Form dropout compression method which handles form white-out and writing in shaded and white-out areas of the form

Claim 3

The method of claim 1 wherein a pixel is a removed pixel if and only if either the neighborhood of the corresponding pixel in the input image is white or there is a pixel in the neighborhood of the pixel which is a removed pixel.

Claim 4

The method of claim 2 wherein the step of determining for each pixel whether the pixel is a removed pixel comprises the steps of: (a) expanding the input image by setting to black each pixel therein which has a black neighbor in a distance less than or equal to N to form a first intermediate image; (b) subtracting the first intermediate image pixel-wise from the template image to form a second intermediate image; (c) expanding the second intermediate image by setting to black each pixel therein which has a black neighbor in a distance less than or equal to N to form a third intermediate image; and (d) performing a binary AND pixelwise between the third intermediate image and the template image to form an image in which the black pixels are removed pixels.

Claim 9

The method of claim 5 wherein the step of determining whether the block contains filled-in data comprises the further steps of: (i) thinning the block in the input image by setting to white each black pixel therein which has a white neighbor in a distance less than or equal to N; and (ii) determining whether the number of black pixels remaining in the block exceeds a predetermined threshold value and, if so, determining that the block contains filled-in data.

Claim 10

An image processing apparatus for compressing, for storage or transmission, the information contained in a bi-level digitized input image by separate handling of a corresponding template image and a compressed image, comprising subtraction logic for subtracting the template image from the input image to generate the compressed image, wherein the subtraction logic comprises: logic for determining for each pixel whether the pixel is an added pixel and, if so, assigning the pixel to be black in the compressed image, wherein a pixel is an added pixel if the corresponding pixel in the template image is white and the corresponding pixel in the input image is black, wherein the subtraction logic comprises logic for determining for each pixel whether the pixel is a removed pixel and, if so, assigning the pixel to be black in the compressed image, wherein a pixel is a removed pixel if the corresponding pixel in the template image is black, and the corresponding pixel in the input image is white.

Claim 11

An image processing apparatus for compressing, for storage or transmission, the information contained in a bi-level digitized input image by separate handling of a corresponding template image and a compressed image, comprising subtraction logic for subtracting the template image from the input image to generate the compressed image, wherein the subtraction logic comprises: logic for determining for each pixel whether the pixel is an added pixel and, if so, assigning the pixel to be black in the compressed image, wherein a pixel is an added pixel if the corresponding pixel in the template image is white and the corresponding pixel in the input image is black, wherein the subtraction logic comprises logic for determining for each pixel whether the pixel is a removed pixel and, if so, assigning the pixel to be black in the compressed image, wherein a pixel is a removed pixel if the corresponding pixel in the template image is black, and the corresponding pixel in the input image is white.

Claim 12

Apparatus for compressing, for storage or transmission, the information contained in a bi-level digitized input image of a filled-in form by separate handling of a corresponding template image of a blank form and a compressed image of modifications to the blank form, comprising: means for subtracting the template image from the input image to generate the compressed image, said means for subtracting comprising means for determining for each pixel whether the pixel is an added pixel and, if so, assigning the pixel to be black in the compressed image, wherein a pixel is an added pixel if the corresponding pixel in the template image is white and the corresponding pixel in the input image is black, said means for subtracting further comprising means for determining for each pixel whether the pixel is a removed pixel and, if so, assigning the pixel to be black in the compressed image, wherein a pixel is a removed pixel if the corresponding pixel in the template image is black, and the corresponding pixel in the input image is white.

Claim 13

Apparatus for compressing, for storage or transmission, the information contained in a bi-level digitized input image of a filled-in form by separate handling of a corresponding template image of a blank form and a compressed image of modifications to the blank form, comprising: means for subtracting the template image from the input image to generate the compressed image, said means for subtracting comprising means for determining for each pixel whether the pixel is an added pixel and, if so, assigning the pixel to be black in the compressed image, wherein a pixel is an added pixel if the corresponding pixel in the template image is white and the corresponding pixel in the input image is black, said means for subtracting further comprising means for determining for each pixel whether the pixel is a removed pixel and, if so, assigning the pixel to be black in the compressed image, wherein a pixel is a removed pixel if the corresponding pixel in the template image is black, and the corresponding pixel in the input image is white.

Claim 14

The apparatus of claim 8 wherein a pixel is a removed pixel if and only if either the neighborhood of the corresponding pixel in the input image is white or there is a pixel in the neighborhood of the pixel which is a removed pixel.

Claim 15

The apparatus of claim 9 wherein the means for determining for each pixel whether the pixel is a removed pixel comprises: (a) means for expanding the input image by setting to black each pixel therein which has a black neighbor in a distance less than or equal to N to form a first intermediate image; (b) means for subtracting the first intermediate image pixel-wise from the template image to form a second intermediate image; (c) means for expanding the second intermediate image by setting to black each pixel therein which has a black neighbor in a distance less than or equal to N to form a third intermediate image; and (d) means for performing a binary AND pixelwise between the third intermediate image and the template image to form an image in which the black pixels are removed pixels.

Claim 16

Apparatus for compressing, for subsequent storage or transmission, the information contained in a digitized input image by separate handling of a corresponding template image and an output compressed image, comprising: means for forming a first compressed image from the input image and the template image by way of white out processing; means for forming a second compressed image from the input image and the template image by way of dense areas processing; and means for performing a binary OR operation pixel-wise between the first and second compressed images to form the output image.

Claim 17

Apparatus for compressing, for subsequent storage or transmission, the information contained in a digitized input image by separate handling of a corresponding template image and an output compressed image, comprising: means for forming a first compressed image from the input image and the template image by way of white out processing; means for forming a second compressed image from the input image and the template image by way of dense areas processing; and means for performing a binary OR operation pixel-wise between the first and second compressed images to form the output image.

Claim 18

Apparatus for compressing, for storage or transmission, the information contained in a bi-level digitized input image by separate handling of a corresponding template image and a compressed image, the image comprising a plurality of non-overlapping blocks, comprising: (a) means for determining for each block whether or not the block contains white-out pixels and, if so, copying the block to the compressed image and setting to 1 a corresponding bit in a bitmap, which bitmap has one bit for each image block; (b) means for determining for each block whether the block contains filled-in data and, if so, copying the block to the compressed image and setting to 1 the corresponding bit in the bitmap; (c) means for compressing each block for which the corresponding bit in the bitmap is 0 using a method comprising the steps of subtracting therefrom the corresponding block in the template image to generate the corresponding block in the compressed image, the subtraction step comprising determining for each pixel whether the pixel is an added pixel and, if so, assigning the pixel to be black in the compressed image, wherein a pixel is an added pixel if the corresponding pixel in the template image is white and the corresponding pixel in the input image is black.

Claim 19

Apparatus for compressing, for storage or transmission, the information contained in a bi-level digitized input image by separate handling of a corresponding template image and a compressed image, the image comprising a plurality of non-overlapping blocks, comprising: (a) means for determining for each block whether or not the block contains white-out pixels and, if so, copying the block to the compressed image and setting to 1 a corresponding bit in a bitmap, which bitmap has one bit for each image block; (b) means for determining for each block whether the block contains filled-in data and, if so, copying the block to the compressed image and setting to 1 the corresponding bit in the bitmap; (c) means for compressing each block for which the corresponding bit in the bitmap is 0 using a method comprising the steps of subtracting therefrom the corresponding block in the template image to generate the corresponding block in the compressed image, the subtraction step comprising determining for each pixel whether the pixel is an added pixel and, if so, assigning the pixel to be black in the compressed image, wherein a pixel is an added pixel if the corresponding pixel in the template image is white and the corresponding pixel in the input image is black.

Claim 20

The apparatus of claim 12 wherein the means for determining whether the block contains filled-in data comprises: (i) means for thinning the block in the input image by setting to white each black pixel therein which has a white neighbor in a distance less than or equal to N; and (ii) means for determining whether the number of black pixels remaining in the block exceeds a predetermined threshold value and, if so, determining that the block contains filled-in data.