Image processor, image processing method and apparatus applying same

Claim 2

An image processor, comprising: pseudo-gray-scale image generating circuit means for converting input image data, which is represented by a first prescribed number of bits per pixel, into pseudo-gray-scale image data represented by a second prescribed number of bits, which is less than said first prescribed number of bits; image restoration circuit means for restoring the pseudo-gray-scale image data for each and every one of a plurality of small areas, each of which comprises a plurality of pixels and is provided in a window that scans the pseudo-gray-scale image generated by said pseudo-gray-scale image generating circuit means, with said each small area serving as one restored pixel, and outputting restored image data for a window at each and every position; and similarity operating circuit means for calculating an index value representing a degree of similarity by comparing the restored image data of each window sequentially outputted by the image restoration circuit means and reference data representing a standard image.

Claim 3

An image processor according to claim 1, wherein said pseudo-gray-scale image generating circuit means binarizes the input image data using an error diffusion method and generates dither image data represented by one bit per pixel.

Claim 4

An image processor according to claim 1, wherein said pseudo-gray-scale image generating circuit means subjects the input image data to a four-value conversion using an error diffusion method and generates pseudo-gray-scale image data represented by two bits per pixel.

Claim 5

An image processor according to claim 1, further comprising peak holding circuit means for detecting an index value, which represents the highest degree of similarity, from among similarity index values regarding each of the windows obtained from said similarity operating circuit means, and position data indicative of the window in which this index value is generated.

Claim 6

An image processor according to claim 1, wherein the index value representing said degree of similarity is a difference value in lightness of the image, and said similarity operating circuit means calculates an absolute value of a difference between restored image data and corresponding reference data for each and every small area, sums the absolute values of these differences over all small areas contained in one window and outputs the sum value as a difference value of lightness.

Claim 7

An image processor according to claim 1, further comprising peak holding circuit means for detecting a smallest difference value from among difference values of lightness regarding each of the windows obtained by said similarity operating circuit means, as well as position data indicative of the window in which the smallest difference value is produced.

Claim 8

An image processor according to claim 1, wherein said similarity operating circuit means calculates a cross-correlation value between restored image data and reference data for each and every window, and outputs this cross-correlation value as the index value representing degree of similarity.

Claim 9

An image processor according to claim 7, further comprising peak holding circuit means for detecting a largest cross-correlation value from among the cross-correlation values regarding each of the windows obtained by said similarity operating circuit means, as well as position data indicative of the window in which the largest cross-correlation value is produced.

Claim 10

An image processor according to claim 1, wherein said image restoration circuit means includes: cascade-connected line memories, the number of which corresponds to the number of pixels in the vertical direction of said window, for transferring pseudo-gray-scale image data having the second prescribed number of bits; a circuit for extracting, from each of the line memories, and for each and every small area, pseudo-gray-scale image data of a number of pixels in the horizontal direction of the window; and adder circuit means for summing the extracted pseudo-gray-scale image data for each and every small area and outputting restored image data.

Claim 11

An image processor according to claim 9, further comprising smoothing circuit means for smoothing the restored image data, which is outputted by said adder circuit means, over restored pixels before and behind the restored image data.

Claim 12

An image processor comprising: A/D converter circuit means for converting a video signal, which represents an image of a subject and is provided by a video camera, into input image data pixel by pixel, wherein the input image data is represented by a first prescribed number of bits per pixel; pseudo-gray-scale image generating circuit means for converting the input image data, which is outputted by said A/D converter circuit means, into pseudo-gray-scale image data represented by a second prescribed number of bits, which is less than said first prescribed number of bits; and image restoration circuit means for restoring the pseudo-gray-scale image data for each and every one of a plurality of small areas, each of which comprises a plurality of pixels and is provided in a window that scans the pseudo-gray-scale image generated by said pseudo-gray-scale image generating circuit means, with said each small area serving as one restored pixel, and outputting restored image data for a window at each and every position.

Claim 13

An image processor comprising: A/D converter circuit means for converting a video signal, which represents an image of a subject and is provided by a video camera, into input image data pixel by pixel, wherein the input image data is represented by a first prescribed number of bits per pixel; pseudo-gray-scale image generating circuit means for converting the input image data, which is outputted by said A/D converter circuit means, into pseudo-gray-scale image data represented by a second prescribed number of bits, which is less than said first prescribed number of bits; and image restoration circuit means for restoring the pseudo-gray-scale image data for each and every one of a plurality of small areas, each of which comprises a plurality of pixels and is provided in a window that scans the pseudo-gray-scale image generated by said pseudo-gray-scale image generating circuit means, with said each small area serving as one restored pixel, and outputting restored image data for a window at each and every position.

Claim 14

An image processor according to claim 11, wherein said pseudo-gray-scale image generating circuit means binarizes the input image data using an error diffusion method and generates dither image data represented by one bit per pixel.

Claim 15

An image processor according to claim 11, wherein said pseudo-gray-scale image generating circuit means subjects the input image data to a four-value conversion using an error diffusion method and generates pseudo-gray-scale image data represented by two bits per pixel.

Claim 16

An image processor according to claim 11, wherein said image restoration circuit means includes: cascade-connected line memories, the number of which corresponds to the number of pixels in the vertical direction of said window, for transferring pseudo-gray-scale image data having the second prescribed number of bits; a circuit for extracting, from each of the line memories, and for each and every small area, pseudo-gray-scale image data of a number of pixels in the horizontal direction of the window; and adder circuit means for summing the extracted pseudo-gray-scale image data for each and every small area and outputting restored image data.

Claim 17

An image processor according to claim 14, further comprising smoothing circuit means for smoothing the restored image data, which is outputted by said adder circuit means, over restored pixels before and behind the restored image data.

Claim 18

An image processing method, comprising the steps of: converting input image data, which is represented by a first prescribed number of bits per pixel, into pseudo-gray-scale image data represented by a second prescribed number of bits, which is less than the first prescribed number of bits; generating restored image data by summing said pseudo-gray-scale image data for each and every one of a plurality of small areas, each of which comprises a plurality of pixels and is provided in a window that scans the pseudo-gray-scale image generated, thereby restoring the image data for a window at each and every position; and comparing the restored image data with reference data representing a standard image by calculating an index value representing a degree of similarity between the restored image data of each window and the reference data.

Claim 19

An image processing method, comprising the steps of: converting input image data, which is represented by a first prescribed number of bits per pixel, into pseudo-gray-scale image data represented by a second prescribed number of bits, which is less than the first prescribed number of bits; generating restored image data by summing said pseudo-gray-scale image data for each and every one of a plurality of small areas, each of which comprises a plurality of pixels and is provided in a window that scans the pseudo-gray-scale image generated, thereby restoring the image data for a window at each and every position; and comparing the restored image data with reference data representing a standard image by calculating an index value representing a degree of similarity between the restored image data of each window and the reference data.

Claim 20

An image processing method according to claim 16, wherein said step of converting input image data includes binarizing the input image data using an error diffusion method and generating dither image data represented by one bit per pixel.

Claim 21

An image processing method according to claim 16, wherein said step of converting input image data includes subjecting the input image data to a four-value conversion using an error diffusion method and generating pseudo-gray-scale image data represented by two bits per pixel.

Claim 22

An image processing method according to claim 16, further comprising a step of detecting an index value, which represents the highest degree of similarity, from among similarity index values regarding each of the windows, and position data indicative of the window in which this index value is generated.

Claim 23

An image processing method according to claim 16, wherein the index value representing said degree of similarity is a difference value in lightness of the image, an absolute value of a difference between restored image data and corresponding reference data is calculated for each and every small area, the absolute values of these differences are summed over all small areas contained in one window, and the sum value is outputted as a difference value of lightness.

Claim 24

An image processing method according to claim 20, further comprising a step of detecting a smallest difference value from among difference values of lightness regarding each of the windows obtained, as well as position data indicative of the window in which the smallest difference value is produced.

Claim 25

An image processing method according to claim 16, wherein, in calculation of the similarity index value, a cross-correlation value between restored image data and reference data is calculated for each and every window, and this cross-correlation value is adopted as the index value representing degree of similarity.

Claim 26

An image processing method according to claim 22, further comprising a step of detecting a largest cross-correlation value from among the cross-correlation values regarding each of the windows, as well as position data indicative of the window in which the largest cross-correlation value is produced.

Claim 27

An image processing method according to claim 16, wherein line memories, the number of which corresponds to the number of pixels in the vertical direction of said window, for transferring pseudo-gray-scale image data having the second prescribed number of bits are connected in cascade; pseudo-gray-scale image data of a number of pixels in the horizontal direction of the window is extracted, for each and every small area, from each of the line memories; and the extracted pseudo-gray-scale image data is summed for each and every small area to thereby restore the image data.

Claim 28

An image processing method according to claim 24, further comprising a step of smoothing the restored image data over restored pixels before and behind the restored image data.

Claim 29

An image processing method comprising the steps of: converting a video signal, which represents an image of a subject and is provided by a video camera, into input image data pixel by pixel, wherein the input image data is represented by a first prescribed number of bits per pixel; converting the input image data into pseudo-gray-scale image data represented by a second prescribed number of bits, which is less than said first prescribed number of bits; and summing said pseudo-gray-scale image data for each and every one of a plurality of small areas, each of which comprises a plurality of pixels and is provided in a window that scans the pseudo-gray-scale image, thereby restoring the image data for a window at each and every position, with said each small area serving as one restored pixel.

Claim 30

An image processing method comprising the steps of: converting a video signal, which represents an image of a subject and is provided by a video camera, into input image data pixel by pixel, wherein the input image data is represented by a first prescribed number of bits per pixel; converting the input image data into pseudo-gray-scale image data represented by a second prescribed number of bits, which is less than said first prescribed number of bits; and summing said pseudo-gray-scale image data for each and every one of a plurality of small areas, each of which comprises a plurality of pixels and is provided in a window that scans the pseudo-gray-scale image, thereby restoring the image data for a window at each and every position, with said each small area serving as one restored pixel.

Claim 31

An inspection apparatus for scratches or the like, comprising: image sensing means for imaging a subject and outputting a video signal representing the image of the subject; an A/D converter circuit for converting the video signal, which is outputted by said image sensing means, into input image data; deviation value calculating means for calculating a deviation value regarding lightness, or density of a specific color, in the input image data outputted by said A/D converter circuit; means for determining whether the deviation value obtained by said deviation value calculating means is greater than a predetermined threshold; pseudo-gray-scale image generating circuit means for converting said input image data, which is represented by a first prescribed number of bits per pixel, into pseudo-gray-scale image data represented by a second prescribed number of bits, which is less than said first prescribed number of bits; and image restoration circuit means for restoring the pseudo-gray-scale image data for each and every one of a plurality of small areas, each of which comprises a plurality of pixels and is provided in a window that scans the pseudo-gray-scale image generated by said pseudo-gray-scale image generating circuit means, with said each small area serving as one restored pixel, and outputting restored image data for a window at each and every position; said deviation value calculating means calculating a deviation value for each and every window with regard to said image data, and detecting a maximum value from among these deviation values; said determining means comparing the maximum deviation value with a predetermined threshold value.

Claim 32

An inspection apparatus for scratches or the like, comprising: image sensing means for imaging a subject and outputting a video signal representing the image of the subject; an A/D converter circuit for converting the video signal, which is outputted by said image sensing means, into input image data; deviation value calculating means for calculating a deviation value regarding lightness, or density of a specific color, in the input image data outputted by said A/D converter circuit; means for determining whether the deviation value obtained by said deviation value calculating means is greater than a predetermined threshold; pseudo-gray-scale image generating circuit means for converting said input image data, which is represented by a first prescribed number of bits per pixel, into pseudo-gray-scale image data represented by a second prescribed number of bits, which is less than said first prescribed number of bits; and image restoration circuit means for restoring the pseudo-gray-scale image data for each and every one of a plurality of small areas, each of which comprises a plurality of pixels and is provided in a window that scans the pseudo-gray-scale image generated by said pseudo-gray-scale image generating circuit means, with said each small area serving as one restored pixel, and outputting restored image data for a window at each and every position; said deviation value calculating means calculating a deviation value for each and every window with regard to said image data, and detecting a maximum value from among these deviation values; said determining means comparing the maximum deviation value with a predetermined threshold value.