JP2000101834A - Input information correction method and recording medium recording its program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To apply proper correction to input information in response to a binarization threshold of an image input device that receives the input information. SOLUTION: A correction result 200 is obtained by using a provision processing that provides reference items printed in various densities in advance to a received recording material, a reference item extract processing (1) that extracts a reference items with a required density in input information at a receiver side of the input information 100, a binarization threshold extract processing (2) that detects a binarization threshold of an image input device from the extracted reference item, and a correction processing (3) that uses the detected binarization threshold to correct the input information 100.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to input information for correcting a binary threshold of input information obtained by converting information written on paper or the like into binary by an image input device. The present invention relates to a correction method and a recording medium on which the program is recorded.

[0002]

2. Description of the Related Art When information written on a recording member such as paper is input by an image input device such as a scanner or a facsimile (hereinafter referred to as a facsimile), the obtained input information completely reproduces the original information. Not. The same applies to the case where information is binarized and input.

[0003] In this case, the binarization threshold value of the image input device greatly affects the reproducibility of information. For example, 2
Information input from an image input device having a high binarization threshold has a phenomenon in which black pixels are reduced as compared with the original information, line segments are interrupted, and line widths are reduced. Conversely, when the binarization threshold is low, phenomena such as discontinuous line segments are connected or the line width is increased in the original information.

In order to correct the difference between the input information and the original information, conventionally, for example, for information in which line segments tend to be interrupted, a process of connecting line segments is introduced. The input information has been corrected. However, in the conventional method, since the characteristics of the image input device are not detected and the correction according to the characteristics is not performed, the image input device is not specified, and information is input with various binarization thresholds.
Inappropriate correction cannot be performed.

For example, it is assumed that the line segment of input information is likely to be interrupted as compared with the original information because the binarization threshold value is extremely high, and emphasis is placed on processing to tighten the line segment. In the correction method, if the binarization threshold is not as high as expected, a problem such as excessive connection occurs. Conversely, 2
The line segment with a low threshold value, which should have been broken,
Input information input from an image input device that is connected after input must be processed in the reverse of the connection process, but also in this case, in the conventional method that does not detect the characteristics of the image input device, It cannot be corrected correctly.

As described above, the conventional input information correction method cannot flexibly respond to a change in the binarization threshold of the image input device, and outputs an inappropriate correction result.

[0007]

In the prior art, when input information is input from various image input devices as described above, each of the input information is binarized by the image input device to which the input information is input. There has been a problem that appropriate correction cannot be performed according to the threshold value.

An object of the present invention is to provide a method and a program for correcting an input information which solves the above-mentioned problems by determining a binarization threshold value of an image input device using a reference item given to input information. An object of the present invention is to provide a recorded recording medium.

[0009]

According to a method for correcting input information according to the present invention, information written on a recording member is converted into binary values of white and black by an image input device. A correction method, in which reference items printed at various densities are previously given to the input recording member,
On the receiving side of the input information, a reference item having a predetermined density is extracted from the reference items of the input information, and the binarization threshold value of the image input device is automatically detected by comparing with the original reference item. The input information is corrected by using a threshold value for conversion.

[0010] Further, the drawing information written on the recording member is used as input information, and the automatically detected image input device 2 is used.
The processing for connecting the line breaks is performed by using the binarization threshold.

Further, a recording medium according to the present invention is a computer which records a program used for correcting input information obtained by converting information written on a recording member into binary of black and white by an image input device. Is a readable recording medium, an application processing procedure of applying reference items printed at various densities in advance to the input recording member,
A reference item extraction procedure for extracting a reference item having a predetermined density from the reference items of the input information on the receiving side of the input information, and comparing the extracted reference item with the original reference item to obtain a binary value of the image input device. A binary threshold extraction procedure for detecting a binarization threshold, and a correction procedure for correcting the input information using the detected binarization threshold are recorded.

[0012]

DESCRIPTION OF THE PREFERRED EMBODIMENTS First, the method of the present invention will be described with reference to specific examples.

[0013] Since the characteristics of the FAX are different for each individual, for example, even if the same drawing is transmitted, the drawing (called input information in the present invention) received on the receiving side slightly differs from each other. For example, the lines are faint or darker.

[0014] This is because when transmitting information by facsimile,
The analog information is converted to digital information (black or white) by the transmission FAX, but the binary threshold value used for conversion (whether to convert to black pixels or to white pixels) This is because there is a difference for each model.

As an example, when four or more line segments are written on paper so as to gradually increase in density, such as from a thin line to a dark line in FIG. 1 and transmitted from various facsimile machines, Not all four line segments 〜 are visible, and only two lines can be seen from a fax transmitted with a high binarization threshold (which is not converted to a black pixel unless it is a dark point).

If the receiving side knows that four lines were originally written on the transmitting side paper, and the received information shows only two lines, the transmitted FAX Indicates that the binarization threshold value is higher than that of other FAXes.

The present invention utilizes this fact to automatically detect the facsimile binary threshold.

In the above example, two or four line segments are seen on the receiving side. However, a threshold value is required to make the computer judge "visible" or "invisible". .

In Example 1 of FIG. 1, the shadow (maximum value 3)
Is less than the threshold value (value is 5), so it is determined to be “invisible”. However, in Example 2, it is determined to be “visible”.

Therefore, the threshold value is set to a value which is neither extremely large nor small, and which makes it possible to draw a line of "visible" or "invisible", which is 5 in the above example. Thus, the threshold value is a value used to determine how many line segments are visible on the receiving side.

In the example of FIG. 1 (assumed to have been transmitted from the model A), the second line (example 2) out of the four written lines is "visible". FAX
What is transmitted and received from (referred to as model B) may be "visible" from the first line. Of course, "see"
The threshold value used to determine whether
It is. This allows model A to be compared to model B,
It can be seen that the binarization threshold is relatively high.

FIG. 2 shows a processing procedure in one embodiment of the input information correction method of the present invention. (1) to (3)
Indicates each step, 100 indicates input information, and 200 indicates a correction result.

The input information 100 includes information such as characters and drawings written on paper or the like to which reference items are assigned, such as a scanner,
The data is converted into binary data and input by an image input device (not shown) such as a facsimile. Input information 1
FIG. 3 shows, as an example of 00, a drawing written on paper 104 input by facsimile.

The reference items to be given may be a plurality of points or line segments having different densities, a line segment having a gradually changing density, or the like. FIG. 4 shows an example of the reference item.

In FIG. 4, reference numeral 101 denotes a reference item in which four line segments having different densities are arranged in the vertical direction, reference numeral 102 denotes a reference item in which the line segments are similarly arranged in the horizontal direction, and reference numeral 103 denotes a reference item in which two lines are superimposed.

Further, as a method of applying to the recording member, a method such as printing and pasting can be considered.

[First Embodiment] In the following, as a first embodiment, a plurality of line segments (101 in FIG. 4) having different densities are considered as reference items, and the line segments 1 to 4 are printed on a preprinted paper. A method of correcting the input information 100 obtained by converting the drawing information described above into binary by a scanner will be described.

FIG. 5 shows a paper 104 on which a plurality of reference line segments are printed. The reference item 101 may be provided at any position. For example, the case where the reference item is printed above the left edge of the paper in order to increase the drawing range is shown. The reference item 101 to be printed is a horizontal line segment having the same width and length and different black pixel densities. The amount of change in the black pixel density and the number of line segments associated therewith increase or decrease according to the detection accuracy of the obtained binarization threshold.

Now, the reference item extraction processing (1) shown in FIG.
Is a process of extracting a reference item from the input information in order to compare the reference item 101 before and after the input. Criteria item 10
Various methods are conceivable for extracting 1; however, here, a method of extracting using the fact that the position of the reference item is known in advance on the receiving side of the input information will be described.

FIG. 6 shows an embodiment of the extraction method. Viewing area 1 set according to the position of line segment 1 of reference item 101
05, a horizontal pixel oblique shadow 106 of line segment 1
I take the. A threshold value of 10 is set for the oblique shadow 106 of the black pixel.
7 is determined, and whether or not to extract as a line segment is determined based on whether or not the oblique shadow 106 exceeds the threshold value 107. FIG.
Since the threshold value 107 is exceeded, the extraction is successful. This processing is first performed for the line segment having the lowest black pixel density (line segment 1 in FIG. 6). If the line segment 1 is not extracted, the processing target is sequentially shifted to the line segment 2 and the line segment 3 to the line segment having the higher black pixel density, and the same processing is performed until the line segment is extracted. At this time, information indicating at which line segment extraction was successful is recorded for use in the next binarization threshold value detection process.

In addition to the above method, a method of measuring whether or not to extract as a line segment by measuring all the number of black pixels in the visual field 105 and providing a threshold value to the obtained number of black pixels, etc. Is also conceivable.

Further, for example, the entire reference item 101 is surrounded by a rectangle formed by a thick black line, the rectangle is extracted by pattern matching, and the position of the entire reference item is detected. A method of performing the extraction process for one of the items may be considered. In this method, the reference item 101 may be provided anywhere on the paper 104. This is the same for the reference items 102, 103 and the like.

The binarization threshold detection process (2) is a process for detecting the binarization threshold of the image input device by comparing the reference items 101 before and after the input. By using the information on the number of the line segment that was successfully extracted in the binarization threshold value detection processing (2),
The level of the binarization threshold of the image input device is determined. The levels are expressed as relative numbers.

FIG. 7 shows an example of the image input device 2 in which, when the number of line segments printed as the reference item 101 is four (1 to 4), it is determined from the information on the number of the line segment that has been successfully extracted. It is an example of the level value of a binarization threshold. Level value 4
Indicates that the binarization threshold value is higher than the level value 3. For example, the image input device having the level value 4 is more likely to have cutoff, blurring, and the like in the input information than the image input device having the level value 3. Easy to generate.

The correction process (3) is a process for correcting input information using the level value of the binarization threshold of the image input device obtained in the binarization threshold detection process (2).
Here, as an example of the correction process, a process of connecting line segments in the drawing will be described.

There are various methods for the process of increasing line segment discontinuity. As an example, a method of extracting an end point and connecting end points within a predetermined distance will be described as an example. .

FIG. 8 shows a processing procedure of the method. In FIG. 8, (11) and (12) indicate each step.

The end point extraction process (11) is a process for extracting an end point from the drawing. The extraction of the end points is performed by three-point scanning with every point in the drawing as a point of interest. FIG. 9 shows the embodiment. Appropriate vectors p and q (| p | = | q
| = Constant) and the value of θ satisfies the following condition: inner product of p and q> | p || q | × outer product of determination p and q> 0 (θ is close to 0) , The viewpoint is regarded as an end point. If the extraction of the end points is continued as shown in FIG.
Since 1 is generated, a center point is extracted from the end point group and is set as a representative end point (302 in FIG. 10). Further, the connection direction is determined using the direction difference of the coordinate sequence of the end point group (303 in FIG. 10).

The end point connection process (12) is a process for searching for a black pixel within a certain distance in the connection direction and, when a black pixel is detected, connecting the end point to the black pixel. In the existing method, the search distance is a constant value. In the present invention, this value is set according to the level value of the binarization threshold value obtained in the binarization threshold value detection process (2).

FIG. 11 shows an example of the search distance set from the level value of the binarization threshold.

As described above, for each input information, it is possible to perform appropriate correction according to the binarization threshold value of the image input device to which the input information has been input.

[Second Embodiment] As a second embodiment, a method using morphology (shrinkage and expansion) as a process for correcting input information will be described. The processing up to the binarization threshold value detection processing is the same as that of the first embodiment. By setting the size to be thickened and the size to be thinned by morphology in accordance with the level value of the obtained binarization threshold, for each input information, the binarization threshold of the image input device to which the input information is inputted It is possible to perform an appropriate correction according to.

In this method, in addition to the process of increasing the breaks of line segments, the process of expanding the breaks is also possible.

[Third Embodiment] As a third embodiment,
As a process for correcting input information, a method using a thinning method for gradually reducing a line width so as not to break the connectivity of lines will be described. The processing up to the binarization threshold value detection processing is the same as that of the first embodiment. The thinning method is effective for correction processing when the line width of the input information is larger than the original information. By setting the number of repetitions of the method for each input information according to the level value of the binarization threshold, an appropriate value corresponding to the binarization threshold of the image input device to which the input information is input is set. Correction can be performed.

The present invention may be implemented by a computer having a display unit and an input unit. A computer-readable program such as a magnetic medium or a CD-ROM may be used to execute the above-described steps. It can also be stored in a storage medium and distributed. That is,
A computer-readable recording medium that records a program used for correcting input information obtained by converting information written on a recording member into binary values of white and black by an image input device, and inputs the program. A providing process for providing reference items printed in various densities in advance on the recording member, a reference item extracting process for extracting a reference item having a predetermined density from the reference items of the input information on the receiving side of the input information,
A binarization threshold value extraction process for detecting a binarization threshold value of the image input device by comparing the extracted reference item with an original reference item; and using the detected binarization threshold value. And a correction processing procedure for correcting the input information.

[0046]

As described above, in the input information correcting method according to the present invention, the input information obtained by converting the information written on the recording member into binary of black and white by the image input device is obtained. A method of correcting information, in which reference items printed in various densities are given in advance to the recording member to be input, and on the receiving side of the input information, a reference item of a predetermined density is selected from the reference items of the input information. Since the binarization threshold value of the image input device is automatically detected by extracting and comparing with the original reference item, and the input information is corrected using the binarization threshold value, the The binarization threshold of the device can be automatically detected. As a result, it becomes possible to appropriately correct each input information input from various image input devices according to the binarization threshold value of the device to which the information has been input.

In particular, when drawing information is used as input information, many line breaks occur, and the effect of the present invention is remarkable.

According to the recording medium of the present invention in which a computer-readable program is recorded, the method for correcting the input information can be easily realized by controlling the computer.

[Brief description of the drawings]

FIG. 1 is a diagram for explaining a method of the present invention.

FIG. 2 is a flowchart showing a processing procedure of the present invention.

FIG. 3 is a diagram showing an example of input information in the present invention.

FIG. 4 is a diagram showing an example of reference items used in the present invention.

FIG. 5 is a diagram illustrating an example of paper on which a plurality of reference line segments used in the present invention are printed.

FIG. 6 is an explanatory diagram illustrating an example of a line segment extraction process according to the present invention.

FIG. 7 is a diagram showing a level value of a binarization threshold determined according to the present invention.

FIG. 8 is a flowchart showing a procedure of a process for connecting breaks of line segments according to the present invention.

FIG. 9 is an explanatory diagram showing an example of endpoint extraction according to the present invention.

FIG. 10 is a diagram showing an end point group and representative end points extracted in FIG. 9;

FIG. 11 is a diagram showing an example of a search distance set from a level value of a binarization threshold according to the present invention.

[Explanation of symbols]

 Reference Signs List 100 Input information 101 to 103 Reference item 104 Paper 105 Field of view 106 Projection 107 Threshold value 200 Correction result 301 End point group 302 Representative end point 303 Connection direction

Continuation of front page (72) Inventor Yasuhiro Aoki 3-19-2 Nishi-Shinjuku, Shinjuku-ku, Tokyo F-term in Nippon Telegraph and Telephone Corporation (reference) 5B047 AA01 AB02 BB02 CB21 DB05 DC09 5C077 LL08 LL19 MM27 PP41 PP43 RR04 RR16

Claims (3)

[Claims] 1. A method for correcting input information obtained by converting information written on a recording member into a binary value of white and black by an image input device, wherein various types of information are previously stored in the input recording member. A reference item printed at a proper density is provided, and on the receiving side of the input information, a reference item having a predetermined density is extracted from the reference items of the input information, and is compared with the original reference item. Wherein the binarization threshold value is automatically detected, and the input information is corrected using the binarization threshold value. 2. The input information correction method according to claim 1, wherein drawing information written on a recording member is used as input information, and line breaks are generated using a binarization threshold value of the automatically detected image input device. An input information correction method characterized by performing a connecting process. 3. A computer-readable recording medium which records a program used for correcting input information obtained by converting information written on a recording member into binary values of white and black by an image input device. A process for providing reference items printed in various densities in advance to the input recording member; and a reference item for extracting a reference item having a predetermined density from the reference items of the input information on the receiving side of the input information. An extraction processing procedure, a binarization threshold value extraction processing procedure of detecting a binarization threshold value of the image input device by comparing the extracted reference item with an original reference item, and the detected binarization processing. And a correction processing procedure for correcting the input information using a threshold value.