ANSI INCITS ISO 1831-1980 Printing specifications for optical character recognition.pdf

1、International Standard 1831 0 4iY% 4 INTERNATIONAL ORGANIZATION FOR STANDARDIZATION*ME)YHAPOHAR OPrAHH3AUMR n0 CTAHAAPTkl3Al 0.009 in diameter) covering the nearest void or group of voids likewise having a total surface greater than one-third of that of its circle, shall be at least 1 mm (0.04 in).

2、Non-allowable void 7 Maximum COL 7 lmm lLMinimum COL Figure 9 - Voids 11 IS0 1831-1980 (E) 5.4.4.5 Edge irregularity (see figure 10) An edge irregularity exists where the character extends outside the maximum COL and/or where a part of the character is miss- ing inside the minimum COL. An edge irreg

3、ularity shall be allowed if the projecting part of the character measured along the maximum COL and/or the missing part of the character measured along the minimum COL does not exceed 0,3 mm (0.012 in). Furthermore, the distance between adjacent ir- regularities shall be at least 1 mm (0.04 in) meas

4、ured centre to centre. 5.4.4.8 Spots (see figure 11) Spots are areas outside the maximum COL which contrast with the background. The distinction between allowable spots and non-allowable spots is based on a measurement of their size and distance. Spots may be connected or adjacent to parts of the pr

5、inted image, or may be free standing within the clear area (see 6.10). When the measuring gauge is in best fit to a charac- ter, any extraneous ink outside the maximum COL is a spot. Any extraneous ink of sufficient area, that is nearly as dark or darker than the lightest printing within the minimum

6、 COL, shall be checked. One or more spots shall be allowable if contained entirely in an inspection circle of 0,2 mm (0.008 in) diameter and if their total surface is smaller than one-third of the surface of the circle. If their total surface is greater than one-third of that of the ins- pection cir

7、cle but is contained entirely within the inspection circle, then the distance between the centre of this circle and the centre of the inspection circle (0,2 mm; 0.008 in diameter) covering the nearest spot or group of spots likewise having a total surface greater than one-third of that of its circle

8、, shall be at least 1 mm (0.04 in). Dimensions in millimetres Allowable edge irregularity Maximum COL Mizum COL Minimum COL Maximum COL L Non-allowable edge irregularity Figpre 10 - Edge irregularity 12 IS0 1831-1980 (E) owed in unlimited number Allowable spots Non-allowable spots 0.2 mm circle Maxi

9、mum COL Minimum COL Figure 11 - Spots 5.4.5 Instrumented measurement 5.4.5.1 Apparatus arrangement Illumination : Incandescent lamp. Geometry of illumination : One source at 45” with respect to paper surface. Illuminated area large compared with measuring aperture. Geometry of scanner : 90 with resp

10、ect to paper surface. Aperture 0,2 mm (0.009 in) diameter at sample surface. Spectral response : See 3.2. White reference : See 4.2. 5.4.5.2 Print contrast (see figure 12) Print contrast is the difference between the reflectance R, of a character and the reflectance R,., of the paper on which it is

11、printed. PC = R, - R, where RW is the maximum reflectance found within the area of interest to which the PC of point p is referenced. (In measuring printed images, the area of interest shall be a rec- tangle of approximately twice the nominal character height by twice the nominal character width and

12、 centred on the character being measured.) R, is the reflectance from a small measurement area centred on point p. The reflectances R, and R, shall be measured within an area of 0,2 mm (0.009 in) diameter, if circular, or 0,15 mm (0.005 9 in) side, if square. These reflectance specifications deal on

13、ly with diffuse reflec- tance, and the reflected light used for measurement shall ex- clude specularly reflected light. Reflectance measurements of R, and R, shall be referred to BaS04 as the 100 % value when determining the value of PC. The reflectance measurements shall be made using the black bac

14、king method. The PC of any point of a printed image is highly dependent on the spectral properties of the ink used to create the printed image. 5.4.5.3 Print contrast signal The print contrast signal (PCS) is defined by : PCS = Rw - R, RW It relates the print contrast of any selected point to the re

15、flec- tance of the paper on which it is printed. Although normally reflectance values are referred to BaS04 as the 100 % value, this is not necessary in the determination of PCS. The value of PCS is dependent only on the relative reflectance values of R, and R,. 13 IS0 1831-1980 (E) -_- I Base Dimen

16、sions in millimetres - -4 1 H 2w k Figure 12 - Print contrast 14 IS0 1831-1980 (E) 5.4.5.4 Best fit All measurements described hereafter shall be made in the “best fit” position of the character with the COL masks. The best fit can be achieved visually on an instrument by pos- itioning the actual ch

17、aracter image so that it fills the minimum COL as much as possible and at the same time does not extend beyond maximum COL. More specifically, the overall reflec- tance within minimum COL shall be a minimum. If this con- dition is met for several positions, then the best fit position is that yieldin

18、g the maximum reflectance outside maximum COL. Light portions of the character inside minimum COL, and dark portions outside maximum COL, shall be checked as to edge irregularities, voids and spots. Maximum COL Minimum COL 5.4.5.6 PCS, pc%lax is the highest average PCS value of three consecutive bas

19、ic PCS values for characters with a centreline longer than 2 mm (0.08 in) and of five such consecutive values for characters with a centreline of less than 2 mm (0.08 in). 5.4.5.7 PCS,in PCS,rn is the lowest average PCS value of three consecutive basic PCS values for characters with a centreline lon

20、ger than 2 mm (0.08 in) and of five such consecutive values for characters with a centreline of less than 2 mm (0.08 in). 5.4.5.8 Contrast variation ratio within a character The variation of contrast within a character is defined by the contrast variation ratio : pwnax CVR =- pcsrnin The CVR must sa

21、tisfy the following conditions : CVR 0,80 in range X PCS.80 % 050 in range Y For certain OCR applications, the value given for PCS80 % in range Y might be too stringent. Deviations from this value shall be agreed upon by the parties concerned. Voids are areas inside the minimum COL which have a sign

22、ificantly lower density than the printed image. The distinc- tion between allowable voids and non-allowable voids is based on a measurement of their size and distance. Small voids shall be permitted providing certain conditions are satisfied; larger ones shall not. The size of a void depends on the

23、PCS level at which it is measured. A void shall be allowable if it satisfies the following conditions : All basic PCS values lower than PCSac % shall be considered. The values d mentioned hereafter are : d = 040 in range X d = 0,35 in range Y A void is present at points for which a PCS of less than

24、d is measured. a) Characters with a centreline of more than 2 mm (0.08 in) : - if a point has a PCS d, an allowable void is present at this point; - if two adjacent points have a PCS e, the spot shall not be allowable; - if at most one position has a PCS e, the spot shall be allowable; - if two posi

25、tions have a PCS e, the aperture shall be centred on the position with the smaller PCS and the seven remaining positions defined by steps of 0,l mm (0.004 in) horizontally and vertically are also measured : - if a third position is found with a PCS e, the spot shall not be allowable: - if no third p

26、osition with a PCS e is found, the spot shall be allowable only if its distance to a spot of the same type and to the maximum COL is greater than 1 mm (0.04 in). If in this procedure one or more positions happen to have their centre within maximum COL, these positions shall be disregarded. Spots rem

27、ote from the character, i.e. outside the area of in- terest, are not subject to PCS limitations. However, if located in the clear area (see 6.10) their size shall be limited to 0,2 mm (0.008 in) in diameter. 5.4.6 Computer-aided method An implementation of this method exists and is described in anne

28、x C. 5.4.6.1 Apparatus arrangement The characteristics of the high resolution scanner to be used shall be in accordance with the following arrangement : Spatial resolution : 25 pm (0.001 in) or of higher degree. 5.4.5.12 Spots Aperture : Spots are areas outside the maximum COL which contrast with th

29、e background. The distinction between allowable spots and non-allowable spots shall be based on a measurement of their size. Small spots shall be permitted providing certain conditions are satisfied; larger ones shall not. Spots may be connected or adjacent to parts of the printed image, or may be f

30、ree standing. Spots shall be measured with an aperture of 0,2 mm (0.008 in) diameter, centred on the spot at the point with the highest PCS value. When this position is identified, the eight positions defined by the steps of 0,l mm (0.004 in) horizontally and ver- tically shall also be measured. 25

31、pm (0.001 in) in diameter or equivalent to the degree of resolution. Geometry of illumination : One source at 45O with respect to the paper surface with a large illuminated area compared with the measuring aper- ture. Alternatively, an illumination with a small aperture size at 9o” with respect to t

32、he paper. 16 IS0 1831-1980 (E) Geometry of scanner : 90” with respect to the paper surface. Aperture 0,2 mm (0.008 in) diameter at sample surface. Alternatively, one scanner with large sensitive area at 45O with respect to the paper. Spectral response : See 3.2. White reference : See 4.2. All defini

33、tions of print parameters given hereafter are based upon an integration of the scanned values up to a circular area of 0.2 mm (0.008 in) diameter. 5.4.6.2 Print contrast (see table 6) The print contrast is the difference between the reflectance (R,) of the area of the paper on which the character is

34、 printed and the reflectance (R,) of the point under inspection. R, is the maximum reflectance of the paper. R, shall be measured in a rectangle Q which is centred upon the character to be investigated. The dimensions for the rectangle Q are shown in table 6. Grey scale resolution : R, is the reflec

35、tance at the point p under consideration. 32 or more grey levels. The results from a measuring arrangement with a large area of illumination and a small scanner area are comparable with those received by an arrangement containing a small area of illumina- tion and a large scanner area. An arrangemen

36、t with a small area of illumination and a small sized scanner shall not be permitted. If the spectral response of the optical character recognition system in use is known, the parameters of the printed images may be tested in this spectral band only. Otherwise testing shall be performed in all spect

37、ral bands that are mentioned in 2.2. While measuring these parameters, the paper shall be backed by a medium with less than 3 % reflectance. 5.4.6.3 Definition of the print contrast signal The PCS is defined by the equation PCS = Rw - 4, RW Table 6 - Print contrast Font A Size I III IV Character set

38、 All characters as defined in IS0 1073 Height X width of rectangle Cl mm in 3.90 X 2.50 0.164 x 0.100 4.80 X 2.70 0.190 x 0.107 5,60 X 3,40 0.221 x 0.134 B I III IV Sub-sets 1, 2 4.90 X 2.50 0.170 x 0.100 Sub-sets 3, 4 3,30 X 2.50 0.154 x 0.100 All characters as defined in 4.80 X 2,70 0.190 x 0.107

39、IS0 1073 5.40 x 3.50 0.213 X 0.138 17 IS0 1831-1980 (E) 5.4.6.4 Best fit 5.4.6.8 Contrast variation within a character 5.4.6.4.1 General All measurements and investigations on parameters that are specified in the following shall be performed after centring the COL gauge upon the printed character (b

40、est fit). Definition of best fit : The COL gauge shall be adjusted to be either perpendicular or parallel to the document reference edge. For determination of the printed character, the preliminary stroke edges of the character shall be defined. For this reason the arithmetical average PCS, of all P

41、CSs equal to or greater than 0,3 within the rectangle Q shall be established. The preliminary stroke edges are then found at PCS2 = 0,5.(PCS, + 0,3). The COL gauge shall be moved horizontally and vertically along the so defined preliminary stroke edges of the character until the position is found wh

42、ere the deviation from the minimum COL and maximum COL is at a minimum. If there are several such positions, the position with the highest value for PCSso 9/a shall be chosen (see 5.4.6.5). 5.4.6.4.2 Characters with cut-off All characters for all print tolerance ranges shall be centred in this way w

43、ithout considering the cut-off limit lines see figure 7 a). For those characters of print tolerance range Z which do not satisfy the conditions of the following specifica- tions, the best fit positioning shall be repeated. This second step for best fit shall be performed by using the cut-off limit l

44、ines see figure 7 b). Thereafter all parameters shall be tested under consideration of the cut-off limit lines. 5.4.6.5 PCS within a character The smallest value of the 80 % highest values measured along the centreline is called PCSac %. It shall satisfy the following conditions : PCSm 9/o 0,60 in r

45、ange X PCS80 9/o 050 in range Y PCS the higher the grammage, the greater the opacity. Consequently, there is a similar relationship between opacity and paper thickness, although the use of filler and coating materials have an effect. In general, paper having an opacity exceeding 85 % should be used.

46、 Papers of lower opacity should be used only if needed for the ap- plication and after considering the scanner optical system. Papers having an opacity less than 70 % should not be used. Many inks have the property of permeating the paper to a considerable depth, Applications requiring an OCR docume

47、nt to be printed on both sides may require a higher opacity or thicker paper to compensate for this effect. A.3 Paper gloss A.3.1 Significance of gloss for OCR documents Gloss is the property of a surface responsible for a lustrous or mirror-like appearance. It is a phenomenon related to the specula

48、r reflection of incident light. The effect of gloss is to reflect more of the incident light in a specular manner, and to scatter less. It occurs at all angles of incidence and should not be confused with grazing angle specular reflection that is often referred to as sheen. Paper gloss is undesirabl

49、e for OCR systems since it will change the effective brightness of the paper, thus affecting the print contrast signal. A.3.2 Recommendations Paper for OCR documents should be restricted to the low gloss varieties. The use of coated or super-calendered papers or other papers with a glossy appearance should be avoided. A.4 Variation in paper reflectance Reflectance measurements performed with a very small aperture at a variety of positions at the paper surface result in a variation of the measures obtained. To distinguish reflectance measurements performed visually again