JPH07306483A - Method for detecting face area in photographic picture frame - Google Patents

Abstract

PURPOSE:To accurately detect a face area without performing a special operation. CONSTITUTION:A magnetic track 21a is installed on a photographic film 19, and photographic magnification data is recorded on the magnetic track 21a. At the time of photographic printing, by reading the photographic magnification data and obtaining the product with a standard profile size, the profile size on the image plane is estimated. A skin colored area is extracted from the image plane and the size of the extracted skin colored area is compared with the estimated face size, and in the case both are the same in size, or almost the same, the skin colored area is detected as the face area.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for detecting a face area on a photographic screen, and more particularly, to a face portion of a person from an image recorded on a photographic film, a magnetic floppy of an electronic still camera, a memory card or the like. The present invention relates to a face area detecting method for detecting the.

[0002]

2. Description of the Related Art On a photographic screen, a background image is recorded in addition to a main subject image. However, in producing a hard copy such as a print, if the density and color balance of the main subject image are properly finished, Even if the finish of the background image is inadequate, the hard copy is often regarded as good.

Paying attention to the fact that most of the main subject image is a person's face, a face portion is extracted from the image recorded on the photographic screen, and a hard copy is made so that this face portion can be properly finished. A method of reproducing is known. For example, regarding a photographic film, there is Japanese Patent Laid-Open No. 52-156624, and in the exposure control method described therein, a negative color (hereinafter referred to as a skin color) corresponding to a skin color in a positive image is defined in advance. Has been done. Then, by comparing the color density of each point obtained by scanning the frame, it is determined whether the pixel of each point is a skin color. Next, the average color density of the region composed of the extracted skin color pixels is calculated, and the printing exposure amount is estimated using this average color density. This method is excellent as an exposure control method, but since it is difficult to extract skin color pixels,
For example, if a wall or the like that resembles the skin color is included, there is a problem in that this part is mistakenly recognized as the skin.

Therefore, in order to prevent erroneous recognition of an object and a person's skin, a frame is displayed on the monitor, and a part of the face is designated by a light pen or the like by observing the frame, and this designation is performed. A main image detecting method is known in which pixels having the same color as or similar to those of the other pixels are automatically extracted and the face area is determined by the pixels (Japanese Patent Laid-Open No. 62-189456).
Issue).

[0005]

However, although the above-mentioned conventional main image detecting method is effective in preventing misidentification,
There is a drawback that the operation is troublesome because the face portion of the person must be specified with the runt pen.

The present invention has been made to solve the above-mentioned drawbacks, and provides a face area detecting method for a photographing screen which enables the face area to be accurately detected without performing a special operation. That is the purpose.

[0007]

In order to achieve the above object, the invention of claim 1 records the photographing magnification data at the time of photographing, and reads the recorded photographing magnification data to estimate the size of a person's face. Then, compare the estimated person's face size with the size of the skin color area on the shooting screen, and if the estimated person's face size and skin color area size are the same or similar, It is detected as a region.

According to a second aspect of the present invention, the photographing magnification data at the time of photographing is recorded on a magnetic recording layer provided on the photographic film, and the photographing magnification data recorded at the time of handling the photographic film is read to read the person on the photographing screen. Estimate the size of the human face, compare the estimated human face size with the size of the skin color area on the shooting screen, and if the estimated human face size and skin color area size are the same or similar, The area is detected as a person's face area.

[0009]

According to the first aspect of the present invention, the size of the person's face is estimated based on the recorded photographing magnification data, and the estimated size of the person's face and the size of the skin color area on the photographing screen are compared and estimated. When the size of the person's face and the size of the skin color area are the same or similar, the skin color area is determined and detected as the area of the person's face on the photographing screen. Since the person's face area is detected by comparing the sizes, the face area can be detected without performing a special operation. Since the skin color differs depending on the race, the hue may be different according to the race of the person being photographed.

Further, in the invention of claim 2, the photographing magnification data at the time of photographing is recorded on the magnetic recording layer provided on the photographic film, and the photographing magnification data recorded at the time of handling the photographic film is read to read the person on the photographing screen. Estimate the size of the human face, compare the estimated human face size with the size of the skin color area on the shooting screen, and if the estimated human face size and skin color area size are the same or similar, The area is detected as a human face area. In the present invention, since the magnetic recording layer is used, data recording, reproduction, re-recording, etc. can be easily performed.

[0011]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment in which the present invention is applied to a photographic system including a photographic camera and a photographic printer that handles photographic film will be described below.

FIG. 1 shows a camera for recording photographing magnification data representing a photographing magnification at the time of photographing. Shooting lens 1
Reference numeral 0 is composed of an optical system 10a and a lens barrel 10b holding the optical system 10a, and is moved along the optical axis 12 by the lens moving mechanism 11. The lens moving mechanism 11 is operated by, for example, an operation member 13 that is linked to a rangefinder. Further, the lens moving mechanism 11 actuates a sensor 14 such as a potentiometer to convert the movement amount (linear displacement or rotation amount) of the photographing lens 10 into an electric signal, which is sent to the photographing magnification calculation circuit 15. In addition, this sensor 1
4 may detect the position of the operation member 13 or the taking lens 10. Further, as the sensor 14, not only a sensor that linearly converts the movement amount of the photographing lens 10 but also a sensor that divides the movement range of the photographing lens 10 into a plurality and generates a zone signal that changes in each of these ranges is used. You can

The focal length signal generation circuit 16 generates a signal representing the focal length of the photographing lens 10 and sends it to the photographing magnification calculation circuit 15. The shooting magnification calculation circuit 15 calculates the shooting magnification m according to the following formula.

M = f / (L−f) (1) where L is the distance from the photographing lens to the subject, which is obtained from the movement amount of the photographing lens detected by the sensor 14, and f is the focus of the photographing lens. It is a distance.

Since L >> f, the photographing magnification m may be approximated by the following equation (2), and the photographing magnification m is the distance F from the photographing lens to the film surface and the focal length of the photographing lens. Since f and can be expressed as in Expression (3), the calculation may be performed using Expression (3).

M = f / L (2) m = (F−f) / f (3) A photographic film 19 is coated with a transparent magnetic layer over the entire surface opposite to the emulsion surface. As shown in FIG. 2, the photographing magnification data at the time of photographing is recorded on the magnetic track 21a provided corresponding to the image frame. Reference numeral 21b is a magnetic track used in a photofinishing laboratory, and reference numeral 19b is a perforation formed at a position corresponding to the edge of each frame. The perforation 19b is detected by the sensor of the winding stop device, so that one frame is advanced.

The magnetic track 21a may be further recorded with information indicating the average brightness BV at the time of photographing and information indicating the presence or absence of flash emission. Further, in the above, an example of magnetically recording the photographing magnification data has been described, but it may be optically recorded by using a barcode or an optical mark,
It may be recorded mechanically by a punch hole or the like. Further, the position of recording the information on the film is not limited to the position shown in FIG. 2 and may be between film frames, or may be recorded on the IC attached or printed on the film or the film storage cartridge. Further, in the above, the transparent magnetic layer is applied over the entire surface of the film, but the transparent magnetic layer or the opaque magnetic layer may be applied only at the position near the side edge of the film along the length direction of the film. The vicinity of the side edge of the film does not affect the photographed image frame, so that the magnetic recording density can be increased by increasing the thickness of the magnetic layer.

The photographing magnification data calculated as described above is output to the driver 17. This driver 17
The recording magnetic head 20 is driven to record the photographing magnification data on the magnetic track of the photographic film 19.

A shutter mechanism 25 is arranged between the taking lens 10 and the photographic film 19. The shutter mechanism 25 includes, for example, two shutter blades 26 and 27, and the shutter blades 26 and 27 are formed with notches 26a and 27a, respectively. These shutter blades 26, 27 move away from the fixed pin 30 when the movable pin 29 moves toward the fixed pin 30 by the drive mechanism 28 and move away from the fixed pin 30.
Stack a and 27a. The portion where the notches 26a and 27a overlap is opened, and the light passing through the notch 26a and 27a is opened to the photographic film 19.
And the subject is imaged on the photographic film 19.

FIG. 3 shows a photographic printer. The white light emitted from the light source 35 is converted into the cyan filter 36,
The light enters the mixing box 39 after passing through the magenta filter 37 and the yellow filter 38. In the color correction filter including these filters 36 to 38, the amount of insertion into the optical path 41 is adjusted by the filter adjusting unit 40, and thereby the three color light components of the printing light and its intensity are adjusted. This mixing box 39 is one in which diffusion plates are attached to both ends of a rectangular tube whose inner surface is a mirror surface.

The film carrier 44 is arranged at the print position, the developed photographic film 19 is set, and the film carrier 44 is illuminated by the light transmitted through the mixing box 39. To ensure the flatness of this photographic film 19,
A film mask 45 is provided above the print position. As is well known, the film mask 45 has openings corresponding to the size of the frame, and the photographic film 1
When the sheet 9 is transferred, it is lifted up by a solenoid (not shown) and presses the photographic film 19 during printing.

A reproducing magnetic head 46 is arranged in front of the print position, and the photographing magnification data recorded for each frame is read when the magnetic head 46 is sent to the print position. The read data is sent to the decoder 47 and decoded, and then sent to the arithmetic unit 48.

A scanner 52 composed of a lens 50 and an image area sensor 51 is arranged diagonally above the print position, and measures the transmitted light at each point of the frame set at the print position. The signal of the scanner 52 is converted into a digital signal by the A / D converter 53 and then logarithmically converted by the logarithmic converter 54. After being converted into a density signal by the logarithmic converter 54, the calculation unit 48
To the controller 55. The face area is extracted, the printing exposure amount calculation formula is selected depending on the presence / absence of the face region, and the printing exposure amount is calculated according to the selected calculation formula. To be

Above the print position, a printing lens 58 is provided.
Are arranged, and the image of the set frame is enlarged and projected on the color paper 60 arranged behind the paper mask 59. This baking lens 58 and color paper 60
A shutter 62 whose opening and closing is controlled by a shutter drive unit 61 is arranged between the and.

FIG. 4 shows the arithmetic unit in functional blocks. The memory 66 stores the three-color density (red density R, green density G, blue density B) of each pixel obtained by photometrically measuring each point on the screen. The three color densities are read at the time of exposure amount calculation and sent to the skin color pixel extraction unit 67, where the skin color pixels are extracted. When extracting this skin color. Memory 68
Is performed with reference to the definition of skin color stored in. This skin color is, for example, as shown in FIG. 5, density differences (R−G), (G
It is defined as an ellipse in the orthogonal coordinate system having -B) as an axis, and a pixel whose density difference is included in this ellipse is determined to be a skin color. In addition to this ellipse, the skin color range can be defined by a rectangle, a rhombus, or the like.

The position of the pixel determined to be the skin color pixel is sent to the skin color region estimation unit 69, where the closed region composed of the skin color pixel is determined to be the skin color region, and then the size of the skin color region is determined. calculate. This size may be the length of the longest straight line connecting two points on the contour,
It is desirable to use the area to simplify the calculation. The number of skin color pixels may be used as this area.

On the other hand, the memory 72 stores photographing magnification data. The calculation unit 74 uses this photographing magnification data to obtain the size S of the face of the person recorded on the photographic film 19 from the following equation.

S = S _O × m (4) Here, S _O is the average size of the face.

The determination unit 75 determines the calculated face size S.
And the size of the extracted skin color area are compared, and if the size is the same as or similar to the face size S, the skin color area is determined to be the face area. The position coordinates of the face area are calculated by the feature value extraction unit 7
6, the characteristic value of the arithmetic expression for estimating the exposure amount for printing is extracted with an emphasis on the finish of the face. That is, the feature value extraction unit 76 reads the color densities of the pixels in the face area from the memory 66, and calculates the average value from the color densities of these pixels. Further, the feature value extraction unit 76 also calculates the maximum value and the minimum value in the screen, or the average density of a specific area such as the central portion and the peripheral portion of the screen. The obtained feature value is sent to the calculation unit 77, and is substituted into the photographic color-oriented printing exposure amount calculation formula 77a. On the other hand, the characteristic value extraction unit 78 extracts the characteristic value used in the general printing exposure calculation formula 77b. Specific examples of these baking exposure amount calculation formulas are described in, for example, Japanese Patent Laid-Open No. 62-
It is described in detail in Japanese Patent No. 189456.

The arithmetic expression selection unit 79 selects the printing exposure arithmetic expression 77a when the face area exists in the frame 19a, and the printing exposure amount arithmetic expression 77 when the face area does not exist.
Select b. The printing exposure amount obtained from the selected arithmetic expression is sent to the controller 55.

Next, the operation of the above embodiment will be described. When taking a picture, the camera is aimed at the main subject, the composition is determined, and then the operation member 13 is operated. The lens drive mechanism 11 moves the taking lens 10 along the optical axis 12 in conjunction with the operation member 13 to adjust the focus.
During this focus adjustment, the sensor 14 detects the position of the photographing lens 10 and sends a signal to the photographing magnification calculation circuit 15. Further, the focal length signal generation circuit 16 sends the focal length signal of the photographing lens 10 to the photographing magnification calculation circuit 15.

When the release button is pressed after the focus adjustment, the drive mechanism 28 reciprocates the drive pin 29 to open and close the shutter mechanism 28 to perform photographing.

Simultaneously with or before and after the photographing, the photographing magnification calculation circuit 15 calculates the photographing magnification from the distance L to the subject and the focal length f, and sends this photographing magnification data to the driver 17. The driver 17 drives the recording head 38 to write the photographing magnification data on a magnetic track provided in the peripheral portion of the screen 19a as shown in FIG.

When the photographing of one photographic film 19 is completed, the photographic film 19 is taken out from the camera and submitted to the photo lab. At the photo lab, photographic film 1
9 is developed to convert each frame recorded as a latent image into a visible image.

The developed photographic film 19 is shown in FIG.
It is loaded in the film carrier 44 of the photographic printer shown in FIG. When the photographic film 19 is transported on the film carrier 44, the photographing magnification data recorded on the periphery of the frame 19a is read by the reproducing head 46 as shown in step 100 of FIG. FIG. 6 shows an embodiment of face area detection. The read photographing magnification data is decoded by the decoder 47 and then sent to the calculation unit 48. The calculation unit 48 uses these data to calculate the face size S on the photographic film 19 (step 10).
2).

When the top 19a is set at the print position, the scanner 52 measures red, green, and blue transmitted light at each point on the top 19a (step 104). The photometric values of the three colors are sent to the arithmetic unit 48 after undergoing A / D conversion processing and logarithmic conversion processing.

After photometry of each pixel, the calculation unit 48 extracts the skin color pixel (step 106), and then determines the skin color region formed by the skin color pixel (step 108). The size of the flesh color area is compared with the face size S. If the size is the same as or similar to the face size S (step 110), it is determined to be the face area (step 112). When the determination of all skin color regions is completed (step 114), scene classification is performed. In this scene classification, if a face area exists, it is determined to be a person shooting scene (steps 116 and 118), and if not, it is determined to be another shooting scene (step 120).
For a portrait shooting scene, the printing exposure amount is calculated by substituting the feature value extracted from the feature value extraction unit 76 into the printing exposure amount calculation formula 77a. On the other hand, for other scenes, the printing exposure amount is calculated by substituting the feature value extracted from the feature value extraction unit 78 into the printing exposure amount calculation formula 77b.

After calculating the printing exposure amount, the controller 55
Adjusts the insertion amount of the color correction filters 36 to 38 into the optical path 41 according to the exposure amount for printing. After adjusting this filter,
The shutter 62 is opened for a certain time, and the frame 19a is printed and exposed on the color paper 60. Thereafter, similarly, each frame is sequentially printed on the color paper 60.

FIG. 7 shows another embodiment of face area detection. In this embodiment, a rounded closed contour is extracted from the frame by contour detection (step 12).
2). Next, the size of the rounded area is compared with the face size S, and if the size is the same as or similar to the face size S, this area is determined to be the face area (step 110). Since the other parts are the same as those in FIG. 6, the same reference numerals as those in FIG.

Further, the face pattern corresponding to the photographing magnification is stored in the memory, the corresponding reference face pattern is selected from the photographing magnification data, and the pattern matching processing is performed.
A pattern that matches or is similar to the reference face pattern may be extracted from the frame, and this may be determined as the face area.
Since the face pattern differs depending on the orientation, it is preferable to store some reference face patterns with different orientations in the memory.

FIG. 8 shows an autofocus device. The distance measuring sensor unit 82 includes a light receiving unit including a lens 83 and a line sensor 84, and a light projecting unit including a lens 85 and a light source 86. At the time of distance measurement when the release button is pressed halfway, spot-like near infrared light is projected from the light projecting portion toward the subject, and the light reflected here enters the licensor 84. The output signal of the licensor 84 is sent to the distance measuring circuit 87, and the position of the licensor 84 where the reflected light is incident is checked. The subject distance is detected from this incident position, and a signal of this subject distance is sent to the lens setting mechanism 88. The lens setting mechanism 88 sets the taking lens 10 at a position corresponding to the subject distance when the release button is completely pressed.

The subject distance signal output from the distance measuring circuit 87 is sent to the photographing magnification calculation circuit 15.

In the above embodiment, the photographing magnification data is magnetically recorded, but instead of this, an optical mark or bar code displayed by a light emitting diode or the like may be used. In addition, the face size obtained by the camera may be recorded as shooting magnification data. Further, instead of recording on a photographic film, an IC card may be set in the camera and recorded on it, or it may be recorded on a cartridge. In addition, in the electronic still camera, subject distance data and magnetic data are written in a magnetic floppy or a memory card together with the image data.

Although the photographing magnification data has been described as an example of being recorded at the same time as, or before and after taking a picture, it may be recorded in an electronic notebook or the like and recorded after taking a picture, that is, a photographic film or the like. It should be recorded before handling.

In the above, an example in which a printer detects a face area as an apparatus for handling photographic film has been described, but the present invention is not limited to this, and an image frame recorded on a film is photographed to be used as a CRT. The present invention can also be applied to a display device for displaying, a simulator for photographing an image frame recorded on a film, estimating a printed image, and displaying the image on a CRT.

[0046]

As described above, according to the first and second aspects of the invention, the size of the human face is estimated from the photographing magnification data at the time of photographing, and the estimated face size and the size of the skin color area on the screen are calculated. Since it is determined whether or not it is the face area by comparison, there is an effect that the face area can be accurately detected without requiring a special operation.

[Brief description of drawings]

FIG. 1 is a schematic diagram showing a photographic camera embodying the present invention.

FIG. 2 is an explanatory diagram showing a magnetic track of a photographic film.

FIG. 3 is a schematic diagram of a photographic printer embodying the present invention.

FIG. 4 is a functional block of a calculation unit that calculates a printing exposure amount.

FIG. 5 is a graph showing a range of skin color.

FIG. 6 is a flowchart showing a procedure for detecting a face area.

FIG. 7 is another flowchart showing a procedure for detecting a face area.

FIG. 8 is a block diagram showing an autofocus device.

[Explanation of symbols]

 10 Photographic lens 19 Photographic film 52 Scanner 60 Color paper 84 Line sensor 86 Light source

Claims (2)

[Claims] 1. A photographing magnification data at the time of photographing is recorded, the recorded photographing magnification data is read to estimate the size of a person's face, and the estimated person's face size and the size of a skin color area on the photographing screen are calculated. And a face area detection method for detecting a skin color area as a human face area when the estimated human face size and the skin color area size are the same or similar. 2. The size of a person's face on a photographing screen is estimated by recording photographing magnification data at the time of photographing on a magnetic recording layer provided on a photographic film and reading the photographing magnification data recorded at the time of handling the photographic film. , The estimated human face size is compared with the size of the skin color area on the shooting screen, and if the estimated human face size and the skin color area size are the same or similar, the skin color area is set to the human face area. A method for detecting the face area of the shooting screen.