JP2014049863A - Image processing device, control method therefor, control program, and imaging device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image with no sense of incongruity in an impression of a face when photographing a subject such as a person while irradiating the subject with infrared light in a dark place.SOLUTION: When performing image processing on an image obtained by imaging a subject irradiated with infrared light, a control microcomputer 110 controls a face detection unit 105 to detect a face area of the subject in the image, and detects an iris part from the face area. Then, the control microcomputer controls a luminance change unit 106 to perform iris correction processing for decreasing luminance in the iris part to predetermined luminance.

Description

  The present invention relates to an image processing apparatus that processes an image captured by irradiating a subject with infrared light in a dark place, a control method therefor, a control program, and an imaging apparatus.

  In general, in an imaging device such as a digital video camera, after removing the infrared light cut filter from the optical path, the subject is irradiated with infrared light, and the reflected light is received by the imaging sensor to perform dark place photography. (See Patent Document 1).

JP 2011-166523 A

  By the way, when shooting by irradiating infrared light to a person who is a subject, the iris part of the eye reflects infrared light, so for example, compared to the case where the same person is shot with visible light, Inevitably, there will be a great sense of discomfort in the impression of the face.

  Accordingly, an object of the present invention is to provide an image processing apparatus capable of obtaining an image that does not cause a sense of incongruity in the face impression when a subject such as a person is photographed by irradiating infrared light in a dark place, and a control method thereof, and A control program and an imaging apparatus are provided.

  In order to achieve the above object, an image processing apparatus according to the present invention is an image processing apparatus that performs image processing on an image obtained by imaging a subject irradiated with infrared light, the face of the subject in the image. A face detecting means for detecting an area; an iris detecting means for detecting an iris part from the face area detected by the face detecting means; and a brightness in the iris part detected by the iris detecting means is lowered to a predetermined brightness. Control means for performing iris correction processing as the image processing.

  The control method according to the present invention is a control method of an image processing apparatus that performs image processing on an image obtained by imaging a subject irradiated with infrared light, and detects a face area of the subject in the image. An iris detection step for detecting an iris part from the face area detected in the face detection step, and an iris correction process for reducing the brightness in the iris part detected in the iris detection step to a predetermined brightness. And a control step performed as a process.

  A control program according to the present invention is a control program used in an image processing apparatus that performs image processing on an image obtained by imaging a subject irradiated with infrared light, and the image processing apparatus includes the image on the computer. Detecting a face area of the subject in step, an iris detecting step for detecting an iris part from the face area detected in the face detecting step, and a luminance in the iris part detected in the iris detecting step in advance. And a control step of performing an iris correction process to reduce the brightness as the image process.

  An imaging apparatus according to the present invention includes the above-described image processing apparatus, infrared light irradiation means for selectively irradiating the subject with the infrared light, and imaging means for capturing an image of the subject to obtain an image, The control means performs the iris correction processing when the infrared light is irradiated on the subject by the infrared light irradiation means.

  According to the present invention, it is possible to obtain an image that does not give a sense of incongruity to a facial impression when a subject such as a person is photographed by irradiating infrared light in a dark place.

It is a block diagram which shows an example of an imaging device provided with the image processing apparatus by the 1st Embodiment of this invention. 2A and 2B are diagrams for explaining an image of a face area that has undergone iris correction in the imaging apparatus illustrated in FIG. 1, in which FIG. 1A illustrates an image captured with only visible light in a bright environment, and FIG. The figure which shows the image image | photographed only by visible light in (c) is a figure which shows the image image | photographed in the state which irradiated infrared light and retracted the infrared-light cut filter from the optical path, (d) is (c). It is a figure which shows the image after performing iris correction about the image shown in FIG. 2A and 2B are diagrams for explaining identification of an iris region in the imaging apparatus illustrated in FIG. 1, in which FIG. 1A is a diagram illustrating identification of a rectangular region including eyes in a face, and FIG. 2B is a diagram illustrating a rectangular region illustrated in FIG. The figure which shows the state which specified the area | region of an eye, (c) is the figure which shows the state which specified the iris and the pupil from the area | region of the eye shown in (b), (d) is the state which correct | amended the iris shown in (c). The figure shown, (e) is a figure which shows the rectangular area | region after iris correction. FIG. 2 is a diagram for explaining an iris luminance histogram and a luminance gamma curve detected by the imaging apparatus shown in FIG. 1, (a) is a diagram showing an iris luminance histogram, and (b) is a diagram showing a gamma curve. is there. It is a flowchart for demonstrating the iris correction process performed with the control microcomputer shown in FIG. It is a block diagram which shows an example of an imaging device provided with the image processing apparatus by the 2nd Embodiment of this invention. FIGS. 7A and 7B are diagrams for explaining an image of a face region that has undergone iris correction in the imaging apparatus illustrated in FIG. 6, in which FIG. 7A illustrates an image captured with only visible light in a bright environment, and FIG. The figure which shows the image image | photographed only by visible light in (c) is a figure which shows the image image | photographed in the state which irradiated infrared light and retracted the infrared-light cut filter from the optical path, (d) is (c). The figure which shows the image after performing iris correction about the image shown to (e), (e) is a figure which shows the image after performing iris correction based on the registered iris information. FIG. 7 is a diagram for explaining an iris luminance histogram and luminance gamma curve detected by the imaging apparatus shown in FIG. 6, and (a) is a diagram showing an iris luminance histogram acquired from an image taken in a bright environment; FIG. 7B is a diagram showing a histogram of iris luminance acquired from an image obtained by infrared imaging in a dark place, and FIG. 9C is a diagram showing a gamma curve used for correction. It is a flowchart for demonstrating the iris correction process performed with the control microcomputer shown in FIG. It is a flowchart for demonstrating the iris correction process in an imaging device provided with the image processing device by the 3rd Embodiment of this invention.

  Hereinafter, an example of an image processing apparatus according to an embodiment of the present invention will be described with reference to the drawings.

[First Embodiment]
FIG. 1 is a block diagram illustrating an example of an imaging apparatus including an image processing apparatus according to the first embodiment of the present invention.

  The illustrated imaging apparatus 100 has an imaging optical system 101. The imaging optical system 101 includes, for example, a zoom lens group, a focus lens, a diaphragm, and an ND filter, and an infrared light cut filter 102.

  An imaging unit 103 is disposed at the subsequent stage of the imaging optical system 101. The imaging unit 103 includes an imaging sensor such as a CMOS sensor, a sample / hold circuit, a preprocess circuit, and the like. The output of the imaging unit 103 is given to the signal processing unit 104. The signal processing unit 104 includes a face detection unit 105 and a luminance change unit 106.

  The signal recording / reproducing unit 107 records the image data on a recording medium 108 such as a flash memory as will be described later. Further, the signal recording / reproducing unit 107 reproduces the image data recorded on the recording medium 108 and displays it as an image on the display unit 112 such as a liquid crystal panel.

  The imaging apparatus 100 includes an infrared light irradiation unit 109 and an operation unit 111 that is operated by a user. The control microcomputer 110 controls the entire imaging apparatus.

  When shooting using the imaging apparatus 100, the imaging optical system 101 adjusts the amount of light of the subject image (optical image) with a diaphragm and an ND filter under the control of the control microcomputer 110. Further, the imaging optical system 101 adjusts the zoom magnification with the zoom lens under the control of the control microcomputer 110 and performs focusing with the focus lens.

  The imaging optical system 101 positions or retracts the infrared light cut filter 102 on the optical path (optical axis) in accordance with an instruction from the control microcomputer 110. When the infrared light cut filter 102 is positioned on the optical path, the infrared light component in the optical image is removed. Further, when the infrared light cut filter 102 is retracted from the optical path, the infrared light component in the optical image is not removed.

  As will be described later, the control microcomputer 110 determines whether or not to perform imaging by infrared light irradiation based on the user's operation command and the brightness of the subject. The control microcomputer 110 controls the infrared light irradiation unit (infrared light irradiation means) 109 and the infrared cut filter 102 according to the determination result. That is, the control microcomputer 110 selectively irradiates the subject with infrared light.

  An optical image that is an output of the imaging optical system 101 is formed on a light receiving surface of an imaging sensor provided in the imaging unit 103. The imaging sensor accumulates video signal charges corresponding to the optical image by photoelectric conversion according to the exposure time, and outputs an analog video signal.

  The video signal is sampled and held by the sample / hold circuit and then applied to the preprocess circuit. Then, the gain of the video signal is adjusted by AGC processing, A / D conversion processing is performed, and the digital signal (image data) is supplied to the signal processing unit 104.

  The signal processing unit 104 evaluates each frame of the digital signal under the control of the control microcomputer 110, and performs correction, processing, and the like. In the signal processing unit 104, a face detection unit (face detection unit) 105 detects a face area of the subject in the image data. Then, the face detection unit 105 controls the control microcomputer 110 using the number of detected face areas (that is, the number of subjects), the position and size of the face area in the image, and the positions of eyes and mouth in the face area as face detection results. Send to.

  The control microcomputer 110 specifies the iris partial area of the face based on the face detection result and the image data (hereinafter also referred to as an image) processed by the signal processing unit 104.

  On the other hand, the luminance changing unit 106 evaluates the luminance distribution (histogram) in the designated area designated by the control microcomputer 110 in the image data. Then, the brightness changing unit 106 sends the brightness distribution evaluation result (that is, the brightness histogram) to the control microcomputer 110.

  The luminance changing unit 106 can change the luminance distribution by applying a gamma curve corresponding to the luminance distribution evaluation result to the designated area of the image data. The image data output from the signal processing unit 104 is output to the signal recording / reproducing unit 107.

  The signal recording / reproducing unit 107 displays the image on the image display unit 112 corresponding to the image data under the control of the control microcomputer 110. Further, the signal recording / reproducing unit 107 performs intra-frame coding processing or inter-frame coding processing on the image data, and then records the image data on the recording medium 108.

  When recording the image data on the recording medium 108, the signal recording / reproducing unit 107 determines whether or not the image data is image data obtained as a result of photographing in the state of irradiating infrared light under the control of the control microcomputer 110. Infrared light information indicating this is added to the image data.

  The operation unit 111 is operated by a user, and the user operates the operation unit 111 to send a command or the like to the control microcomputer 110. Then, the control microcomputer 110 controls the imaging device 100 in accordance with the command or the like.

  When reproducing the image data recorded on the recording medium 108, the signal recording / reproducing unit 107 reads and decodes the image data from the recording medium 108 under the control of the control microcomputer 110. Then, the signal recording / playback unit 107 sends the decoded image data to the signal processing unit 104.

  At this time, the signal recording / reproducing unit 107 sends the infrared light information added to the image data to the control microcomputer 110. Thereby, the control microcomputer 110 can determine whether or not the image data to be reproduced is image data obtained as a result of photographing in a state where infrared light is irradiated.

  The signal processing unit 104 processes the decoded image data as described later, and then sends it back to the signal recording / reproducing unit 107. Then, the signal recording / reproducing unit 107 displays an image corresponding to the image data on the display unit 112.

  Here, the iris correction when photographing by irradiating infrared light in a dark place will be described.

  FIG. 2 is a diagram for explaining an image of a face area that has undergone iris correction in the imaging apparatus shown in FIG. FIG. 2A is a diagram illustrating an image captured with only visible light in a bright environment, and FIG. 2B is a diagram illustrating an image captured with only visible light in a dark place. FIG. 2 (c) is a diagram showing an image taken with infrared light being radiated and the infrared light cut filter retracted from the optical path, and FIG. 2 (d) is shown in FIG. 2 (c). It is a figure which shows the image after performing iris correction about the image.

  In the example shown in FIG. 2A, since the face of the person A is photographed with only visible light in a sufficiently bright environment, the color of the iris 201 in the person A is dark and appears dark together with the pupil 202 in the central portion. ing. On the other hand, in FIG. 2 (b), the face of the same person A is photographed with only visible light in a dark place, and the image is darker than the image shown in FIG. I can't confirm it clearly.

  In the example shown in FIG. 2C, the infrared light irradiation unit 109 is used to irradiate the face of the person A with infrared light, and the infrared light cut filter 102 provided in the photographing optical system 101 is retracted from the optical path. The face of person A was photographed. The iris 201 has a high reflectance with respect to infrared light, and the pupil 202 has a low reflectance. Therefore, in FIG. 2C, the iris 201 of the person A appears bright, and only the pupil 202 at the center appears dark.

  In a dark place, the pupil 202 is generally opened and slightly enlarged, and therefore, the pupil 202 is also conspicuous, so that the iris of the person A in FIG. 2C is compared with the image shown in FIG. It looks as if 201 has become smaller. As a result, the user feels uncomfortable even though they are the same person.

  In order to reduce such a sense of incongruity, here, as shown in the image shown in FIG. 2D, iris correction is performed to reduce the brightness of the iris 201, and the image shown in FIG. Get a face.

  Here, the identification of the iris part region (iris region) in the face region will be described.

  FIG. 3 is a diagram for explaining identification of an iris region in the imaging apparatus shown in FIG. FIG. 3A is a diagram showing identification of a rectangular region including eyes in the face, and FIG. 3B is a diagram showing a state in which an eye region is identified from the rectangular region shown in FIG. It is. 3C is a diagram showing a state in which the iris and pupil are identified from the eye region shown in FIG. 3B, and FIG. 3D is a state in which the iris shown in FIG. 3C is corrected. FIG. Further, FIG. 3E is a diagram showing a rectangular area after iris correction.

  First, the control microcomputer 110 specifies a rectangular area including the eye 300 based on the face detection result, that is, the face size and the eye position (see FIG. 3A).

  Subsequently, the control microcomputer 110 determines the portion of the skin 306 according to the luminance spatial frequency and hue. Then, the control microcomputer 110 specifies the region of the eye 300 surrounded by the skin 306 based on the boundary between the region determined to be the skin 306 and the size of the eye estimated from the size of the face. Here, the region excluding the shaded portion shown in FIG. 3B is the region identified as the eye 300.

  The region identified as the eye 300 includes an iris 301 to be corrected, a pupil 302 at the center of the iris 301, a white eye 304 around the iris 301, and shadows and wrinkles at the boundary between the eye 300 and the skin 306. Are integrated into the eyeline 305.

  The control microcomputer 110 specifies the regions of the iris 301 and the pupil 302 based on the luminance and the spatial frequency of the luminance. Here, the region excluding the hatched portion shown in FIG. 3C is a region identified as the iris 301 and the pupil 302.

  The areas identified as the iris 301 and the pupil 302 are objects to be corrected (iris correction). When the iris correction is performed, the control microcomputer 110 performs a reflection portion (catch light) 303 for the light source of infrared light irradiation and A process for reducing the brightness of the iris 301 is performed while maintaining the brightness of the pupil 302.

  Thereby, for example, an iris 301 after iris correction shown in FIG. 3D is obtained. When iris correction is performed, the rectangular area shown in FIG. 3A is corrected as shown in FIG. The control microcomputer 110 performs the above-described iris region specification for the left and right eyes.

  FIG. 4 is a diagram for explaining an iris luminance histogram and luminance gamma curve detected by the imaging apparatus shown in FIG. FIG. 4A is a diagram showing an iris luminance histogram, and FIG. 4B is a diagram showing a gamma curve.

  Now, the luminance changing unit 106 evaluates the luminance distribution for the regions of the iris 301 and the pupil 302 shown in FIG. 3C, acquires the luminance histogram shown in FIG. 4A, and controls the luminance histogram. Sent to the microcomputer 110.

  In FIG. 4A, the luminance is low, that is, the first peak 401 located in the dark part indicates the luminance in the pupil 302. Further, the second peak 402 in a portion where the luminance is slightly bright indicates the luminance in the iris 301. A third peak 403 in a bright portion indicates the luminance of the catchlight 303.

  On the other hand, the luminance changing unit 106 obtains a gamma curve according to the luminance histogram. Then, the luminance changing unit 106 changes the gamma curve (that is, the luminance distribution) in the designated area designated by the control microcomputer 110, that is, the iris and pupil areas here.

  In FIG. 4B, the luminance changing unit 106 changes the gamma curve indicated by the broken line to the gamma curve 410 indicated by the solid line. That is, the luminance changing unit 106 maintains the current state of the portion of the pupil 302 surrounded by the broken line circle 411 and the portion of the catch light 303 surrounded by the broken line circle 413 without changing the luminance.

  The luminance changing unit 106 performs processing for reducing the luminance of the iris 301 only to a predetermined luminance based on the gamma curve 410 under the control of the control microcomputer 110. The control microcomputer 110 performs the brightness adjustment processing of the iris 301 for the left and right eyes that specify the iris region.

  FIG. 5 is a flowchart for explaining the iris correction processing performed by the control microcomputer 110 shown in FIG.

  When the iris correction process is started, the control microcomputer 110 determines whether or not the image to be processed is an image captured by irradiating infrared light (step S501). In this determination, when the iris correction process is performed at the time of photographing, the control microcomputer 110 performs the determination according to the control state of the infrared light cut filter 102 and the infrared light irradiation unit 109. On the other hand, when performing the iris correction process at the time of reproduction, the control microcomputer 110 determines the irradiation of the infrared light depending on whether or not the aforementioned infrared light information is added to the image data to be processed. become.

  If the image to be processed is not an image taken by irradiating infrared light (NO in step S501), the control microcomputer 110 ends the iris correction process.

  On the other hand, if the image to be processed is an image taken by irradiating infrared light (YES in step S501), control microcomputer 110 initializes built-in counter i to 0 (step S502). Then, the control microcomputer 110 controls the face detection unit 105 to perform face detection in the processing target image (step S503), the number of detected faces (number of people), and the position and size of each face in the image, Then, the position of the eye is acquired.

  Subsequently, the control microcomputer 110 compares the value of the counter i with the number of detected face areas (number of detected persons) to determine whether or not the value of the counter i <the detected number of persons (step S504). If the value of ≧ detected number of persons (NO in step S504), the control microcomputer 110 determines that there is no face to be processed and ends the iris correction process.

  On the other hand, if the value of counter i <the number of detected persons (YES in step S504), control microcomputer 110 sets the iris and pupil regions for the detected i-th face as described in FIG. Specify (step S505). Then, the control microcomputer 110 performs luminance correction according to the gamma curve described with reference to FIG. 4 for the specified iris and pupil region, that is, iris correction processing (step S506).

  Next, the control microcomputer 110 adds 1 to the built-in counter i (step S507), and returns to the process of step S504.

  Thus, in the first embodiment of the present invention, when an object such as a person is photographed by irradiating infrared light in a dark place, the brightness of the iris is corrected (that is, the brightness is reduced). Therefore, it is possible to achieve the same iris luminance as that of an image photographed with only visible light in a sufficiently bright environment, and to reduce the sense of incongruity between the two.

[Second Embodiment]
Next, an example of an imaging apparatus including the image processing apparatus according to the second embodiment of the present invention will be described.

  FIG. 6 is a block diagram illustrating an example of an imaging apparatus including an image processing apparatus according to the second embodiment of the present invention. In FIG. 6, the same components as those in the imaging apparatus shown in FIG.

  6 includes a non-volatile memory (storage unit) 614 and the signal processing unit 104 further includes a feature amount extraction unit (feature amount extraction unit) 613. Then, the imaging apparatus 600 performs iris correction processing according to the density of the iris color of the person registered in advance.

  In the imaging apparatus 600 illustrated in FIG. 6, the feature amount extraction unit 613 analyzes the image based on the position and size of the face in the image detected by the face detection unit 105 under the control of the control microcomputer 110, and A feature amount (extracted feature amount) indicating the feature of the face is extracted. This feature amount relates to a specific shape of facial components such as mouth, eyes, eyebrows, and nose, and positions of these components, as described in Japanese Patent Application Laid-Open No. 2005-266981, for example. Contains information.

  Note that when extracting a feature value, the feature value is extracted from the face region by, for example, edge detection using a neural network or a spatial filter. The feature amount may include not only information on the shape and position described above but also information on saturation and hue.

  In the nonvolatile memory 614, feature amounts (registered feature amounts) of a plurality of persons are registered in advance, and iris information indicating the color density of the iris is registered in association with the registered feature amounts. The control microcomputer 610 compares the feature amount extracted by the feature amount extraction unit 613 with the feature amount registered in the nonvolatile memory 614, and a person in the processing target image is registered in advance according to the comparison result. It is determined whether or not a person is present. If it is determined that the person in the image to be processed is a registered person, the control microcomputer 110 acquires iris information related to the person from the nonvolatile memory 614.

  FIG. 7 is a diagram for explaining an image of a face area that has undergone iris correction in the imaging apparatus illustrated in FIG. 6. FIG. 7A is a diagram illustrating an image captured with only visible light in a bright environment, and FIG. 7B is a diagram illustrating an image captured with only visible light in a dark place. FIG. 7 (c) is a diagram showing an image taken with infrared light being radiated and the infrared light cut filter retracted from the optical path, and FIG. 7 (d) is shown in FIG. 7 (c). It is a figure which shows the image after performing iris correction about the image. Further, FIG. 7E is a diagram showing an image after performing iris correction based on the registered iris information.

  In the example shown in FIG. 7A, the face of the person B is photographed with only visible light in a sufficiently bright environment, but the color of the iris 701 in the person B is different from that of the person A shown in FIG. Thin. In the person B, only the pupil 702 in the central portion is dark.

  On the other hand, in FIG. 7B, the face of the same person B is photographed with only visible light in a dark place, and the image is darker than the image shown in FIG. Can not be confirmed.

  In the example shown in FIG. 7C, the infrared light irradiation unit 109 is used to irradiate the face of the person B with infrared light, and the infrared light cut filter 102 provided in the photographing optical system 101 is retracted from the optical path. The face of person B was photographed. The iris 701 has a high reflectance with respect to infrared light, and the pupil 202 has a low reflectance. For this reason, in FIG. 7C, the iris 701 of the person B appears brighter and only the pupil 702 in the central portion appears darker.

  In the dark place, the pupil 702 is opened and slightly enlarged, but since the person B originally has a dark color only in the pupil 702, the image shown in FIG. 7C is much less than the image shown in FIG. 7A. There is no sense of incongruity.

  When such an image of the person B is subjected to iris correction by reducing the brightness of the portion of the iris 702 at the same degree as the image of the person A shown in FIG. 2C, as shown in FIG. The correction result is different from the color of the iris 702 of the original person B.

  For this reason, in the imaging apparatus shown in FIG. 6, when the color density of the iris 702 is registered in advance as the iris information for the person B, the iris correction process is performed according to the iris information. As a result, as shown in FIG. 7E, a correction result close to the color of the iris 702 of the original person B is obtained.

  FIG. 8 is a diagram for explaining an iris luminance histogram and luminance gamma curve detected by the imaging apparatus shown in FIG. FIG. 8A is a diagram showing a histogram of iris luminance acquired from an image photographed in a bright environment, and FIG. 8B is obtained from an image obtained by infrared light photographing in a dark place. It is a figure which shows the histogram of iris luminance. FIG. 8C shows a gamma curve used for correction.

  Now, the luminance changing unit 106 evaluates the luminance distribution for the regions of the iris 701 and the pupil 702 shown in FIG. 7A, acquires the luminance histogram shown in FIG. 8A, and controls the luminance histogram. Sent to the microcomputer 110.

  Similarly, the luminance changing unit 106 evaluates the luminance distribution for the regions of the iris 701 and the pupil 702 shown in FIG. 7C, obtains the luminance histogram shown in FIG. Send to control microcomputer 110.

  In FIG. 8A, the first peak 801 having a low luminance, that is, a dark portion, indicates the luminance in the pupil 702. Further, the second peak 802 that is the luminance Lo indicates the luminance in the iris 701. And the 3rd peak 803 in a bright part has shown the brightness of catch light.

  Here, it is assumed that the nonvolatile memory 614 stores iris information indicating the feature amount extracted from the face area of the person B photographed in a sufficiently bright environment and the luminance Lo of the iris portion.

  Similarly, in FIG. 8B, the first peak 811 indicates the luminance of the pupil portion, and the second peak 812 indicates the luminance Li of the iris portion. The third peak 813 shows the brightness of the catchlight.

  On the other hand, the luminance changing unit 106 obtains a gamma curve according to the luminance histogram and iris information under the control of the control microcomputer 110. Then, the luminance changing unit 106 changes the gamma curve (that is, the luminance distribution) in the designated area designated by the control microcomputer 110, that is, the iris and pupil areas here.

  In FIG. 8C, the luminance changing unit 106 changes the gamma curve indicated by the broken line to the gamma curve 820 indicated by the solid line. That is, for the portion of the pupil 702 surrounded by the broken line circle 821 and the portion of the catch light surrounded by the broken line circle 823, the luminance changing unit 106 maintains the current state without changing the luminance.

  On the other hand, the luminance changing unit 106 performs a process of reducing the luminance of only the iris 301 based on the gamma curve 820 under the control of the control microcomputer 110. Here, the luminance changing unit 106 changes the luminance Li of the portion of the iris 701 surrounded by the broken-line circle 822 by the gamma curve 820 to the luminance Lo of the portion of the iris 701 obtained from the iris information. Then, the control microcomputer 110 performs the brightness adjustment processing of the iris 701 portion for the left and right eyes that specify the iris region.

  Next, a flowchart of iris correction processing performed by the control microcomputer 610 will be described with reference to FIG.

  FIG. 9 is a flowchart for explaining iris correction processing performed by the control microcomputer shown in FIG. In FIG. 9, the same steps as those in the flowchart described in FIG. 5 are denoted by the same reference numerals, and the description thereof is omitted.

  In step S505, the control microcomputer 110 specifies the iris and pupil regions for the detected i-th face, and then controls the feature amount extraction unit 613 to extract the feature amount of the i-th face region ( Step S906). Then, the control microcomputer 110 compares the person feature quantity registered in the nonvolatile memory 614 with the person feature quantity extracted in step S906 to determine whether or not the person is a registered person (step S907).

  If it is a registered person (YES in step S907), control microcomputer 110 acquires iris information relating to the person registered in nonvolatile memory 614 (step S908). On the other hand, if the person is not a registered person (NO in step S907), the control microcomputer 110 acquires the standard iris information registered in the nonvolatile memory 614 (step S909). This standard iris information is information indicating a standard iris color (predetermined iris color).

  Subsequent to step S908 or S909, the control microcomputer 110 controls the luminance changing unit 106 to generate a gamma curve using the iris information acquired in step S908 or S909 as described with reference to FIG. Then, the control microcomputer 110 performs luminance correction according to the gamma curve, that is, iris correction processing for the specified iris and pupil regions (step S910). Thereafter, the control microcomputer 110 performs the process of step S507 and returns to the process of step S504.

  As described above, in the second embodiment of the present invention, when a subject such as a person is photographed by irradiating infrared light in a dark place, the brightness of the iris is corrected using previously registered iris information. Therefore, according to the original darkness of a subject such as a person, it is possible to obtain the same iris luminance as an image photographed with only visible light in a sufficiently bright environment, and to reduce the sense of incongruity between the two. .

[Third Embodiment]
Next, an example of an imaging apparatus including an image processing apparatus according to the third embodiment of the present invention will be described. Note that the configuration of the imaging apparatus according to the third embodiment is the same as that of the imaging apparatus shown in FIG.

  In the third embodiment, feature amounts relating to a plurality of human face areas are registered in advance in the nonvolatile memory 614. On the other hand, the original iris color density of each person, that is, iris information for each person is not registered in the nonvolatile memory 614, but a plurality of iris colors (that is, brightness) are different from each other. Iris information is registered in the non-volatile memory 614 regardless of the person.

  The control microcomputer 610 sequentially selects iris information registered in the non-volatile memory 614 (that is, changes the iris information sequentially), and performs iris correction processing using the iris information for the face area detected by the face detection unit 605. To obtain a face area after iris correction. Then, the control microcomputer 610 controls the feature amount extraction unit 613 to extract the feature amount of the face area after the iris correction.

  Thereafter, the control microcomputer 610 compares the feature quantity extracted by the feature quantity extraction unit 613 with the feature quantity registered in the nonvolatile memory 614 to determine whether or not the person in the image is a person registered in advance. To do.

  The control microcomputer 110 compares the feature amount with the feature amount registered in the nonvolatile memory 614 by the feature amount extraction unit 613 until the person in the image is determined to be a pre-registered iris information. Are sequentially selected, iris correction processing is performed, and the person is determined as described above.

  FIG. 10 is a flowchart for explaining iris correction processing in an imaging apparatus including an image processing apparatus according to the third embodiment of the present invention. In FIG. 10, the same steps as those in the flowcharts shown in FIGS. 5 and 9 are denoted by the same reference numerals, and the description thereof is omitted.

  In step S505, after the control microcomputer 110 specifies the iris and pupil regions for the detected i-th face, the control microcomputer 110 initializes another built-in counter j to 0 (step S1006). Subsequently, in step S906, the control microcomputer 110 controls the feature amount extraction unit 613 to extract the feature amount of the i-th face region.

  Subsequently, as described above, in step S907, the control microcomputer 110 determines whether the person in the image is a registered person. If registered, the control microcomputer 110 adds 1 to the counter i in step S507 and returns to the process in step S504.

  On the other hand, when determining in step S907 that the person is not a registered person, the control microcomputer 110 compares the value of the counter j with the number of iris information registered in the nonvolatile memory 614, and the value of the counter j <the value of the iris information. It is determined whether the number is a number (step S1010). If the value of counter j is equal to or greater than the number of iris information (NO in step S1010), it is assumed that control microcomputer 110 has performed iris correction processing using all iris information registered in nonvolatile memory 614, and in step S507. Proceed to processing.

  If the value of counter j <the number of iris information (YES in step S1010), control microcomputer 110 acquires j-th iris information registered in advance from nonvolatile memory 614 (step S1011). Then, the control microcomputer 110 controls the luminance changing unit 106 to generate a gamma curve using the j-th iris information as described in FIG. Then, the control microcomputer 110 controls the brightness changing unit 106 to perform iris correction processing for the i-th face region according to the gamma curve (step S1012).

  Subsequently, the control microcomputer 110 adds 1 to the built-in counter j (step S1013), and returns to the process of step S906.

  As described above, in the third embodiment of the present invention, when a plurality of iris information is registered regardless of a pre-registered person and a subject such as a person is photographed by irradiating infrared light in a dark place. Then, after correcting the brightness of the iris using the iris information registered in advance, the feature amount of the face area is extracted to determine a subject such as a person.

  Therefore, the feature after performing iris correction processing even if the extracted feature value changes because the iris color becomes brighter when a subject such as a person is photographed by irradiating infrared light in a dark place As a result of performing person determination using the amount, erroneous determination can be reduced.

  As is clear from the above description, in the example shown in FIG. 1, the signal processing unit 104 and the control microcomputer 110 function as iris detection means and control means. Here, at least the signal processing unit 104 and the control microcomputer 110 constitute an image processing apparatus.

  As mentioned above, although this invention was demonstrated based on embodiment, this invention is not limited to these embodiment, Various forms of the range which does not deviate from the summary of this invention are also contained in this invention. .

  For example, the function of the above embodiment may be used as a control method, and this control method may be executed by the image processing apparatus. In addition, a program having the functions of the above-described embodiments may be used as a control program, and the control program may be executed by a computer included in the image processing apparatus. The control program is recorded on a computer-readable recording medium, for example.

  Each of the above control method and control program has at least a face detection step, an iris detection step, and a control step.

  The present invention can also be realized by executing the following processing. That is, software (program) that realizes the functions of the above-described embodiments is supplied to a system or apparatus via a network or various recording media, and the computer (or CPU, MPU, etc.) of the system or apparatus reads the program. To be executed.

DESCRIPTION OF SYMBOLS 102 Infrared light cut filter 103 Image pick-up part 104 Signal processing part 105 Face detection part 106 Brightness change part 107 Signal recording / reproducing part 109 Infrared light irradiation part 110 Control microcomputer 613 Feature-value extraction part 614 Nonvolatile memory

Claims (7)

An image processing apparatus that performs image processing on an image obtained by imaging a subject irradiated with infrared light,
Face detecting means for detecting a face area of the subject in the image;
Iris detection means for detecting an iris part from the face area detected by the face detection means;
Control means for performing, as the image processing, iris correction processing for reducing the brightness of the iris portion detected by the iris detection means to a predetermined brightness;
An image processing apparatus comprising:   The image processing apparatus according to claim 1, wherein the iris detection unit detects the iris portion according to a spatial frequency and a hue of luminance in the face area. A feature amount extracting means for extracting a feature amount indicating the feature of the face region as an extracted feature amount from the face region;
A feature amount indicating the feature of each face area of a plurality of subjects is registered as a registered feature amount, and iris information indicating the brightness of an iris portion in each of the subjects is registered in association with the registered feature amount. Means and
When the control unit compares the extracted feature quantity with the registered feature quantity and determines that the subject related to the extracted feature quantity is the subject related to the registered feature quantity based on the comparison result, The image processing apparatus according to claim 1, wherein the iris correction processing is performed with the luminance indicated by the corresponding iris information as the predetermined luminance. A feature amount extracting means for extracting a feature amount indicating the feature of the face region as an extracted feature amount from the face region;
A storage unit in which a feature amount indicating a feature of each face area of a plurality of subjects is registered as a registered feature amount;
The control means compares the extracted feature quantity with the registered feature quantity, and determines whether the subject related to the extracted feature quantity is a subject related to the registered feature quantity based on the comparison result, 3. The image according to claim 1, wherein the determination is performed using an extracted feature amount extracted from a face area obtained as a result of performing the iris correction processing by sequentially changing a predetermined luminance. 4. Processing equipment. A control method for an image processing apparatus that performs image processing on an image obtained by imaging a subject irradiated with infrared light,
A face detection step of detecting a face area of the subject in the image;
An iris detection step of detecting an iris portion from the face area detected in the face detection step;
A control step of performing, as the image processing, iris correction processing for lowering the luminance in the iris portion detected in the iris detection step to a predetermined luminance;
A control method characterized by comprising: A control program used in an image processing apparatus that performs image processing on an image obtained by imaging a subject irradiated with infrared light,
A computer included in the image processing apparatus,
A face detection step of detecting a face area of the subject in the image;
An iris detection step of detecting an iris portion from the face area detected in the face detection step;
A control step of performing, as the image processing, iris correction processing for lowering the luminance in the iris portion detected in the iris detection step to a predetermined luminance;
A control program characterized by causing The image processing apparatus according to any one of claims 1 to 4,
Infrared light irradiation means for selectively irradiating the subject with the infrared light;
Imaging means for capturing an image of the subject and obtaining an image,
The imaging apparatus according to claim 1, wherein the control unit performs the iris correction processing when the infrared light is irradiated on the subject by the infrared light irradiation unit.

Images