JP4227257B2 - camera - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a camera capable of recognizing an object situation.
[0002]
[Prior art]
1) Conventionally, as shown in Japanese Patent Laid-Open No. 7-128711, it is good that the person who is the subject is not aware of it so that the person who is the subject is not aware of an unnatural expression. If the camera's shooting lens is correctly pointed at the subject without looking through the camera's viewfinder, the photographer can sense and shoot with sound or light. Or there was one that automatically took a picture when the camera was facing the subject.
[0003]
2) There have been several techniques for recognizing facial expressions, such as JP-A-3-252775, JP-A-8-249447, JP-A-8-249453, and JP-A-10-255043. There was nothing to tie.
[0004]
3) In order to cause the camera to perform shooting operations when a subject enters a specific position within the viewfinder field of the camera, such as for wildlife photography, an infrared projector / receiver is installed so as to sandwich this specific position. In some cases, a shooting command is issued as a remote control signal when a subject crosses between a light projecting / receiving device.
[0005]
4) Also, as disclosed in Japanese Patent Laid-Open No. 57-115524, when a moving subject reaches a preset distance position, it automatically detects the focus and activates the shutter release mechanism. There was a thing.
[0006]
[Problems to be solved by the invention]
However, in the conventional technique of 1) above, although the subject can be captured in the shooting screen, whether the subject person is firmly facing the camera, whether the eyes are closed, and further, The photographer must determine whether the camera is facing the camera with a large distance from the camera position, and the probability of failure is higher than when looking directly into the viewfinder of the camera. There was an inconvenience.
[0007]
The conventional technique for recognizing facial expressions in (2) above has not been applied to camera functions, so the photographer must still determine whether or not to shoot by looking at the facial expressions of the person who is the subject. However, there is an inconvenience that it is troublesome for those who want to shoot automatically without as much trouble as possible. There was also the inconvenience of not being able to answer the request to take a good facial expression unattended. In addition, there was no idea of directing the effect of enlivening the atmosphere that matched the facial expression.
[0008]
In the prior art (3), automatic photographing is possible only at the place where the infrared light projecting / receiving device is installed, and there is a disadvantage that there is no degree of photographing freedom and the apparatus becomes large.
[0009]
In the conventional technique of (4) above, when another subject exists near the target subject or suddenly jumps into the target location, if another subject reaches the previously set distance position, There is an inconvenience that a subject is not in focus and another subject is in focus.
[0015]
  (Object of invention)
  Of the present inventionFirstAn object of the present invention is to provide a camera capable of recognizing the facial expression of a subject and changing the brightness of a recording screen in accordance with the determination result of the facial expression.
[0017]
  Of the present inventionSecondAn object of the present invention is to provide a camera that can recognize the facial expression of a subject and change the recording screen to a color that matches the facial expression according to the determination result of the facial expression.
[0018]
[Means for Solving the Problems]
  In order to achieve the first object, the invention described in claim 1 is based on the object scene image detecting means for detecting the image information of the object scene and the image information from the object scene image detecting means. Subject faceFacial expressionRecognizeFacial expression recognition meansAnd theFacial expression recognition meansWith information fromFacial expressionAccording to the determination means of determining and the determination result of the determination meansScreen brightness changing means for changing the brightness of the recording screen, and a recording operation for recording the subject on the screen with the brightness changed by the screen brightness changing meansThe camera has a control means for performing the above.
[0019]
  In order to achieve the second object, the invention according to claim 2 is characterized in that an object scene image detecting means for detecting image information of the object scene and image information from the object scene image detecting means. Based on the subjectFacial expressionRecognizeFacial expression recognition meansAnd theFacial expression recognition meansWith information fromFacial expressionAccording to the determination means of determining and the determination result of the determination meansScreen color changing means for changing the color of the recording screen, and a recording operation for recording the subject with the screen color changed by the screen color changing meansThe camera has a control means for performing the above.
[0026]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, the present invention will be described.The following with reference to the drawingsThis will be described in detail based on the embodiment.
[0027]
FIG. 1 is a central longitudinal sectional view showing a camera common to each embodiment of the present invention, and FIG. 2 is a block diagram showing a configuration of a main part according to the first embodiment of the present invention.
[0028]
In these figures, 1 is a camera body and 2 is a photographing lens. Reference numeral 3 denotes a main mirror having a half mirror near the photographing optical axis. The main mirror 3 is bonded and fixed to a main mirror receiving plate 4 (an opening is provided near the photographing optical axis), and an axis 4a provided on the main mirror receiving plate 4 is fixed. It is possible to turn from the observation state in which the mirror is lowered in FIG. In the observation state with the mirror down, the subject light passing through the photographing lens is reflected 45 degrees upward by the main mirror, forms an image on the focus plate 5, becomes an erect image by the penta roof prism 6, and is observed by the photographer through the eyepiece 7. Is done. Denoted at 8 is a field image detection means comprising a CCD (solid-state imaging device), which also serves as a photometric sensor. Reference numeral 9 denotes an object scene image detection lens, which forms an image connected to the focus plate 5 on the sensor surface of the object scene image detecting means 8.
[0029]
Reference numeral 10 denotes a sub-mirror, which is bonded and supported by the sub-mirror receiving plate 11 and is rotatably supported by the shaft 11a of the sub-mirror receiving plate 11. The sub mirror 10 guides the subject light that has passed through the half mirror portion near the photographing optical axis of the main mirror 3 in the mirror-down observation state of FIG. 1 to a focus detection unit disposed below the camera, and the sub mirror receiving plate 4 is a mirror (not shown). In the retracted state outside the photographing optical path, the main mirror receiving plate 4 acts so as to close the opening near the photographing optical axis. 12 is a field lens of the focus detection optical system, 13 is a reflection mirror, 14 is a secondary imaging lens of the focus detection optical system, 15 is a focus detection sensor of a known phase difference detection system for passive autofocus, and 16 is a focal plane shutter. , 17 is a lens aperture, and 18 is a film.
[0030]
2 is a scene image, 19a is a state in which the subject person is facing the front, 19b is a state in which the subject person is facing sideways (not facing the front), Each is shown. Reference numeral 20 denotes a CPU that controls the entire camera, and includes a face recognition unit 21 that recognizes the face of the subject based on image information from the object scene image detection unit 8, and information from the face recognition unit 21. A determination unit 22 that determines whether the face is in a predetermined direction, and a subject recording operation control unit 23 that performs a subject recording operation in accordance with the determination result of the determination unit 22 are provided. A camera exposure function unit 24 includes a lens diaphragm 17 and a focal plane shutter 16.
[0031]
1 shown in FIG. 1 is provided in the vicinity of the optical axis of the photographic optical system, iRED projects near infrared light in the same direction as the photographic optical axis, and 26 is a CCD by an advancing / retracting mechanism (not shown) in synchronization with the projection of the iRED 25. A near-infrared light transmitting visible light cut filter 27 entering the front surface of the object scene image detecting means 8 is a known date module for imprinting a date and caption from the back surface of the film. An effect filter 28 is provided so that an imaging lens can enter and retract from the light beam by an actuator (not shown) and an advance / retreat mechanism (not shown), and at least two different types of filters can be selected. Yes.
[0032]
Next, the operation of the main part of the camera in the above configuration will be described with reference to the flowchart of FIG.
[0033]
When a main switch (not shown) is turned on in step 1, power is supplied to the camera, and a shooting preparation initial state is set. In step 2, the CPU 20 determines whether a release button (not shown) of the camera is pressed to the first stroke and the switch SW-1 is turned on. If the switch SW-1 is OFF, the process jumps to step 10.
[0034]
In step 3, the CPU 20 takes in a photometric output from the object scene image detecting means 8 comprising a CCD, performs a photometric calculation, and determines an exposure control value. In the next step 4, focus detection calculation is performed from the output of the focus detection sensor 15 of the known phase difference detection type passive autofocus device to determine the photographing lens driving amount for focusing. In the subsequent step 5, the focus adjustment lens 2a of the photographic lens 2 is driven based on the photographic lens driving amount obtained in the above step 4 to adjust the focus. In the next step 6, the CPU 20 converts the object scene image focused on the subject that the photographer was aiming for into the object image detection means 8 made up of a CCD for 1/30 second video. We let you take in rate sequentially.
[0035]
In the next step 7, the face recognition means 21 recognizes the person's face from the captured object scene image, and the determination means 22 determines whether the recognized person's face is facing the front. If the subject person of the object scene image is facing the front as in 19a of FIG. 2, the process proceeds to step 8, and if not, the process returns to step 2.
[0036]
Note that the following methods (a) to (c) are known as methods for extracting a person image facing the front from the object scene image (performed by the face recognition means 21 and the determination means 22). In the first embodiment, any one of the methods is used.
[0037]
(A) As shown in “Proposal of Modified HSV Color System Effective for Face Area Extraction” in the Journal of the Institute of Television Engineers of Japan, Vol. 49, No. 6, pp. 787-797 (1995) To extract the face area by focusing on the skin color area.
[0038]
(B) As shown in “Method of extracting a face region from a still gray scene image” in the Journal of the Institute of Electronics, Information and Communication Engineers Vol. J74-D-II, No. 11, pp. 1625-1627 (1991) A method for extracting the head region of a front person image using geometric shape features of each part constituting the head part of the front person image such as the eyes and mouth.
[0039]
(C) In the case of a moving image, a contour edge of a person image generated by a subtle motion of a person between frames, as shown in “Video phone face area detection and its effect” in Image Lab 1991-11 (1991) A method to extract a frontal person image using.
[0040]
In Step 8, the subject recording operation control means 23 controls the aperture diameter of the diaphragm 17 and the shutter time of the focal plane shutter 16 based on the exposure control value determined in Step 3 above, and the film 18 To the exposure. Then, in the next step 9, the film is wound up by one frame, and in preparation for the next shooting, when the winding of the film is completed, the process returns to step 2.
[0041]
If the switch SW-1 is OFF in step 2 and the process proceeds to step 10, here, the CPU 20 changes the exposure setting without measuring the photometric timer (which keeps the switch SW-1 ON by pressing the release button). In order to be able to do this, go to see the state of a timer that keeps the metering ready state for a predetermined time), and return to step 2 if it is in operation. Further, if the predetermined time has elapsed and the operation has not been performed, the process proceeds to step 11. Here, the state of the main switch (not shown) is checked, and if it is ON, the process returns to step 2 and the following is repeated. On the other hand, if it is OFF, the process proceeds to step 12 to cut off the power supply to the camera.
[0042]
According to the first embodiment described above, the direction of the face of the subject is recognized, and the subject recording operation is performed when the face is directed in a predetermined direction, particularly the front, so that the subject is not burdened. This has the effect of preventing failure photos where a person is not properly facing the camera.
[0043]
(Second Embodiment)
FIG. 4 is a block diagram showing the circuit configuration of the main part of the camera according to the second embodiment of the present invention, and FIG. 5 is a flowchart showing the operation of the main part in the second embodiment of the present invention.
[0044]
In these drawings, the same parts as those in the first embodiment are indicated by the numbers as they are, and the corresponding parts are indicated by numbers obtained by adding 200 to the numbers in the first embodiment. Only the points different from the first embodiment will be described here.
[0045]
In FIG. 4, 219 is an object scene image, 219a is a state in which the subject person is opening his eyes and looking toward the camera, and 219b is a state in which the subject person is closing his eyes. Reference numeral 219c shows a state where the person who is the subject opens his eyes but does not point his eyes at the camera. A CPU 220 controls the entire camera, and includes an eye recognition unit 221 that recognizes the subject's eyes based on image information from the object scene image detection unit 8, and information from the eye recognition unit 221. Determination means 222 for determining whether the eyes are in a specific state (for example, whether the eyes are open or the line of sight is facing the camera), and subject recording operation according to the determination result of the determination means 222 It has the control means 223 which performs.
[0046]
Next, the operation of the main part of the camera in the above configuration will be described with reference to the flowchart of FIG.
[0047]
Steps 201 to 205 are the same as steps 1 to 5 in FIG. 3 in the first embodiment, and a description thereof is omitted.
[0048]
In step 206, the CPU 200 sequentially converts the object scene image focused on the subject that the photographer was aiming into the object image detection means 8 comprising a CCD at a 1/30 second video rate. Let them be captured. In addition, the pupil has the property of reflecting the incident light in approximately the same direction, and the brightness of the coaxial illumination state is significantly higher than other parts of the face, so even if weak near infrared light is used, only the pupil is Brighter images are taken. Accordingly, the near-infrared light is projected onto the subject by the iRED 25 and the object scene image transmitted by the near-infrared light transmitting visible light cut filter 26 is converted into a 1/30 second video by the object scene image detecting means 8. If images are taken in sequentially at a rate, an eye image can be obtained more effectively.
[0049]
In the next step 207, the eye recognizing means 221 recognizes the human eye from the captured object scene image, and the judging means 222 determines whether the recognized human eye is open or the line of sight is a camera. It is determined whether it is facing. If the eyes of the person who is the subject of the object scene image are open as in 219a or 219c in FIG. 4, the process proceeds to step 208. If the eyes are closed as in 219b, the process returns to step 202. Alternatively, if the eyes of the person who is the subject of the object scene image are opened as in 219a in FIG. 4 and the line of sight is facing the camera, the process proceeds to step 208, and the eyes are opened as in 219c. However, if the eyes are not directed toward the camera or the eyes are closed as in 219b, the process may return to step 202.
[0050]
In addition, a method (performed by the eye recognition unit 221 and the determination unit 222) for extracting a person's eyes (and the line of sight (sight line) direction) from the object scene image is performed in the following (d) to (h). Methods are publicly known, and any one of these methods is used in the second embodiment.
[0051]
(D) A method of dividing the eye region into a vertical line and a horizontal line passing through the center of the pupil and calculating the viewpoint position using the area ratio of the divided regions as a feature amount as disclosed in Japanese Patent Laid-Open No. 3-17696.
[0052]
(E) As disclosed in Japanese Patent Laid-Open No. 4-255015, a method for obtaining the relative movement amount of the line of sight from changes in pupil center coordinates by extracting pupil contour data.
[0053]
(F) A method of projecting infrared light onto a face and extracting an eyeball having a particularly high reflectance as disclosed in Japanese Patent Laid-Open No. 5-300601.
[0054]
(G) As disclosed in Japanese Patent Laid-Open No. 9-21611, a method of irradiating a person who is a subject substantially coaxially with a photographing lens to detect high-intensity reflection of a pupil and extract an eye.
[0055]
(H) As shown in Japanese Patent Laid-Open No. 9-251342, the acquired image is divided into regions, and a face region is found from the hue and saturation information of each region. Next, by binarizing the hue image, candidates for the eye part and the mouth part having color attributes different from those of the skin color part are obtained, and the eye area and the mouth area are determined by collating with the shade patterns of the eyes and mouth. Then, an edge image is generated for the detected eyes and mouth, the edge image is mapped perpendicularly to the one-dimensional axial direction, and the head of the eye and the left and right mouths are detected. Further, the cut-out image of the eye is binarized, the center of gravity of the black pixel is set as the center of gravity of the pupil, and the pupil vector is obtained from the eye point. Finally, the gaze point is obtained from the eye position in the face direction. That technique.
[0056]
Steps 208 to 212 are the same as steps 8 to 12 in FIG. 3 in the first embodiment, and a description thereof is omitted.
[0057]
According to the second embodiment, the subject recording operation is performed when the eye state of the subject is recognized and the eye is in a predetermined state, particularly when the eye is opened firmly and the eye is facing the camera. As a result, the photographer is not burdened, and there is an effect of preventing a failure photograph in which a person who is a subject closes his eyes or does not properly look at the camera.
[0058]
(Third embodiment)
FIG. 6 is a block diagram showing the circuit configuration of the main part of a camera according to the third embodiment of the present invention, and FIG. 7 is a flowchart showing the operation of the main part in the third embodiment of the present invention.
[0059]
In these drawings, the same parts as those in the first embodiment are indicated by the numbers as they are, and the corresponding parts are indicated by numbers obtained by adding 300 to the numbers in the first embodiment. Only the points different from the first embodiment will be described here.
[0060]
In FIG. 6, 319 is an object scene image, 319a is a state in which a person who is a subject has no expression, 319b is a state of joy that a person who is a subject is laughing, and 319c is a person who is a subject crying. 319d shows the anger state of the person who is the subject, and 319e shows the surprise state of the person who is the subject. Reference numeral 320 denotes a CPU that controls the entire camera, and includes a facial expression recognition unit 321 that recognizes a facial expression of a subject based on image information from the object scene image detection unit 8, and information from the facial expression recognition unit 321. A determination unit 322 for determining whether the facial expression is in a specific state (for example, a state of joy, sadness, anger, or surprise), and a control unit 323 for performing a subject recording operation according to the determination result of the determination unit 322 Have.
[0061]
Next, the operation of the main part of the camera in the above configuration will be described with reference to the flowchart of FIG.
[0062]
Steps 301 to 306 are the same as steps 1 to 6 in FIG. 3 in the first embodiment, and description thereof is omitted.
[0063]
In step 307, the facial expression recognition unit 321 recognizes a human facial expression from the captured object scene image, and the determination unit 322 determines that the recognized human facial expression is in a specific state (for example, joy, sadness, anger). , Is in a surprise state). If the facial expression of the person who is the subject of the object scene image is in a state of joy, sadness, anger, or surprise as in 319b to 319e in FIG. Return to step 302.
[0064]
Note that the following methods (i) to (k) are known as methods for recognizing a facial expression of a person from the object scene image (performed by the facial expression recognition means 321 and the determination means 322). In the third embodiment, any one of the methods is used.
[0065]
(I) As shown in Japanese Patent Laid-Open No. 3-252775, a module for measuring muscle movement is provided, and this module is used as a standard in the learning mode based on the temporal change pattern of facial muscle movement. A method that learns and stores facial expression patterns, and recognizes facial expressions in recognition mode by comparing them with the captured facial expression patterns.
[0066]
(J) As shown in Japanese Patent Laid-Open No. 8-249447, the facial image signal is subjected to wavelet transform, and the average power of the spatial frequency obtained thereby is compared with the average power when there is no expression to recognize facial expressions. Technique.
[0067]
(K) As shown in JP-A-8-249453 and JP-A-10-255043, the expression category is considered to be six types of basic facial expressions of anger, disgust, fear, sadness, happiness, and surprise. Process time-series images for each basic facial expression. For example, an optical flow algorithm is used from two consecutive images in a moving image of a person's face for two areas each including a right eye and a mouth, which are areas most noticed when a person reads a partner's facial expression. To get the velocity vector. Discrete Fourier transform is performed on each component of the velocity vector, and the low frequency component of the Fourier transform coefficient is extracted as a feature vector. Next, a method of calculating a feature vector generation probability using an HMM (Hidden Markov Model) and performing recognition processing.
[0068]
Steps 308 to 312 are the same as steps 8 to 12 in FIG. 3 in the first embodiment, and description thereof is omitted.
[0069]
According to the third embodiment, when the facial expression of the subject is recognized and the face becomes a predetermined facial expression, especially when the facial expression is interesting, such as joy, sadness, anger, or surprise. In addition, since the subject recording operation is performed, there is no burden on the photographer, so that it is not necessary to take an ordinary photograph with almost no expression, and the probability that a masterpiece can be taken is increased.
[0070]
(Fourth embodiment)
FIG. 8 is a block diagram showing the circuit configuration of the main part of a camera according to the fourth embodiment of the present invention, and FIG. 9 is a flowchart showing the operation of the main part in the second embodiment of the present invention.
[0071]
In these drawings, the same parts as those in the first embodiment are indicated by the numbers as they are, and the corresponding parts are indicated by numbers obtained by adding 400 to the numbers in the first embodiment. Only the points different from the first embodiment will be described here.
[0072]
In FIG. 8, 419 is an object scene image, 419a is a person standing on a stick, 419b is a person sitting on a cheek cane, and 419c is a person on one arm. Each of these states is shown. A CPU 420 controls the entire camera, and includes a pose recognition unit 421 for recognizing a pose of a subject based on image information from the object scene image detection unit 8 and information from the pose recognition unit 421. Determining means 422 for determining whether the pose is in a specific state (for example, sitting with a cheek cane sitting, raising one arm, etc.), and control for performing the subject recording operation according to the determination result of the determining means 422 Means 423 are included.
[0073]
Next, the operation of the main part of the camera in the above configuration will be described with reference to the flowchart of FIG.
[0074]
Steps 401 to 406 are the same as steps 1 to 6 in FIG. 3 in the first embodiment, and description thereof is omitted.
[0075]
In step 407, the pose recognition unit 421 recognizes a person's pose from the captured object scene image, and the determination unit 422 causes the recognized person's pose to sit in a specific state (for example, poking a cheek cane). Whether one arm is raised). If the pose of the person who is the subject of the object scene is in a state of sitting on the cheek cane, raising one arm, etc. as in 419b and 419c in FIG. Return to step 402.
[0076]
As a method for recognizing a pose from an object scene image (performed by the pose recognizing means 421 and the determining means 422), the following method (m) is well known, and this fourth embodiment Then, this method shall be used.
[0077]
(M) A method of extracting a contour of a specific part of an imaged subject and comparing it with a stored pattern to recognize a pose as disclosed in JP-A-7-57103.
[0078]
Steps 408 to 412 are the same as steps 8 to 12 in FIG. 3 in the first embodiment, and description thereof is omitted.
[0079]
According to the fourth embodiment, the subject is recorded when the posture (pose) of the subject is recognized, and when the subject is in a predetermined posture (pose), particularly when the subject is in an interesting characteristic pose. Since the operation is performed, there is no burden on the photographer, and there is no need to take a picture of a boring pose like a stick standing, and there is an effect that the probability of taking a masterpiece photograph is increased.
[0080]
(Fifth embodiment)
FIG. 10 is a block diagram showing the circuit configuration of the main part of a camera according to the fifth embodiment of the present invention, and FIG. 11 is a flowchart showing the operation of the main part in the fifth embodiment of the present invention.
[0081]
In these drawings, the same parts as those in the first embodiment are indicated by the numbers as they are, and the corresponding parts are indicated by numbers obtained by adding 500 to the numbers in the first embodiment. Only the points different from the first embodiment will be described here.
[0082]
In FIG. 10, 519 is an object scene image, 519a shows a state where a person who is a subject is standing on a stick, and 519b shows a state where a person who is a subject starts running. Reference numeral 520 denotes a CPU that controls the entire camera. The CPU 520 includes a motion recognition unit 521 that recognizes the motion of the subject based on image information from the object scene image detection unit 8, and information from the motion recognition unit 521. A determination unit 522 that determines whether the operation is in a specific state (for example, a state in which the vehicle has started running), and a control unit 523 that performs a subject recording operation according to the determination result of the determination unit 522 are provided.
[0083]
Next, the operation of the main part of the camera in the above configuration will be described with reference to the flowchart of FIG.
[0084]
Steps 501 to 506 are the same as steps 1 to 6 in FIG. 3 in the first embodiment, and a description thereof will be omitted.
[0085]
In step 507, the motion recognition unit 521 recognizes a human motion from the captured object scene image, and the determination unit 522 puts the recognized human motion into a specific state (for example, a state in which the vehicle has started running). Determine whether it is. If the movement of the person who is the subject of the object scene image has started running as in 519b, the process proceeds to step 508, and if not, the process returns to step 502.
[0086]
As a method for recognizing the motion from the object scene image (performed by the motion recognizing means 521 and the determining means 522), the following method (n) is known, and the fifth embodiment In the form, this method is used.
[0087]
(N) As disclosed in Japanese Patent Laid-Open No. 7-57103, a method of extracting a contour of a specific part of an imaged subject and comparing it with a stored pattern to recognize an operation.
[0088]
Steps 508 to 512 are the same as steps 8 to 12 in FIG. 3 in the first embodiment, and description thereof is omitted.
[0089]
According to the fifth embodiment, the subject recording operation is performed when the subject performs a predetermined motion when the subject performs a predetermined motion, and particularly when the subject performs a characteristic motion that is interesting as a photograph. There is no need to take pictures of boring movements that are close to a stick, and the probability of taking a masterpiece is increased.
[0090]
(Sixth embodiment)
FIG. 12 is a block diagram showing the circuit configuration of the main part of a camera according to the sixth embodiment of the present invention, and FIG. 13 is a flowchart showing the operation of the main part in the sixth embodiment of the present invention.
[0091]
In these drawings, the same parts as those in the first embodiment are indicated by the numbers as they are, and the corresponding parts are indicated by numbers obtained by adding 600 to the numbers in the first embodiment. Only the points different from the first embodiment will be described here.
[0092]
In FIG. 12, 619 is an object scene image, 619a is a state in which the person who is the subject has no expression, 619b is a state of joy that the person who is the subject is laughing, and 619c is a person who is crying. 619d shows the anger state of the person who is the subject, and 619e shows the surprise state of the person who is the subject. A CPU 620 controls the entire camera. The CPU 620 includes a facial expression recognition unit 621 for recognizing a facial expression of a subject based on image information from the object scene image detection unit 8, and information from the facial expression recognition unit 621. The determination unit 622 determines whether the facial expression is in a specific state (for example, a state of joy or sadness), and further includes a control unit 623 that performs a subject recording operation according to the determination result of the determination unit 622.
[0093]
Next, the operation of the main part of the camera in the above configuration will be described with reference to the flowchart of FIG.
[0094]
Steps 601 to 606 are the same as steps 1 to 6 in FIG. 3 in the first embodiment, and a description thereof will be omitted.
[0095]
In step 607, the facial expression recognition unit 621 recognizes a human facial expression from the captured object scene image, and the determination unit 622 changes the recognized human facial expression to a specific state (for example, a joyful state). Determine whether it is. If the expression of the person who is the subject of the object scene image is in a joyful state as in 619b, the process proceeds to step 608. Otherwise, go to step 609.
[0096]
Note that a method for recognizing a human facial expression from the object scene image (performed by the facial expression recognizing means 621 and the determining means 622) is performed in the same manner as in the third embodiment.
[0097]
In step 608, positive exposure correction is performed with respect to the exposure control value determined in step 603 so that the photographing screen becomes bright (a bright atmosphere is created). Then, in the next step 609, the facial expression recognition means 621 recognizes the human facial expression from the captured scene image, and the judgment means 622 recognizes the recognized human facial expression in a specific state (for example, sadness). State). If the facial expression of the person who is the subject of the object scene image is in a sad state as indicated by 619c in FIG. 12, the process proceeds to step 610; otherwise, the process returns to step 602.
[0098]
Note that the method for recognizing a human facial expression from the object scene image (performed by the facial expression recognition unit 621 and the determination unit 622) is the same as that in the third embodiment described above, as described in step 607 above. It shall be performed by a well-known method.
[0099]
In step 610, negative exposure correction is performed on the exposure control value determined in step 603 so that the shooting screen becomes dark (a dark atmosphere is created).
[0100]
Steps 611 to 615 are the same as steps 8 to 12 in FIG. 3 in the first embodiment, and description thereof is omitted.
[0101]
According to the sixth embodiment, when the facial expression of the subject is recognized and the facial expression becomes a predetermined facial expression, a bright / dark distinctive facial expression is obtained especially as a photo atmosphere such as joy and sadness. Since the brightness of the subject recording screen is changed according to the atmosphere when it becomes, there is an effect of enlivening the atmosphere created by the expression without placing a burden on the photographer.
[0102]
(Seventh embodiment)
FIG. 14 is a block diagram showing the circuit configuration of the main part of a camera according to the seventh embodiment of the present invention, and FIG. 15 is a flowchart showing the operation of the main part in the seventh embodiment of the present invention.
[0103]
In these drawings, the same parts as those in the first embodiment are indicated by the numbers as they are, and the corresponding parts are indicated by numbers obtained by adding 700 to the numbers in the first embodiment. Only the points different from the first embodiment will be described here.
[0104]
In FIG. 14, 719 is an object scene image, 719a is a state where a person who is a subject has no expression, 719b is a state of joy that a person who is a subject is laughing, and 719c is a person who is a subject crying. 719d shows the anger state of the person who is the subject, and 719e shows the surprise state of the person who is the subject. Reference numeral 720 denotes a CPU that controls the entire camera, and the facial expression recognition means 721 for recognizing the facial expression of the subject based on the image information from the object scene image detection means 8 and the information from the facial expression recognition means 721 Control unit 722 for determining whether or not the subject is in a specific state (for example, a state of joy, sadness, or anger), and further, a control for performing a subject recording operation and a text / character recording operation according to the determination result of determination unit 722 Means 723 are included. A text / character generating means 27 corresponds to a known date module for imprinting the date and caption from the back of the film. Reference numeral 729 denotes a photographed subject recording image.
[0105]
Next, the operation of the main part of the camera in the above configuration will be described with reference to the flowchart of FIG.
[0106]
Steps 701 to 706 are the same as steps 1 to 6 in FIG. 3 in the first embodiment, and a description thereof will be omitted.
[0107]
In step 707, the facial expression recognition unit 721 recognizes the human facial expression from the captured object scene image, and the determination unit 722 changes the recognized human facial expression to a specific state (for example, a joyful state). Judge whether it is. If the facial expression of the person who is the subject of the object scene image is in a joyful state as indicated by 719b in FIG. 14, the process proceeds to step 708; otherwise, the process proceeds to step 709.
[0108]
Note that the method of recognizing a human facial expression from the object scene image (performed by the facial expression recognizing means 721 and the determining means 722) is performed by the same known method as in the third embodiment.
[0109]
In step 708, a known date module 27 for imprinting the date and caption as text / character generating means from the back of the film is driven, and a bright image such as “♪ HAPPY ♪” shown in FIG. Copy text and characters on film 18.
[0110]
In step 709, the facial expression recognition unit 721 recognizes a human facial expression from the captured object scene image, and the determination unit 722 changes the recognized human facial expression to a specific state (for example, a state of sadness). Judge whether it is. If the expression of the person who is the subject of the object scene image is in a sad state as indicated by 719c in FIG. 14, the process proceeds to step 710, and if not, the process proceeds to step 711.
[0111]
Note that the method for recognizing the facial expression of a person from the object scene image (performed by the facial expression recognition means 721 and the determination means 722) is the same as that in the third embodiment, as in the above-described step 707. It is done like a technique.
[0112]
In step 710, a known date module 27 for copying the date and caption as text / character generating means from the back of the film is driven, and the comfort such as “★ don't cry” shown at 729 c in FIG. The text 18 and the text and characters of sad images such as “… I'm lonely…” and “Sad!” Are imprinted on the film 18.
[0113]
In step 711, the facial expression recognition unit 721 recognizes a human facial expression from the captured object scene image, and the determination unit 722 changes the recognized human facial expression to a specific state (for example, an angry state). Judge whether it is. If the expression of the person who is the subject of the object scene image is in an angry state as indicated by 719d in FIG. 14, the process proceeds to step 712. Otherwise, the process returns to step 702.
[0114]
Note that the method for recognizing the facial expression of a person from the object scene image (performed by the facial expression recognition means 721 and the determination means 722) is the same as that in the third embodiment, as in the above-described step 707. It shall be done by a method.
[0115]
In step 712, a known date module 27 for copying the date and caption as text / character generating means from the back side of the film is driven, and the text praising like "Don't get so angry" or 729d in FIG. The text and character that image anger such as “▲ I'm angry! ▲” shown in FIG.
[0116]
Steps 713 to 717 are the same as steps 8 to 12 in FIG. 3 in the first embodiment, and description thereof is omitted.
[0117]
According to the seventh embodiment, when the facial expression of the subject is recognized and the facial expression becomes a predetermined facial expression, the facial expression of the photograph has a distinct characteristic, particularly joy, sadness, and anger. When this happens, text and characters that match the atmosphere are recorded together with the subject, so there is an effect of enlivening the atmosphere created by facial expressions without placing a burden on the photographer.
[0118]
(Eighth embodiment)
FIG. 16 is a block diagram showing the circuit configuration of the main part of the camera according to the eighth embodiment of the present invention, and FIG. 17 is a flowchart showing the operation of the main part in the eighth embodiment of the present invention.
[0119]
In these drawings, the same parts as those in the first embodiment are indicated by the numbers as they are, and the corresponding parts are indicated by numbers obtained by adding 800 to the numbers in the first embodiment. Only the points different from the first embodiment will be described here.
[0120]
In FIG. 16, 819 is an object scene image, 819a is a state where the person who is the subject has no expression, 819b is a state of joy that the person who is the subject is laughing, and 819c is a person who is the subject crying. 819d shows the anger state of the person who is the subject, and 819e shows the surprise state of the person who is the subject. A CPU 820 controls the entire camera. The CPU 820 includes a facial expression recognition unit 821 for recognizing a facial expression of a subject based on image information from the object scene image detection unit 8 and information from the facial expression recognition unit 821. Determination means 822 for determining whether the facial expression is in a specific state (for example, a state of joy, sadness, or anger), and further, subject recording operation and screen color recording operation are performed according to the determination result of the determination means 822. Control means 823 is included. Reference numeral 28 denotes a screen color changing means, and an effect filter is provided so that the photographing lens can enter and retract from the light beam by an actuator (not shown) and a forward / backward mechanism (not shown), and yellow, blue, red, etc., respectively. Filters that can produce effects that match the atmosphere of the subject can be selected. Reference numeral 829 denotes a photographed subject recording image.
[0121]
Next, the operation of the main part of the camera in the above configuration will be described with reference to the flowchart of FIG.
[0122]
Steps 801 to 806 are the same as steps 1 to 6 in FIG. 3 in the first embodiment, and a description thereof will be omitted.
[0123]
In step 807, the facial expression recognition unit 821 recognizes a human facial expression from the captured object scene image, and the determination unit 822 changes the recognized human facial expression to a specific state (for example, a joyful state). Judge whether it is. If the expression of the person who is the subject of the object scene image is in a joyful state as indicated by 819b in FIG. 16, the process proceeds to step 808; otherwise, the process proceeds to step 809.
[0124]
Note that the method of recognizing a human facial expression from the object scene image (performed by the facial expression recognizing means 821 and the determining means 822) is assumed to be performed by the same known method as in the third embodiment.
[0125]
In step 808, the effect filter based on yellow of the screen color changing means 28 is made to enter the luminous flux of the photographing lens, and the screen color of a bright image as the sun shines as shown in 829b of FIG. 18 is imprinted.
[0126]
In step 809, the facial expression recognition unit 821 recognizes a human facial expression from the captured object scene image, and the determination unit 822 changes the recognized human facial expression to a specific state (for example, a sad state). Judge whether it is. If the expression of the person who is the subject of the object scene image is in a sad state as indicated by 819c in FIG. 16, the process proceeds to step 810. Otherwise, the process proceeds to step 811.
[0127]
Note that the method for recognizing a human facial expression from the object scene image (performed by the facial expression recognition unit 821 and the determination unit 822) is the same as that in the third embodiment described above, as described in step 807 above. This is performed as in a known method.
[0128]
In step 810, the blue color-based effect filter of the screen color changing means 28 is caused to enter the luminous flux of the photographing lens, so that the screen color of the sad blue image as shown in 829c of FIG. Copy.
[0129]
In step 811, the facial expression recognition unit 821 recognizes a human facial expression from the captured object scene image, and the determination unit 822 changes the recognized human facial expression to a specific state (for example, an angry state). Judge whether it is. If the expression of the person who is the subject of the object scene image is in an angry state as indicated by 819d in FIG. 16, the process proceeds to step 812, and if not, the process returns to step 802.
[0130]
Note that the method for recognizing a human facial expression from the object scene image (performed by the facial expression recognition unit 821 and the determination unit 822) is the same as that in the third embodiment described above, as described in step 807 above. It shall be performed by a well-known method.
[0131]
In step 812, an effect filter based on red color of the screen color changing means 28 is entered into the light flux of the photographing lens, and a screen color that images an anger like a fiery flame as shown in 829d of FIG. 18 is imprinted.
[0132]
In step 813, the control means 823 that performs the subject recording operation and the screen color recording operation based on the exposure control value determined in step 803 described above determines the aperture diameter of the diaphragm 17 and the shutter time of the focal plane shutter 16. The film 18 is controlled to be exposed. Then, in the next step 814, after the effect filter is retracted out of the light flux of the photographing lens, the film is wound up by one frame to prepare for the next photographing. After the film winding is completed, the process returns to step 802.
[0133]
Steps 815 to 817 are the same as steps 10 to 12 in FIG. 3 in the first embodiment, and a description thereof is omitted.
[0134]
In the eighth embodiment, the screen color is changed. However, in order to record an atmosphere that matches the facial expression on the screen in the same way, the soft focus that softens the screen or the fog appears A special effect performed by a known optical filter represented by foggy or a pattern may be added to the screen.
[0135]
According to the eighth embodiment described above, when the facial expression of the subject is recognized and the face becomes a predetermined facial expression, a facial expression with a distinctive feature such as joy, sadness, and anger. Since the screen color changed in accordance with the atmosphere is recorded together with the subject when the image becomes, there is an effect of enlivening the atmosphere created by the expression without placing a burden on the photographer.
[0136]
(Modification)
In each of the above embodiments, a CCD (solid-state image sensor) is provided in place of the film 18, and a known so-called digital camera component such as an image sensor driving circuit, a digital image processing circuit, or an image storage means is provided. It can be applied not only to silver halide cameras but also to electronic still cameras. For example, as a means for changing the brightness of the subject recording screen in the sixth embodiment, a method for changing the gain of a CCD (solid-state imaging device) instead of a film, in addition to a method for changing the exposure with an aperture and a shutter. There is also.
[0137]
The seventh embodiment has a text / character ROM as the text / character generating means, and during the digital image processing, text and characters read from the ROM by known image composition are superimposed on the subject. It is conceivable to perform a recording operation together.
[0138]
Similarly, as the screen color changing means of the eighth embodiment, it is conceivable that during digital image processing, the screen color is changed by known color adjustment and recorded together with the subject. Furthermore, it is possible to produce a special effect or add a pattern by known image composition.
[0139]
【The invention's effect】
  As described above, according to the first aspect of the present invention, the face of the subjectFacial expressionRecognize the faceFacial expressionDepending on the judgment result ofChanging the brightness of the recording screenIt is possible to provide a camera that can be used.
[0140]
  According to the invention of claim 2, the subjectFacial expressionRecognizeFacial expressionDepending on the judgment result ofChange the recording screen to a color that matches your facial expressionIt is possible to provide a camera that can be used.
[Brief description of the drawings]
FIG. 1 is a central longitudinal cross-sectional view showing a camera common to each embodiment of the present invention.
FIG. 2 is a block diagram showing a circuit configuration of a main part of the camera according to the first embodiment of the present invention.
FIG. 3 is a flowchart showing the operation of the main part of the camera according to the first embodiment of the present invention.
FIG. 4 is a block diagram showing a circuit configuration of a main part of a camera according to a second embodiment of the present invention.
FIG. 5 is a flowchart showing the operation of the main part of the camera according to the second embodiment of the present invention.
FIG. 6 is a block diagram showing a circuit configuration of main parts of a camera according to a third embodiment of the present invention.
FIG. 7 is a flowchart showing the operation of the main part of the camera according to the third embodiment of the present invention.
FIG. 8 is a block diagram showing a circuit configuration of main parts of a camera according to a fourth embodiment of the present invention.
FIG. 9 is a flowchart showing the operation of the main part of the camera according to the fourth embodiment of the present invention.
FIG. 10 is a block diagram showing a circuit configuration of main parts of a camera according to a fifth embodiment of the present invention.
FIG. 11 is a flowchart showing the operation of the main part of the camera according to the fifth embodiment of the present invention.
FIG. 12 is a block diagram showing a circuit configuration of main parts of a camera according to a sixth embodiment of the present invention.
FIG. 13 is a flowchart showing the operation of the main part of the camera according to the sixth embodiment of the present invention.
FIG. 14 is a block diagram showing a circuit configuration of main parts of a camera according to a seventh embodiment of the present invention.
FIG. 15 is a flowchart showing operations of main parts of a camera according to a seventh embodiment of the present invention.
FIG. 16 is a block diagram showing a circuit configuration of main parts of a camera according to an eighth embodiment of the present invention.
FIG. 17 is a flowchart showing the operation of the main part of the camera according to the eighth embodiment of the present invention.
[Explanation of symbols]
8 Field image detection means comprising CCD
20, 220, 320, 420 CPU
21 Face recognition means
22, 222, 322, 422 determination means
23, 223, 323, 423 Subject recording operation control means
24 Camera exposure function section
27 Text / character generation means (date module)
28 Screen color changing means (effect filter)
221 Eye recognition means
321,621,721,821 Facial expression recognition means
421 Pose recognition means
520, 620, 720, 820 CPU
521 motion recognition means,
522, 622, 722, 822 determination means
523,623 Subject recording operation control means
723 Subject & text character recording operation control means
823 Subject & screen color recording operation control means

Claims (2)

And the scene image detection means for detecting the image information of the object scene, and recognizing facial expression recognition means the expression of the face of the subject based on image information from該被Utsushikai image detecting means, from the facial expression recognition unit Determining means for determining facial expression according to information, screen brightness changing means for changing the brightness of the recording screen according to the determination result of the determining means, and brightness changed by the screen brightness changing means And a control means for performing a recording operation for recording a subject on the screen . And the scene image detection means for detecting the image information of the object scene, and recognizing facial expression recognition means the expression of the face of the subject based on image information from該被Utsushikai image detecting means, from the facial expression recognition unit Determining means for determining facial expression according to information; screen color changing means for changing the color of the recording screen in accordance with the determination result of the determining means; and subject with the screen color changed by the screen color changing means And a control means for performing a recording operation for recording the camera.

Images