JPH06282630A - Video id photo system - Google Patents

Abstract

PURPOSE:To suppress the data capacity of face picture data and to facilitate an operation as a personal information data base including face pictures even for a portable personal computer by reducing and binarizing only the face pictures. CONSTITUTION:A skin color area centroid position coordinate calculation part 202 obtains the picture area of a color considered as a skin color detected in a skin color detection part 201 and calculates the centroid position coordinates of the area. A background part identification reference color calculation part 203 calculates a reference color for discriminating the face pictures and background part pictures and a write starting coordinate calculation part 204 calculates write starting coordinates for displaying the reduced and binarized face pictures in a portable ID photo system. A face picture binarization processing part 207 binarizes the face pictures luminance-converted in a face picture luminance conversion part 206 and a face picture transfer part 208 for the portable ID photo system transfers the face pictures to the portable ID photo system. Since only the face pictures are reduced and binarized, the data capacity of the face picture data can be reduced.

Description

Detailed Description of the Invention

[0001]

FIELD OF THE INVENTION This invention relates to a video ID photo system for making ID cards.

[0002]

2. Description of the Related Art Image information has a large amount of information as compared with character and numerical information, so that there are many restrictions on the storage capacity, processing time, etc., and therefore its use is limited. . However, in recent years, such restrictions have been removed with the progress and development of image information devices.

By the way, one of the fields in which an image plays an important role is an ID (identification) field. Particularly in the field of personal identification, the importance of facial photographs has long been recognized, and there is a history of using them for ID purposes such as silver lead photographs and instant photographs.

However, in the information of such printing paper,
The information exists only in the print itself, and it cannot be converted into an electronic file, processed, or duplicated, and its application is extremely limited.

In order to eliminate such a problem, it is known to convert facial photograph information into an electric signal and handle it. For example, FIG. 11 is cited from Japanese Patent Laid-Open No. 63-316275.

FIG. 1 shows an ID card producing device,
In this device, the subject 1 is imaged by the color TV camera 2,
The image signal thus obtained is converted into a digital multi-gradation signal by the A / D conversion circuit 3 and temporarily recorded in the frame memory 4.

Reference numeral 5 denotes an image signal processing circuit, which performs calculations for removing color turbidity due to an incorrect spectral absorption element of a color material applied to a full-color video printer. 6 is a controller for controlling the operation of the entire apparatus, 7 is an input keyboard, and 8 is a full-color video printer unit.

The keyboard 7 is operated, whereby the controller 6 generates a graphic image or a character image, which is combined and edited with the person image of the subject 1 stored in the frame memory 4 to create a screen of an ID card. After being converted into a TV image signal, it is displayed on a CRT and converted into an optical image, which is imaged on a color photographic paper by an optical system and exposed. Then, the exposed printing paper is developed and printed out.

According to this system, a subject image can be processed, edited and printed together with character information and the like, and necessary information including the subject image can be printed on one card to form an ID card.

By the way, in another example of using a face photograph,
There is a database for managing the information of members who belong to organizations such as companies and schools. As an example of such a database system, the one shown in FIG. 12 is known.

According to this device, an image signal obtained from a video image pickup device 10 such as a still video recording player, a video camera, a still video camera or a video presentation camera is taken in through an image processor 11 and displayed on a monitor 12. Also, it can be recorded in the data file 13 for later retrieval and display, or can be printed out by the video printer 14. As described above, in order to obtain an ID image, each person is photographed by using a color video camera, a still video camera or the like, and is recorded and stored as a face image database. At that time, the ID number is keyed in at the same time as the person is photographed, and the ID number is recorded as the image data file name.

In addition, for printing for an ID card, card ground image data is transferred to a frame memory in advance, and 1
By entering the ID number for each person,
The face image data of each person having the file name of the number is read from the face image database and transferred so as to be applied to the predetermined face image portion of the ID card to create an image of one face image-containing ID card. After that, the data in the frame memory is converted into a video signal, transferred to a video printer, and printed out.

In recent years, two types of personal computers, a desktop type and a laptop type, are mainly used. Recently, however, a combination of the above-mentioned two types has come out, and it is possible to carry it with one system. Mobile operation is becoming possible. As an example of this, "MAC POWER" issued by ASCII Corporation.
R "'93 February issue, pp. 153-159.

[0014]

In the conventional video ID photo system described above, the face image is used as a personnel information database in addition to printing the face image for the ID card. Even if the face image is compressed due to the full-color image data, if the number of people increases from several thousand to 10,000, it must be stored in a large capacity hard disk or magneto-optical disk.

However, since the personnel information data is used very frequently, the system itself is too large to move and use the system device everywhere, and therefore the mobile operation is very impossible.

Therefore, the development of a portable video ID photo system is desired, and a system such as a notebook type personal computer can be considered as an example of this. A liquid crystal display is used for the image display portion, and a face image is also included. Face images are difficult to display to display personnel information.

Therefore, it is necessary to binarize the face image, etc. However, it takes time for the calculation process to perform the conversion process by software in the system, and it is difficult to use as a system. That said, it is sufficient to increase the processing capacity at a workstation or the like, but that would cost too much for the system itself. Further, even if only the personnel information data is used, it is very difficult to use it without a face image for searching or searching.

According to the present invention, the data volume of face image data is small, and it becomes easy to operate as a personnel information database including face images even on a portable personal computer such as a notebook personal computer, and from a portable ID photo system. It is an object of the present invention to provide a video ID photo system in which operations such as issuing an ID card and searching / registering / deleting personnel information can be easily performed.

[0019]

In order to achieve the above object, the invention corresponding to claim 1 is a face image photographing means for photographing a face image and converting it into image data, and a memory for storing the image data. Means, calculating means for calculating the barycentric position coordinates in the skin color region of the face portion based on the image data stored in the storage means, and identification reference color data for distinguishing the face image from the background portion, and the barycentric position The face image data is read out from the coordinates, only the face image is reduced, and the processing means for performing the binarization processing and the data of this processing means are transferred to the portable ID photo system having the display means, and the personnel image including the face image is transferred. A video ID photo system including means for displaying information on the display means.

[0020]

According to the first aspect of the invention, the barycentric position coordinates in the skin color region of the face part and the identification reference color data for distinguishing the face image from the background part are calculated, and the face image is calculated from the barycentric position coordinates. Read data and reduce only face image
Since the data was digitized and transferred to the mobile ID photo system for display, the face image data capacity was small, and it was used as a personnel information database including face images even on laptops and other portable computers. Is easy to operate, and I from the portable ID photo system
Operations such as issuing a D card and searching / registering / deleting personnel information can be done easily.

[0021]

Embodiments of the present invention will be described below with reference to the drawings.

First, an example of the overall configuration of an apparatus to which the present invention is applied will be described with reference to FIG. In FIG. 1, 101 is a color TV camera (color video camera), 102 is an analog / digital converter (A / D converter), 103 is a frame memory, 104 is a digital / analog converter (D / A converter), 105 is an image display unit,
106 is an image database that is a face image database,
Reference numeral 107 is a character database, and 108 is a card image memory with format data. A processor 109 has a controller 109a, an image processing unit 109b, a search processing unit 109c, a list processing unit 109d, and a layout processing unit 109e. 110 is a display conversion unit, 111 is a character display unit, 112 is a keyboard, 114 is a binary image memory, and 115 is a video printer.

Reference numeral 116 denotes a face image which is reduced in size and binarized, and then the portable I
A face image processing transfer unit 117 for a mobile ID photo system for transferring to the D photo system is a mobile ID photo system.

Of these, the color video camera 101
Is for obtaining the image signal by photographing the upper half of the person, and the A / D converter 102 outputs the analog signal RGB of the image which is the output signal from the color video camera 101.
Is converted into a digital signal.

The frame memory 103 is for temporarily storing the signal data output from the A / D converter 102 as a frame image. The D / A converter 104 is
It is for converting a digital signal output from the frame memory 103 into an analog video signal and outputting the analog video signal.

The image display unit 105 uses a TV monitor, a color liquid crystal display or the like, and uses the D / A converter 1.
The output signal of 04 is converted into, for example, an NTSC signal, which is for visualizing and displaying as an image.

The image database memory 106 is capable of recording face image data of a person recorded in the frame memory 103, storing it as an image database, and reading it. The character database 107 holds, as a data file, character data such as an ID number, name, affiliation name, job title, gender, date of birth, date of employment. The card image data memory with format data 108 is for holding image data as a base image of the ID card.

The processor 109 plays a central role in controlling the apparatus of this embodiment, and controls the entire system such as a list work function, a name display control, an image data transfer photographing support control, and arithmetic processing.
That is, various controls and processes described later are performed under the control of the controller 109a that controls various controls. The image processing unit 109b in the processor 109 includes a character image creation processing function, an image cutout processing function, an image composition processing function,
It has a reduced list image creation processing function, a facial color conversion processing function, a facial color extraction processing function, and the like, and details of these will be described later.

Further, the search processing unit 109c in the processor 109 performs a search from various databases 106 to 108 and extracts necessary data. The list processing unit 109d is a functional unit that performs necessary processing according to the list. The layout processing unit 109e is a functional unit that performs necessary layout processing.

The list processing unit 109d includes a list processing control unit 109d1 for performing list processing and a list memory unit 10 for storing ID number data of prospective photographers in order.
9d2 and a list data file memory 109d3 that can save and store the data of the list memory unit 109d2 as a file and read and use it at any time.

The display conversion unit 110 includes a database 109.
The display color of the information of the name and character read from is changed, and the display is controlled so that the operator can visually distinguish whether the person is a facial image photograph updater or a new photographer.

The character display unit 111 has a function of receiving character data output from the processor 109 and converting the character data into, for example, an NTSC signal, and is used for visualizing as a character image. The keyboard 112 is used by an operator for inputting ID number data of a person who is to be photographed into the system and for inputting instructions for system control. Also, the video printer 115 is a D / A
The image output from the converter 104 is for color printing on a sheet for output.

The face image processing / transferring unit 116 for mobile ID photo system is for reducing and binarizing the face image output from the frame memory 103 for output to the mobile ID photo system 117. A detailed description of the face image processing transfer unit 116 and the mobile ID photo system 117 will be given in the second and third embodiments described later.

This apparatus is roughly classified into a photographing function, a search function,
It can be divided into print functions. The function of the image processing unit 109b, which is the function of the processor 109, is an important function in the present invention, and various other functions are provided, but basically, a character image creation processing function, an image cutout processing function, The image synthesis processing function, the reduced list image creation processing function, the facial color conversion processing function, and the facial color extraction processing function are provided.

In the apparatus of the present invention, a database is utilized to realize a convenient system. Face image data is stored in the (face) image database memory 106, and
The personnel information data is stored in the character database memory 107, and the ID card base image data, characters, and face image layout format data necessary for printing are stored in the formatted card image data memory 108. It can be recorded and stored in an external memory such as a magneto-optical disk and read out.

Search processor 10 in processor 109
With the function of 9c, it is possible to search the name from the ID number using the database, and to search the ID face images of a plurality of people or one person from each personnel information item, and read from the database memory 106. The display control function is provided so that the operator can visually distinguish whether the person is a facial image photograph updater or a new photographer by changing the display color of the information of the issued name characters.

With the function of the processor 109, the character display section 111 can display information such as a condition list of search keywords, names of search results, and ID numbers and names during list processing. And so on.

List processing unit 109d of processor 109
By providing the, it becomes possible to perform shooting by the list and print processing by the list, which can contribute to automation of the work and labor saving of the work. Also,
By providing the layout processing unit 109e, when creating an ID card image, it is possible to easily perform a layout corresponding to an arbitrary layout of characters and facial images, and play a part in improving workability. There is.
The binary image memory 114 is a memory used for character font expansion processing in the ID card image during printing.

Details will be described in detail in the following embodiments. In the present system, "normal photographing", "normal printing", "list-based photographing", "list-based print processing", and "complex face color" Face color conversion processing for saving and printing in various colors "," Keyword copying function for facilitating input operation for search "," Reduced list image that makes it easy to pick up and use necessary information " Each function such as "display", "a processing function capable of quickly generating image data of a print image at the time of printing an ID card", and "a function of creating image data for an ID card with good character quality" is realized. Next, shooting (file filing) will be described.

FIG. 2 is a block diagram showing the elements necessary for photographing in the configuration of FIG.
In contrast to the block diagram of, the blocks are the blocks required here, except for the elements rewritten with dotted lines. Further, FIG. 3 is a diagram showing in detail the list processing unit 109d. Next, the operation of this embodiment configured as described above will be described. First, the basic shooting, "normal shooting"
Will be described.

The color video camera 101 photographs the upper body including the face of a person. Set the camera in advance for white balance adjustment, lens aperture adjustment, and focus adjustment. The analog video signal RGB output from the color video camera 101 is converted into a digital signal by the A / D converter 102 and sequentially written in the frame memory 103. The digital data written in the frame memory 103 is sequentially read while being synchronized so that it can be output as a video signal.

The read digital data is D /
The A converter 104 converts the analog signal into an NTSC signal (which may be an RGB signal), and the image display unit 10
It is displayed in 5. As a result, the image display unit 105 can monitor the upper half-body image of the person. The lighting condition and the color video camera 101 are adjusted so that a face image can be appropriately captured while viewing this image.

To take a face image used as an ID image,
First, the image data being taken is captured in the frame memory 103. The image data in the frame memory 103 is sequentially rewritten at a speed corresponding to the scanning speed of the video camera 101, and is held as moving image data. Therefore, in order to freeze (freeze) the face image on the frame memory 103, the processor 109 outputs a freeze control signal to the frame memory 103.

In order to perform this operation, the operator can input a freeze command from the keyboard 112 at the moment when he wants to freeze, and the processor 10 receives this signal.
The memory address control 9 of the frame memory 103 stops the sequential write data address counter of the frame memory 103 to disable writing. As a result, the image data on the frame memory 103 is frozen to the image at the time of inputting the freeze command.

However, by causing the processor 109 to continue the read data address control operation, the image data in the frame memory 103 is read out regardless of the presence or absence of the freeze operation, and the D / A converter 10 is read.
4 and can output as a video signal.

By displaying it on the image display unit 105, the freeze image is displayed, and not only the moving image of the camera image but also the still image can be viewed. After freezing the face image, by inputting an ID number from the keyboard 112 and inputting a save command, the processor 109 records this ID number as a file name in the image database memory 106 and saves it.

In order to print the ID card image, the I stored in the image database memory 106 is used.
The face image data for D, the character image data such as the ID number stored in the character database memory 107, the card image data with format data stored in the card image data memory with format data 108 are transferred to the frame memory 103, While controlling the memory address controller by the controller 109a, the address is controlled so that the above-mentioned images are written in the predetermined image positions on the frame memory 103. ID
After the card image is created on the image display unit 105, the video signal is checked by the video printer 115 by the controller 109a, and then the ID card image is printed.

FIG. 2 shows a second embodiment for realizing the present invention. The skin color detection unit 201 inputs a color data value to be a skin color in advance with the keyboard 112, and detects a color considered to be a skin color from the face image on the frame memory 103 on the basis of the color. Skin color centroid position coordinate calculation unit 202
Calculates an image area of a color considered to be a skin color detected by the skin color detection unit 201 and calculates barycentric position coordinates of the area. The background portion identification reference color calculation unit 203 calculates a reference color for distinguishing the face image from the background portion image. The writing start coordinate calculation unit 204 outputs the reduced and binarized face image to the mobile phone I.
The writing start coordinates for display in the D-photo system are calculated.

The face image reduction unit 205 reduces the face image.
The face image brightness conversion unit 206 converts the brightness of the face image reduced by the face image reduction unit 205. Face image binarization processing unit 207
The binarizes the face image whose brightness has been converted by the face image brightness conversion unit 206. Face image transfer unit 2 for mobile ID photo system
08 transfers the face image image-processed by the face image binarization processing unit 207 to the mobile ID photo system. Next, the operation will be described. First, the detection of the skin color of the face image will be described.

For example, the standard Japanese skin color is (Rf, G
f, Bf), the skin color is (Rf ± Δr, Gf ± Δg,
Bf ± Δb) is set, and all color points in the range of that color are detected as shown in FIG. In the above, the color is detected in the RGB color space, but it is also possible to detect the skin color when using the hue in the color space such as LUV or HSL. Next, the calculation of the barycentric position coordinates (xg, yg) of the detected skin color image area will be described.

First, a method of calculating the x coordinate will be taken up.
The image data in the frame memory 103 is read by the controller 109a while controlling the address, and the total number of dots of the color points in the image area of the flesh color detected there is P, and the flesh color on one line in the vertical direction The number of points is Px, and the x-coordinate on the line is x, and the skin-color centroid position coordinate calculation unit 202 performs calculation. Where x
g is calculated by the following equation (1). xg = [. SIGMA. (px.multidot.x)] ÷ P (1) Further, the same is done for ya.

Next, the calculation of the reference color data for distinguishing the face image from the background portion will be described. First, as shown in FIG. 8, several points of color data on the upper right end or upper left end are sampled, and the average value of the colors is set to (Rh, Gh, Bh).
Then, give this color a width (Rh ± Δr ', Gh ± Δ
g ', Bh ± Δb'). This color data is used as reference color data. Next, the brightness conversion and binarization of the reduced face image data will be described.

Since the reduced face image data is RGB color space data, it is necessary to convert it to the YIQ color space in order to convert the luminance. The relationship between the RGB color space and the YIQ color space is as shown in the following expression (2).

[0054]

[Equation 1] Therefore, the formula of the luminance conversion is as follows. Yf = 0.299 Ra + 0.587 Ga + 0.114'Ba This brightness-converted reduced face image data Yf is sequentially binarized as follows. (11) The luminance-converted reduced face image data Yf is sequentially added pixel by pixel from the beginning. The calculation formula is as follows. Ys = ΣYf (12) If Ys <255, “0” is recorded and the brightness data value of the next pixel is added. (13) If Ys ≧ 255, record “1” and Y0
= 255-Ys, the luminance data value of the next pixel is added. (14) If 20≤Ys≤30, generate a random number from 0 to 255 and add the random number value to the added luminance data value Ys at that time. (15) The binarized face image data is collected every 8 bits and recorded and stored in the image database of the mobile ID photo system.

(16) If the binarized face image data is less than 8 bits, the less than 8 bits is regarded as “0” data and 8
It is recorded and saved in the image database of the mobile ID photo system in the form of bits. Next, a procedure for converting a person image for the mobile ID photo system and recording and storing the same will be described.

First, a reduction value m for reducing a face image is input with a keyboard or a mouse. Alternatively, input it in advance. Next, the reading start coordinates (xg, yg) of the face image and the background identification reference color data (Rh ± Δ
r ', Gh ± Δg', Bh ± Δb ') are calculated and temporarily stored. In addition, a write start flag for writing in the memory of the mobile ID photo system is recorded and stored in the image database memory of the mobile ID photo system.
Next, the face image is divided into four regions with (xg, yg) as the center.
It is divided into (1), (2), (3), and (4), and (xg, y
g) Read out the face image and reduce it while controlling the address. The reduced face image data is converted to brightness,
Binarized image processing is performed and recorded and stored in an external memory.

This image processing is performed in the order of areas (1), (2), (3) and (4) as shown in FIG. Here, this operation will be described with reference to the flowcharts of FIGS. 8, 9 and 10. First, set the reduction ratio m of the face image (input)
Yes (S1). This reduction corresponds to m ² forming the face image. This is achieved by converting each pixel block into one pixel. S
When the reduction ratio m is set at 1, the barycentric coordinates (xg, yg) of the skin color area of the face image are calculated (S2).

Next, the reference color for distinguishing the face image from the background portion is set (S3). The background of this type of face image for ID is usually a monochromatic background such as blue. Therefore, no matter which part of the background portion is sampled, the background color is included in a limited narrow range. The reference color is a color range (± Δr, ± Δr
g, ± Δb), it is determined whether or not the color of the scanning point is always within the color range of this reference color while scanning the face image portion, and if it is within this range. Is for determining that the scanning point is off the face portion.

Next, the write start flag is transferred (S4). This is a signal that the writing of the face image, which has been reduced in size, converted in luminance and binarized, in the memory is started in the portable ID photo system. By setting this flag, it is recognized that the data transferred next to the memory side is image data. Next, the starting point for scanning the original image is set (S5).

In this embodiment, as shown in FIG.
The face image is divided into four with the skin color center of gravity as the center, and the area (1),
The original image is scanned in the order of (2), (3), and (4). B and D are parameters representing these four areas. B is x = xg
With 0 as the center line, 0 indicates a region on the right side of the line, and 1 indicates a region on the left side of the line. Further, D indicates an area below the line when 0 is the center line with y = yg, and an area above the line when 1 is 0. Therefore, region (1) is B = 0, D = 0, region
(2) is represented as B = 0, D = 1, region (3) is represented as B = 1, D = 0, and region (4) is represented as B = 1, D = 1. The skin color centroid coordinates (xg, yg) are input as the initial values of x and y.

Next, the process proceeds to the step of determining which area should be scanned. This determination is performed in steps S6 to S18. At the start of scanning, the xy coordinates of the scanning point are (xg, yg
) Is set, the steps of S6 to S18 are bypassed. During the sequential scanning of the areas (1) to (4), this part is "Which area should be scanned next?" Between the already scanned area and the area to be scanned, or This is a step of determining "Is all scanning completed?" And the like, which will be described in detail later.

In the steps so far, the point (xg, yg),
That is, the scanning start point is set at the skin color center of gravity coordinates.
From this point, as described in S19, the vertex (xg, yg)
And the color signal (pixel data) of each pixel point in the rectangular block defined by the vertices (xg + (m-1), yg + (m-1)).

S20 is a step for obtaining the average value of the color components (R, G, B) of each pixel in the block detected in S19, and this average value is stored in the memory reduced to 1 / m. Color components (pixel data) Ra, Ga,
It becomes Ba.

When the pixel data Ra, Ga, Ba are obtained, this and reference color data Rh ± Δr, Gh ± Δ
g, Bh ± Δb are compared (S30), and this pixel data is the reference color data Rh ± Δr, Gh ± Δ.
It is determined whether or not g, Bh ± Δb (S21).
That is, only the image of the face portion is processed so as to be reduced and stored in the memory.

If the obtained pixel data is not the background color, the process proceeds to step S22, and the counter value is incremented by one. This count value is used to indicate the read address in the x direction of the reduced pixel data stored in the memory. That is, it is transferred into the memory together with the pixel data.

When the counter is incremented,
The obtained pixel data is subjected to luminance conversion (S23), binarized (S24), and the pixel data is actually transferred to the memory together with the incremented count value. This completes the image processing of the original one block (one pixel in the memory) of the face image.

After that, the process moves to the next block (S2
6). In this case, since each block is sequentially advanced to the right in FIG. 5A, next, the vertices (xg + m, yg) and the vertices (xg + (2m- 1), y
g + (m-1)) The color signal (pixel data) of each pixel point in the rectangular block is detected, and the average value of the color components (R, G, B) of each pixel in the block is calculated. , Obtain the color component (pixel data) of the pixel stored in the memory.

In this way, the scanning of the first line of the area (1) proceeds, but the average value of the pixels in the block is shown in FIG.
When approaching the portion (that is, the contour portion) of the block P in (a), it is determined in the next step S21 that the pixel data of this average value is within the reference color (that is, within the background color) described above. If it is determined that the background portion of the original image has come, as shown in S27, the current parameter B
And the value in the y-coordinate counter C. This count value is transferred to the memory together with the pixel data and used as an address when reading.

Next, in order to shift to the scanning of the second line of the area (1), the y coordinate is increased by m and the x coordinate is set to xg.
The scanning point is moved to the starting point of the second line (S28). Then S6
However, at this stage, steps S6 to S18 still pass through, and similar scanning for each block is started from the starting point (xg, yg + m) of the second line. Thereafter, similarly, scanning of the region (1) proceeds line by line.

After the scanning of several lines, when the scanning of the bottom line of the face image portion of the area (1) is completed, the process jumps again to S6, but at this time y = ymax, so
After passing through S6 to S15, proceed to S17 at S16, and go to S
In 17 the scan area is changed to D = 1 (ie area
(Changed to (2)), and the scanning coordinates also move to (xg, yg -1) which is the starting point of the first line of the area (2). After that, the procedure for obtaining the face image inside the region (2) is the same as in the case of the region (1) described above. However, in this embodiment, the scanning is set so that both the main scanning and the sub-scanning proceed from a point close to the skin color barycentric coordinates to a point far from it, so that in the area (2),
The scanning in the y direction will proceed from bottom to top.

In the area (2), when the line scanning is completed to some extent, the background color of the upper part of the face image is then scanned. When the scanning of the last line (uppermost line) is completed, it is determined that y <0 in S12, and B is determined in S13.
Since there is no = 1, the process jumps to step S14. Step 14 shows the scanning of the area (3), and S15 shows the starting point position of the scanning in the area (3). Thereafter, similarly, the scanning of the area (3) is completed, and the operation of shifting to the scanning of the area (4) is performed by S16 to S18.

In the case of FIG. 4B, the data cannot be read out as it is, so the following operation is performed. First, at the same time as the face image reduction processing, the face image contour data Rf is counted by the counter from the beginning. At the same time, the number of pixels Nf of two adjacent face image data lines Lf is compared and the difference between them is obtained. │Nf-1 -Nf│ = k

At this time, k = 10 is used as a threshold value, and if k ≧
If it is 10, the face image contour recognition data count number C1 up to the previous line and the face image contour recognition data count number C2 up to the next line are temporarily stored. Similarly, C3 and C4 are also temporarily stored. After reading the area (1),
C1, C2, C3 and C4 are read out and the coordinates (xs1, ys1) of Rf-1 and Rf corresponding to C1 and C2 are read.
And (xs2, ys2), and the coordinates (xs3, ys3) and (xs4, ys4) of Rf-1 and Rf corresponding to C3 and C4 are set on the frame memory while controlling the addresses. At this time,

(21) If C1 <C2, the face image data above (or to the left of) Lf is read by using the coordinates of Rf as the start coordinates, and the face image data is reduced, converted in luminance, and binarized. Record and store in the internal or external memory of the photo system. (22) If C1> C2, the coordinates of Rf-1 are used as the reading start coordinates, and the face image data below (or to the right of) Lf-1 is read and the same as in (1).

In the case of FIG. 4B, first, Rf-1 (Cs1, x
s1, ys1) and Rf (Cs2, xs2, ys2) are compared,
Start reading from Rf (Cs2, xs2, ys2). As soon as this area ends, Rf-1 (Cs3, xs3, ys3) and Rf
(Cs4, xs4, ys4) is compared and Rf (Cs4, xs
4, ys4). The same applies to regions (2), (3), and (4). Further, the image processing described above can be performed in the same manner even when multi-valued.

FIG. 3 shows a third embodiment for realizing the present invention. The display unit 301 displays personnel information data including a face image. The display conversion unit 302 is a memory 303
The above data is converted so that it can be displayed on the display unit 301. The memory 303 writes character data in the image database memory 310 and the character database memory 311. The memory address controller 304 writes to and reads from the memory 303. The controller 305 controls the entire system. The keyboard 306 is used by the operator to input instructions to the system. The mouse or the touch pen 307 is used by the operator to input an instruction to the system similarly to the keyboard 306. Image processing unit 3
08 creates a character image from character data, synthesizes a face image and a character image, and displays a list of face images. The search processing unit 309 searches for the necessary face image and character data. The image database memory 310 records and stores face images and the like. Character database memory 3
Reference numeral 11 records and saves character data of personnel information such as ID number and name. The binarized face image reading unit 312 reads the face image recorded and stored in the image database memory 310 and writes it in the memory 303. Printer 313
Prints the image on the memory 303.

In order to display the binarized face image from the image database memory 310, the following is done. First,
The controller 305 initializes the memory 303. Next, the write start flag is read from the image database memory 310, and the write start coordinates (xw0, yw0) calculated in advance by the image processing unit 308 are set to (x
An address corresponding to w0, yw0) is set in the memory address controller 304. Next, the binarized face image is read from the image database memory 310, as follows. (31) Convert 1-byte data into 8-bit data. (32) Write 1 dot with 1 bit on 303. (33) When the face image contour recognition data Rf is detected, the data is counted, and the process moves to the next line.
Repeat (32).

(34) After counting C1 of Rf, the operations of (31) to (33) are stopped, and the process moves to the next area.
Similarly, in regions (1) to (4), (1) to (4) in FIG.
Repeat the operation of (4). Areas (1) to (4) are all in memory 3
After being written on 03, it is displayed on the display unit 301 via the display conversion unit 302. Although not shown here, character data of personnel information is also displayed on the display unit 301 at the same time.

As described above, in this embodiment, the binarized face image is displayed together with the personnel information so that it can be used in a portable personal computer using a liquid crystal display such as a notebook personal computer and a pen input personal computer. By doing
Realize a user-friendly system.

[0080]

According to the present invention, the data capacity of face image data is small, and even a portable personal computer such as a laptop computer can be easily operated as a personnel information database including face images. It is possible to provide a video ID photo system that can easily perform operations such as issuing an ID card from the ID photo system and searching / registering / deleting personnel information.

[Brief description of drawings]

FIG. 1 is a block diagram showing a schematic configuration of a first embodiment of a video ID photo system of the present invention.

FIG. 2 is a block diagram showing a schematic configuration of a second embodiment of a video ID photo system of the present invention.

FIG. 3 is a block diagram showing a schematic configuration of a third embodiment of a video ID photo system of the present invention.

FIG. 4 is a diagram for explaining the operation of FIG.

FIG. 5 is a diagram for explaining the operation of FIG.

FIG. 6 is a diagram for explaining the skin color detection principle of FIG. 1;

FIG. 7 is a diagram for explaining a method of calculating reference color data for distinguishing the face image and the background portion of FIG.

FIG. 8 is a flowchart for explaining the order of image processing in FIG.

9 is a flowchart for explaining the order of image processing in FIG.

FIG. 10 is a flowchart for explaining the order of image processing in FIG.

FIG. 11 is a diagram for explaining a first example of a conventional video ID photo system.

FIG. 12 is a diagram for explaining a second example of the conventional video ID photo system.

[Explanation of symbols]

101 ... Color TV camera, 102 ... A / D converter, 1
03 ... Frame memory, 104 ... D / A converter, 105
... image display unit, 109a ... controller, 112 ... keyboard, 115 ... video printer, 201 ... skin color detection unit, 202 ... skin color area barycentric position coordinate calculation unit, 203 ... background portion identification reference color calculation unit, 204 ... writing start coordinate calculation 205: face image reduction unit, 206 ... face image brightness conversion unit, 207 ... face image binarization processing unit, 208 ... face image transfer unit for mobile ID photo system.

Claims (1)

[Claims] 1. A face image capturing means for capturing a face image and converting it into image data, a storage means for storing the image data, and a skin color region of a face portion based on the image data stored in the storage means. Calculating means for calculating the barycentric position coordinates and the identification reference color data for distinguishing the face image from the background portion, and reading the face image data from the barycentric position coordinates to reduce only the face image and perform binarization processing. A video ID photo system comprising: processing means; and means for transferring data of the processing means to a portable ID photo system having a display means and displaying personnel information including a face image thereof on the display means.