JP4364466B2 - Imaging device - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an image pickup apparatus, and more particularly to an image pickup unit that converts an optical signal from a subject into an image signal that is an electrical signal via an optical system and outputs the image signal. The present invention relates to an imaging apparatus in which an image is cut out and saved in a file.
[0002]
[Prior art]
In recent years, 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 to eliminate shooting failures There are many. In general, the subject is often a person, and there is no digital camera specially equipped with a person-specific setting mode. In Japanese Patent Laid-Open No. 10-334213, a face image of a target person image is automatically recognized from color image data including a person image without being affected by the shooting background and illuminance, and an area corresponding to the size of the face image is defined. A technique for cutting out is disclosed. According to this, an image acquisition CPU for acquiring a color image including a human image, a color liquid crystal display unit for displaying the acquired color image and the like, and a plurality of faces for recognizing a human facial image from the color image. A face recognition color memory in which recognition color data is stored in advance, a recognition instruction unit for instructing a face image recognition process, and an instruction for the image recognition process, and the color data of the entire area of the color image and the face recognition color data are A face image recognition CPU that recognizes, as a face image, an area of color data that matches and matches one of the face recognition color data, an area instruction unit that indicates a cut-out area of the recognized face image, and an instruction for the cut-out area And a frame creation CPU that creates a frame of an area according to the size of the face image, and a face image cut-out CPU that cuts out a face image of the area surrounded by the frame.
[0003]
[Problems to be solved by the invention]
Conventionally, when taking a photograph or the like, there has been a problem that the face of the photographed image approaches or tilts to the left or right or up and down. In addition, when tilted, it is troublesome for a person to manually specify a cutout position or specify a face position by looking at an image.
Japanese Patent Laid-Open No. 10-334213 discloses a region corresponding to the size of the face image by automatically recognizing the face image of the target person image from color image data including the person image without being affected by the photographing background and illuminance. This is a technique for cutting out images, and it is not considered to correct the balance of the size to be cut out or the inclination of the image.
In view of such a problem, the present invention provides an imaging device capable of automatically cutting out a face image whose size and inclination are corrected by recognizing and discriminating the face image and saving it as another image file. Objective.
[0004]
[Means for Solving the Problems]
In order to solve this problem, the present invention provides an image pickup apparatus having an image pickup means for converting an optical signal relating to a subject obtained through an optical system into an image signal and outputting image data. A face image recognizing unit for recognizing a face image from the image data of the subject, a face part determining unit for determining each part of the face image from the face image recognized by the face image recognizing unit, and the face part When the face image is recognized by the face image recognizing means and the face image extracting means for extracting the image data of the face image from the image data of the subject based on each part of the face image determined by the determining means A subject image file corresponding to the image data of the subject, and a face image file corresponding to the image data of the face image cut out by the face image cutting means. And means, the face image cut-out unit is collimated perpendicular direction of the face portion image frame straight line cut connecting the center points of each part of the face image is determined by the determining means, and the right and left The size of the face on the face image from which the left and right and top and bottom margins are extracted in the image data of the face image to be cut out by making the upper and lower margins equal to each other so that the lower margin is larger than the upper margin. The image data of the face image is cut out so as to be a constant ratio with respect to the height . The subject of the certificate photo is a person. Therefore, when photographing a person, it is important to photograph without missing a photo opportunity. Then, the image data of the photographed subject is stored in a file. In particular, since a digital camera digitizes and records an image signal, analysis by a computer is easy. According to this invention, when the face image is recognized from the image data of the subject by the face image recognition means, the face image extraction means cuts out the image data of the face image from the image data of the subject and corresponds to the subject image data. Since it is recorded as a face image file corresponding to the image data of a face image different from the image file, a certificate photograph can be created even when the face is at the edge of the image . Each part (each part of the face image) is arranged almost in contrast to the center line of the face. Therefore, if the image data of the face image is cut out so that the straight line connecting the center points of the parts is parallel to the vertical direction of the image frame to be cut out, the face can be cut out without being inclined. According to this technical means, the image data of the face image is cut out so that the straight line connecting the center points of the determined portions of the face image is parallel to the vertical direction of the image frame to be cut out. Can be cut out. The most important points of a certificate photograph are high image quality and good balance between the background of the image plane and the face. The balance is determined by the ratio of the left, right, top and bottom margins and the face in the image data of the face image to be cut out. The left and right margins are the same, and the upper and lower margins are larger than the upper margin. This is because the bottom has a neck and chest. According to such technical means, the left and right and upper and lower margins in the image data of the face image to be cut out are a fixed ratio with respect to the size of the face on the face image to be cut out. Can do.
[0005]
Further, the invention of claim 2, wherein the recording means, wherein said object image file and said face image file, configured to associate with record. When filing the cut face image and the original image, it is preferable that the face image is associated with the original face image. For example, there is a method of changing the format or extension by making the file name the same. According to this technical means, the subject image file and the face image file are recorded in association with each other, so that the original data and the extracted face data can be easily organized. Further, the invention of claim 3 is configured to fill a portion of the face image other than the face on the face image and the body part integrated with the face with a predetermined color with respect to the image data of the cut face image. It is characterized by that. The feature of the certificate photo is that the background is filled with a certain color. This is because it makes the person stand out more. However, when creating a certificate photo from a general photo, some background is often taken. Therefore, an operation for painting the background with a predetermined color is required. The face image referred to here also refers to a body part that is integrated with the face. According to such technical means, since the portion other than the cut out face image is painted with a predetermined color, it is possible to make the person stand out more.
[0006]
According to a fourth aspect of the present invention, there is provided display means for displaying the contents of image data, and the display means defines a face image area to be cut out when the face image cutout means cuts out the image data of the face image. It is configured to display with a frame. Here, the face image area refers to the face image and its background. When there is a display means, the most clearly recognizable method is that the image area to be cut out can be visually observed. Therefore, it is preferable to display the face image area to be cut out with a frame. According to this technical means, when the image data of the face image is cut out, the face image area to be cut out is displayed with a frame, so that the cut out area can be clearly recognized and the operability is improved. Further, the invention of claim 5 is provided with selection means for selecting recording or erasing of an image, and the selection means is configured to be able to select recording or erasing of an image displayed by the display means. And The captured image or the cut-out image is not all necessary images. It is preferable in terms of operability if these images can be observed by the display means and recording or erasing can be selected at that time. According to such technical means, since the face image displayed by the display means can be selected to record or erase the image by the selection means, it is possible to improve the operability and effectively use the memory. Further, the invention of claim 6 is characterized in that the face image is not recorded when the area of the face occupied in the face image displayed by the display means is smaller than a predetermined area. As described above, the most important points of the certificate photograph are high image quality and a good balance between the background of the image surface and the face. In particular, one index for determining the quality of image quality is the area of the face. In other words, the larger the area, the better the image quality. According to such a technical means, when the area of the face occupied in the face image displayed by the display means is smaller than a predetermined area, the face image is not recorded, so that useless use of the memory can be prevented and the quality is poor. You can prevent taking a photo for the certificate. The invention of claim 7 is characterized in that the area of the face is determined by the total number of pixels occupied by the area. The pixel density per unit area of a CCD that photoelectrically converts an image is constant. Therefore, the larger the area, the larger the total number of pixels. That is, the area and the image quality are in a proportional relationship. According to this technical means, the area of the face is determined by the sum of the number of pixels occupied by the area, so that the image quality can be accurately determined with simple control. The invention according to claim 8 is characterized in that the face part determining means is configured to determine each part of the mouth, nose and eyes from the face image recognized by the face image recognizing means. The best part to identify a person is the face, and a face image is extracted from the subject, and a clear image must be taken only after each part (part) such as eyes, mouth, and nose can be identified from the face image. Can do. Also, by cutting out the image data of the face image using the center points of each part such as the identified eyes, mouth, and nose, the face can be cut out without tilting.
[0007]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, the present invention will be described in detail with reference to embodiments shown in the drawings. However, the components, types, combinations, shapes, relative arrangements, and the like described in this embodiment are merely illustrative examples and not intended to limit the scope of the present invention only unless otherwise specified. .
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 that collects an optical image of a subject, a diaphragm unit 2 that focuses a light beam collected by the lens 1, and a plurality of lenses (not shown) are moved and focused, or the diaphragm unit 2 is A motor driver 11 to be driven, a CCD (Charge Coupled Device) 3 that photoelectrically converts an optical image that has passed through the lens 1 and the diaphragm 2, and a CDS (Correlated Double Sampling) 4 that reduces noise contained in the CCD 3. An A / D converter 5 that converts an analog signal from the CCD 3 into a digital signal, a timing generator 13 that generates the timing of the CCD 3, the CDS 4, and the A / D converter 5, and image processing according to image processing parameters. Imaging by a digital signal processing circuit 7 to be performed, a frame memory 6 for storing a recorded image of an imaging pixel and an image processed image, and a liquid crystal display (LCD) A display unit 8 for displaying an image, an image compression / expansion circuit 9 for compressing or expanding image data processed by the digital signal processing circuit 7 into source image data, and image data compressed by the image compression / expansion circuit 9 are stored. A memory card 10, a microcomputer (hereinafter referred to as a microcomputer) 14 that executes predetermined control based on a control program, an EEPROM (Electrically Erasable and Programmable Read Only Memory) 16 that stores parameters, and an operator who operates the camera body The camera operation unit 17 includes a release button for operating the camera, an OSD (On-Screen Display) 15 that monitors the number of films and the light emission state of the strobe, and a strobe 12 that illuminates the subject. The lens 1, the diaphragm 2, and the CCD 3 mainly constitute image capturing means, the display unit 8, the digital signal processing circuit 7 and the microcomputer 14 mainly constitute display means, and the camera operation unit 17 mainly constitutes selection means.
[0008]
Next, an outline of the operation of the digital still camera 100 having this configuration will be described with reference to FIG. When the operator looks into the subject from a finder (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 to the motor driver 11 to thereby image the subject. Is focused on the CCD 3. If necessary, the strobe 12 is caused to emit light. A series of these operations is automatically performed by the microcomputer 14 based on sensor information (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 contained in the data is reduced by the CDS 4. Here, the 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 both from the video signal included in the signal period, the reset noise, and the reset noise included only in the field-through period. The analog signal is converted into a 10-bit digital signal by the A / D converter 5, input to the digital signal processing circuit 7, and temporarily stored in the frame memory 6. Then, data temporarily stored in the frame memory 6 is processed according to an instruction from the microcomputer 14 according to the parameters stored in the EEPROM 16, and the processed image is stored in the frame memory 6 again. This processing includes white balance processing. Further, the data written in the frame memory 6 is sent to the control unit of the display unit 8, and the content is displayed on the LCD.
The frame memory 6 is an image memory that can store image data of at least one screen of image pickup pixels. For example, a video random access memory (VRAM), a static random access memory (SRAM), a dynamic random access memory (DRAM). ) Or a commonly used memory such as SDRAM (Synchronous DRAM).
[0009]
Here, if the operator wants to record the image on the memory card 10 by the operator's intention, the microcomputer 14 instructs the digital signal processing circuit 7 to send the image to the memory card 10 in response to an instruction from the camera operation unit 17. 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, the image is compressed by the JPEG (Joint Photographic Experts Group) method and stored in the memory card 10. As this encoding algorithm, ADCT (adaptive discrete cosine) is used, and hierarchical encoding in which an image having a low resolution is first encoded and gradually becomes higher is also adopted. Thus, the memory card is for compressing the data stored in the frame memory 6 and storing the compressed data. In addition to this, for example, it may be configured to record in an internal memory of about 8 MB or a smart media / compact flash.
Conversely, when displaying the contents of the memory card 10 on the display unit 8 or when transferring image data by connecting to another PC via an external terminal, the desired memory card is inserted into a connector (not shown) of the camera body. Then, when instructed from the camera operation unit 17, the microcomputer 14 instructs the digital signal processing circuit 7 to read out the compressed image data of the memory card, inputs it to the image compression / decompression circuit 9, and inputs the data according to the compression algorithm. The image is expanded and restored, and an image is displayed on the display unit 8.
[0010]
FIG. 6 is a schematic block diagram of the face image cutout unit according to the embodiment of the present invention. This configuration includes an image memory 20 that stores one image of a subject, an image capturing unit 21 that captures a predetermined unit from the memory into another memory or a register, a control unit 22 that controls the whole, and a plurality of A face feature storage unit 24 that stores facial features, a recognition / discrimination unit 23 that recognizes a face from the data from the image capture unit 21 and the data from the face feature storage unit 24 and discriminates each part, and the result data Are comprised of a face image cutout unit 26 that cuts out a predetermined face image and an output unit 25 that outputs a final determination result to the outside. Here, the image memory 20 may use the frame memory 6 of FIG. Further, other parts may be realized by the microcomputer 14 of FIG. 1 or may be realized by a dedicated LSI. The recognition / determination unit 23 and the face feature storage unit 24 mainly constitute a face image recognition unit and a face part determination unit.
[0011]
Next, before describing the detection of a face image, an outline of a known face image recognition technique will be described. Note that the face recognition in the present invention does not have to be a level at which it can be reliably recognized as a conventional individual face, and a two-way recognition level of whether the subject is a face or another object is sufficient. is there. The target items in face image recognition are roughly divided into the following two.
1) Person identification: Identify who the target person is.
2) Facial expression identification: what kind of facial expression a person has is identified.
That is, the person identification of 1) is a face structure recognition and can be said to be a static identification. Also, facial expression identification in 2) is recognition of face shape change 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, these identification methods include 1) a two-dimensional method and 2) a three-dimensional method, and 1) a two-dimensional method is mainly used in a computer. These detailed contents are omitted here. Further, as a facial expression identification method, there is a concept based on FACS (Facial ACtion unit System), which can be expressed using the position of the feature point of the facial expression component.
In the future, it is possible to apply these technologies to room entry management systems, person image database systems, recognition communication systems, and the like.
[0012]
FIG. 2 is an operation flowchart of the embodiment of the present invention. This will be described with reference to FIGS. The subject image data 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 recognition and the discrimination of each part of the face are performed from the data with the face feature storage unit 24 storing various face feature 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 (eyes, nose, mouth) is determined from the data (S3). As a result, when the face image is recognized and each part is discriminated (YES route), the following description is divided for each embodiment. FIG. 3 is a face image for explaining the first embodiment of the present invention. First, the face image recognition means recognizes the face image 1 from the image data of the subject. The face part determination means determines each part of the face image 1 from the face image 1 recognized by the face image recognition means. Then, the face image cutout means (face image cutout unit 26) cuts out the image data of the face image 1 from the image data of the subject based on each part of the face image 1 determined by the face portion determination means. When the face image 1 is recognized by the face image recognition unit, the recording unit stores the subject image file corresponding to the image data of the subject and the face image corresponding to the image data of the face image 1 cut out by the face image cutout unit. Create and record files. More specifically, the face image cutout unit 26 and the control unit 22 divide the area of the face image 1 into parts. That is, it is divided into three parts, that is, a mouth part 3, a nose part 4, and an eye part 5 (S4). Next, the center A of the mouth, the center B of the nose, and the center C of the eye are determined (S5), and the straight line 2 closest to the points A, B, and C3 is determined (S6). Here, the straight line 2 is cut out so as to be parallel to the vertical direction of the frame 14 of the cut out image. As described above, the most suitable part for specifying the person is the face, and the face image 1 is extracted from the subject, and the parts such as the mouth 3, the nose 4 and the eyes 5 can be identified from the face image 1. You can shoot clear images for the first time. Each part is arranged almost in contrast to the center line 2 of the face. Therefore, if the image data of the face image 1 is cut out so that the straight line 2 connecting the center points A, B, and C of each part is parallel to the vertical direction of the frame 14 of the face image 1 to be cut out, the face is not inclined. Can be cut out.
[0013]
FIG. 4 and FIG. 5 are face image diagrams for explaining the second embodiment of the present invention. 4, the left and right margins 8 and 9 are determined from the size of the face on the face image 1 to be cut out, and the verticality of the cut out frames 6 and 7 is determined (S7). Next, the upper and lower margins 10 and 11 are determined from the size of the face on the face image 1 with reference to FIG. 5, and the horizontal positions of the cutout frames 12 and 13 are determined (S8). Next, the face image 1 is cut out along the cutout frames 6, 13, 7, and 12 determined in steps 7 and 8 (S9). As described above, the most important points of the certificate photograph are high image quality and a good balance between the background of the image surface and the face. The balance is determined by the ratio of the left and right margins and the face in the image data of the face image 1 to be cut out. In general, the left and right margins 8 and 9 are made equal, and the upper and lower margins 10 and 11 make the lower margin 11 larger than the upper margin 10. This is because the bottom has a neck and chest. As described above, since the left and right and upper and lower margins of the image data of the face image 1 to be cut out are a fixed ratio with respect to the size of the face on the face image 1 to be cut out, a well-balanced photo can be produced. .
[0014]
Next, as a third embodiment of the present invention, a clipped face image file is created (S10), and an original image (captured image) file is created (S11). When filing the cut face image and its original image, it is more convenient later to associate them. For example, if the original image is Rimg0001. jpg, the face image is set to Rimg0001. Like tif, there is a method of changing the format or extension with the same file name. In addition, the image file name is composed of 8 characters, the upper 4 characters are arbitrary alphabets or numbers, and the lower 4 characters are numbers. Alternatively, there is a method in which the upper 4 characters of the original image and the face image are different and the lower 4 characters are set to the same value (original image: Rimg0001.jpg, face image Rpic0001.jpg). As a result, the original image (subject image file) and the face image (face image file) are recorded as a file based on the above-described predetermined relationship, so that the original data and the extracted face data can be easily organized. Become. Further, as a fourth embodiment of the present invention, a feature of the certificate photograph is that the background is filled with a specific color. This is because the person stands out even more by doing this. However, when creating a certificate photo from a general photo, some background is often taken. Therefore, an operation for painting the background with a predetermined color is required. The face image referred to here also refers to a body part that is integrated with the face. Here, as a fifth embodiment of the present invention, if such an image area to be cut out on the display unit 8 is visible, can be recognized region of the face image 1 to cut out most clearly. Therefore, it is preferable to display the area of the face image 1 to be cut out with a frame. This can clearly recognize the region of the face image 1 to cut out, thereby improving the operability. Further, as a sixth embodiment of the present invention, captured images or the clipped image are not all necessary images. It is preferable in terms of operability if these images are observed by the display unit 8 and recording or erasing can be selected at that time. Thereby, the operability can be improved and the memory can be used effectively.
[0015]
As described above, as the seventh embodiment of the present invention, the most important points of the certificate photograph are that the image quality is high and the background of the image plane and the face are well balanced. It is. In particular, one index for determining the quality of image quality is the area of the face. In other words, the larger the area, the better the image quality. That is, the pixel density per unit area of the CCD that photoelectrically converts the image is constant. Therefore, the larger the area, the larger the total number of pixels. That is, it can be said that the area and the image quality are in a proportional relationship. For this reason, the area of the face is determined by the total number of pixels that the area occupies, so that the image quality can be accurately determined with simple control. Further, when the area of the face occupied by the face image displayed by the display unit 8 is smaller than a predetermined area , the face image is not recorded, so that useless use of the memory can be prevented and a certificate photo with poor quality is taken. You can prevent it.
[0016]
【The invention's effect】
As described above, according to the present invention, in the first aspect, when the face image is recognized from the image data of the subject by the face image recognizing unit, the face image extracting unit extracts the image data of the face image from the image data of the subject. Because it is recorded as a face image file corresponding to the image data of the face image different from the subject image file corresponding to the image data of the subject, even if the face is at the edge of the image, a certificate photo is created can do. In addition, since the image data of the face image is cut out so that the straight line connecting the approximate center points of each part of the face is parallel to the vertical direction of the image frame to be cut out, the face can be cut out without being inclined. In addition, the image data of the face image is cut out so that the left, right, top and bottom margins in the image data of the face image to be cut out are a fixed ratio with respect to the size of the face on the face image to be cut out. Also, since the left and right margins are equal and the bottom has a neck and chest, the top and bottom margins are larger than the top margin, so that a well-balanced photo can be produced. According to the second aspect , the subject image file (original data) and the face image file (face data) are recorded in association with each other, so that the original data and the extracted face data can be easily organized. According to the third aspect , the face other than the face on the cut face image and the body part integrated with the face is painted in a predetermined color, so that the person can be more prominent. According to the fourth aspect , when the image data of the face image is cut out, the face image area to be cut out is displayed with a frame, so that the cut out area can be clearly recognized and the operability is improved. According to the fifth aspect , since the face image displayed by the display unit can be selected to record or delete the image by the selection unit, the operability can be improved and the memory can be used effectively. According to the sixth aspect of the present invention, since the face image is not recorded when the area of the face in the face image displayed by the display means is smaller than the predetermined area, useless use of the memory can be prevented, and the certificate photograph with poor quality can be prevented. You can prevent shooting. According to the seventh aspect of the present invention, since the area of the face is determined by the total number of pixels occupied by the area, the image quality can be accurately determined by simple control. The invention according to claim 8 is characterized in that the face part determining means is configured to determine each part of the mouth, nose and eyes from the face image recognized by the face image recognizing means. The best part to identify a person is the face, and a face image is extracted from the subject, and a clear image is taken only after each part (part) such as eyes, mouth, and nose can be identified from the face image. Can do. Also, by cutting out the image data of the face image using the approximate center point of each part such as the identified eye, mouth, nose, etc., the face can be cut out without tilting.
[Brief description of the drawings]
FIG. 1 is a block diagram of a digital still camera according to an embodiment of the present invention.
FIG. 2 is a flowchart for explaining an embodiment of the present invention.
FIG. 3 is a face image (part 1) for explaining the first embodiment of the present invention;
FIG. 4 is a face image (No. 2) for describing a second embodiment of the present invention;
FIG. 5 is a face image for explaining a second embodiment of the present invention.
FIG. 6 is a schematic block diagram of a face image cutout unit according to the embodiment of the present invention.
[Explanation of symbols]
20 image memory, 21 image capture unit, 22 control unit, 23 recognition / discrimination unit, 24 face feature storage unit, 25 output unit, 26 face image cutout unit

Claims (8)

In an imaging apparatus having an image imaging means for converting an optical signal relating to a subject obtained through an optical system into an image signal and outputting image data,
Face image recognition means for recognizing a face image from the image data of the subject;
Face part discrimination means for discriminating each part of the face image from the face image recognized by the face image recognition means;
Face image cutout means for cutting out the image data of the face image from the image data of the subject based on each part of the face image determined by the face portion determination means;
When the face image is recognized by the face image recognition unit, a subject image file corresponding to the image data of the subject, and a face image file corresponding to the image data of the face image cut out by the face image cutout unit the creation and recording means for recording,
The face image cutting means is
A straight line connecting the center points of each part of the face image determined by the face part determining means is parallel to the vertical direction of the image frame to be cut out, and
The left and right margins are equal, and the upper and lower margins are set so that the lower margin is larger than the upper margin, whereby the left and right and upper and lower margins in the image data of the face image to be cut out are on the face image to be cut out. To be a certain percentage of the face size,
An image pickup apparatus configured to cut out image data of the face image . The recording means, the subject image file and with said face image file, association with the imaging apparatus according to claim 1, characterized in that it is configured to record. The image data of the extracted face image, the face and said pigment and a portion other than the body portion to be integral on the face image, or claim 1, characterized in that it is configured to fill a predetermined color 2. The imaging device according to 2 . A display means for displaying the contents of the image data is provided,
The display means, the face image by cut-out means when cutting out the image data of the face image, the image pickup apparatus to 3 according claims 1, characterized in that the area of the facial image is configured to display a frame cutting . A selection means for selecting whether to record or erase the image;
5. The imaging apparatus according to claim 4 , wherein the selection unit is configured to be able to select recording or erasing of the image displayed by the display unit. 6. The imaging apparatus according to claim 5 , wherein the face image is not recorded when an area of the face occupied in the face image displayed by the display unit is smaller than a predetermined area. The imaging apparatus according to claim 6 , wherein the area of the face is determined by a total number of pixels occupied by the area. It said face portion discrimination means, from said recognized face image by the face image recognizer, mouth, nose, claims 1, characterized in that it is configured to determine the parts of the eye 7 any one of The imaging device described in 1.

Images