JP5074066B2 - Image processing apparatus and image processing method - Google Patents

Description

  The present invention mainly relates to an image processing apparatus and an image processing method.

  In recent years, in the field of dentistry, dental technicians have created a crown (ceramic crown prosthesis) of a color close to the original tooth color of the patient, and this crown is placed on the patient's teeth. . As such a treatment method, for example, a ceramic crown method or the like is known. In the treatment by the ceramic crown method, the creation of a crown as a prosthesis is essential. When creating a crown having a color close to the color of the original tooth of the patient, for example, an image obtained by photographing the patient's teeth with an imaging device such as a digital camera may be used.

If a digital camera with high pixels and high operability is used, it is possible to easily acquire an image of an affected area such as a dentition or a tooth, and confirm the image immediately after acquisition. However, due to factors such as white balance color correction being different for each image, the tooth color may be different for each acquired image, even for images acquired from the same patient.
On the other hand, for example, as shown in Patent Document 1, using a pattern matching calculation (correlation calculation) of an image, a corresponding position between a multiband image that is a colorimetric image and an RGB image is obtained, and the correspondence of the signal is obtained. From the relationship, there is a method of correcting the color of the RGB image.
JP 2005-341175 A

  When the color correction method shown in Patent Document 1 is used in a dentistry field, a dentition image of an RGB image and a tooth image of a multiband image are used. In this case, the tooth image of the multiband image is used for pattern matching as a template image for color correction. That is, it is necessary to associate the tooth image of the multiband image with the tooth included in the dentition image of the RGB image. However, the RGB image size and the multiband image may have different tooth image sizes. In addition, it is conceivable to adjust the image size by enlarging or reducing one of the images, but it may be difficult to match the two image sizes with desired accuracy. Furthermore, there have been cases in which RGB images and multiband images are taken with different inclinations. In these cases, even if attention is paid to the tooth shape in the multiband image as in the conventional method, the tooth of the RGB image corresponding to the tooth in the multiband image may not be accurately extracted. Specifically, there is a problem that the tooth image of the multiband image is matched with a part different from the tooth, for example, gums, on the RGB image.

  The present invention has been made in consideration of such circumstances, and has been made to solve the above-described problem. The object of the present invention is to obtain an image when the obtained image is color-corrected using a region serving as a color correction reference. It is an object of the present invention to provide an image processing apparatus and an image processing method capable of accurately extracting a target region corresponding to a region serving as a reference for color correction on a processed image.

  In order to solve the above problem, an image processing apparatus according to the present invention is an image processing apparatus that performs color correction on an acquired first image, based on color data of each pixel constituting the first image. Histogram information generation means for generating histogram information in an image, and a color correction coefficient calculation area for setting, as a color correction coefficient calculation area, a pixel on the first image in which the color data is included in a predetermined range based on the histogram information An image processing apparatus comprising: setting means.

  Further, in the image processing apparatus of the present invention, the color data of each pixel is color data relating to a plurality of colors, and the histogram information generation unit includes a plurality of color data included in each pixel of the first image. It is preferable to generate histogram information of color data relating to any color.

  Further, the color data is a luminance value, and the histogram information is information on the luminance value for all the pixels included in the first image and the total number of pixels indicating the luminance value, A color correction coefficient calculation region setting unit calculates an average luminance value of the first image based on the histogram information, and a pixel having a luminance value larger than the average luminance value among pixels on the first image, or Preferably, any one of the pixels having a luminance value smaller than the average luminance value is set as the color correction coefficient calculation target region.

  In the image processing apparatus of the present invention, the histogram information generation unit generates, from the first image, histogram information of green color data among RGB color system color data of each pixel of the first image. It is preferable to do.

  The image processing apparatus of the present invention calculates a correspondence relationship between pixel color data in the color correction coefficient calculation region and target color data included in a second image serving as a reference for color correction of the first image. It is preferable to further include a correction coefficient calculation unit and a color correction unit that performs color correction of the first image based on the correspondence relationship calculated by the correction coefficient calculation unit.

  Further, the image processing method of the present invention is an image processing method for correcting the color of the acquired first image, and the histogram information in the first image is based on the color data of each pixel constituting the first image. A histogram information generation process for generating a color correction coefficient, and based on the histogram information, color correction coefficient calculation for setting a pixel on the first image in which the color data of the first image is included in a predetermined range as a color correction coefficient calculation target area And an area setting process.

  According to the present invention, when color correction is performed on an acquired image using a region serving as a reference for color correction, a region corresponding to a region serving as a reference for color correction on the image can be accurately extracted. There is an effect.

An image processing system according to an embodiment of the present invention will be described below with reference to the drawings.
FIG. 1 is a schematic block diagram showing the image processing system according to the present embodiment. The image processing system includes an RGB image input unit 10, a colorimetric image input unit 20, a cradle 30, a display unit 200, and an image processing apparatus 100.

Next, the internal configuration of each device will be described.
The RGB image input unit 10 inputs, for example, RGB image data acquired by photographing using a digital camera, a scanner device, or the like to the image processing apparatus 100 via the cradle 30. Here, the RGB image data is image data having three luminance values of red (R), green (G), and blue (B) for each pixel. In the present embodiment, the color data is a value for each color indicating the degree of color expressed quantitatively. For example, in the RGB color system, there are three color data of a red luminance value, a green luminance value, and a blue luminance value. In the present embodiment, the RGB image data will be described as an image in which the dentition of the patient to be imaged is arranged substantially at the center, as shown in FIG.
In addition, when capturing RGB images, a subject to be photographed is photographed in a state of being illuminated by natural light or room light. That is, the illumination condition of the RGB image varies depending on the environment in which the image is captured.

The colorimetric image input unit 20 inputs multiband image data obtained by multiband imaging to the image processing apparatus 100 via the cradle 30. Here, multi-band imaging refers to imaging in which seven types of spectral images are captured as still images by sequentially irradiating a subject (patient's teeth) with illumination light in seven types of wavelength bands (seven colors of illumination light). Point to.
In the present embodiment, the multiband image data is described as an image in which one of the teeth of a patient's dentition to be imaged is arranged substantially at the center, as shown in FIG. Hereinafter, RGB image data and multiband image data are collectively referred to as image data.
The cradle 30 can be electrically connected to the RGB image input unit 10 and the colorimetric image input unit 20, and connects the RGB image input unit 10 and colorimetric image input unit 20 to the image processing apparatus 100.

The image processing apparatus 100 is a computer terminal such as a personal computer, a PDA (Personal Digital Assistants: information portable terminal), or a mobile phone, and includes an image storage unit 110, a correction coefficient calculation unit 120, and an RGB color correction unit 130. Is provided.
The image storage unit 110 stores input RGB image data and multiband image data. The RGB image data includes information such as a dentition, a lip, and a gingival stalk that are color correction targets. Further, the multiband image data includes not only the tooth to be colorimetric but also information on the adjacent tooth and gum gum.

The correction coefficient calculation unit 120 calculates a correction coefficient indicating the correspondence between the subject color of the RGB image data and the subject color of the multiband image data. The correction coefficient calculation unit 120 includes a tooth region extraction unit 121, a reference region extraction unit 124, an average value calculation unit 125, and a correction coefficient calculation unit 126.
The tooth region extraction unit 121 extracts a tooth region from the RGB image data. Specifically, when the value indicated by the color data of the G component of each pixel in the RGB image data is included in a predetermined range, the tooth region extraction unit 121 determines that the pixel related to the color data is a pixel in the tooth region. Extract as The tooth region extraction unit 121 includes a histogram generation unit 122 and a luminance range calculation unit 123.
The histogram generation unit 122 generates frequency distribution information of the luminance value of the G component, that is, histogram information, for all the pixels of the RGB image data. Here, the histogram information is information including the total number of pixels related to the luminance value, that is, the frequency and the luminance value for each luminance value in the image data to be color corrected.
Based on this histogram information, for example, as shown in FIG. 4, it is possible to generate a histogram that is a graph with luminance values on the horizontal axis and frequencies on the vertical axis.

The luminance range calculation unit 123 calculates a tooth region from the RGB image data. That is, the luminance range calculation unit 123 sets a predetermined range of luminance values as the tooth region in the histogram information generated by the histogram generation unit 122.
Here, the predetermined range is set based on the statistics (average value and standard deviation) of the data of each pixel in the image in consideration of the case where the signal value of the image data increases or decreases as a whole. For example, when external light is incident on a photographing apparatus that acquires an RGB image, the R value, the G value, and the B value may change differently, and the RGB value may change as a whole. Further, depending on the shooting conditions, the signal value of the image data may rise or fall as a whole. Even in such a case, if the predetermined range is fixed, the region to be extracted may not be recognized as a tooth region. Therefore, the tooth region can be accurately recognized by setting a predetermined range to be extracted based on the statistics of the data of each pixel.

The reference area extraction unit 124 extracts a reference area including a tooth from the multiband image data. A specific extraction method will be described later.
The average value calculation unit 125 calculates the average value of the color data of the tooth region of the RGB image data extracted by the tooth region extraction unit 121. This average value is defined as the first average value. Further, the average value calculation unit 125 calculates the average value of the color data of the reference region of the multiband image data extracted by the reference region extraction unit 124. This average value is defined as the second average value.
The correction coefficient calculation unit 126 calculates a correction coefficient that associates the RGB image data with the color of the multiband image data based on the first average value and the second average value calculated by the average value calculation unit 125. A specific calculation method will be described later.

The RGB color correction unit 130 performs color correction processing of RGB image data based on the correction coefficient calculated by the correction coefficient calculation unit 126.
The display unit 200 is a display such as a cathode ray tube (CRT) or a liquid crystal display (LCD), and displays images and information such as RGB image data and multiband image data.

Next, the operation of the image processing system according to the embodiment of the present invention will be described with reference to the drawings. FIG. 5 is a diagram illustrating an operation example according to the present embodiment.
The RGB image input unit 10 performs the following first color correction process on the RGB image data to be color corrected in advance. Then, the RGB image input unit 10 writes the RGB image data subjected to the first color correction process into the image storage unit 110 of the image processing apparatus 100 via the cradle 30 (step S1).

The first color correction processing is performed when RGB image data (RAW image data) that has not been subjected to image processing such as gamma correction, saturation enhancement, and edge enhancement is used. This is because it is displayed on the display unit 200.
In order to avoid this, the RGB image input unit 10 uses a method of multiplying the RAW image data by a fixed matrix. For example, there is a method of performing the first color correction process using a 3 × 3 matrix of a11 to a33 shown in (Equation 1). Here, R ′, G ′, and B ′ indicate the luminance values of R, G, and B after the first color correction processing. Moreover, a11-a33 shows the fixed matrix mentioned above.
As described above, RGB image data is affected by external light. For this reason, it is desirable to multiply the RAW image data not by a fixed matrix but by a matrix in consideration of the shooting environment. However, it is difficult to accurately select a matrix in consideration of the shooting environment. Therefore, although not sufficient for color correction, the RAW image data is uniformly multiplied by a fixed matrix without taking the photographing environment into consideration. As the fixed matrix, for example, a matrix created on the assumption that the image is taken with a D65 illumination light source can be used. By setting such a fixed matrix in advance, the image displayed on the display unit 200 after the first color correction processing becomes bright enough to be visible to the dentist.

  When the RGB image data is written in the image storage unit 110, the histogram generation unit 122 reads the RGB image data from the image storage unit 110, and sets a predetermined area in the RGB image data. For example, a rectangular area in which the aspect ratio of the RGB image data is a predetermined ratio is cut out as the predetermined area. As in the RGB image data example shown in FIG. 2, the aspect ratio of the RGB image data may be 50%. In this way, by setting the predetermined region to be cut out in advance, it is possible to extract a region where there are many pixels corresponding to the dentition.

  In the region including the set dentition, the histogram generator 122 generates histogram information of the G component of the RGB image data. The histogram generation unit 122 outputs a luminance range calculation command signal including the generated histogram information, the set region information, and the read RGB image data to the luminance range calculation unit 123 (step S2). Here, the region information is information indicating the range of the region including the dentition. If it is possible to identify a region including a dentition, for example, coordinate information of two points including the coordinates of the start point of the rectangular range and the coordinates of the end point can be used as the region information.

The luminance range calculation unit 123 receives the input luminance range calculation command signal, and calculates the first average luminance value g1 of the G component of the RGB image data in the region including the dentition based on the histogram information (Step S3). ). FIG. 6 is a diagram illustrating an average luminance value g1 in the histogram of the G component of the RGB image data in the region including the dentition.
Here, a luminance range equal to or lower than the average luminance value g1 is a luminance range 900, and a luminance range exceeding the average luminance value g1 is a luminance range 901. The luminance range 900 is a luminance value range in which many imaging objects other than teeth are included. The luminance range 901 is a luminance value range in which teeth are included.
Next, as shown in FIG. 7, the luminance range calculation unit 123 calculates the second average luminance value g2 in the region including the dentition (step S4).
Here, as shown in (Equation 2), the calculation method of the average luminance values g1 and g2 is obtained by multiplying the luminance value by the frequency of the pixel related to the luminance based on the histogram information to be calculated. The value is added for all luminance values, and the added value is divided by the total number of pixels.

This makes it possible to easily exclude a luminance range 900 that is equal to or lower than the average luminance value g1 shown in FIG. 7, that is, pixels that include a large amount of non-toothed gums, lips, and the like.
Next, as illustrated in FIG. 7, the luminance range calculation unit 123 calculates the luminance range 902 based on the standard deviation σ calculated from the histogram information in the luminance range 901 and the average luminance value g2. Specifically, the luminance range calculation unit 123 calculates the range of the luminance value g of the G component that satisfies (Expression 3), and sets the calculated range as the luminance range 902.

The range of the luminance value g of the G component that satisfies (Expression 3) is a region of the dentition shown in FIG. Here, by setting the lower limit, it is possible to remove the pixel portion corresponding to the gingiva. In addition, by setting an upper limit, it is possible to remove a regular reflection pixel portion from the tooth. For this reason, there is an effect that a pixel portion corresponding to a tooth can be extracted.
The luminance range calculation unit 123 extracts pixels included in the luminance range 902 as tooth regions (step S5). And the average RGB value calculation command signal about the correction object image containing the coordinate information of the extracted tooth area | region and RGB image data is output to the average value calculation part 125 (step S6).
The average value calculation unit 125 receives the input average RGB value calculation command signal and calculates an average luminance value for each color component of all pixels corresponding to the input tooth region in the RGB image data. That is, the average value calculation unit 125 calculates an average RGB value in the tooth region of the RGB image data including the average luminance value r3 of the R component, the average luminance value g3 of the G component, and the average luminance value b3 of the B component (step S7).
The operations from step S1 to step S7 described above are processing performed until the correction coefficient used for performing the second color correction processing of the RGB image data is calculated.

Next, an image processing operation of multiband image data that is a colorimetric image will be described.
The colorimetric image input unit 20 performs RGB conversion processing on multiband image data captured by a spectral image capturing apparatus or the like. At that time, characteristics of the display unit 200, illumination conditions for multiband imaging, camera characteristics, and the like are taken into consideration. The colorimetric image input unit 20 writes the multiband image data subjected to the RGB conversion processing to the image storage unit 110 via the cradle 30 (step S8). This multiband image data includes target color data that is a target value for color correction of the color data of the luminance range 902 in the RGB image.

  Next, when the multiband image data is written in the image storage unit 110, the reference region extraction unit 124 reads the multiband image data from the image storage unit 110, and extracts a reference region including a tooth (step S9). As shown in FIG. 3, the multiband image is captured in advance so that one of the patient's teeth is placed in the center of the image. Therefore, it is possible to set a predetermined rectangular reference area at the center of the multiband image as shown in FIG. In the case of the multiband image of FIG. 3, this reference area may be a rectangular reference area having a predetermined aspect ratio in the center. When setting as a rectangular area, the aspect ratio of the reference area may be 10%, for example, as in the example of the multiband image shown in FIG. Moreover, you may perform the process which removes from the reference area | region the tooth | gear regularly reflected by illumination light.

The reference area extraction unit 124 calculates the average RGB value calculation command signal for the multiband image including the coordinate information of the reference area indicating the area including the tooth of the extracted multiband image data and the multiband image data. It outputs to 125 (step S10).
The average value calculation unit 125 receives the input average RGB value calculation command signal, and calculates an average luminance value for each color component of all pixels corresponding to the input reference area in the multiband image data. That is, the average value calculation unit 125 calculates an average RGB value in the reference region including the average luminance value r4 of the R component, the average luminance value g4 of the G component, and the average luminance value b4 of the B component (step S11).
The average value calculation unit 125 outputs a correction coefficient calculation command signal including the calculated average RGB value and RGB image data in the RGB image data and the multiband image data to the correction coefficient calculation unit 126 (step S12). ).

  The correction coefficient calculation unit 126 receives the input correction coefficient calculation command signal, and converts the average RGB value in the reference area of the multiband image data to the average RGB value of the tooth area in the RGB image data based on (Equation 4). Divide by. As a result, the correction coefficient calculation unit 126 calculates a correction coefficient c that is a ratio of RGB values of the reference area and the tooth area (step S13). Then, the correction coefficient calculation unit 126 outputs the calculated correction coefficient c and the RGB color correction command signal including the RGB image data to the RGB color correction unit 130 (step S14).

The RGB color correction unit 130 receives the input RGB color correction command signal and multiplies the RGB values of the RGB image data of all the pixels by the color correction coefficient c calculated by the correction coefficient calculation unit 126, thereby 2 color correction processing is performed (step S15).
The RGB color correction unit 130 outputs an image display command signal including the corrected RGB image data subjected to the second color correction process to the display unit 200 (step S16). The display unit 200 outputs an RGB image based on the corrected RGB image data based on the image display command signal (step S17).

  In the embodiment described above, when color correction is performed on an acquired image using a region serving as a reference for color correction by the processing of steps S1 to S5, a region serving as a reference for color correction on the acquired image. It is possible to accurately extract a region corresponding to. That is, the histogram generation unit 122 can generate histogram information in the RGB image based on the RGB image data of each pixel constituting the RGB image. Further, the luminance range calculation unit 123 can set, as a tooth region, a pixel on an RGB image whose luminance value is included in a predetermined range based on the histogram information. For example, an RGB image obtained by photographing the oral cavity contains many tooth regions. For this reason, pixels indicating luminance values in a predetermined range corresponding to the tooth region are concentrated on a part of the histogram information of the RGB image data in the RGB image. A pixel whose luminance value is included in the predetermined value can be set as a tooth region. By this. Even when the RGB image and the multiband image have different tooth image sizes, the tooth region on the RGB image corresponding to the reference region in the multiband image can be accurately extracted. In addition, a tooth region can be accurately extracted even when photographing with different inclinations in photographing a tooth image and photographing a dentition image.

  Further, the dentist does not need to set a region corresponding to a region for color correction on the multiband image on the RGB image. Further, the dentist does not need to determine whether or not the region is included in the regular reflection region. For this reason, for example, in dental imaging and dentition imaging of a patient at the time of dental treatment, a dentist can perform from imaging to image confirmation in a short time without complicated operations. In addition, the luminance range calculation unit 123 can objectively extract the tooth region without depending on the subjective judgment of the dentist. For this reason, it is possible to accurately extract a region corresponding to a region serving as a reference for color correction.

Further, the distribution range of the luminance values of the RGB image data in the RGB image becomes a different distribution range for each photographing even for the same photographing object depending on the illumination condition. However, the luminance range calculation unit 123 extracts a tooth region based on the average luminance value in the histogram information. For this reason, the brightness | luminance range calculation part 123 can extract a tooth area | region correctly irrespective of illumination conditions.
In the region including the set dentition, the histogram generation unit 122 generates histogram information of any color data of the color data included in each pixel of the RGB image data. Thereby, in the RGB image, if any of the color data (for example, red, green or blue in the case of the RGB color system) has a tooth region characteristic, the tooth region can be accurately extracted. . That is, the tooth region pixels can be extracted from the RGB image according to the characteristics of the color data of the region corresponding to the region serving as a reference for color correction of the RGB image.

  Further, the histogram generation unit 122 detects the histogram information of the green color data from the RGB image among the color data of the RGB image. Thereby, when an image including a tooth, such as in the oral cavity, is acquired, a pixel including the tooth and a pixel other than that can be classified. That is, the teeth are almost white and the gums and lips are reddish. For this reason, in the histogram information of the green color data, the luminance values of gums and the like have a low distribution range, and the luminance values of the teeth have a high distribution range. Thereby, it is possible to accurately extract a region corresponding to a region subjected to color correction, that is, a tooth region on an RGB image.

  In addition, highly accurate color correction can be performed by the processing of steps S1 to S17. That is, the RGB image is not photographed in a light-shielded state, and thus is affected by outside light. This causes a deviation in the balance of R values and the like in the RGB image data. In addition, digital cameras and the like used for taking RGB images have different spectral sensitivities depending on products. And it is difficult to analyze the spectrum sensitivity for every digital camera which a dentist uses. On the other hand, multi-band imaging is performed in a state where light is shielded so as not to be affected by external light other than the above seven types of illumination light. Further, the spectral characteristics of the seven types of illumination light, the spectral sensitivity of the imaging element that receives the reflected light from the object, and the like are accurately measured in advance. Therefore, multiband image data acquired by multiband imaging can be set as a color correction reference. And as above-mentioned, the tooth area | region extraction part 121 can extract the part containing a tooth area | region correctly. Therefore, highly accurate color correction can be performed based on the multiband image data serving as a reference.

In step S17, for example, as shown in FIG. 9, corrected RGB image data may be displayed together with multiband image data. Then, the dentist who performs the device operation may further perform color correction processing with higher accuracy by further setting the tooth region in the RGB image and setting the reference region in the multiband image.
Further, in the present embodiment, the tooth region is extracted based on the histogram information of green of the RGB image, that is, the G component. However, when the color data of the pixels in the color correction coefficient calculation area is concentrated on a part of the histogram information, for example, in the case of an RGB image, the color correction coefficient calculation area is extracted using either the red or blue histogram information. Also good.

  The embodiment of the present invention has been described in detail above with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes design changes and the like without departing from the gist of the present invention. In addition, the present invention is not limited to a dental colorimetry system, and also includes a skin colorimetry system, and other fields such as paint colors of automobiles or buildings, spectral characteristics of foodstuffs, and spectroscopic characteristics of art objects such as paintings or sculptures. It can also be applied to colorimetric systems that measure properties, clothing dyeing, and the like.

Note that, as described above, a digital camera or the like may be used when shooting an RGB image, but a spectral image shooting device or the like used for multiband shooting may be used. At this time, one or more kinds of illumination light may be selected from the seven kinds of illumination light, and a frame sequential still image for sequentially irradiating them may be acquired.
Note that the luminance range calculation unit 123 in the present embodiment calculates the first average luminance value g1 and the second average luminance value g2. However, a desired luminance range may be calculated as necessary or according to the distribution of luminance values in the histogram information.

The illumination light used for multiband imaging is not limited to the seven types of wavelength bands, and can be selected as necessary. In addition, multiband imaging is not limited to the above method as long as multiband image data serving as a reference for color correction can be acquired.
In the present embodiment, the first color correction process and the second color correction process are performed. However, the first color correction process is not necessarily performed.
The display unit 200 may have a function of displaying image information on a display such as a cathode ray tube (CRT) or a liquid crystal display (LCD), or printing information using a printer or the like. Alternatively, the information may be written to the storage means or output to a computer device connected via a network.

  Note that the image processing apparatus described in the present invention corresponds to the image processing apparatus 100. The first image described in the present invention corresponds to RGB image data. The histogram information generation means described in the present invention corresponds to the histogram generation unit 122. The predetermined range described in the present invention corresponds to the range indicated by reference numeral 902. The color correction coefficient calculation area described in the present invention corresponds to a tooth area. The color correction coefficient calculation region setting unit described in the present invention corresponds to the luminance range calculation unit 123. The average value of the luminance values for all the pixels described in the present invention corresponds to the average luminance value g1. The second image described in the present invention corresponds to a reference region extracted from multiband image data. The target color data described in the present invention corresponds to the color data of the reference area. The correction coefficient calculation means described in the present invention corresponds to the correction coefficient calculation unit 126. The color correction means described in the present invention corresponds to the RGB color correction unit 130.

  The RGB image input unit 10, the colorimetric image input unit 20, and the image processing apparatus 100 described above have a computer system therein. Then, the operations of the tooth region extraction unit 121, the histogram generation unit 122, the luminance range calculation unit 123, the reference region extraction unit 124, the average value calculation unit 125, the correction coefficient calculation unit 126, and the RGB color correction unit 130 of the image processing apparatus 100 are described. The process is stored in a computer-readable recording medium in the form of a program. Further, the computer system reads out and executes this program, whereby the above processing is performed. The computer system here includes a CPU, various memories, an OS, and hardware such as peripheral devices.

  A program for realizing the functions of the image processing apparatus 100 shown in FIG. 1 may be recorded on a computer-readable recording medium. Further, a program for realizing each step shown in FIG. 5 may be recorded on a computer-readable recording medium. The program recorded on this recording medium may be read by a computer system and executed. As a result, the color correction target image data may be subjected to color correction processing based on the multiband image data. Here, the “computer system” may include an OS and hardware such as peripheral devices.

Further, the “computer system” includes a homepage providing environment (or display environment) if a WWW system is used.
The “computer-readable recording medium” means a flexible disk, a magneto-optical disk, a ROM, a writable nonvolatile memory such as a flash memory, a portable medium such as a CD-ROM, a hard disk built in a computer system, etc. This is a storage device.

Further, the “computer-readable recording medium” means a volatile memory (for example, DRAM (Dynamic DRAM) in a computer system that becomes a server or a client when a program is transmitted through a network such as the Internet or a communication line such as a telephone line. Random Access Memory)), etc., which hold programs for a certain period of time.
The program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the “transmission medium” for transmitting the program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.
The program may be for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

1 is a block diagram illustrating an overall configuration of an image processing system according to an embodiment of the present invention. It is a figure which shows the RGB image data example by the same embodiment. It is a figure which shows the example of multiband image data by the embodiment. It is a figure which shows the example of the histogram of the RGB image in the embodiment. It is a figure which shows the operation | movement flow of the image processing system in the embodiment. It is a figure which shows the example of the histogram of the RGB image in the embodiment. It is a figure which shows the example of the histogram of the RGB image in the embodiment. It is a figure which shows the example of the tooth area | region of the RGB image in the embodiment. It is an example of a screen displayed in the case of the manual color correction process in the same embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 RGB image input part 20 Colorimetric image input part 30 Cradle 100 Image processing apparatus 110 Image memory | storage part 120 Correction coefficient calculating part 121 Tooth area extraction part 122 Histogram generation part 123 Luminance range calculation part 124 Reference area extraction part 125 Average value calculation part 126 correction coefficient calculation unit 130 RGB color correction unit 200 display unit

Claims (6)

In an image processing apparatus that performs color correction on a first image that is captured without being shielded from light ,
Histogram information generating means for generating histogram information in the first image based on color data of each pixel constituting the first image;
Color correction coefficient calculation area setting means for setting, as a color correction coefficient calculation area, a pixel on the first image in which the color data is included in a predetermined range based on the histogram information;
Calculates correspondence between pixel color data in the color correction coefficient calculation area and target color data included in a multiband image obtained by sequentially irradiating a subject with illumination light in a plurality of wavelength bands while being shielded from light Correction coefficient calculation means for
A color correction unit that performs color correction of the first image based on the correspondence calculated by the correction coefficient calculation unit;
An image processing apparatus comprising: The spectral characteristics of the illumination light are accurately measured in advance,
The image processing apparatus according to claim 1, wherein the multiband image is an image taken by an imaging apparatus in which a spectral sensitivity of an imaging element is accurately measured in advance . Reference area extraction means for extracting a predetermined reference area from the multiband image;
A first average value that is an average of pixel color data in the color correction coefficient calculation area set by the color correction coefficient calculation area setting unit is calculated, and the color data of the pixel in the reference area extracted by the reference area extraction unit is calculated. An average value calculating means for calculating a second average value that is an average;
With
Wherein the correction coefficient calculating means, wherein the first mean value based on the second average value, the image processing apparatus according to claim 1 or claim 2, characterized in that to calculate the corresponding relationship. The color correction coefficient calculating region setting means, on the basis of the average value of the luminance value in the histogram information, from the first image of claims 1 to 3, characterized in that to extract the color correction coefficient calculating area The image processing apparatus according to any one of claims . The color correction coefficient calculation area is a tooth area,
The histogram information generating means generates histogram information of a green component in a region including the dentition of the first image,
The color correction coefficient calculating region setting means, based on the histogram information of the green component, sets the luminance range, wherein the pixels included in the luminance range of claim 1, wherein the extracting as the tooth region Item 4. The image processing device according to any one of Items 3 to 3 . An image processing method executed by an image processing apparatus that performs color correction on a first image that is captured without being shielded from light .
A histogram information generating step of generating histogram information in the first image based on color data of each pixel constituting the first image;
Based on the histogram information, a color correction coefficient calculation area setting process for setting a pixel on the first image in which the color data is included in a predetermined range as a color correction coefficient calculation area;
Calculates correspondence between pixel color data in the color correction coefficient calculation area and target color data included in a multiband image obtained by sequentially irradiating a subject with illumination light in a plurality of wavelength bands while being shielded from light Correction coefficient calculation process to
A color correction process for performing color correction of the first image based on the correspondence calculated by the correction coefficient calculation process;
An image processing method comprising:

Images