an optical character recognition operation to determine characters of the image of the document, wherein the graphical widget presents one or more parameters associated with the camera being in an determined appropriate range position.   
     
     
         61 . The system of  claim 60 , wherein the pre-processing emphasizes characters associated with a foreground portion of the image of the document attenuates image objects that are background to the characters associated with the foreground portion by detecting edges of the characters in the given obtained source image using an image processing operation, thickening edges of the characters of the detected edge characters to generate a first intermediate image data using a second image processing operation, and thresholding the first intermediate image data. 
     
     
         62 . The system of  claim 60 , wherein the appropriate range position is determined at an optimum focal length of the camera to the document. 
     
     
         63 . The system of  claim 60 , wherein the appropriate range position is determined at an acceptable focal length of the camera to the document. 
     
     
         64 . The system of  claim 60 , wherein the instructions, when executed by the processor, cause the processor to:
 automatically capture and store the pre-processed image when the document is within a range of positions, the range being determined based on the characters associated with the document in the pre-processed image.   
     
     
         65 . The system of  claim 60 , wherein the system device comprises a handheld electronic device. 
     
     
         66 . The system of  claim 60 , wherein the camera operates to capture images at 20-30 frames per second. 
     
     
         67 . A non-transitory computer readable medium for capturing the image of the document for optical character recognition, the computer readable medium having instructions stored thereon, wherein execution of the instructions by a processor of a computing device, cause the processor to:
 obtain a plurality of source images, including a first source image and a second source image, continuously acquired via a camera, each of the obtained plurality of source images containing characters associated with the document, wherein the first source image is acquired by the camera at a first capture position, and wherein the second source image is acquired by the camera at a second capture position, wherein the first capture position is different from the second capture position;   for each of the plurality of obtained source images, pre-process a given obtained source image to generate a pre-processed image of the given obtained source image; and   present, on a graphical user interface, via a display of the computing device, i) the pre-processed image and ii) a graphical indicator to guide physical repositioning of the camera to capture an image to be used by an optical character recognition operation to determine characters of the image of the document, wherein the graphical widget presents one or more parameters associated with the camera being in an determined appropriate range position.