JP2003108996A - Image processor and image processing method, image processing program and computer-readable storage medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enable a user to freely adjust and change the setting parameter for image processing. SOLUTION: This image processor is provided with a control part calculating the plurality of set parameters necessary for execution of the prescribed image processing; a display part displaying the calculated set parameter candidates as a plurality of set parameter candidate groups; and an input part selecting a desired set parameter candidate from the displayed set parameter candidate groups, and capable of specifying a value of the set parameter belonging to the selected set parameter candidate. The user selects a desired value from the plurality of set parameter candidate groups, changes or finely adjusts the value, or executes trial and error, to obtain the optimum set parameter value.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing technique used for position detection, for example, and an image processing apparatus and an image processing method for displaying a plurality of parameters necessary for various image processings. The present invention relates to a program and a computer-readable storage medium.

[0002]

2. Description of the Related Art In an image processing apparatus, various processes are performed according to a user's request. In image processing, there are many kinds of processing in which it is necessary to optimally set a plurality of parameters in order to appropriately execute various required processing. Many of these parameters exist depending on the process,
Since they may be related to each other, if all of these parameters are left set by the user, it becomes very complicated and the operability deteriorates. For this reason, it is generally performed to automatically set the image processing apparatus. In order to realize such automatic parameter setting, various techniques for calculating and setting a combination of parameters considered to be optimal on the image processing apparatus side have been developed and are actually used. In these techniques, only one set that seems to be optimal as a combination candidate of parameters is automatically selected.

[0003]

However, this method has a problem that the user cannot adjust the value because the optimum value is automatically fixed on the image processing apparatus side. On the user side, there is a drawback that the degree of freedom in setting is reduced, so that fine adjustment, optimization, and tuning according to the situation cannot be performed. Particularly in image processing, it is often difficult for the apparatus to automatically select the optimum value. Image processing data is relatively susceptible to disturbances, and there are a wide variety of images to be processed. Therefore, a set of parameters selected on the device side according to a certain criterion is not always optimal in various usage situations.

Further, usually only one set of parameter candidates is calculated. Furthermore, each parameter is often not displayed to the user. Therefore, there is a problem in that even if a user wants to make some changes or modifications to the parameter settings, the information to realize them is not presented to the user.
When the parameter information is not given, it becomes extremely difficult for the user to understand the complex relation of many parameters and to guess the optimum value.

The present invention was developed for the purpose of solving such problems. A main object of the present invention is to display a list of parameter candidates and select an optimum candidate on the user side, and an image processing apparatus, an image processing method, and an image processing program capable of changing set values when necessary. Another object is to provide a computer-readable storage medium.

[0006]

In order to achieve the above object, an image processing apparatus according to a first aspect of the present invention performs predetermined image processing on an input image. This image processing device displays a control unit that calculates a plurality of setting parameters necessary for performing the predetermined image processing, a display unit that displays the calculated setting parameter candidates as a plurality of setting parameter candidate groups, and a display unit that displays the setting parameter candidates. A desired setting parameter candidate is selected from the set parameter candidate group, and an input unit capable of designating the value of the setting parameter belonging to the selected setting parameter candidate is provided.

The image processing apparatus according to a second aspect of the present invention is a binarization process for replacing an input image with a binary image with a predetermined threshold as a reference. Is automatically determined. This image processing device, a control unit that calculates a plurality of setting parameters necessary for determining the automatic threshold, a display unit that displays the calculated setting parameter candidates as a plurality of setting parameter candidate group, It is characterized by further comprising: an input unit capable of selecting a desired setting parameter candidate from the displayed setting parameter candidate group and designating a value of the setting parameter belonging to the selected setting parameter candidate.

Further, the image processing apparatus according to the third aspect of the present invention performs an edge detection process for detecting an edge portion on the input image based on a predetermined threshold value. This image processing device, a control unit that calculates a plurality of setting parameters necessary for performing the edge detection process,
A display unit for displaying the calculated setting parameter candidates as a plurality of setting parameter candidate groups, and selecting a desired setting parameter candidate from the displayed setting parameter candidate group, and setting parameters belonging to the selected setting parameter candidate. And an input unit capable of designating the value of.

Further, in the image processing apparatus according to claim 4 of the present invention, in addition to the features described in any one of claims 1 to 3, the image processing apparatus is further designated by the input section. It is characterized by comprising setting parameter value adjusting means capable of adjusting the value of the set parameter.

Further, in the image processing device according to claim 5 of the present invention, in addition to the features described in any one of claims 1 to 4, the feature of each setting parameter candidate is added to the setting parameter candidate. It is characterized in that an index indicating is added.

Furthermore, the image processing apparatus according to claim 6 of the present invention is characterized in that, in addition to the characteristics described in claim 5, the index is the time required for the predicted processing. .

Furthermore, an image processing apparatus according to a seventh aspect of the present invention performs predetermined image processing on an input image. This image processing device includes an input image storage unit that inputs and holds image data from the outside, an image processing unit that is connected to the input image storage unit, reads image data, and performs the predetermined image processing, and the image processing unit. Displayed on the display unit, and a display unit for displaying a list of a set of setting parameter candidates calculated by the control unit, the control unit calculating a setting parameter candidate required for performing the predetermined image processing. And an input unit capable of changing the value of the setting parameter based on the setting parameter candidate group.

Further, the image processing method according to claim 8 of the present invention is an image processing method for performing predetermined image processing on an input image. This image processing method includes a step of calculating a plurality of setting parameters necessary for performing the predetermined image processing, a step of displaying the calculated setting parameter candidates as a plurality of setting parameter candidate groups, and a displayed setting. Selecting a desired setting parameter candidate from the parameter candidate group and designating the value of the setting parameter belonging to the selected setting parameter candidate.

Furthermore, an image processing method according to a ninth aspect of the present invention is a binarization process for replacing an input image with a binary image based on a predetermined threshold value, and the threshold value. An image processing method for automatically determining a threshold value for automatically changing a value. This image processing method includes a step of calculating a plurality of setting parameters necessary for determining the automatic threshold, a step of displaying the calculated setting parameter candidates as a plurality of setting parameter candidate groups, and Selecting a desired setting parameter candidate from the set of setting parameter candidates, and designating the value of the setting parameter belonging to the selected setting parameter candidate.

An image processing method according to a tenth aspect of the present invention is an image processing method for performing edge detection processing for detecting an edge portion on an input image based on a predetermined threshold value. This image processing method includes a step of calculating a plurality of setting parameters necessary for performing the edge detection process, a step of displaying the calculated setting parameter candidates as a plurality of setting parameter candidate groups, and a displayed setting parameter. And a step of selecting a desired setting parameter candidate from the candidate group and designating a value of the setting parameter belonging to the selected setting parameter candidate.

Furthermore, the image processing method according to claim 11 of the present invention is characterized in that, in addition to the features described in any one of claims 8 to 10, the image processing method further includes a setting parameter specified. It is characterized by having a step of adjusting the value.

Further, the image processing program according to claim 12 of the present invention is an image processing program for performing predetermined image processing on an input image. The image processing program includes means for calculating a plurality of setting parameters necessary for performing the predetermined image processing, means for displaying the calculated setting parameter candidates as a plurality of setting parameter candidate groups, and the displayed setting. And a means for selecting a desired setting parameter candidate from the parameter candidate group and designating a value of the setting parameter belonging to the selected setting parameter candidate. This program also includes a form that can be downloaded via a network.

Furthermore, in the image processing program according to claim 13 of the present invention, in addition to the features described in claim 12, the image processing program further adjusts the value of the designated setting parameter. It is characterized by having means.

Further, a computer-readable recording medium according to a fourteenth aspect of the present invention stores the image processing program according to the twelfth or thirteenth aspect. The recording medium is a CD-ROM, C
DR, CD-RW, flexible disk, cassette tape, MO, DVD-ROM, DVD-RAM, DV
It includes a magnetic disk such as a D-RW, a DVD + RW, an optical disk, a magneto-optical disk, a semiconductor memory, and other media capable of storing a program.

[0020]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings. However, the embodiments described below exemplify an image processing apparatus and an image processing method for embodying the technical idea of the present invention, an image processing program, and a computer-readable storage medium. The invention does not specify an image processing apparatus, an image processing method, an image processing program, and a computer-readable storage medium as follows.

Further, in this specification, in order to facilitate understanding of the claims, the numbers corresponding to the members shown in the embodiments are referred to as "claims column" and "to solve the problem." It is added to the members shown in the column of "means". However, the members shown in the claims are not limited to the members of the embodiment. The sizes and positional relationships of members shown in the drawings may be exaggerated for clarity of explanation.

In the present specification, the image processing apparatus or the image processing method is not limited to the apparatus or the method for performing the image processing itself, but also includes the apparatus or the method for performing the processing related to the image processing. Further, the present invention is not limited to a device that performs processing in hardware, and is intended to include a device that performs processing in software. For example, a general-purpose or dedicated computer, workstation, terminal, or mobile device capable of performing image processing in which software or programs, plug-ins, objects, libraries, applets, compilers, etc. are installed in a general-purpose circuit or computer and related processing. Type electronic device, PD
The image processing apparatus also includes electronic devices such as A, a pager, a smartphone, and the like. Further, in the present specification, the program itself is also included in the image processing apparatus.

Hereinafter, as Embodiments of the present invention, Embodiment 1 which presents a list of parameters in a process called automatic threshold value determination and Embodiment 2 which presents a list of parameters in an edge detection process will be respectively described. . Further, for various image processings other than these, it is possible to display a list of parameters similarly to these and contribute to tuning of the user.

[Image Processing Apparatus] The configuration of the image processing apparatus according to the embodiment of the present invention will be described with reference to FIG. Figure 11
The image processing apparatus shown in (1) is an input image storage unit 1 for inputting image data from the outside, and an image processing unit 3 connected to the input image storage unit 1 for reading image data and performing various processing
And a control unit 4 for calculating control parameter for performing predetermined image processing in the image processing unit 3 and a candidate for setting parameter necessary for the image processing, and a display unit for displaying the set parameter candidate group calculated by the control unit 4. 5 and an input unit 6 that allows the user to adjust desired setting parameters with reference to the setting parameter candidate group displayed on the display unit 5. The relationship between the members and the connection form are not limited to the example shown in FIG. 11, and the image processing unit 3 and the control unit 4 may be replaced with each other or may be configured by one member.

The input image storage unit 1 stores the image input from the image source 7 connected thereto as data. For example, a real-time image taken by an image pickup camera, a prerecorded reproduced image, a prerecorded still image, or the like is used as an input image, and this is converted into a digital signal from an analog signal by an A / D converter, for example. Image data such as binarized data and multi-tone grayscale data. The input image storage unit 1 uses a memory that stores input image data, such as a RAM that is a volatile memory.

The image processing section 3 serves as a work area for reading input image data from the input image storage section 1 and performing image processing. The control unit 4 connected to the image processing unit 3 specifies an address for calling the image data from the input image storage unit 1. The control unit 4 is composed of a CPU and the like, and the image processing unit 3 reads out necessary image data according to an address designated by the control unit 4 and performs image processing. The control unit 4 further calculates candidates for setting parameters necessary for performing image processing. A feature of the embodiment according to the present invention is that the calculated setting parameter is displayed and the user can change the setting parameter rather than the image processing algorithm and the setting parameter calculating method itself. Therefore, as for the image processing and its setting parameters, known image processing and image processing to be developed in the future can be used. A specific example of image processing will be described later. Various setting parameters calculated according to a predetermined procedure are held in a memory inside the control unit 4. There are various types of setting parameters depending on the image processing, and a specific example will be described later. The obtained set of setting parameters is held in the internal memory as a first set of setting parameter candidates. Further, the setting parameters different from the above are calculated by the same procedure, and the second setting parameter candidate group is held in the internal memory. Hereinafter, this operation is repeated to obtain a plurality of setting parameter candidate groups.

The plurality of obtained setting parameter candidate groups are
It is sent from the control unit 4 to the display unit 5 and displayed outside. As for the display method, a plurality of setting parameter candidate groups are simultaneously displayed in a list format as shown in the examples of FIG. 2 and FIG. 8, and respective indexes (described later) indicating the characteristics of each setting parameter candidate group can be confirmed. To do. Further, when the user specifies a desired setting parameter candidate, details of each setting parameter belonging to the setting parameter candidate are displayed. The user refers to the calculated setting parameter candidate group displayed on the display unit 5, inputs the optimum parameter value for the user's system or apparatus from the input unit 6, or adjusts the calculated value. Can be changed. Input section 6
Can use various pointing devices such as mouse, tablet, digitizer, light pen, keyboard, numeric keypad, jog dial, touch pad, slide pad and AccuPoint. For example, from the screens shown in FIGS. 2 and 8, each setting parameter of the setting parameter candidate group selected by the user is automatically input in each input field. In this state, the user operates the input unit 6 to move the cursor to the desired parameter field to increase / decrease the default calculated value or directly input a value. As described above, the input unit constitutes the setting parameter adjusting means, and the user further fine-tunes the parameter value according to the usage situation while referring to various optimal parameter values automatically calculated by the image processing apparatus. can do. The value input or corrected from the input unit 6 is input to the control unit 4, and the control unit 4 updates the display content of the display unit 5 according to the input information.

[Embodiment 1 Automatic threshold determination] A method for displaying a list of various parameters in automatic threshold determination will be described below as Embodiment 1. FIG. 1 shows a list of parameter candidate groups for automatic threshold value determination, and FIG. 2 shows an example of a user interface of a program for realizing this embodiment.

The binarization process is a process which is carried out as a pre-process of image processing or the like and which replaces a multi-valued image with a binary image above and below the specific threshold value. In a normal binarization process, since the threshold value is fixed, if a change occurs in the input multivalued image due to the influence of disturbance, a desired binary image may not be obtained. Therefore,
A method is known in which the threshold value is not fixed and is varied so that the threshold value is always the optimum value according to the input image. This method is generically called automatic threshold value determination.

If the target image data changes, the set threshold value may not be optimum. Therefore, it is necessary to calculate the optimal threshold value when the image changes,
It is necessary to set various parameters to determine the optimum threshold value according to the image data. It is difficult to leave all settings of such a plurality of parameters to the user. Therefore, the image processing apparatus calculates each setting parameter, displays the calculated setting parameter candidates for user confirmation, and allows the user to adjust each value. Further, by calculating a plurality of sets of setting parameter candidates that are considered to be appropriate and displaying them in a list, the user can refer to or select these plural setting parameter candidate groups and adjust them to desired setting parameters. It will be possible.

[Procedure for Automatic Threshold Determination] In the following, in the automatic threshold determination, the step of binarizing an input image of 256 gradations and automatically setting the threshold will be described with reference to the flowchart of FIG. explain. The gradation or the number of colors of the input image is not limited to this, but 24 colors or 24
Even with an input image of all colors, the binarization process can be performed by the same method.

[Density Histogram] First, a density value histogram is created (S1). What is a density histogram?
It is a graph which shows the density distribution of the pixel contained in an input image. An example of the waveform of the density histogram is shown by the thick line in FIG. This density histogram is an enlargement of the one displayed at the lower left of the screen in the user interface of FIG. 2 for the purpose of explanation. In this example, the density value for each pixel of the original image data is represented by a gradation of 0 (black) to 255 (white), and for each density value, the number of pixels having that density value in the input image is counted. , The total number is plotted for each gradation.

Next, the density histogram waveform is differentiated (S2). In the example of FIG. 4, the differential waveform is displayed as a wavy line by superimposing it on the original density histogram. The density histogram waveform and its differential waveform can be distinguished even at the time of simultaneous display by changing the color classification and line type (thin line, thick line, wavy line, alternate long and short dash line, etc.). Alternatively, the original image and the binarized image may be switched to display only one waveform. Also, a plurality of preview screens may be provided for each waveform.

Next, with respect to the differential waveform obtained in step S2, a value that crosses the zero point as shown in FIG.
That is, a number is attached to the point that becomes the zero-cross point. Figure 4
As a result, the peak values in the density histogram are indirectly numbered by this (S
3). In the example of FIG. 4, a number is attached below each peak (a zero-cross point in the differential waveform) to indicate the existence of the peak and its number. By displaying this number, the user is made to recognize the existence of the peak. Peak numbers are displayed as numbers (1, 2, 3, ...)
Arbitrary characters or symbols such as or alphabet (a, b, c, d, ...) Can be used. Further, in FIG. 4, they may be added in order from right to left. The peak information is
The device may calculate and process without notifying the user.

Next, a threshold value is determined from the differentiated waveform (S4). In general, when there is one threshold value for the binarization processing, it is preferable to draw it between the large peaks displayed in the histogram. Therefore, a number is assigned to each peak, and a threshold value is set between the peaks and the peak value is calculated and determined. The position at which the threshold value is set, that is, the density value set as the threshold value is, for example, the offset when the intermediate position between the peak number and the previous peak is taken as the reference and the intermediate position is set to 100%. Can be expressed by position. Alternatively, when the peak number used as the threshold value is N and the offset value is P,
The threshold value may be a density value at a point between the N-1th peak and the Nth peak and internally dividing these peak values into P: (100-P). In this method, N = 3, P =
In the case of 67, the concentration that internally divides these peak values at 67:33 between the second and third peak numbers becomes the threshold value. Further, the means for specifying the threshold value may use a method other than these. As described above, the image processing apparatus automatically calculates the threshold value in the binarization process.

The threshold value is not limited to the case where only one threshold value is set, and it may be desired to set a plurality of threshold values depending on the situation. Further, various requests are made, such as wanting to cut the background part from the input image. Multiple thresholds are set according to these conditions. In the example of FIG. 4, the upper limit threshold and the lower limit threshold are set. In addition to these thresholds, there are various setting parameters for automatic threshold determination. Each setting parameter is explained below

[Types of Setting Parameters] As shown in FIG. 1, the parameters in the automatic threshold value determination are the peak number and the offset position which are the reference for the upper threshold value and the lower threshold value, and the smoothness, Examples include frequency cut level, lower limit cut level, and upper limit cut level.

[Upper limit threshold value, lower limit threshold value, peak number, offset] A plurality of threshold values can be provided. In this example, the upper limit threshold value and the lower limit threshold value are set. In the input image, pixels having densities between the lower threshold and the upper threshold are set to 255, and pixels having other densities are set to 0. The identification of the threshold value is displayed by the peak number and the offset position as described above. That is, the lower limit threshold is specified in the format of m% of the nth peak, and the upper limit threshold is specified in the format of 1% of the kth peak. For example, in Candidate 1 of FIG. 1, the upper threshold is set at a position 20% offset from the middle between the first peak and the second peak, and similarly the lower threshold is the second peak. Offset between the 3rd and 3rd peak
It is set to the 0% position. FIG. 5 shows an example of setting the upper limit threshold and the lower limit threshold.

[Smoothness] The original waveform of the density histogram has a lot of jaggies due to noise and the like, and many peaks stand as it is. Therefore, it is necessary to perform smoothing processing to smooth the jaggies of the waveform. The smoothness is a parameter indicating the degree of smoothing processing. Specifically, the original waveform of the density histogram is filtered.

[Frequency cut level] A threshold value is set for the differential waveform of the density histogram, and the threshold value and below are not processed. This threshold is called a frequency cut level. FIG. 6 shows an example of setting the frequency cut level.

[Lower limit cut level, upper limit cut level]
The lower limit of density is set for the density histogram, and the lower limit is not processed. This threshold is called the lower limit cut level. Similarly, the upper limit is the upper limit cut level. FIG. 6 shows an example in which the lower limit cut level and the upper limit cut level are set. For example, the data corresponding to the background can be cut by setting when it is desired to exclude the information about the background included in the input image.

[Index] Furthermore, an index showing the characteristics of each setting parameter candidate group can be written together. The index indicating the characteristics is, for example, a standard of processing speed or accuracy, or a value indicating the stability of automatic threshold value determination against a disturbance.By presenting these together with the candidate group, the user can refer to the index. However, there is an advantage that a desired candidate can be selected.

[User Interface of Automatic Threshold Determination Program] FIG. 2 is a user interface screen of software for setting an automatic threshold. This figure shows the display contents of the display unit. The preview display field 8 is provided at the upper left of the screen, the waveform display field 9 is provided at the lower left, the learning result display field 10 is provided at the lower right, and the learning result display field 10 is provided at the upper right. The processing result display field 11 is configured.

[Preview display column] Preview display column 8
Displays a preview of the captured input image and the state after binarization processing. In the preview display field 8, color or black-and-white original data and binarized data after processing can be switched and displayed. In the preview display field 8, when the user designates a desired area on the screen with a mouse or the like as an input unit, information on the designated pixel can be displayed. For example, on the preview screen, when the user clicks on the area to be used as the reference value for automatic threshold determination with the mouse or the like, the control unit acquires the pixel density at the position clicked with the mouse, and ± n It has a range of pixel densities. With respect to the pixel density having this width, the lower density is temporarily set as the lower limit threshold and the upper density is temporarily set as the upper threshold. The two threshold values are converted into a peak and an offset by the above-described method, and the density of the peak is calculated between the peak of the density histogram and the peak of the density histogram. Since the user can confirm the result by the peak number and the offset position, the upper limit threshold value and the lower limit threshold value can be reset, changed, or adjusted with reference to these values.

[Waveform Display Column] As shown in FIG. 4, this is a column for displaying the density histogram waveform and its differential waveform. The peak number can be displayed on the waveform. Further, the upper limit threshold, the frequency cut level, the lower limit cut level, etc. can be displayed together. Each waveform, threshold value, etc. can be displayed individually or simultaneously by switching the display. At that time, in order to distinguish each waveform, the line type, color, etc. may be changed and displayed.

[Learning Result Display Column, Processing Result Display Column] In the learning result display column 10, a set parameter candidate group calculated by the control unit is displayed. The order in which the candidate groups are displayed is the total evaluation order determined by the image processing apparatus side to be optimum, not the order of accuracy or speed. When the user selects a desired setting parameter candidate with an input unit such as a mouse or a digitizer, each setting parameter belonging to the selected setting parameter candidate is input to the processing result display field 11. Here, the user can select each dialog box in the processing result display field 11 and adjust it to a desired value. When the binarization processing is executed with the set value, the binarized image is displayed in the preview display field 8 and at the same time the processing result display field 11 is displayed.
Each set value calculated in is displayed.

[Second Embodiment Edge Detection] Next, a second embodiment will be described.
A method of displaying a list of parameter candidate groups at the time of setting parameters when automatically detecting edges will be described.
FIG. 7 shows a list of candidate groups, and FIG. 8 shows an example of a user interface of a program for executing this embodiment. The parameter candidate group displayed in the candidate window of FIG. 8 is
It corresponds to each value in the list of FIG. In this example,
Three parameters, an edge candidate threshold value, an edge removal threshold value, and an edge detection threshold value are displayed.

The meaning of each parameter will be described below with reference to FIG. 9, and the procedure for automatically detecting an edge based on the parameter will be described with reference to the flowchart of FIG. For example, in a rectangular input image as shown in FIG. 9A, it is assumed that the positions of both ends of the area B in the areas A and B are to be detected.

First, a target rectangle is projected (projection) to create a projected density array (S'1). Then, the waveform as shown in FIG. 9B is obtained. Figure 9
In the waveform of (b), the horizontal axis represents the position, and the vertical axis represents the density value in 256 gradations from 0 (black) to 255 (white), and black becomes white as it goes downward and upward. Although this projected density array is not displayed on the user side in the example of FIG. 8, it may be displayed so that the user can confirm the waveform. Further, if necessary, this waveform may be subjected to smoothing processing. In that case, smoothness for smoothing can be added as a parameter. Further, the waveform before and after smoothing may be displayed so that the user can confirm it.

[Edge Candidate Threshold] Then, an edge candidate is detected from the projected density array with the edge candidate threshold as a reference (S'2). Here, the edge candidate threshold is
This is a parameter for detecting an edge candidate, and a portion where the projected density array intersects the edge candidate threshold is set as an edge candidate. As shown in FIG. 9C, a portion that intersects the edge candidate threshold value indicated by a thick line is an edge candidate. That is, a boundary having a density higher or higher than the edge candidate threshold value is detected as an edge candidate to be obtained.

[Edge Removal Threshold] Further, edges are selected by the edge removal threshold shown by the broken line (S ').
3). Here, the edge removal threshold value is a threshold value indicating a value to be ignored in edge detection. A peak whose projection density array intersects the edge removal threshold value is excluded from the processing because it is not subject to edge detection. In FIG. 9C, the left edge candidate (the area corresponding to A in FIG. 9A) is excluded. In other words, in order to detect a point where the density changes gently as an edge, it is necessary to exclude the point where the density changes abruptly. In other words, the edge detection threshold here is a parameter for excluding a region that does not want to be an edge and that changes abruptly from the edge detection region, and those that exceed the edge detection threshold are candidates for edge detection. do not do.

[Edge Detection Threshold] Further, the position and number of edges are calculated based on the differential waveform in the vicinity of the selected edge candidates (S'4). First, as shown in FIG. 9D, a differential waveform of the projected density array is created. The differential waveform may be obtained for the entire projected density array, but it is more efficient to obtain the differential waveform by differentiating only the vicinity of the edge candidate selected in S′3. The portion of the differential waveform that intersects the edge detection threshold is defined as an edge. In the example of FIG. 9D, two positive and negative edge detection thresholds are prepared, and the peak position in the region where the differential waveform exceeds the positive edge detection threshold and the negative edge detection threshold are exceeded. The position of the peak in the area is determined as the edge position. In this example,
Two edges are detected.

As described above, the edge is detected based on the set parameters. In the edge detection process, the edge detection depends on the above-mentioned parameters of the edge candidate threshold, the edge removal threshold, and the edge detection threshold. By changing these setting parameter values, the result and accuracy of edge detection change. The setting parameter candidate group is the same as in the first embodiment.
The control unit of the image processing apparatus automatically calculates according to a predetermined condition. A plurality of setting parameter candidate groups are displayed in a list on the display unit. The display of the list of setting parameter candidates will be described below with reference to FIG.

[User Interface of Edge Detection Processing] FIG. 8 shows a user interface of the edge detection processing program as an image displayed on the display unit. In FIG. 8, the middle row is a setting parameter candidate group display window 13 that displays the setting parameter candidate group, and the upper row is the threshold setting field 14 that displays the details of the parameters.
The lower row shows the processing result display column 11B in which the edge is actually detected.
Are configured.

The user designates a desired candidate from the setting parameter candidate group display window 13 in the middle row from the input section. When a desired candidate is selected from the displayed candidates 1 to 4 with a mouse as an input unit, the setting parameters belonging to the selected candidate are automatically input and displayed in the upper threshold setting field 14. To be done. The display of the threshold value setting field 14 is changed to a value corresponding to each candidate by changing the candidates 1 to 4. The user further highlights each window of the threshold setting field 14 with a mouse or the like as an input unit and pushes a button provided at the right end to raise or lower the value,
Alternatively, you can directly enter the numerical value. The user
Each setting parameter is adjusted to a desired value with reference to the display of the setting parameter candidate group display window 13. With the setting parameters specified, the threshold setting field 14
When the learning button 12 provided in the lower part of is pressed, the value of the setting parameter currently specified is stored.

At the bottom of the processing result display field 11B, four buttons are provided, and a trial button 15, a retry button 16, a stop button 17, and an execute button 18 are arranged from the left. When the trial button 15 is pressed, edge detection is tried according to the designated setting parameter, and the result is displayed in the processing result display field 11B. In this state, when the user refers to the result and further adjusts the setting parameter,
When the retry button 16 is pressed, the edge detection is tried again based on the changed setting parameter, and the processing result display field 11B is updated. When it is desired to cancel the edge detection processing, the cancel button 17 is pressed. When the value of the setting parameter is finally determined, the execute button 18 is pressed to execute edge detection.

Not limited to the above embodiment, presenting a list of parameters to the user in image processing is also effective in other image processing. In particular, when there are a plurality of parameters to be set, it is necessary to set the optimum value after understanding the meaning of each parameter, which is very troublesome and difficult. For this reason, the setting parameter is automatically calculated on the image processing apparatus side. However, unless the calculated setting parameter is presented to the user, the user cannot adjust the setting parameter value or set it by himself. Therefore, by causing the image processing apparatus to automatically calculate the setting parameter,
(EN) An image processing device and method that save labor and flexibility while allowing the user to adjust setting parameters automatically calculated by the user while saving time and effort.

[0058]

As described above, according to the image processing apparatus, the image processing method, the image processing program, and the computer-readable storage medium of the present invention, it is possible to easily set parameters in image processing. The merit that each setting parameter value can be adjusted to an appropriate value according to the usage situation is obtained. that is,
The image processing device, the image processing method, the image processing program, and the computer-readable storage medium according to the present invention automatically display the result of calculating the setting parameter candidates so that the user can confirm the result. This is because the user can directly change the value. In particular, by calculating a plurality of setting parameter candidates and displaying the list to the user, the user can select a value according to the situation while taking various setting values into consideration. As a result, the user can select desired values from a plurality of setting parameter candidate groups, and change or finely adjust these values if necessary. As described above, the present invention allows the user to adjust more optimal parameter values while maintaining the merit of reducing the burden on the user by automatically calculating the complicated parameter settings. It is possible to realize optimization that cannot be done.

[Brief description of drawings]

FIG. 1 is a list showing a parameter candidate group for automatic threshold value determination.

FIG. 2 is an image diagram showing an example of a user interface of an automatic threshold value determination program.

FIG. 3 is a flowchart showing a step of setting a threshold value by automatic threshold value determination.

FIG. 4 is an enlarged graph of the waveform of the density histogram shown in FIG.

5 is a graph showing the upper limit threshold and the lower limit threshold in the waveform of the density histogram shown in FIG.

6 is a graph showing the upper limit cut level, the lower limit cut level, and the frequency cut level in the differential waveform of the density histogram shown in FIG.

FIG. 7 is a list showing setting parameter candidate groups for edge detection processing.

FIG. 8 is an image diagram showing an example of a user interface of an edge detection program.

FIG. 9 is a schematic diagram illustrating setting parameters in edge detection processing.

FIG. 10 is a flowchart showing a step of performing edge detection processing.

FIG. 11 is a block diagram showing a configuration of an image processing apparatus according to an embodiment of the present invention.

[Explanation of symbols]

1. Input image storage unit 3 Image processing unit 4 ... Control unit 5 ... Display 6 ... Input section 7 ... Image source 8 ... Preview display column 9: Waveform display column 10 ... Learning result display column 11 ... Processing result display column 11B: Processing result display column 12 ... Learn button 13 ... Setting parameter candidate group display window 14 ... Threshold setting field 15 ... Try button 16 ... Retry button 17 ... Cancel button 18 ... execute button

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁷ Identification code FI theme code (reference) G06T 11/80 G06T 11/80 E H04N 1/40 H04N 1/40 103A 1/403 FF term (reference) 5B050 DA02 EA08 EA14 FA02 FA08 FA13 5B057 BA11 CA08 CB06 CE03 CE12 CH01 CH11 DA17 DB09 DC23 5C077 LL02 LL19 MP01 PP47 PQ08 PQ12 PQ19 PQ23 RR15 SS01 TT06 5L096 AA06 CA01 DA01 FA37 GA02 GA51 GA53

Claims (14)

[Claims] 1. An image processing apparatus that performs predetermined image processing on an input image, wherein a control unit that calculates a plurality of setting parameters necessary for performing the predetermined image processing, and a calculated setting parameter candidate A display unit that displays a plurality of setting parameter candidate groups, and a desired setting parameter candidate can be selected from the displayed setting parameter candidate groups, and an input that can specify the value of the setting parameter belonging to the selected setting parameter candidate And an image processing apparatus. 2. An image which is a binarizing process for replacing an input image with a binary image based on a predetermined threshold value, and which automatically determines the threshold value for automatically changing the threshold value. In the processing device, a control unit that calculates a plurality of setting parameters necessary for determining the automatic threshold value, a display unit that displays the calculated setting parameter candidates as a plurality of setting parameter candidate groups, and An image processing apparatus, comprising: an input unit capable of selecting a desired setting parameter candidate from the set of setting parameter candidates and designating a value of a setting parameter belonging to the selected setting parameter candidate. 3. An image processing apparatus for performing edge detection processing for detecting an edge portion of an input image based on a predetermined threshold value, control for computing a plurality of setting parameters necessary for performing the edge detection processing. Section, a display section that displays the calculated setting parameter candidates as a plurality of setting parameter candidate groups, and a desired setting parameter candidate is selected from the displayed setting parameter candidate groups, and the selected setting parameter candidates are selected. An image processing apparatus comprising: an input unit capable of designating a value of a setting parameter to which the image processing apparatus belongs. 4. The image processing apparatus further comprises setting parameter value adjusting means capable of adjusting the value of the setting parameter designated by the input unit. Image processing device. 5. The image processing apparatus according to claim 1, wherein the setting parameter candidate is added with an index indicating a characteristic of each setting parameter candidate. 6. The image processing apparatus according to claim 5, wherein the index is a time required for a predicted process. 7. An input image storage unit for inputting and holding image data from the outside in an image processing apparatus for performing predetermined image processing on an input image.
(1), an image processing unit (3) connected to the input image storage unit (1) to read image data and perform the predetermined image processing, and the predetermined image processing in the image processing unit (3) A control unit (4) that calculates the setting parameter candidates necessary to perform the setting, a display unit (5) that displays a list of setting parameter candidate groups calculated by the control unit (4), and the display unit ( An input unit (6) that can change the value of the setting parameter based on the setting parameter candidate group displayed in 5),
An image processing apparatus comprising: 8. An image processing method for performing predetermined image processing on an input image, the step of calculating a plurality of setting parameters necessary for performing the predetermined image processing, and a plurality of calculated setting parameter candidates. And a step of selecting a desired setting parameter candidate from the displayed setting parameter candidate group and designating a value of the setting parameter belonging to the selected setting parameter candidate. An image processing method comprising: 9. An image processing method for determining an automatic threshold value capable of changing the threshold value, which is a binarization processing for replacing an input image with a binary image based on a predetermined threshold value. In, a step of calculating a plurality of setting parameters necessary for determining the automatic threshold value, a step of displaying the calculated setting parameter candidates as a plurality of setting parameter candidate groups, the displayed setting parameter candidates And a step of selecting a desired setting parameter candidate from the group and designating a value of the setting parameter belonging to the selected setting parameter candidate. 10. An image processing method for performing an edge detection process for detecting an edge portion of an input image based on a predetermined threshold value, the step of calculating a plurality of setting parameters necessary for performing the edge detection process. And a step of displaying the calculated setting parameter candidates as a plurality of setting parameter candidate groups, selecting a desired setting parameter candidate from the displayed setting parameter candidate groups, and setting the parameters belonging to the selected setting parameter candidates. And a step of designating a value of a parameter. 11. The image processing method according to claim 8, further comprising the step of adjusting the value of a designated setting parameter. 12. An image processing program for performing predetermined image processing on an input image, a means for calculating a plurality of setting parameters necessary for performing the predetermined image processing, and a plurality of calculated setting parameter candidates. Means for displaying as a setting parameter candidate group, and means for selecting a desired setting parameter candidate from the displayed setting parameter candidate group and designating a value of the setting parameter belonging to the selected setting parameter candidate. An image processing program comprising: 13. The image processing program according to claim 12, further comprising means for adjusting the value of a designated setting parameter. 14. A computer-readable recording medium storing the image processing program according to claim 12 or 13 or downloadable from a network.