JP2006059162A - Tooth image correction method and device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To make a face image give a good impression and reduce time for correction processing by automatically correcting a tooth image to make the teeth whiter. <P>SOLUTION: The invention is composed of a mouth area selection step that selects a mouth area from an image, a tooth pixel candidate detection step that detects a tooth pixel candidate from the mouth area based on a predetermined brightness condition, a certification step that certifies the tooth pixel candidate that is distributed uninterruptedly over the predetermined range or more as a tooth pixel group, and a correction step that performs correction to change the brightness of the certified tooth pixel group. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a tooth image correction technique for correcting teeth of an image.

In recent years, with the widespread use of digital cameras and film scanners that digitize photographic film, photographed images are often handled as digital data. When a person, an animal, or the like is photographed, the image quality of the photographed image differs depending on the photographing situation. Therefore, a technique for improving the image quality and increasing the value of the image is required.
Techniques for correcting captured images include, for example, identifying red-eye areas based on the degree of contact between the iris area and other areas and the inclusion relationship in order to correct red-eye, and correcting red-eye for the specified red-eye area. There is an image processing apparatus that performs (see Patent Document 1). This corrects the red-eye phenomenon in which the light of the flash is reflected by the iris and the pupil appears red or gold depending on the shooting angle or the like, thereby making the finished image natural.

JP 2002-247596 A

  When a person's face is photographed, the finished image is greatly influenced not only by the impression of the eyes but also by the impression of the mouth. For example, in general, a captured image in which teeth appear whiter has a better facial impression, and the value of the image is higher. However, although the device of Patent Document 1 corrects red eyes, it cannot correct teeth. For this reason, a technique for increasing the value of an image by correcting teeth to become whiter is desired. If the correction of the teeth of the photographed image is performed manually, there is a problem that the correction cannot be performed properly or a long time is required for the operation.

  SUMMARY OF THE INVENTION The present invention has been made in view of the above-described problems, and an object of the present invention is to provide a tooth image correction technique that can improve the impression of a face by correcting teeth of an image to be whiter and reduce the labor involved in correction processing. Is to provide

  To achieve this object, the tooth image correction method according to the present invention includes a mouth region selection step for selecting a mouth region from an image, and a tooth pixel candidate is detected from the mouth region based on a predetermined luminance condition. A tooth pixel candidate detecting step, a certification step for authorizing the tooth pixel candidates that are continuously distributed over a predetermined range as a tooth pixel group, and a correction step for performing correction to change the luminance of the certified tooth pixel group; It is in the point comprised from.

  That is, according to the above-described feature configuration, the tooth pixel candidate is detected based on the luminance condition, and thus the tooth pixel candidate composed of relatively bright pixels with respect to other pixels in the mouth area can be appropriately detected. In addition, since tooth pixel candidates that are continuously distributed over a predetermined range are used as tooth pixels, tooth pixel candidates that are not likely to be sparsely distributed tooth pixels, such as whiteout, can be excluded from correction targets. Thus, unnecessary processing can be prevented and labor and time for image processing can be saved. Furthermore, since the correction for changing the luminance value of the tooth pixel group is performed, the corrected image after correction can be made natural.

Another feature of the tooth image correction method according to the present invention for achieving this object is that the tooth pixel candidate detection step uses the brightness condition that the brightness condition is brighter than an average brightness value of all pixels in the mouth area. It is in.
That is, according to the above feature configuration, pixels having a luminance value larger than the average luminance value of the mouth area are detected as tooth pixel candidates, so that the luminance condition can be changed according to the brightness of the entire mouth area. For this reason, for example, when the brightness of the entire mouth region is low and the brightness of the tooth pixel is low, the tooth pixel candidate can be appropriately detected according to the image quality of the image, the photographing situation, and the like.

Furthermore, another characteristic configuration is that the correction step performs correction to change the saturation of the tooth pixel group prior to the change of the luminance of the tooth pixel group.
That is, according to the above characteristic configuration, since the saturation is changed, the correction of the teeth of the image can be made more effective, and the finish of the corrected image can be made natural.

  Further, the correction step may be configured to perform correction for changing the luminance of the tooth pixel group based on a predetermined target luminance and a correction factor, and in this case, correction is performed so as to be directed to the target luminance value. Therefore, it is possible to make the corrected image finish natural.

  Furthermore, the correction rate may be determined according to the difference between the target luminance and the luminance of the tooth pixel group. In this case, the correction rate is corrected according to the luminance of the tooth pixel group before correction. The finish of the corrected image can be made good without being too bright or too dark.

  The present invention also covers a program for causing a computer to execute the above-described tooth image correction method and a medium on which the program is recorded. Such a tooth image correction program selects a mouth region from an image. A mouth area selection function, a tooth pixel candidate detection function for detecting tooth pixel candidates from the mouth area based on a predetermined luminance condition, and the tooth pixel candidates continuously distributed over a predetermined range as tooth pixel groups An authorization function for authorization and a correction function for performing correction to change the luminance of the authorized tooth pixel group are provided. Naturally, such a tooth image correction program can also obtain all the effects of the above-described tooth image correction method. It is also preferable to add the function according to the dependent claim described in the tooth image correction method to the tooth image correction program.

In the present invention, a tooth image correction apparatus that performs the above-described tooth image correction method is also subject to the right. Such a tooth image correction apparatus includes a mouth area selection unit that selects a mouth area from an image, and a predetermined area. Based on the brightness condition, a tooth pixel candidate detection unit that detects a tooth pixel candidate from the mouth area, and a recognition unit that recognizes the tooth pixel candidates that are continuously distributed over a predetermined range as a tooth pixel group, A correction unit that performs correction to change the luminance of the tooth pixel group. Naturally, such a tooth image correction apparatus can also obtain all the effects of the above-described tooth image correction method. It is also preferable to add a configuration according to the dependent claim described in the tooth image correction method to the tooth image correction device.
Other features and advantages of the present invention will become apparent from the following description of embodiments using the drawings.

Hereinafter, a first embodiment of a tooth image correction technique according to the present invention will be described with reference to the drawings.
FIG. 1 is an external view of a photographic printing apparatus according to the present invention. This photographic printing apparatus includes a printing station 1B as a photographic printer that performs exposure processing and development processing on photographic paper P, and a developed photographic film. 2A, an operation station 1A that processes a captured image taken from an image input medium such as a digital camera memory card 2b and generates / transfers print data used in the print station 1B.

  This photo printing apparatus is also called a digital minilab. As can be understood from FIG. 2, the printing station 1B pulls out the roll-shaped printing paper P stored in the two printing paper magazines 11 and prints it with the sheet cutter 12. The back print unit 13 prints print processing information such as color correction information and frame number on the back side of the photographic paper P, and the print exposure unit 14 cuts the print paper P into the size. The photographed image is exposed on the surface (photosensitive surface) of the photographic paper P, and the exposed photographic paper P is sent to a processing tank unit 15 having a plurality of development processing tanks for development processing. After drying, the photographic paper P, that is, the photographic prints P, sent to the sorter 17 from the transverse feed conveyor 16 at the upper part of the apparatus is accumulated in a plurality of trays of the sorter 17 in a state of being sorted in order units (see FIG. 1). ).

  A photographic paper transport mechanism 18 is laid to transport the photographic paper P at a transport speed in accordance with various processes for the photographic paper P described above. The photographic paper transport mechanism 18 is composed of a plurality of nipping and transporting roller pairs including a chucker type photographic paper transport unit 18a disposed before and after the print exposure unit 14 in the photographic paper transport direction.

  The print exposure unit 14 applies R (red), G (green), and B (blue) to the printing paper P conveyed in the sub-scanning direction based on print data from the operation station 1A along the main scanning direction. A line exposure head for irradiating laser beams of the three primary colors (1) is provided. The processing tank unit 15 includes a color developing tank 15a for storing a color developing processing liquid, a bleach-fixing tank 15b for storing a bleach-fixing processing liquid, and a stabilizing tank 15c for storing a stable processing liquid.

  At the upper position of the desk-like console of the operation station 1A, there is disposed a film scanner 20 capable of acquiring a photographed image from a photographed image frame of the photographic film 2a with a resolution exceeding 2000 dpi, and is attached to a digital camera or the like. A media reader 21 that acquires captured images from various semiconductor memories, CD-Rs, and the like used as the captured image recording medium 2b is incorporated in a general-purpose personal computer that functions as the controller 3 of the photographic printing apparatus. The general-purpose personal computer is also connected with a monitor 23 for displaying various information, and a keyboard 24 and a mouse 25 as operation input devices used as operation input units used for various settings and adjustments.

  The controller 3 of this photographic printing apparatus has a functional unit for performing various operations of the photographic printing apparatus using hardware and / or software, with the CPU as a core member, as shown in FIG. The function unit particularly related to the present invention includes an image input unit 31 that takes a photographed image read by the film scanner 20 or the media reader 21 and performs pre-processing necessary for the next processing, various windows, and various types. Creation of a graphic operation screen including operation buttons and the like and construction of a graphic user interface (hereinafter abbreviated as GUI) for generating a control command from a user operation input (via the keyboard 24, mouse 25, etc.) through such a graphic operation screen GUI unit 33 and control frames sent from GUI unit 33 A print management unit 32 that performs image processing on the captured image transferred from the image input unit 31 to the memory 30 in order to generate desired print data based on an operation command input directly from the keyboard 24 or the like; A video control unit 35 that generates a video signal for causing the monitor 23 to display graphic data sent from the GUI unit 33, or a simulated image as a print source image, an expected finished print image, or the like during pre-judge printing work such as correction. A print data generation unit 36 that generates print data suitable for the print exposure unit 14 installed in the print station 1B based on the processed captured image that has been subjected to image processing, and a raw capture according to the customer's request Write images and processed shots that have been processed to CD-R Etc. formatter 37 for formatting the like to form for.

  When the photographic image recording medium is the film 2a, the image input unit 31 separately sends the scan data for the pre-scan mode and the main scan mode to the memory 30, and performs preprocessing according to each purpose. When the captured image recording medium is the memory card 2b, when the captured image includes thumbnails (low resolution data), the captured image main data (high data) is used for the purpose of displaying a list on the monitor 23. The thumbnail image is sent to the memory 30 separately from the resolution data. If a thumbnail is not included, a reduced image is created from this data and sent to the memory 30 as a thumbnail.

  The print management unit 32 includes a print order processing unit 60 that manages the print size, the number of prints, and the like, an image processing unit 70 that performs various types of image processing on the captured image developed in the memory 30, and whitening the image teeth. A tooth image correcting means 80 for correcting the image and a means for realizing a photo retouching function such as density correction and resolution conversion. The tooth image correction means 80 is implemented in the print management unit 32 as a program.

  As shown in FIG. 4, the tooth image correction unit 80 includes a mouth area selection unit 82, a tooth pixel group candidate detection unit 83, a recognition unit 84, and a correction unit 85. The mouth area selection unit 82 is a processing unit that executes a mouth area selection step of selecting a mouth area from an image, and the tooth pixel group candidate detection unit 83 determines a tooth pixel candidate from the mouth area based on a predetermined luminance condition. The recognition unit 84 is a processing unit that executes a recognition step of recognizing the tooth pixel candidates that are continuously distributed over a predetermined range as a tooth pixel group. The correction unit 85 is a processing unit that executes a correction step for performing correction to change the luminance of the certified tooth pixel group. In the present embodiment, an input unit 81 that reads an image and receives an operation input from the keyboard 24 and the mouse 25 and an output unit 86 that outputs a corrected image to the memory 30 are further provided.

  Next, the tooth image correction processing procedure of the tooth image correcting means 80 configured as described above will be described with reference to FIG. First, a photographed image, specifically, digital image data of the photographed image is captured through the film scanner 20 and the media reader 21 and developed in the memory 30. Subsequently, the tooth image correcting unit 80 displays a correction operation screen including an image display frame for displaying an image and a mouth area display frame for displaying a mouth area of the image on the monitor 23.

  The input means first reads an image for tooth correction from the memory 30 (# 100). This image is developed in the memory 30 as 8-bit color image data. Specifically, when an image for tooth correction is specified on the correction operation screen of the monitor 23 by an operation input from the keyboard 24 or the mouse 25, the specified image is read. At this time, the read image is displayed in the image display frame of the correction operation screen.

The mouth area selection unit 82 selects a mouth area including teeth from the image (# 200). In the present embodiment, the mouth area is selected by an operation input from the keyboard 24 or the mouse 25. For example, a circular area is set on the image display frame of the correction operation screen of the monitor 23, and this is configured as a mouth area. The circular area is set by designating predetermined two points on the image displayed in the image display frame, the center, and one point on the periphery with the keyboard 24 and the mouse 25. Further, the mouth area set in this way is cut out from the image, and is enlarged and displayed in accordance with the mouth area display frame of the correction operation screen. In the present embodiment, correction is performed on the cut-out mouth area.
In addition, it is good also as a structure which detects a mouth area | region automatically instead of the operation input by the keyboard 24 or the mouse | mouth 25. FIG. In this case, for example, another known means such as ASP may be used via a communication network.

  The tooth pixel group candidate detection unit 83 detects a tooth pixel candidate from the mouth area based on a predetermined luminance condition (# 300). Here, a relatively bright pixel among the pixels in the mouth area is detected as a tooth pixel candidate. Specifically, the average luminance value of all the pixels in the mouth area is calculated, and pixels having a luminance value larger than the average luminance value are set as tooth pixel candidates. Here, FIG. 6 shows an example of the image a before correction and the corrected image b after correction. The average luminance value of the image a is 130, and pixels having a luminance value of 130 or more are detected as tooth pixel candidates.

  The recognition unit 84 recognizes tooth pixel candidates continuously distributed over a predetermined range as a tooth pixel group (# 400). Specifically, first, the continuity of each tooth pixel candidate is determined, and the tooth pixel candidates that are continuously distributed are grouped as a tooth pixel candidate group. The determination of continuity is performed, for example, by setting a pixel of interest from tooth pixel candidates and when there are tooth pixel candidates in the vicinity of 8 around the pixel of interest and determining the same tooth pixel candidate group. Then, each tooth pixel candidate newly determined as the same tooth pixel candidate group is determined as a target pixel, thereby setting one tooth pixel candidate group. Similarly, continuity is determined for all tooth pixel candidates, and the tooth pixel candidate groups are collected. Subsequently, an area ratio with respect to the mouth region of each tooth pixel candidate group is obtained, and a tooth pixel candidate group having this area ratio larger than a certain value is recognized as a tooth pixel group. This removes sparsely distributed tooth pixel candidates that are not likely to be tooth pixels.

  The correction unit 85 changes the luminance of the tooth pixel group certified by the certification unit 84 (# 500). The correction unit 85 of the present embodiment changes the luminance of the tooth pixel group based on a predetermined target luminance and a correction rate. The correction rate here is determined according to the difference between the target luminance and the luminance of the tooth pixel group. For example, the target brightness is set to 220 and the correction rate is set to 35%, and the corrected brightness of the tooth pixel is calculated as target brightness × correction rate + tooth pixel brightness × (1−correction rate). Use to change the brightness of the tooth pixel. Furthermore, the correction unit 85 of the present embodiment changes the saturation of the tooth pixel group prior to changing the luminance of the tooth pixel group. Here, correction is performed to lower the saturation by 25%. Finally, the correction unit 85 combines the corrected mouth area with the image to create a corrected image.

  First, the output unit 86 displays the corrected image in the image display frame of the correction operation screen on the monitor 23 instead of the image before correction. When the correction is confirmed by an operation input from the keyboard 24 or the mouse 25, the corrected image is stored in the memory 30 (# 600). Further, when the corrected image is printed by the photo printing apparatus, the corrected image is output to the print data generating unit 36 in order to create print data.

  As shown in FIG. 6, the corrected image b has a white tooth part and a good facial impression as compared with the image a before correction, and the tooth image correction technique according to the present invention is applied. Thus, the value of the image can be increased.

External view of photographic printing apparatus employing tooth image correction technology according to the present invention Schematic diagram showing the configuration of the print station of the photo printing device Functional block diagram explaining the functional elements built in the controller of the photo printing device The block diagram which shows the structure of the tooth image correction means which concerns on this invention The flowchart which shows the process sequence of the tooth image correction technique which concerns on this invention. The figure which shows the example of the image before and after implementation of the correction process by the tooth image correction technique which concerns on this invention

Explanation of symbols

80 Tooth image correction means 82 Mouth area selection unit 83 Tooth pixel group candidate detection unit 84 Authorization unit 85 Correction unit

Claims (7)

A mouth area selection step for selecting a mouth area from an image;
A tooth pixel candidate detecting step for detecting a tooth pixel candidate from the mouth area based on a predetermined luminance condition;
A certification step of authorizing the tooth pixel candidates continuously distributed over a predetermined range as a tooth pixel group;
A tooth image correction method comprising: a correction step for performing correction for changing the luminance of the certified tooth pixel group.   The tooth image correction method according to claim 1, wherein the tooth pixel candidate detection step uses the brightness condition as being brighter than an average brightness value of all the pixels in the mouth area.   The tooth image correction method according to claim 1 or 2, wherein the correction step performs correction to change a saturation of the tooth pixel group prior to a change in luminance of the tooth pixel group.   The tooth image correction method according to any one of claims 1 to 3, wherein the correction step performs correction by changing the luminance of the tooth pixel group based on a predetermined target luminance and a correction factor.   The tooth image correction method according to claim 3, wherein the correction rate is determined according to a difference between the target brightness and the brightness of the tooth pixel group. Mouth area selection function to select the mouth area from the image,
Tooth pixel candidate detection function for detecting tooth pixel candidates from the mouth area based on a predetermined luminance condition;
An authorization function for authorizing the tooth pixel candidates continuously distributed over a predetermined range as a tooth pixel group;
A tooth image correction program for causing a computer to execute a correction function for performing correction for changing the luminance of the certified tooth pixel group. A mouth area selector for selecting a mouth area from an image;
A tooth pixel candidate detection unit that detects a tooth pixel candidate from the mouth region based on a predetermined luminance condition;
A recognition unit that certifies the tooth pixel candidates that are continuously distributed over a predetermined range as a tooth pixel group;
A tooth image correction apparatus including a correction unit that performs correction to change the luminance of the certified tooth pixel group.