Image detection system

• US 6,002,800 A
• Filed: 05/16/1996
• Issued: 12/14/1999
• Est. Priority Date: 05/22/1995
• Status: Expired due to Term

• Current Assignee: Canon Ayutthaya Limited (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Donelly, Ross Alexander, Demetriou, Stamatios
• Primary Examiner(s): Chang, Jon
• Application Number:
  US08/649,072
• Time in Patent Office: 1,307 Days
• Field of Search: 382/209, 382/195, 382/218, 382/294, 382/295, 382/296, 382/297, 382/298, 382/216, 382/217, 382/135
• US Class Current: 382/216
• CPC Class Codes: G06V 10/7515 Shifting the patterns to accommodate for positional errors
• CPC Class Codes: H04N 1/00843 based on recognising a copy prohibited original, e.g. a banknote pattern authentication and markers therefor, forgery detection G06V20/95; character recognition G06V30/10; document-oriented image-based pattern recognition G06V30/40; testing paper currency or similar valuable papers for genuineness G07D7/00
• CPC Class Codes: H04N 1/00848 by detecting a particular original
• CPC Class Codes: H04N 1/00875 Inhibiting reproduction, e.g. by disabling reading or reproduction apparatus

Abstract

An image detection system is disclosed for the detection of an image in an input pixel stream. An image is input as a input pixel stream and accumulated and converted into cells which are formed into cell data portions from regions of a corresponding image of the input pixel stream. A template storage ROM stores at least one template that comprises a multiplicity of cell data entries derived form an desired image to be detected. A comparator matrix is connected to the cell converter and the template ROM for comparing the cell data portions with a multiplicity of cell data entries to derive a template detection signal when a predetermined number of the cell data portions match with the multiplicity of said cell data entries. The system finds particular use in the prevention of fraudulent copying of images, such as bank notes using colour laser copiers and printers.

Claims

1. Apparatus for the detection of an image in an input pixel stream, said apparatus comprising:

(i) image input means for receiving said input pixel stream;

(ii) cell converter means for forming cell data portions formed from regions of a corresponding image of said input pixel stream;

(iii) template storage means for storing at least one template, said template comprising a multiplicity of cell data entries derived from the desired image to be detected, wherein each cell data entry constitutes a range of values, said range of values being derived from maximum and minimum data entry values for a particular corresponding portion of said desired image when said particular corresponding portion of said desired image is subjected to a predetermined amount of rotation, scaling and translation or any combination thereof; and

(iv) comparator means for comparing said cell data portions of said cell converter means with said multiplicity of cell data entries to derive a template detection signal when at least an adjacent pair of said cell data portions match with a corresponding pair of said cell data entries for an optimal rotation position of said adjacent pair of cell data portions, and wherein said comparator means simultaneously compares a column of said cell data portions with said cell data entries of said template to determine if any column of said template matches with said column of cell data portions.

2. Apparatus as claimed in claim 1, wherein said multiplicity of cell data entries comprises all said cell data entries within said template.

3. Apparatus as claimed in claim 1, wherein said cell data portions must occur within said range in order to provide the desired match.

4. Apparatus as claimed in claim 1, wherein said comparator means simultaneously compares a column of said cell data portions with the whole of said cell data entries of said template to determine if any column of said template matches with said column of cell data portions.

5. Apparatus as claimed in claim 4, wherein said comparator means simultaneously compares a 180 degree rotation of said column of cell data portions with the whole of said template to determine if any column of said template matches with said rotated column of cell data portions.

6. Apparatus as claimed in claim 1, wherein said comparator means simultaneously compares a column of said cell data portions with the whole of said template to determine if any column of said template matches with a column of a 90 degree rotation of said columns of said template.

7. Apparatus as claimed in claim 4, 5 or 6, wherein said comparator means simultaneously compares a column of said cell data portions with the whole of said template to determine if any column of said template matches with a column of a 270 degree rotation of said columns of said template.

8. Apparatus as claimed in claim 1 wherein said template storage means contains multiple templates and said comparator means carries out a comparison for each one of said templates.

9. Apparatus as claimed in claim 1 wherein said comparator means loads a subsequent template while simultaneously carrying out said comparisons of said cell data portions of said cell converter means with said multiplicity of cell data entries.

10. Apparatus for the detection of an image in an input pixel stream, said apparatus comprising:

(i) image input means for receiving said input pixel stream;

(ii) cell converter means for forming cell data portions from overlapping regions of said pixel stream, said cell data portions being divided into a series of phases with each of said phases having cell data portions derived from non-overlapping regions;

(iii) template storage means for storing at least one template, said template comprising a multiplicity of cell data entries derived from a desired image to be detected, wherein each cell data entry constitutes a range of values, said range of values being derived from maximum and minimum data entry values for a particular corresponding portion of said desired image when said particular corresponding portion of said desired image is subjected to a predetermined amount of rotation, scaling and translation or any combination thereof; and

(iv) comparator means for comparing said cell data of each of said series of phases of said cell converter means with said multiplicity of cell data entries to derive a template detection signal when at least an adjacent pair of said cell data portions match with a corresponding pair of said cell data entries for an optimal rotation position of said adjacent pair of cell data portions, wherein said comparator means simultaneously compares a column of said cell data portions with said cell data entries of said template to determine if any column of said template matches with said column of cell data portions.

11. Apparatus as claimed in claim 10, further comprising:

(v) detected template storage means for storage of a plurality of template entries, with each said template entry including detected location data corresponding to a location of the template detected by said template detection signal; and

(vi) dual template detection means for detecting an occurrence of two templates from the same image in said pixel stream.

12. Apparatus as claimed in claim 11, wherein said dual template detection means includes distance determination means for determining the distance between the detected location data of said detected templates.

13. Apparatus as claimed in claim 12, wherein said distance determination means includes distance comparator means for determining if said distance between the detected location data is substantially the same as an expected predetermined distance between said detected templates.

14. Apparatus as claimed in claim 10, wherein said cell data portions include a data value derived form a group of pixels, said pixels covering a two-dimensional area of said image.

15. Apparatus as claimed in claim 14, wherein said cell converter means forms multiple sets of said cell data portions, with each set of said cell data portions being composed from a contiguous two dimensional area of pixels in the input pixel stream.

16. Apparatus as claimed in claim 12 or 13, wherein said distance is a vector measure having magnitude and directional components.

17. Apparatus for comparing a first predetermined array of cell data values with a second predetermined array of template data values, said apparatus comprising:

(i) input means for inputting, a column at a time, said first predetermined array of cell data values to a comparator matrix means;

(ii) a comparator matrix means for simultaneously determining if said column of cell data values matches with any of a plurality of columns of said second predetermined array of template data values and producing a column matching signal designating the said matched column of said second predetermined array of template data values, said comparator matrix means for simultaneously determining if said column of cell data values matches with any of a plurality of columns of a predetermined number of rotations of said second predetermined array of template data values and producing a rotated column matching signal designating said matched column of said predetermined number of rotations of said second predetermined array of template data values, wherein said column of cell data values is simultaneously input to said comparator matrix means in a first order corresponding to a first rotation case and in a second order corresponding to a second rotation case;

(iii) tally array means for storing said column matching signals for a series of columns of said first predetermined array of cell data values; and

(iv) template match detection means for deriving from said stored column matching signals, a template match signal signifying the occurrence of a match between said template and a portion of said first predetermined array of cell data values.

18. Apparatus as claimed in claim 17, wherein:

said tally array further includes means for storing said rotated column matching signals for a series of columns of said first predetermined array of cell data values; and

said template match detection means further includes means to derive, from said stored rotated column matching signals, a template match signal signifying the occurrence of a match between a rotation of said template and a portion of said first predetermined array of cell data values.

19. Apparatus as claimed in claim 18 wherein said rotations include substantially 90, 180 and 270 degrees.

20. Apparatus as claimed in claim 17, wherein:

said comparator matrix means simultaneously determines if said column of cell data values matches with any of a plurality of rows of said second predetermined array of template data values and produces a row matching signal designating the said matched row of said second predetermined array of template data values;

said apparatus further comprising;

second tally array means for storing said row matching signals for a series of columns of said first predetermined array of cell data values, and

second template match detection means for deriving from said stored row matching signals, a second template match signal signifying the occurrence of a match between said template and a portion of said first predetermined array of cell data values.

21. Apparatus as claimed in claim 17 wherein the number of elements of said column of cell data values is the same as the number of values in said column of said second predetermined array of template data values.

22. Apparatus as claimed in claim 17 or 18, wherein a template data value comprises two numbers which delimit a range of values, and wherein a column of cell data values matches a corresponding column of said template data values when each of said cell data values is within the range delimited by said template data value.

23. An image processing method comprising the steps of:

inputting image data representing an input image;

forming cell data portions from a plurality of regions of said input image;

forming cell data portions from a plurality of regions of a specific image;

determining a representative value for each of said cell data portions of said specific image;

determining a range of representative values for each of said cell data portions of said specific image, said range being derived from the maximum and minimum representative values for a particular cell data portion when said plurality of regions of said specific image is subjected to a predetermined amount of rotation, scaling and translation or any combination thereof;

determining whether a first cell data portion of said input image includes an average data value, for said first cell data portion, within said range of representative values for a corresponding cell data portion of said specific image and generating a first determination result;

determining whether a second cell data portion of said input image includes an averaged data value, for said second cell data portion, within said range of representative values for a corresponding cell data portion of said specific image and generating a second determination result; and

discriminating whether the input image includes the specific image based on the first and second determination results and positional information about the first and second cell data portions of said input image, wherein at least an adjacent pair of cell data portions of said input image returns an overall maximum determination result for an optimal rotation position of said plurality of regions of said specific image.

24. A method according to claim 23, wherein the image data is colour component data which is used for forming a colour image.

25. A method according to claim 24, wherein the colour component data is selected one of Cyan, Magenta, Yellow and Black.

26. A method according to claim 23, further comprising the step of performing density conversion on the image data before the determinations.

27. A method according to claim 23, wherein said discrimination is performed in synchronism with the input of said image data.

28. A method according to claim 23, wherein said regions of said specific image correspond to N×

M pixel block.

29. A method according to claim 23, wherein said positional information includes distance information and direction information.

30. A method according to claim 23, further comprising the step of controlling an image processing apparatus based on the discrimination result.

31. An image processing method comprising the steps of:

inputting image data representing an input image;

forming cell data portions formed from a plurality of regions of a specific image;

determining a range of representative values for each of said cell data portions of said specific image, said range being derived form the maximum and minimum representative values for a particular cell data portion when said plurality of regions of said specific image is subjected to a predetermined amount of rotation, scaling and translation or any combination thereof;

extracting cell data values for each of a plurality of cells corresponding to a first region of the input image; and

discriminating whether the input image includes a specific image by comparing the extracted cell data values with a range of representative values for each of a plurality of cell data portions corresponding to a second region of the specific image, wherein a column of cell data values is simultaneously compared with the cell portions of said specific image to determine if any column of said cell data portions matches with said column of cell data values, wherein at least an adjacent pair of cell data values of said input image returns an overall maximum determination result for an optimal rotation position of said plurality of cell data portions of said specific image, and wherein the discrimination is performed by compensating a minute aberration between the first region of the input image and the second region of the specific image.

32. A method according to claim 31, wherein the image data is colour component data which is used for forming a colour image.

33. A method according to claim 32, wherein the colour component data is selected one of Cyan, Magenta, Yellow and Black.

34. A method according to claim 31, wherein said discrimination is performed in synchronism with the input of said image data.

35. A method according to claim 31, wherein said minute aberration is smaller than a size of the cell.

36. A method according to claim 31, further comprising the step of controlling an image processing apparatus based on the discrimination result.

37. A computer program product comprising a computer readable medium having a computer program recorded therein for performing an image processing method comprising the steps of:

inputting image data representing an input image;

forming cell data portions from a plurality of regions of said input image;

forming cell data portions from a plurality of regions of a specific image;

determining a representative value for each of said cell data portions of said specific image;

determining a range of representative values for each of said cell data portions of said specific image, said range being derived from the maximum and minimum representative values for a particular cell data portion when said plurality of regions of said specific image is subjected to a predetermined amount of rotation, scaling and translation or any combination thereof;

determining whether a first cell data portion of said input image includes an averaged data value, for said first cell data portion, within said range of representative values for a corresponding cell data portion of said specific image and generating a first determination result;

determining whether a second cell data portion of said input image includes an averaged data value, for said second cell data portion, within said range of representative values for a corresponding cell data portion of said specific image and generating a second determination result; and

discriminating whether the input image includes the specific image based on the first and second determination results and positional information about the first and second cell data portions of said input image, wherein at least an adjacent pair of cell data portions of said input image returns an overall maximum determination result for an optimal rotation position of said plurality of regions of said specific image.

38. A computer program product comprising a computer readable medium having a computer program recorded therein for performing an image processing method comprising the steps of:

inputting image data representing an input image;

forming cell data portions from a plurality of regions of a specific image;

determining a range of representative values for each of said cell data portions of said specific image, said range being derived from the maximum and minimum representative values for a particular cell data portion when said plurality of regions of said specific image is subjected to a predetermined amount of rotation, scaling and translation or any combination thereof;

extracting cell data values for each of a plurality of cells corresponding to a first region of the input image; and

discriminating whether the input image includes a specific image by comparing the extracted cell data values with a range of representative values for each of a plurality of cell data portions corresponding to a second region of the specific image, wherein a column of cell data values is simultaneously compared with the cell data portions of said specific image to determine if any column of cell data portions matches with said column of cell data values, wherein at least an adjacent pair of cell data values of aid input image returns an overall maximum determination result for an optimal rotation position of said plurality of cell data portions of said specific image, and wherein the discrimination is performed by compensating a minute aberration between the first region of the input image and the second region of the specific image.