JP2003092701A - Imaging apparatus - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an imaging apparatus for automatically depressing a release button by recognizing and discriminating a face image so as not to lose the photo opportunity and for preventing an unsharpened picture from being photographed so as to record only sharp pictures. SOLUTION: The imaging apparatus of this invention comprises; an image memory 20 for storing one picture of an object; an image capturing section 21 for capturing the picture stored in the memory to other memory or a register in a prescribed unit; a control section 22 for controlling the entire sections; a face feature storage section 24 for storing features of a plurality of faces; a recognition/discrimination section 23 for recognizing a face on the basis of data from the image capturing section 21 and data from the face feature storage section 24 to discriminate each part of the face; an edge detection section 26 for detecting an edge detection value from the resulting data; and an output section 25 for externally outputting the final determination result.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image pickup device,
In particular, it has an image pickup means for converting an optical signal from a subject through an optical system into an image signal which is an electric signal and outputting the image signal.
The present invention relates to an image pickup apparatus in which a release button is automatically pressed when a face of a subject is detected.

[0002]

2. Description of the Related Art In recent years, along with the development of personal computers, the use of digital cameras as image input devices has become widespread. Especially, it is mostly used by photographers who do not have special technology, and the shutter speed, exposure, and focus are automatically set according to the subject in order to eliminate shooting failures. There are many. Further, in general, the subject is often a person, and there is no digital camera having a special setting mode peculiar to the person. Japanese Unexamined Patent Application Publication No. 2001-51338 discloses a camera capable of recognizing the orientation of a subject's face and performing a subject recording operation when the face faces a predetermined direction. According to this, the object scene image detecting means for detecting the image information of the object scene, the face recognizing means for recognizing the face of the subject based on the image information from the object scene detecting means, and the face recognizing means. It has a determining means for determining whether or not the face is facing in a predetermined direction based on the information from, and a control means for performing the subject recording operation according to the determination result of the determining means.

[0003]

Conventionally, in a digital camera image pickup device having a mode in which the shutter speed, exposure, and focusing are automatically set according to the subject, it is the photographer who presses the release button to photograph the subject. It depends on the intention. Therefore, in the case of photographing a person, even if the photographer recognizes the person, the release timing may be shifted and the photographing opportunity may be missed. Further, Japanese Laid-Open Patent Publication No. 2001-51338 is a technique for recognizing the orientation of a face and performing a subject recording operation when the orientation is a predetermined orientation.
If the camera shakes, you may not be able to clearly capture your face. In view of such a problem, the present invention automatically presses the release button by recognizing and discriminating a face image, does not miss a shutter opportunity, and prevents shooting an unclear image, and records only a clear image. An object is to provide an imaging device.

[0004]

In order to solve the above problems, the present invention provides an image pickup means for converting an optical signal obtained through an optical system into an image signal and outputting the image signal. The image pickup apparatus further includes: a face image recognition unit that recognizes a face image from the image signal; and a face portion determination unit that determines each portion of the face image from the data of the face image recognition unit. When all the respective parts of the face image can be discriminated by the discriminating means, the release button for photographing the subject is pressed or the photographing operation is performed. The most common subject in a camera is a person. Therefore, when taking a picture of a person, it is important to take the picture without missing a photo opportunity. For that purpose, it is necessary to recognize that the subject is a person. The most suitable part for identifying a person is a face, and a face image is extracted from the subject and the eyes are extracted from the face image.
A clear image can be taken only after the parts such as the mouth, nose, and eyebrows can be identified. In particular, a digital camera records an image signal by digitizing the image signal, so that it can be easily analyzed by a computer. According to the invention, when the face portion determining means can determine all the respective portions of the face image, the release button for photographing the subject is pressed or the image capturing operation is performed, so that the operability is improved. Then
You can shoot clear images without missing a photo opportunity. According to the invention of claim 2, when the face part discriminating means cannot discriminate all of the respective parts of the face image,
It is also an effective means of the present invention that the operation of the face part discriminating means is continued until all the respective parts of the face image can be discriminated. The face image is discriminated by capturing the contour of the face and features such as eyes, nose, eyebrows, and ears. Then, if it is simply determined that it is a face, it can be determined by capturing the contour. However, in order to clearly capture the entire face, it is necessary to continue the discrimination operation until all the parts can be discriminated. According to such a technical means, when all the respective parts of the face image cannot be discriminated, the operation of the face part discriminating means is continued until all the respective parts of the face image can be discriminated. Can be taken.

According to a third aspect of the present invention, the image signal is stored continuously, and the image signal is stored only when all the respective portions of the face image can be discriminated by the face portion discriminating means. Is also an effective means of the present invention. The storage capacity of the memory is finite. Further, the photographer selects a necessary image from the images recorded in the memory or deletes an unnecessary image. At this time, if an unclear image is recorded in the memory, the operation becomes complicated and the memory is wasted. According to such a technical means, the image signal is stored only when all the respective parts of the face image can be discriminated, so that the operability is improved and the memory is not wasted. According to a fourth aspect of the present invention, the face portion discriminating means has edge detecting means for detecting a feature point of an edge for each portion of the face image, and the edge detection value from the edge detecting means is a predetermined threshold value. If it is smaller, it is also an effective means of the present invention to wait until the edge detection value exceeds the threshold value or to continue the operation of the edge detection means. The features of each part of the face are characterized by edges. Therefore, the edge of each portion has a unique threshold value, and it can be determined by comparing the edge detection value from the edge detecting means with this threshold value. According to such a technical means, the edge detection value waits until it exceeds the threshold value or the operation of the edge detection means is continued, so that the image of each portion can be surely captured clearly. According to a fifth aspect of the present invention, when the edge detection means is repeatedly operated while continuously capturing the image signal and the edge detection value from the edge detection means exceeds a predetermined threshold for a predetermined period, Capturing an image signal or pressing the release button is also an effective means of the present invention. In the fourth aspect, the edge detection operation is continued until the edge detection value exceeds the threshold value, but in this case, it may take too long to detect. Therefore, when the detection time and the threshold value have a range and the allowable range is exceeded, the image signal is taken in, or the release button is pressed to take an image. According to such a technical means, when the edge detection value from the edge detection means exceeds a predetermined threshold for a predetermined period,
Since the image signal is fetched or the release button is pressed, the operation time is shortened.

Further, in the invention of claim 6, the image pickup device further comprises display means for displaying data contents, and when the image pickup device satisfies the image pickup condition, the display means may be so informed. It is an effective means of the present invention. The photographer needs to recognize when the face image discrimination is completed. Therefore, it is preferable that the camera has a display means such as a liquid crystal. According to such a technical means, when the image pickup condition is satisfied, the fact is displayed on the display means, so that the photo opportunity can be accurately grasped and the operability is improved. Further, according to the invention of claim 7, it is also effective that the display means displays a message to that effect on the display means when the image pickup device does not satisfy the condition for image pickup after a predetermined time elapses. It is a means. According to such a technical means, when the image capturing condition is not satisfied, the fact is displayed on the display means, so that the photographer can quickly perform the next operation. Further, in the invention of claim 8, the image pickup device further comprises alarm means for emitting a sound, and when the condition for image pickup by the image pickup device is satisfied, it is also an effective means of the present invention to emit a sound by the alarm means. is there. The photographer needs to recognize when the face image discrimination is completed. However, I do not always look at the display. Therefore, if it is determined by the sound, it becomes easier for the photographer to understand. According to the technical means, when the image capturing condition is satisfied, the alarm means emits a sound, so that the display is not overlooked and the operability is further improved. Further, the invention of claim 9 is an effective means of the present invention, wherein the alarm means emits a sound by the alarm means when the image capturing device does not satisfy the condition for capturing an image after a predetermined time elapses. is there. According to such a technical means, when the image pickup device does not satisfy the image pickup condition after a predetermined time elapses, the alarm means emits a sound, so that the photographer can quickly perform the next operation. .

Further, in the invention of claim 10, the sound of the alarm means may change the frequency or melody of the sound depending on whether the condition for imaging by the imaging device is satisfied or not. Is an effective means. When only one type of alarm sound is emitted regardless of the content of the alarm, it is not possible to determine which alarm the alarm sounds. Therefore, it is more preferable to change the sound according to the content of the alarm. According to such a technical means, the frequency of the sound or the melody is changed depending on whether or not the image pickup condition is satisfied by the image pickup device, so that the alarm content can be discriminated and the operability is further improved. Further, in the invention of claim 11, the release button is further provided with selection means for selecting whether or not to press the release button even when the face portion determination means detects a face image, and the selection means The feature is that the release button is manually pressed when the selection is made. The photographer does not always shoot only people, and some people do not want to shoot. Therefore, it is more preferable if the photographer can select whether to press the release button automatically or manually. According to such a technical means, when the selection means selects whether or not to press, the release button is manually pressed, so that the operability of the photographer is further improved.

[0008]

BEST MODE FOR CARRYING OUT THE INVENTION The present invention will be described in detail below with reference to the embodiments shown in the drawings. However, the constituent elements, types, combinations, shapes, relative arrangements, and the like described in this embodiment are merely explanatory examples, not the gist of limiting the scope of the present invention thereto, unless specifically stated. .. FIG. 1 is a block diagram of a digital still camera according to an embodiment of the present invention. In this configuration, a lens 1 for condensing an optical image of a subject, a diaphragm 2 for converging the light flux condensed by the lens 1, and a plurality of lenses (not shown) are moved to focus or the diaphragm 2 is moved. Motor driver 1 to drive
1, a CCD (Charge Coupled Device) 3 for photoelectrically converting an optical image that has passed through the lens 1 and the diaphragm 2, and a CDS (C) for reducing noise included in the CCD 3.
or related Double Sampling) 4, an A / D converter 5 for converting an analog signal from the CCD 3 into a digital signal,
A timing generator 13 for generating timings of the CCD 3, the CDS 4, and the A / D converter 5, a digital signal processing circuit 7 for performing image processing according to image processing parameters,
A frame memory 6 for storing the image pickup pixels and the image processed image, and a liquid crystal (LCD: Liquid Crystal Displa).
y), a display unit 8 for displaying a captured image, an image compression / expansion circuit 9 for compressing or expanding the image data processed by the digital signal processing circuit 7 into source image data, and an image compressed by the image compression / expansion circuit 9. A memory card 10 that stores data, a microcomputer (hereinafter, referred to as a microcomputer) 14 that executes predetermined control based on a control program, and an EEPROM (Elect
rically Erasable and Programmable Read Only Memor
y) 16, a camera operating section 17 provided with a release button or the like for the operator to operate the camera body, and an OSD (On-Screen Disp) that monitors the number of films and the flash emission state.
play) 15 and a strobe 12 for illuminating a subject. The lens 1, the diaphragm 2 and the CCD 3 mainly constitute image pickup means, the display section 8, the digital signal processing circuit 7 and the microcomputer 14 mainly constitute monitor means, and the camera operation section 17 mainly constitutes selection means.

Next, an outline of the operation of the digital still camera 100 of this configuration will be described with reference to FIG.
When the operator looks into the subject through a viewfinder (not shown) and presses the release button of the camera operation unit 17, the microcomputer 14
Detects the signal and drives the lens 1 and the diaphragm 2 with respect to the motor driver 11 to focus the image of the subject on the CCD 3. The strobe 12 is made to emit light if necessary. These series of operations are automatically performed by the microcomputer 14 based on information from a sensor (not shown). The image focused on the CCD 3 is sequentially taken out by the clock generated from the timing generator 13, and the noise included in the data is reduced by the CDS 4. Here, reset noise is dominant in the noise included in the output signal of the CCD. In order to reduce this noise, the reset noise is canceled by subtracting the video signal and the reset noise included in the signal period and the reset noise included only in the field through period. Then, the analog signal is A
The / D converter 5 converts the signal into a 10-bit digital signal, which is input to the digital signal processing circuit 7 and temporarily stored in the frame memory 6. Then, the data stored in the frame memory 6 is processed according to an instruction from the microcomputer 14 by the parameter stored in the EEPROM 16, and the processed image is stored in the frame memory 6 again. White balance processing is included in this processing. Further, the data written in the frame memory 6 is sent to the control unit of the display unit 8 and the contents are displayed on the LCD. The frame memory 6 is an image memory capable of accumulating image data of at least one screen of image pickup pixels, and is, for example, a VRAM (Video Random Access Memor).
y), SRAM (Static Random Access Memory), DRA
M (Dynamic Random Access Memory) or SDR
A commonly used memory such as AM (Synchronous DRAM) is used. Here, if the operator wishes to record the image on the memory card 10, the camera operating unit 17 gives an instruction, and the microcomputer 14 follows the instruction to the digital signal processing circuit 7 to display the image on the memory card. The control to transfer to 10 is executed. That is, the image-processed image is read from the frame memory 6 and sent to the image compression / expansion circuit 9. Here, JPEG (Joint Photogra
The image is compressed by the phic Experts Group) method and stored in the memory card 10. The encoding algorithm is ADC
Using T (adaptive discrete cosine), a low-resolution image is first encoded, and a hierarchical encoding in which the resolution is gradually increased is also adopted. As described above, the memory card compresses the data stored in the frame memory 6 and stores the compressed data. Other than this, for example, about 8MB internal memory or smart media
It may be configured to record on a compact flash (registered trademark) or the like. On the contrary, when displaying the contents of the memory card 10 on the display unit 8 or when connecting to another PC through an external terminal to transfer image data, insert a desired memory card into a connector (not shown) of the camera body. do it,
When instructed from the camera operation unit 17, the microcomputer 14 instructs the digital signal processing circuit 7 to read the compressed image data of the memory card, inputs it to the image compression / expansion circuit 9, and expands the data according to the compression algorithm. The image is returned to the original state and the image is displayed on the display unit 8.

FIG. 2 is a schematic block diagram of the face image recognition section according to the embodiment of the present invention. This configuration has an image memory 20 for storing one image of a subject, an image capturing unit 21 for capturing a predetermined unit from the memory into another memory or a register, a control unit 22 for controlling the overall control, and a plurality of units. A facial feature storage unit 24 for storing facial features, and a recognition / discrimination unit 23 for recognizing a face from the data from the image capturing unit 21 and the data from the facial feature storage unit 24 to discriminate each part.
And an edge detector 26 that detects an edge detection value from the result data, and an output unit 25 that outputs the final determination result to the outside. Here, the image memory 20 may use the frame memory 6 of FIG. Further, the other parts may be realized by the microcomputer 14 of FIG. 1 or may be realized by a dedicated LSI.
The recognition / discrimination unit 23 and the facial feature storage unit 24 mainly constitute the face image recognition unit and the face portion discrimination unit, and the edge detection unit mainly constitutes the edge detection unit. Next, before entering into the description of face image detection, an outline of a known face image recognition technique will be described. It should be noted that the face recognition in the present invention does not have to be a level that can be surely recognized as a face of an individual in the related art, and a recognition level of alternative between a subject as a face and another object other than that is sufficient. is there. The target items in face image recognition are roughly divided into the following two. 1) Identification of person: Identify who the target person is. 2) Facial expression identification: The facial expression of a person is identified. That is, 1) person identification is structure recognition of a face and can be said to be static identification. The facial expression identification in 2) is recognition of a change in the shape of the face, and can be said to be dynamic identification. In the case of the present invention, it can be said that the identification is simpler than the above. Further, there are 1) a two-dimensional method and 2) a three-dimensional method as methods for identifying these, and in computers, the 1) two-dimensional method is mainly used. The detailed contents of these are omitted here. In addition, FACS (Facial ACtion u
(nit system), which can be expressed using the positions of the feature points of facial expression components. From now on,
It is possible to apply these technologies to entry management systems, person image database systems, recognition communication systems, and the like.

FIG. 3 is an operation flowchart of the first embodiment of the present invention. Description will be made with reference to FIGS. 1 and 2. The image data of the subject is photoelectrically converted by the CCD shown in FIG. 1, subjected to image processing, and stored in the image memory 20. The image data is captured by the image capturing unit 21 in a predetermined unit (frame, byte) (S1).
Next, the image data is input to the recognition / discrimination unit 23, and the face is recognized and each portion of the face is discriminated from the data with the face characteristic storage unit 24 storing various face characteristic data stored in advance. This recognition method is performed based on various algorithms. The result is transmitted to the control unit 22 one by one, the face image is recognized (S2), and each part is discriminated from the data (S3). As a result, when the face image is recognized and each part is determined (YES route), the control unit 22 outputs a result signal to the output unit 25 and presses a release button (not shown) of the camera operation unit 17 (S4). When the face image is not detected in steps S2 and S3 or when each part is not determined (NO route), the control unit 22 outputs a result signal to the output unit 25 and returns to step S1 to recognize the face image.・ Continue the discrimination operation. As described above, the most common subject in the camera is a person. Therefore, when taking a picture of a person, it is important to take the picture without missing a photo opportunity. For that purpose, it is necessary to recognize that the subject is a person. The most suitable part for identifying a person is a face, and a face image is extracted from the subject, and a clear image is captured only after the parts such as eyes, mouth, nose, and eyebrows can be identified from the face image. be able to. In particular, digital cameras record image signals by digitizing them,
Easy to analyze by computer. As a result, operability is improved, and a clear image can be taken without missing a photo opportunity. Further, the face image is discriminated by capturing the contours of the face and features such as eyes, nose, eyebrows, and ears. And if you just want to determine that it is a face,
It can be identified by capturing the contour. However, in order to clearly capture the entire face, it is necessary to continue the discrimination operation until all the parts can be discriminated. This makes it possible to capture a clear image.

FIG. 4 is an operation flowchart of the second embodiment of the present invention. Description will be made with reference to FIGS. 1 and 2. The image data of the subject is photoelectrically converted by the CCD shown in FIG. 1, subjected to image processing, and stored in the image memory 20. The image data is captured by the image capturing unit 21 in a predetermined unit (frame, byte) (S1).
0). Next, the image data is input to the recognition / discrimination unit 23, and the face is recognized and each portion of the face is discriminated from the data with the face characteristic storage unit 24 storing various face characteristic data stored in advance. This recognition method is performed based on various algorithms. The result is transmitted to the control unit 22 one by one,
The face image is recognized (S11), and each part is discriminated from the data (S12). As a result, when the face image is recognized and each part is determined (YES route), the control unit 22 outputs a result signal to the output unit 25 and presses a release button (not shown) of the camera operation unit 17 (S13). Step S
If the face image is not detected in S11 or S12 or if each part is not determined (NO route), the control unit 22
Outputs a result signal to the output unit 25, returns to step S10, and continues the face image recognition / discrimination operation. Here, the storage capacity of the memory is finite. Further, the photographer selects a necessary image from the images recorded in the memory or deletes an unnecessary image. At this time, if an unclear image is recorded in the memory, the operation becomes complicated and the memory is wasted. As a result, the image signal is stored only when all the respective parts of the face image can be discriminated, so that the operability is improved and the memory is not wasted.

FIG. 5 is an operation flowchart of the third embodiment of the present invention. Description will be made with reference to FIGS. 1 and 2. The image data of the subject is photoelectrically converted by the CCD shown in FIG. 1, subjected to image processing, and stored in the image memory 20. The image data is captured by the image capturing unit 21 in a predetermined unit (frame, byte) (S1).
5). Next, the image data is input to the recognition / discrimination unit 23, and the face is recognized and each portion of the face is discriminated from the data with the face characteristic storage unit 24 storing various face characteristic data stored in advance. This recognition method is performed based on various algorithms. The result is transmitted to the control unit 22 one by one,
The face image is recognized (S16), and each part is discriminated from the data (S17). As a result, when the face image is recognized and each part is determined (YES route), the area is divided for each face part (S18), and the data is sent to the edge detection unit 26. The edge detection unit 26 detects an edge for each area (S19), determines whether the edge of the eye area is the edge threshold A or more (S20), and determines whether the edge of the nose area is the edge threshold B or more (S21). ), It is determined whether the edge of the mouth area is equal to or more than the edge threshold C (S22), and all are
If S, the control unit 22 outputs a result signal to the output unit 25 and presses a release button (not shown) of the camera operation unit 17 (S23). When it is less than the threshold value in steps S20, S21, and S22 (NO route), the process returns to step S15, and the face image recognition / discrimination operation and the edge detection operation are continued. As described above, the feature of each part of the face is characterized by the edge. Therefore, the edge of each part has a unique threshold value, and it can be determined by comparing the edge detection value from the edge detection unit 26 with this threshold value. As a result, the standby state is maintained until the edge detection value exceeds the threshold value or the operation of the edge detection unit 26 is continued, so that the image of each portion can be captured clearly. Further, in the above, the edge detection operation is continued until the edge detection value exceeds the threshold value, but in this case, it may take too long to detect. Therefore, the detection time and the threshold value may be set to have a range, and if the allowable range is exceeded, the image signal may be captured, or the release button may be pressed to capture an image.
As a result, when the edge detection value from the edge detection unit 26 exceeds the predetermined threshold for a predetermined period, the image signal is taken in or the release button is pressed, so that the operation time is shortened.

FIG. 6 is an operation flowchart of the fourth embodiment of the present invention. Description will be made with reference to FIGS. 1 and 2. The image data of the subject is photoelectrically converted by the CCD shown in FIG. 1, subjected to image processing, and stored in the image memory 20. The image data is captured by the image capturing unit 21 in a predetermined unit (frame, byte) (S3).
0). Next, the image data is input to the recognition / discrimination unit 23, and the face is recognized and each portion of the face is discriminated from the data with the face characteristic storage unit 24 storing various face characteristic data stored in advance. This recognition method is performed based on various algorithms. The result is transmitted to the control unit 22 one by one,
The face image is recognized (S31), and each part is discriminated from the data (S32). As a result, when the face image is recognized and each part is determined (YES route), the display unit 8 in FIG.
The LCD indicates that the image can be taken (S33). In the case of NO in step S31 or S32, it is determined whether or not a predetermined time has elapsed (S34), and when the time has elapsed (YES route), the LCD of the display unit 8 in FIG.
5). As described above, the photographer needs to recognize when the face image determination is completed. Therefore, it is preferable that the camera has a display means such as a liquid crystal. As a result, when the image capturing condition is satisfied, the fact is displayed on the display unit 8, so that it is possible to accurately capture the photo opportunity.
Operability is improved. Further, if the image capturing condition is not satisfied, the fact is displayed on the display unit 8, so that the photographer can quickly perform the next operation.

FIG. 7 is an operation flowchart of the fifth embodiment of the present invention. Description will be made with reference to FIGS. 1 and 2. The image data of the subject is photoelectrically converted by the CCD shown in FIG. 1, subjected to image processing, and stored in the image memory 20. The image data is captured by the image capturing unit 21 in a predetermined unit (frame, byte) (S4).
0). Next, the image data is input to the recognition / discrimination unit 23, and the face is recognized and each portion of the face is discriminated from the data with the face characteristic storage unit 24 storing various face characteristic data stored in advance. This recognition method is performed based on various algorithms. The result is transmitted to the control unit 22 one by one,
The face image is recognized (S41), and each part is discriminated from the data (S42). As a result, when the face image is recognized and each part is determined (YES route), the first alarm sound is emitted by the sounding device (not shown) of the camera operation unit 17 of FIG. 1 (S43). If NO in step S41 or S42, it is determined whether or not a predetermined time has elapsed (S44), and if it has elapsed (YES route), a second alarm sound is emitted by a sounding device (not shown) of the camera operation unit 17 of FIG. (S45). As described above, the photographer needs to recognize when the face image determination is completed. However, I do not always look at the display. Therefore, if it is determined by the sound, it becomes easier for the photographer to understand. As a result, when the image capturing condition is satisfied, the sound is emitted by the sound generator, so that the display is not overlooked and the operability is further improved. Further, when the image pickup device does not satisfy the image pickup condition after the lapse of a predetermined time, the sound is emitted by the sound generator, so that the photographer can quickly perform the next operation. Here, when only one type of alarm sound is emitted regardless of the content of the alarm, it is not possible to determine which alarm the alarm is. Therefore, it is more preferable to change the sound according to the content of the alarm.
Thereby, the content of the alarm can be discriminated and the operability is further improved.

In the above description, the photographer does not always photograph only the person, and there are persons who do not want to photograph. Therefore, if the photographer can select whether to press the release button automatically or manually, the operability of the photographer is further improved.

[0017]

As described above, according to the present invention, in claim 1, when all the respective portions of the face image can be discriminated by the face portion discriminating means, the release button for photographing the subject is pressed. Or the image capturing operation is performed,
Operability is improved, and you can shoot clear images without missing a photo opportunity. According to a second aspect of the present invention, when all the respective parts of the face image cannot be discriminated, the operation of the face part discriminating means is continued until all the respective parts of the face image can be discriminated. can do.
According to the third aspect, the image signal is stored only when all the respective parts of the face image can be discriminated, so that the operability is improved and the memory is not wasted. According to the fourth aspect of the invention, the edge detection value waits until it exceeds the threshold value or the operation of the edge detection means is continued, so that the image of each portion can be surely captured clearly. According to a fifth aspect of the present invention, when the edge detection value from the edge detecting means exceeds a predetermined threshold for a predetermined period, the image signal is captured or the release button is pressed, so that the operation time is shortened. Claim 6
When the image capturing condition is satisfied, the fact is displayed on the display unit, so that it is possible to accurately capture the photo opportunity and improve the operability. According to the seventh aspect, when the image capturing condition is not satisfied, the fact is displayed on the display means, so that the photographer can quickly proceed with the next operation. According to the eighth aspect, when the image capturing condition is satisfied, the alarm means emits a sound, so that the display is not overlooked and the operability is further improved. Claim 9
If the image pickup device does not satisfy the image pickup condition after a lapse of a predetermined time, the alarm means emits a sound, so that the photographer can quickly perform the next operation. According to the tenth aspect, the frequency of the sound or the melody is changed depending on whether or not the image pickup condition is satisfied by the image pickup device, so that the alarm content can be discriminated and the operability is further improved. According to the eleventh aspect, since the release button is manually pressed when the selection means selects whether or not to press the button, the operability of the photographer is further improved.

[Brief description of drawings]

FIG. 1 is a block diagram of a digital still camera according to an embodiment of the present invention.

FIG. 2 is a schematic block diagram of a face image recognition unit according to the embodiment of the present invention.

FIG. 3 is an operation flowchart of the first embodiment of the present invention.

FIG. 4 is an operation flowchart of the second embodiment of the present invention.

FIG. 5 is an operation flowchart of the third embodiment of the present invention.

FIG. 6 is an operation flowchart of the fourth embodiment of the present invention.

FIG. 7 is an operation flowchart of the fifth embodiment of the present invention.

[Explanation of symbols]

20 image memory, 21 image capturing unit, 22 control unit, 23 recognition / determination unit, 24 face feature storage unit, 25
Output unit, 26 Edge detection unit

─────────────────────────────────────────────────── ─── Continued Front Page (51) Int.Cl. ⁷ Identification Code FI Theme Coat (Reference) // H04N 101: 00 H04N 101: 00 F Term (Reference) 2H054 AA01 2H102 AA71 BB08 BB33 5B057 AA20 BA02 BA19 BA26 DA08 DB02 DB06 DB09 DC16 DC36 5C022 AA13 AB55 AC31 AC42 AC52 AC69 5L096 AA02 AA06 BA08 CA02 FA06 GA19 JA16

Claims (11)

[Claims] 1. An image pickup apparatus having an image pickup means for converting an optical signal obtained through an optical system into an image signal and outputting the image signal, comprising: a face image recognition means for recognizing a face image from the image signal; A face part discriminating means for discriminating each part of the face image from the data of the face image recognizing means is further provided, and when each part of the face image can be discriminated by the face part discriminating means, photographing of a subject is executed. An image pickup apparatus, wherein a release button is pressed or an image pickup operation is performed. 2. When the face portion discriminating means cannot discriminate all the respective portions of the face image, the operation of the face portion discriminating means is continued until all the portions of the face image can be discriminated. The image pickup apparatus according to claim 1, wherein: 3. The image signal is continuously stored, and the image signal is stored only when all the respective portions of the face image can be discriminated by the face portion discriminating means. 2. The imaging device according to 2. 4. The face portion discriminating means has edge detecting means for detecting a feature point of an edge for each portion of the face image, and when an edge detection value from the edge detecting means is smaller than a predetermined threshold value, The image pickup apparatus according to claim 1, wherein the edge detection value is on standby or the operation of the edge detection unit is continued until the edge detection value exceeds the threshold value. 5. The image signal is captured when the edge detection unit repeatedly operates while continuously capturing the image signal and the edge detection value from the edge detection unit exceeds a predetermined threshold for a predetermined period. 3. The image pickup device according to claim 1, wherein the release button is pressed. 6. The image pickup device further comprises display means for displaying data contents, and when the image pickup condition of the image pickup device is satisfied, a message to that effect is displayed on the display means. 5. The imaging device according to item 5. 7. The display means displays a message to that effect on the display means when the image pickup device does not satisfy the image pickup condition after a predetermined time has elapsed.
The image pickup device according to any one of claims 1 to 5. 8. The image pickup device further comprises alarm means for emitting a sound, and when the image pickup condition of the image pickup device is satisfied,
The image pickup apparatus according to claim 1, wherein the alarm means emits a sound. 9. The alarm means emits a sound by the alarm means when the image capturing device does not satisfy a condition for capturing an image after a predetermined time elapses.
5. The imaging device according to item 5. 10. The sound of the alarm means changes the frequency or melody of the sound depending on whether or not the image pickup condition of the image pickup device is satisfied. Imaging device. 11. The release button further comprises selection means for selecting whether or not to press the release button even when the face portion determination means detects a face image, and the selection means selects whether or not the release button is pressed. The image pickup apparatus according to claim 1, wherein the release button is manually pressed when pressed.