US20110279701A1 - Image pickup device, face detection method, and computer-readable recording medium - Google Patents
Image pickup device, face detection method, and computer-readable recording medium Download PDFInfo
- Publication number
- US20110279701A1 US20110279701A1 US13/191,927 US201113191927A US2011279701A1 US 20110279701 A1 US20110279701 A1 US 20110279701A1 US 201113191927 A US201113191927 A US 201113191927A US 2011279701 A1 US2011279701 A1 US 2011279701A1
- Authority
- US
- United States
- Prior art keywords
- face detection
- face
- parameter
- image
- mode
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N2101/00—Still video cameras
Definitions
- the present invention relates to an image pickup device like a digital camera having a face detection function of detecting the face of a person in an image, a face detection method and a computer-readable recording medium.
- digital cameras or digital video cameras which pick up an image of an object using a CCD or a MOS type solid-state image sensor, have a face detection function of automatically detecting the face of a subject person when picking up a still image or a dynamic image.
- a face detection function of automatically detecting the face of a subject person when picking up a still image or a dynamic image.
- such digital cameras or the like having a face detection function perform focus control and exposure control based on image information on a region of a detected face part (face region).
- a user needs a bothersome operation of setting plural parameters which set down a face detection operation, such as a process time, the number of persons to be detected, and a face area ratio, when picking up an image.
- the present invention has been made in view of the foregoing circumstance, and it is an object of the invention to provide an image pickup device, a face detection method and a computer-readable recording medium which enable an effective face detection in accordance with an object without causing a user to do bothersome setting.
- an image pickup device comprises: an image pickup unit which picks up an object; and a face detection unit which detects a face region from the object image picked up by the image pickup unit in accordance with a value of at least one parameter which corresponds to respective plural face detection modes set beforehand and which defines a detection condition of a face region.
- a face detection method for detecting a face region from an object image picked up by an image pickup unit comprises: a step of repeating an detection operation of a face region from the object image in a first face detection mode, and acquiring predetermined detection information on a detection condition in a second face detection mode having a different detection condition of a face region from the first face detection mode while repeating the detection operation in the first face detection mode; and a step of changing over a detection operation mode of a face region from the object image to the second face detection mode when a content of the predetermined detection information satisfies the detection condition in the second face detection mode.
- a computer-readable recording medium recording a face detection control program that allows a computer of an image processing device having a face detection function of detecting a face region from an object image to execute: a process of selecting any one of plural face detection modes set beforehand as an operation mode in detecting a face region; and a process of detecting a face region from the object image in accordance with values of a first parameter and a second parameter, the first parameter and the second parameter corresponding to the selected face detection mode, and defining a detection condition of a face region.
- a computer-readable recording medium recording a face detection control program that allows a computer of an image processing device having a face detection function of detecting a face region from an object image to execute: a process of repeating a detection operation of a face region from the object image in a first face detection mode, and of acquiring predetermined detection information on a detection condition in a second face detection mode having a different detection condition of a face region from the first face detection mode while repeating the detection operation in the first face detection mode; and a process of changing over a detection operation mode of a face region from the object image to the second face detection mode when a content of the acquired predetermined detection information satisfies the detection condition in the second face detection mode.
- FIG. 1 is a block diagram showing the structure of a digital camera common to the individual embodiments of the invention
- FIG. 3 is a flowchart showing the operational contents of a face detection according to a first embodiment
- FIG. 4 is a flowchart continuous from FIG. 3 ;
- FIG. 5 is an explanatory diagram showing a face searching region in a frame image and parameters used in a face detection operation
- FIG. 6A is a diagram showing an example of a through image with face detection frames being displayed
- FIG. 6B is a diagram showing an example of a through image with face detection frames being displayed
- FIG. 8A is a process-speed characteristic diagram showing a relationship between a process speed necessary for a cycle of face detection and a size of a face to be detected;
- FIG. 8B is a process-speed characteristic diagram showing a relationship between a process speed necessary for a cycle of face detection and the number of faces to be detected (the number of persons);
- FIG. 9 is a flowchart showing the process of a face detection by a controller according to a second embodiment.
- FIG. 10 is a flowchart continuous from FIG. 9 .
- FIG. 1 is a block diagram showing the general structure of a digital camera according to the embodiment.
- the digital camera has functions of AE (automatic exposure), AF (auto focus), and face detection, and generally comprises the following individual units.
- the digital camera has a CCD 2 which performs photoelectric conversion on an optical image of an object imaged by an optical system 1 , and outputs an imaging signal.
- the CCD 2 is driven by a drive signal generated by a CCD driving unit 4 in accordance with a timing signal generated by a timing generator (TG) 3 .
- the output signal of the CCD 2 is converted into a digital signal by an A/D converter 5 , and is transmitted to an image processing unit 6 .
- the optical system 1 has a focus lens and a lens motor for moving the focus lens on an optical axis.
- the lens motor is driven by a drive signal generated by a lens driving unit 8 in accordance with an instruction from a controller 7 . Accordingly, the focus lens has a position controlled on the optical axis.
- the image processing unit 6 performs a RGB interpolation process of generating color component data (RGB data) on R, G, B for each pixel on an imaging signal undergone A/D conversion, a YUV conversion process of generating YUV data having a brightness signal (Y) and a color-difference signal (U, V) from the RGB data for each pixel, and a digital signal process for improving an image quality, such as auto white balancing or contour enhancing.
- the YUV data converted through the image processing unit 6 is successively stored in an SDRAM 9 .
- the digital camera further has a display unit 10 comprised of a liquid crystal monitor and a drive circuit thereof.
- a recording mode for image pickup the YUV data stored in the SDRAM 9 is converted into a video signal through the image processing unit 6 every time the SDRAM 9 stores one frame of data pieces. Thereafter, the converted video signal is displayed as a through image on the screen of the display unit 10 (liquid crystal monitor).
- a JPEG converter 11 compresses and encodes image data temporarily stored in the SDRAM 9 in the JPEG format, and the compressed and encoded image is recorded as a still image file in an external memory 13 , which comprises, for example, various kinds of memory cards, through an external memory I/F 12 .
- the still image file recorded in the external memory 13 is arbitrarily read out in accordance with a selection operation of a user in a reproducing mode.
- the read-out still image file is expanded by the JPEG converter 11 , and is extracted as YUV data in the SDRAM 9 . Thereafter, the YUV data is displayed as a still image on the display unit 10 .
- An operation unit 14 includes a plurality of keys, such as a power key, a mode changing key for changing over a basic operation mode of the digital camera between the recording mode and the reproducing mode, a MENU key, and a shutter key.
- Each key has an operational status scanned by the controller 7 as needed.
- the shutter key has a so-called half shutter function of enabling a user to operate the shutter key in two stages through a half-pressed position for a preliminary image pickup and a full-pressed position for instructing an actual image pickup operation.
- a face detection processing unit 15 detects a face part having a similar characteristic to model patterns relating to a face of a person, such as a contour and a color prepared (stored) beforehand, on image data of one frame (hereinafter, frame image) generated by the image processing unit 6 . Further, the face detection processing unit 15 creates coordinate information on a region corresponding to a detected face part (hereinafter, face region), and transmits the coordinate information to the controller 7 . More specifically, the face detection processing unit 15 comprises a frame memory for temporarily storing the frame image, an image processing circuit for executing various image processes necessary for a face detection operation, and a plurality of registers for storing parameters used in a face detection operation.
- set as operation modes (face detection modes) of the face detection processing unit 15 in detecting a face region are a speed preference mode and a person-number preference mode having different conditions for detecting a face region.
- the face detection processing unit 15 executes a face detection process in accordance with a face detection mode.
- the kind of the face detection mode can be arbitrarily changed by the user.
- the controller 7 comprises a CPU and peripheral circuits, and the like, controls the individual units of the digital camera, and performs AE control based on brightness information included in an imaging signal, AF control through a contrast detection scheme, and face detection control, and the like.
- Various kinds of programs for causing the controller 7 to do such controls and various data necessary for respective controls are stored in a flash memory 16 which is a nonvolatile memory where rewriting of stored data is possible.
- the flash memory 16 stores various data necessary for embodying the invention, in addition to the programs to be run by the controller 7 .
- the flash memory 16 further stores setting information or the like on various functions of the digital camera set by the user.
- FIG. 2 is a conceptual diagram showing a preference setting table T stored in the flash memory 16 .
- the preference setting table T indicates setting parameters corresponding to the face detection modes (speed preference mode and person-number preference mode).
- the setting parameters indicated in the preference setting table T are minimum face sizes detectable through a face detection, i.e., an image size Xmin in a horizontal direction which is the minimum value of a face size, an image size Ymin in a vertical direction, and a maximum number of faces to be detected, i.e., a face Max which is the maximum value of the number of detected faces.
- the controller 7 sets the setting parameters indicated in the preference setting table T as initial values in the registers of the face detection processing unit 15 .
- the speed preference mode is a mode which sets a preference (importance) for a processing speed in a face detection
- the person-number preference mode is a mode which sets a preference (importance) for the number of faces to be detected, i.e., a detailed face detection.
- Values of the setting parameters corresponding to both modes are values in accordance with the preference contents (condition of detecting a face region) of the respective modes. That is, the face Max which is the maximum value of the number of faces to be detected is “5” in the speed preference mode, and is “10” in the person-number preference mode.
- the face size (Xmin, or Ymin) which is the minimum value of a face size is indicated by a percentage (N %) when the size of a frame image in the vertical direction is taken as 100% (see, FIG. 6A ), and is “16%” in the speed preference mode, and is “10%” in the person-number preference mode.
- N % a percentage
- an image size shown in FIG. 2 (36 pix, 22 pix) is an expedient value corresponding to an explanation of a specific operational content relating to a face detection to be discussed later.
- the values of the above-explained setting parameters are decided in view of the following points. That is, in general, in a face detection, the number of persons in an image subjected to a detection (hereinafter, frame image) and a size of a face of a person vary. Accordingly, a face present in a frame image (face region) is detected while gradually changing the size of a face to be detected from a small size to a large size. At this time, a process speed necessary for a cycle of face detection has an intimate relationship between the number of faces to be detected (number of detected faces) and a largeness of a face (face size).
- FIG. 8A is a diagram showing a process speed (time) for a face size in a case where five persons are present in a frame image and the face sizes of the respective persons are same.
- a process speed necessary for a cycle of face detection becomes slow as a smaller face is to be detected, and in a case where a large face more than or equal to some extent is to be detected, the difference in the largeness of faces hardly affects to a process speed.
- FIG. 8B is a diagram showing a process speed for the number of faces to be detected in a case where the sizes of respective faces present in a frame are all 10 percent.
- a process speed necessary for a cycle of face detection becomes fast as the number of faces to be detected becomes small. Note that process speeds shown in the figures are expedient speeds.
- a process speed necessary for a cycle of face detection relates to a largeness of a face to be detected and the number thereof, i.e., a largeness of a region subjected to a pattern matching, and the number of those regions. That is, the larger the size of a detectable face is, the larger a region subjected to a pattern matching becomes, and the number thereof becomes small. As the size of a detectable face becomes small, a region subjected to a pattern matching becomes small, and the number of those regions becomes large. Accordingly, the number of detecting whether an image of a target region is a face or not increases, thereby dramatically reducing a process speed.
- a process speed necessary for a cycle of face detection relates to a largeness of a face to be detected (face size) and the number of faces (number of detected faces).
- a process speed also intimately relates to the size of a face present in a frame image and the number of persons. That is, in a case where a face present in a frame image is large, even if faces are densely present, the number of faces which can be present in a frame image is limited.
- the face Max (maximum value of the number of faces to be detected) is set to “5” and the face size (minimum value of detection size) is set to “16 percent” as values of setting parameters corresponding to the speed preference mode.
- the face Max is set to “10” and the face size is set to “10 percent” as values of the setting parameters corresponding to the person-number preference mode.
- the controller 7 causes the face detection processing unit 15 to perform face detection on an image data (frame image) of an object acquired through an image-pickup operation at a predetermined frame rate. Every time a face detection operation of the face detection processing unit 15 is completed, the controller 7 transmits a new frame image acquired right after the completion of the face detection operation to the face detection processing unit 15 .
- the face detection processing unit 15 executes a face detection process at all times asynchronously with the frame rate.
- the face detection processing unit 15 sets almost all region of the frame image other than an outer circumferential part as a face searching region, and performs a face detection process on the face searching region.
- the size of the face searching region is 290 pixels by 220 pixels (see, FIG. 5 ).
- the controller 7 in the digital camera acquires setting information on the kind of the face detection mode set at this time (e.g., the kind of the face detection mode set when the face detection function was used at a previous time) from the flash memory 16 (step SA 1 ).
- the controller 7 determines which one of the face detection modes between the speed preference mode and the person-number preference mode is set (step SA 2 ).
- the controller 7 reads out the setting parameters corresponding to the set mode from the preference setting table T (see, FIG. 2 ), and sets those values to the face detection processing unit 15 as initial values for a face detection operation. That is, when it is determined that the “speed preference mode” is set, the controller 7 sets the values “36, 36” as the face sizes (Xmin, Ymin), and sets the maximum value of the number of faces to be detected (face Max) to “5” (step SA 3 ).
- the controller 7 sets the face sizes (Xmin, Ymin) to “22, 22”, and sets the maximum value of the number of faces to be detected (face Max) to “10” (step SA 4 ).
- FIG. 5 is an explanatory diagram showing a face searching region 101 in a frame image 100 and parameters used in a face detection operation.
- the face detection processing unit 15 sets sizes Xf, Yf of a face detection region 102 subjected to a pattern matching to the initial values (Xmin, Ymin) set by the controller 7 (step SA 10 ).
- the face detection processing unit 15 sets the value of a detection counter to “0” (step SA 11 ).
- the face detection processing unit 15 sets the values of start points Xs, Ys of the face detection region 102 to “0”, and sets the values of end points Xe, Ye of the face detection region 102 to values corresponding to the start points Xs, Ys and the sizes Xf, Yf (step SA 12 ). In this manner, the face detection processing unit 15 executes a parameter initialization process.
- the face detection processing unit 15 executes a face detection process through a pattern matching on the face detection region 102 having the sizes Xf, Yf (step SA 13 ).
- the face detection processing unit 15 repeats the same face detection process through the following procedures while updating the position and size of a face detection region 102 .
- the face detection processing unit 15 sets shift units ⁇ X and ⁇ Y of the face detection region 102 in the X direction and the Y direction to 20% of the sizes Xf, Yf of the face detection region at the time (step SA 17 ). Thereafter, the face detection processing unit 15 updates the start point Xs and the end point Xe to shift the face detection region 102 by what corresponds to the shift unit ⁇ X in the X direction (step SA 18 ).
- step SA 19 NO
- the face detection processing unit 15 executes a face detection process every time the face detection region 102 is shifted in the X direction through the foregoing process.
- the face detection processing unit 15 shifts the face detection region 102 in the Y direction by what corresponds to the shift unit ⁇ Y, and updates the start points Xs, Ys, and the end points Xe, Ye to move the position of the face detection region 102 in the X direction to the left end (step SA 20 ).
- the face detection processing unit 15 repeats shifting in the X direction from a new position in the Y direction, and executes a face detection process every time the face detection region 102 is shifted.
- the face detection processing unit 15 repeatedly shifts the face detection region 102 until a new end point Ye in the Y direction crosses over the bottom end coordinate position (in the embodiment, 220) of the face searching region 101 (step SA 21 : NO). Namely, the face detection processing unit 15 repeats the face detection process while shifting the face detection region 102 little by little (by the shift units ⁇ X, ⁇ Y) from the left to the right, and the top to the bottom of the face searching region 101 .
- step SA 21 Every time the end point Ye of the face detection region 102 in the Y direction crosses over the bottom end coordinate position of the face searching region 101 (step SA 21 : YES), the face detection processing unit 15 enlarges the sizes Xf, Yf of the face detection region 102 in the X direction and the Y direction at that time to sizes of 1.2 times (step SA 22 ). Afterward, the face detection processing unit 15 repeats the face detection process while shifting the face detection region 102 of a new size (Xf, Yf) from the left to the right, top to the bottom of the face searching region 101 as explained before (step SA 23 : NO).
- step SA 15 every time a face is detected while the foregoing face detection process is repeated (step SA 14 : YES), the face detection processing unit 15 counts up the value of the detection counter (step SA 15 ).
- the value of the detection counter i.e., the number of faces detected reaches the maximum value (face Max) (step SA 16 : YES)
- the face detection processing unit 15 terminates the face detection operation to the frame image 100 .
- the process returns to the step SA 5 in FIG. 3 .
- step SA 5 , SA 7 NO
- the face detection operation from the step SA 10 to the step SA 23 shown in FIG. 4 is repeatedly performed on a new frame image.
- FIGS. 6A and 6B are diagrams showing an example of a through image 110 with a face detection frame A being displayed at a time when the face detection operation to a frame image, i.e., the face detection process of a cycle is completed.
- the face detection frame A is displayed by the controller 7 synthesizing OSD (On Screen Display) data of the face detection frame A with YUV data of a through image stored in the SDRAM 9 .
- a face region detected by the face detection processing unit 15 is used as, for example, a photometric region when the controller 7 performs AE control, and an acquisition region of a contrast value (AF evaluation region) when the controller 7 performs AF control.
- the controller 7 When the user operates a predetermined key for setting (changing) a mode, the controller 7 displays a mode selection screen exemplified in FIG. 7 on the display unit 10 in response to the operation of the user. As the user selects a face detection mode (speed preference mode or person-number preference mode) through an operation like moving a cursor, the controller 7 sets the mode selected by the user as a new face detection mode.
- a face detection mode speed preference mode or person-number preference mode
- step SA 7 determines whether the face detection mode set at the time is the speed preference mode or not (step SA 8 ).
- step SA 8 determines whether the face detection mode set at the time is the speed preference mode or not.
- step SA 9 the controller 7 causes the face detection processing unit 15 to stop the face detection operation at the time, and temporarily changes the values of the face sizes (Xmin, Ymin) and the maximum value (face Max) of the number of faces to be detected to the values corresponding to the person-number preference mode.
- step SA 9 Thereafter, while the shutter key is being pressed halfway, the controller 7 causes the face detection processing unit 15 to perform the face detection operation to a frame image in the person-number preference mode.
- the controller 7 sets back the setting values to the setting values for the speed preference mode at a time when the half-pressing of the shutter key is released. Afterward, in the image-pickup standby state, the operations from the step SA 5 to the step SA 23 are repeated while the face detection function is being enabled.
- the maximum value of the number of detected faces (face Max) is set to “5”, and the initial value of the size of the face detection region 102 is set to “36, 36” (16% in face size).
- the maximum value of the number of detected faces (face Max) is set to “10”, and the initial value of the size of the face detection region 102 is set to “22, 22” (10% in face size).
- the face detection performances such as the number of faces to be detected (the number of detected faces) and the face size
- the face detection performances are small in comparison with the person-number preference mode, but a process speed necessary for a cycle of face detection becomes fast, so that the face detection operation ensures a high responsiveness.
- the face detection frame A see, FIGS. 6A , 6 B
- the responsiveness thereof is less than that of the speed preference mode, but it is possible to detect a small face far away, and it is possible to detect faces of a large number of persons. That is, it is possible to do face detection in detail.
- the user can cause the digital camera to perform efficient face detection corresponding to specific contents of an object, such as the number of persons in an angle of view, and a face size, by just selecting the kind of the face detection mode.
- the user In a case where the user individually sets the parameters, such as a detectable face size, and the number of detectable faces, it is necessary that the user should have a proficiency in setting of those parameters (combination of parameter values). For example, when the user wants to detect only a large face, it is desirable to reduce the number of faces to be detected (maximum number of persons). In a case where the user does not have a proficiency in setting of those parameters, but sets the maximum number of persons largely, this results in an achievement of an unintentional responsiveness.
- the digital camera of the embodiment a user needs to only select the kind of the face detection mode, so that everyone can cause the digital camera to do efficient face detection in accordance with specific contents of an object.
- the face detection mode has the two kinds: the speed preference mode where a preference is given to a process speed in detecting a face; and the person-number preference mode where a preference is given to the number o face to be detected (detection of faces in detail), but the kinds of the face detection mode set beforehand may be greater than or equal to three.
- Individual face detection modes may have different conditions for detecting a face region by combining the values of greater than or equal to two parameters. That is, a mode which has a preference (importance) to an operational content other than a process speed in detecting a face and the number of faces to be detected may be set.
- the embodiment relates to a digital camera which automatically sets (changes) the foregoing face detection mode.
- the digital camera has the same basic structure as that of the first embodiment, but the flash memory 16 stores a program for causing the controller 7 to execute the following process.
- the controller 7 performs an initializing process of setting a person-number preference flag OFF (step SB 1 ).
- the controller 7 sets the person-number preference mode as the face detection mode. Namely, the controller 7 reads out the setting parameters corresponding to the person-number preference mode from the preference setting table T (see, FIG. 2 ), and set those values as initial values used for a face detection operation in the face detection processing unit 15 (step SB 2 ).
- the controller 7 causes the face detection processing unit 15 to do the face detection operation like that of the first embodiment (step SB 3 ).
- step SB 8 the controller 7 determines whether or not the size of the detected face is less than 16% and whether or not the number of detected faces (number of detected faces) reaches the maximum, i.e., “10” which is the maximum value (face Max) in the person-number preference mode based on coordinate information (start points Xs, Ys, and end points Xe, Ye) of the face detection region 102 (see, FIG. 5 ) transmitted from the face detection processing unit 15 (steps SB 5 , SB 7 ).
- step SB 5 When it is determined that the size of the detected face is less than 16%, and when a relatively small face is detected in a frame image (step SB 5 : YES), the controller 7 sets the person-number preference flag in an ON state (step SB 6 ).
- step SB 7 When the number of detected faces reaches the maximum (step SB 7 : YES) or when the number of detected faces does not reach the maximum but a cycle of the face detection process is completed (step SB 8 : YES), the controller 7 displays one or plural face detection frames on a through image based on all coordinate information transmitted from the face detection processing unit 15 until that time (step SB 9 ).
- step SB 10 when the person-number preference flag is set ON (step SB 10 : YES), the controller 7 once sets back the person-number preference flag OFF (step SB 11 ). Thereafter, the controller 7 returns the process to the step SB 3 , and causes the face detection processing unit 15 to perform the face detection process on a next frame image while keeping the face detection mode being in the person-number preference mode (step SB 3 ). Namely, in a case where at least one face having a size less than 16% is included in one or plural faces detected in a most recent frame image, when the size of the detected face does not satisfy the detection condition of a face region in the speed preference mode, the controller 7 keeps the face detection processing unit 15 to perform the face detection process in the person-number preference mode. Therefore, it is possible to do effective face detection in accordance with the specific contents of an object.
- step SB 10 when the person-number preference flag is not set ON (step SB 10 : NO), as shown in FIG. 10 , the controller 7 changes over the face detection mode from the person-number preference mode to the speed preference mode (step SB 12 ). That is, in a case where the sizes of faces detected from a most recent frame is all greater than or equal to 16% in the person-number preference mode, the controller 7 changes over the face detection mode from the person-number preference mode to the speed preference mode.
- the controller 7 reads out the setting parameters corresponding to the speed preference mode from the preference setting table T (see, FIG. 2 ), and sets those parameters as initial values used for the face detection operation to the face detection processing unit 15 .
- the controller 7 starts a timing counter operation to acquire an operation timing every predetermined time (three seconds) after the change over of the face detection mode (step SB 13 ).
- the controller 7 causes the face detection processing unit 15 to do the face detection operation in the speed preference mode (step SB 14 ).
- step SB 17 NO
- step SB 15 YES
- the controller 7 determines whether or not the number of faces detected (number of detected faces) at the time reaches the maximum, i.e., whether or not the number of faces detected at the time reaches “five” which is the maximum value (face Max) of the speed preference mode (step SB 16 ).
- step SB 16 When the number of detected faces reaches the maximum value (step SB 16 : YES), or when the number of detected faces does not reach the maximum, but when a cycle of the face detection process is completed (step SB 17 : YES), the controller 7 displays one or plural face detection frames on a through image based on all coordinate information transmitted from the face detection processing unit 15 (step SB 18 ).
- step SB 19 NO
- the process returns to the step SB 14 . That is, the controller 7 causes the face detection processing unit 15 to perform the face detection process on a next frame image in the speed preference mode not changed as it is. Accordingly, it is possible to do effective face detection in accordance with an object.
- the face detection mode is temporarily changed from the speed preference mode to the person-number preference mode, it is determined at all times whether or not a change to the person-number preference mode is necessary based on a result of face detection in the person-number preference mode.
- the face detection mode is automatically changed to the person-number preference mode, so that even if the specific contents of an object change at an arbitrary time, it is possible to cope with such a change promptly.
- predetermined detection information of the invention is a size of a face detected through the face detection operation in the person-number preference mode.
- the face detection mode is changed over to the speed preference mode in a case where the predetermined information satisfies the detection condition in the speed preference mode, but the face detection mode may be changed over as follows.
- the face detection mode may be changed over to the speed preference mode.
- the face detection mode may be changed over to the speed preference mode.
- the face detection mode may be changed over to the speed preference mode.
- the face detection modes are the speed preference mode and the person-number preference mode
- the detection condition of a face region in each mode is based on the values of plural parameters, such as the size of a smallest detectable face (minimum value of a face size), and a maximum number of faces detectable (maximum value of the number of detected faces).
- the detection condition of a face region in each face detection mode may be based on the value of a single parameter.
- each of the face detection modes may be a mode having a detection condition which is based on only the size of the smallest face detectable, or a mode having a detection condition which is based on the maximum number of faces should be detected, as long as individual modes have different detection condition of a face region.
- the detection condition of a face region in each face detection mode is not limited to one which is based on a single or two parameter values, and may be one which is based on more than or equal to three kinds of parameters. In this case, however, the specific operation of automatically determining a necessity of changing the face detection mode, and of changing over the face detection mode as needed becomes complex, as the kinds of the face detection mode are large numbers.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
An image pickup device can effectively detect a face in accordance with an object without causing a user to do bothersome setting. A speed preference mode and a person-number preference mode both having different detection conditions of a face region are prepared beforehand as face detection modes. The user is caused to select a desired face detection mode, and minimum values of a face size set as detectable in a face detection and a maximum number of face regions to be detected are set to values corresponding to the face detection mode selected by the user. In a case where an image-pickup preparation is set by pressing a shutter key halfway, when the face detection mode is the speed preference mode, the mode is forcibly changed to the person-number preference mode.
Description
- This is a Continuation Application of U.S. application Ser. No. 12/152,890, filed May 16, 2008, which is based upon and claims the benefit of priority from Japanese Application No. 2007-133353, filed May 18, 2007, the entire contents of which are incorporated herein by reference.
- 1. Field of the Invention
- The present invention relates to an image pickup device like a digital camera having a face detection function of detecting the face of a person in an image, a face detection method and a computer-readable recording medium.
- 2. Description of the Related Art
- Recently, digital cameras or digital video cameras, which pick up an image of an object using a CCD or a MOS type solid-state image sensor, have a face detection function of automatically detecting the face of a subject person when picking up a still image or a dynamic image. In general, such digital cameras or the like having a face detection function perform focus control and exposure control based on image information on a region of a detected face part (face region).
- To speed up a process of detecting a face (detection of a face region) on an arbitrary image and to eliminate unnecessary detection processes, a technology of causing a user to set the respective maximum values of a process time, the number of persons to be detected, and a face area ratio (a ratio between an area of a process target image and a total area of a face region already detected), and of terminating a detection process when any one of such values becomes maximum, is known.
- To cause digital cameras or the like to perform effective face detection with the foregoing technology, however, a user (photographer) needs a bothersome operation of setting plural parameters which set down a face detection operation, such as a process time, the number of persons to be detected, and a face area ratio, when picking up an image.
- The present invention has been made in view of the foregoing circumstance, and it is an object of the invention to provide an image pickup device, a face detection method and a computer-readable recording medium which enable an effective face detection in accordance with an object without causing a user to do bothersome setting.
- To achieve the object, an image pickup device according to the first aspect of the invention comprises: an image pickup unit which picks up an object; and a face detection unit which detects a face region from the object image picked up by the image pickup unit in accordance with a value of at least one parameter which corresponds to respective plural face detection modes set beforehand and which defines a detection condition of a face region.
- According to the second aspect of the invention, a face detection method for detecting a face region from an object image picked up by an image pickup unit, comprises: a step of selecting any one of plural face detection modes as an operation mode in detecting a face region; and a step of detecting a face region from the object image picked up by the image pickup unit in accordance with values of a first parameter and a second parameter, the first parameter and the second parameter corresponding to a selected face detection mode, and defining a detection condition of a face region.
- According to the third aspect of the invention, a face detection method for detecting a face region from an object image picked up by an image pickup unit, comprises: a step of repeating an detection operation of a face region from the object image in a first face detection mode, and acquiring predetermined detection information on a detection condition in a second face detection mode having a different detection condition of a face region from the first face detection mode while repeating the detection operation in the first face detection mode; and a step of changing over a detection operation mode of a face region from the object image to the second face detection mode when a content of the predetermined detection information satisfies the detection condition in the second face detection mode.
- According to the fourth aspect of the invention, a computer-readable recording medium recording a face detection control program that allows a computer of an image processing device having a face detection function of detecting a face region from an object image to execute: a process of selecting any one of plural face detection modes set beforehand as an operation mode in detecting a face region; and a process of detecting a face region from the object image in accordance with values of a first parameter and a second parameter, the first parameter and the second parameter corresponding to the selected face detection mode, and defining a detection condition of a face region.
- According to the fifth aspect of the invention, a computer-readable recording medium recording a face detection control program that allows a computer of an image processing device having a face detection function of detecting a face region from an object image to execute: a process of repeating a detection operation of a face region from the object image in a first face detection mode, and of acquiring predetermined detection information on a detection condition in a second face detection mode having a different detection condition of a face region from the first face detection mode while repeating the detection operation in the first face detection mode; and a process of changing over a detection operation mode of a face region from the object image to the second face detection mode when a content of the acquired predetermined detection information satisfies the detection condition in the second face detection mode.
- According to the invention, it becomes possible to do effective face detection according to an object without causing a user to do bothersome settings.
- These objects and other objects and advantages of the present invention will become more apparent upon reading of the following detailed description and the accompanying drawings in which:
-
FIG. 1 is a block diagram showing the structure of a digital camera common to the individual embodiments of the invention; -
FIG. 2 is a conceptual diagram for a preference setting table; -
FIG. 3 is a flowchart showing the operational contents of a face detection according to a first embodiment; -
FIG. 4 is a flowchart continuous fromFIG. 3 ; -
FIG. 5 is an explanatory diagram showing a face searching region in a frame image and parameters used in a face detection operation; -
FIG. 6A is a diagram showing an example of a through image with face detection frames being displayed; -
FIG. 6B is a diagram showing an example of a through image with face detection frames being displayed; -
FIG. 7 is a diagram showing a mode selection screen; -
FIG. 8A is a process-speed characteristic diagram showing a relationship between a process speed necessary for a cycle of face detection and a size of a face to be detected; -
FIG. 8B is a process-speed characteristic diagram showing a relationship between a process speed necessary for a cycle of face detection and the number of faces to be detected (the number of persons); -
FIG. 9 is a flowchart showing the process of a face detection by a controller according to a second embodiment; and -
FIG. 10 is a flowchart continuous fromFIG. 9 . - An explanation will be given of the embodiments of the invention in detail with reference to the accompanying drawings. In the embodiments, an explanation will be given of a case where an image pickup device of the invention is constituted by a digital camera.
- The first embodiment of the invention will be explained first.
FIG. 1 is a block diagram showing the general structure of a digital camera according to the embodiment. The digital camera has functions of AE (automatic exposure), AF (auto focus), and face detection, and generally comprises the following individual units. - That is, the digital camera has a
CCD 2 which performs photoelectric conversion on an optical image of an object imaged by anoptical system 1, and outputs an imaging signal. TheCCD 2 is driven by a drive signal generated by aCCD driving unit 4 in accordance with a timing signal generated by a timing generator (TG) 3. The output signal of theCCD 2 is converted into a digital signal by an A/D converter 5, and is transmitted to animage processing unit 6. - The
optical system 1 has a focus lens and a lens motor for moving the focus lens on an optical axis. The lens motor is driven by a drive signal generated by alens driving unit 8 in accordance with an instruction from acontroller 7. Accordingly, the focus lens has a position controlled on the optical axis. - The
image processing unit 6 performs a RGB interpolation process of generating color component data (RGB data) on R, G, B for each pixel on an imaging signal undergone A/D conversion, a YUV conversion process of generating YUV data having a brightness signal (Y) and a color-difference signal (U, V) from the RGB data for each pixel, and a digital signal process for improving an image quality, such as auto white balancing or contour enhancing. The YUV data converted through theimage processing unit 6 is successively stored in anSDRAM 9. - The digital camera further has a
display unit 10 comprised of a liquid crystal monitor and a drive circuit thereof. In a recording mode for image pickup, the YUV data stored in theSDRAM 9 is converted into a video signal through theimage processing unit 6 every time the SDRAM 9 stores one frame of data pieces. Thereafter, the converted video signal is displayed as a through image on the screen of the display unit 10 (liquid crystal monitor). In picking up an image under the recording mode, aJPEG converter 11 compresses and encodes image data temporarily stored in theSDRAM 9 in the JPEG format, and the compressed and encoded image is recorded as a still image file in anexternal memory 13, which comprises, for example, various kinds of memory cards, through an external memory I/F 12. - The still image file recorded in the
external memory 13 is arbitrarily read out in accordance with a selection operation of a user in a reproducing mode. The read-out still image file is expanded by theJPEG converter 11, and is extracted as YUV data in theSDRAM 9. Thereafter, the YUV data is displayed as a still image on thedisplay unit 10. - An
operation unit 14 includes a plurality of keys, such as a power key, a mode changing key for changing over a basic operation mode of the digital camera between the recording mode and the reproducing mode, a MENU key, and a shutter key. Each key has an operational status scanned by thecontroller 7 as needed. Note that the shutter key has a so-called half shutter function of enabling a user to operate the shutter key in two stages through a half-pressed position for a preliminary image pickup and a full-pressed position for instructing an actual image pickup operation. - A face
detection processing unit 15 detects a face part having a similar characteristic to model patterns relating to a face of a person, such as a contour and a color prepared (stored) beforehand, on image data of one frame (hereinafter, frame image) generated by theimage processing unit 6. Further, the facedetection processing unit 15 creates coordinate information on a region corresponding to a detected face part (hereinafter, face region), and transmits the coordinate information to thecontroller 7. More specifically, the facedetection processing unit 15 comprises a frame memory for temporarily storing the frame image, an image processing circuit for executing various image processes necessary for a face detection operation, and a plurality of registers for storing parameters used in a face detection operation. - In the embodiment, set as operation modes (face detection modes) of the face
detection processing unit 15 in detecting a face region are a speed preference mode and a person-number preference mode having different conditions for detecting a face region. The facedetection processing unit 15 executes a face detection process in accordance with a face detection mode. The kind of the face detection mode can be arbitrarily changed by the user. - The
controller 7 comprises a CPU and peripheral circuits, and the like, controls the individual units of the digital camera, and performs AE control based on brightness information included in an imaging signal, AF control through a contrast detection scheme, and face detection control, and the like. Various kinds of programs for causing thecontroller 7 to do such controls and various data necessary for respective controls are stored in aflash memory 16 which is a nonvolatile memory where rewriting of stored data is possible. - In the embodiment, the
flash memory 16 stores various data necessary for embodying the invention, in addition to the programs to be run by thecontroller 7. Theflash memory 16 further stores setting information or the like on various functions of the digital camera set by the user.FIG. 2 is a conceptual diagram showing a preference setting table T stored in theflash memory 16. The preference setting table T indicates setting parameters corresponding to the face detection modes (speed preference mode and person-number preference mode). The setting parameters indicated in the preference setting table T are minimum face sizes detectable through a face detection, i.e., an image size Xmin in a horizontal direction which is the minimum value of a face size, an image size Ymin in a vertical direction, and a maximum number of faces to be detected, i.e., a face Max which is the maximum value of the number of detected faces. Thecontroller 7 sets the setting parameters indicated in the preference setting table T as initial values in the registers of the facedetection processing unit 15. - In the face detection modes, the speed preference mode is a mode which sets a preference (importance) for a processing speed in a face detection, and the person-number preference mode is a mode which sets a preference (importance) for the number of faces to be detected, i.e., a detailed face detection. Values of the setting parameters corresponding to both modes are values in accordance with the preference contents (condition of detecting a face region) of the respective modes. That is, the face Max which is the maximum value of the number of faces to be detected is “5” in the speed preference mode, and is “10” in the person-number preference mode. Moreover, the face size (Xmin, or Ymin) which is the minimum value of a face size is indicated by a percentage (N %) when the size of a frame image in the vertical direction is taken as 100% (see,
FIG. 6A ), and is “16%” in the speed preference mode, and is “10%” in the person-number preference mode. Note that an image size shown inFIG. 2 (36 pix, 22 pix) is an expedient value corresponding to an explanation of a specific operational content relating to a face detection to be discussed later. - In the embodiment, the values of the above-explained setting parameters are decided in view of the following points. That is, in general, in a face detection, the number of persons in an image subjected to a detection (hereinafter, frame image) and a size of a face of a person vary. Accordingly, a face present in a frame image (face region) is detected while gradually changing the size of a face to be detected from a small size to a large size. At this time, a process speed necessary for a cycle of face detection has an intimate relationship between the number of faces to be detected (number of detected faces) and a largeness of a face (face size).
-
FIG. 8A is a diagram showing a process speed (time) for a face size in a case where five persons are present in a frame image and the face sizes of the respective persons are same. A process speed necessary for a cycle of face detection becomes slow as a smaller face is to be detected, and in a case where a large face more than or equal to some extent is to be detected, the difference in the largeness of faces hardly affects to a process speed.FIG. 8B is a diagram showing a process speed for the number of faces to be detected in a case where the sizes of respective faces present in a frame are all 10 percent. A process speed necessary for a cycle of face detection becomes fast as the number of faces to be detected becomes small. Note that process speeds shown in the figures are expedient speeds. - A process speed necessary for a cycle of face detection relates to a largeness of a face to be detected and the number thereof, i.e., a largeness of a region subjected to a pattern matching, and the number of those regions. That is, the larger the size of a detectable face is, the larger a region subjected to a pattern matching becomes, and the number thereof becomes small. As the size of a detectable face becomes small, a region subjected to a pattern matching becomes small, and the number of those regions becomes large. Accordingly, the number of detecting whether an image of a target region is a face or not increases, thereby dramatically reducing a process speed.
- As explained above, a process speed necessary for a cycle of face detection relates to a largeness of a face to be detected (face size) and the number of faces (number of detected faces). In addition, a process speed also intimately relates to the size of a face present in a frame image and the number of persons. That is, in a case where a face present in a frame image is large, even if faces are densely present, the number of faces which can be present in a frame image is limited.
- Therefore, in detecting a smaller face, the number of detectable faces should be large, but in contrast, in detecting a large face only, the number of detectable faces can be reduced. In view of the foregoing points, according to the embodiment, the face Max (maximum value of the number of faces to be detected) is set to “5” and the face size (minimum value of detection size) is set to “16 percent” as values of setting parameters corresponding to the speed preference mode. The face Max is set to “10” and the face size is set to “10 percent” as values of the setting parameters corresponding to the person-number preference mode.
- Next, the operation of the digital camera having the foregoing structure relating to a face detection will be explained. First, a basic operation will be explained. In the digital camera, when a face detection function is enabled in an image-pickup standby state in the recording mode, the
controller 7 causes the facedetection processing unit 15 to perform face detection on an image data (frame image) of an object acquired through an image-pickup operation at a predetermined frame rate. Every time a face detection operation of the facedetection processing unit 15 is completed, thecontroller 7 transmits a new frame image acquired right after the completion of the face detection operation to the facedetection processing unit 15. As the facedetection processing unit 15 receives the new frame image from thecontroller 7, the facedetection processing unit 15 executes a face detection process at all times asynchronously with the frame rate. In this case, the facedetection processing unit 15 sets almost all region of the frame image other than an outer circumferential part as a face searching region, and performs a face detection process on the face searching region. In the following explanation, as a matter of convenience, let us suppose that the size of the face searching region is 290 pixels by 220 pixels (see,FIG. 5 ). - A specific operation will be explained with reference to the flowcharts of
FIGS. 3 and 4 . As shown inFIG. 3 , when the face detection function is enabled in the recording mode or when the recording mode is set with the face detection function being enabled, thecontroller 7 in the digital camera acquires setting information on the kind of the face detection mode set at this time (e.g., the kind of the face detection mode set when the face detection function was used at a previous time) from the flash memory 16 (step SA1). - Thereafter, the
controller 7 determines which one of the face detection modes between the speed preference mode and the person-number preference mode is set (step SA2). Next, thecontroller 7 reads out the setting parameters corresponding to the set mode from the preference setting table T (see,FIG. 2 ), and sets those values to the facedetection processing unit 15 as initial values for a face detection operation. That is, when it is determined that the “speed preference mode” is set, thecontroller 7 sets the values “36, 36” as the face sizes (Xmin, Ymin), and sets the maximum value of the number of faces to be detected (face Max) to “5” (step SA3). On the other hand, when it is determined that the “person-number preference mode” is set, thecontroller 7 sets the face sizes (Xmin, Ymin) to “22, 22”, and sets the maximum value of the number of faces to be detected (face Max) to “10” (step SA4). - Afterward, when there is no operation of changing over the face detection mode and a shutter key half-press operation by the user (steps SA5, SA7: NO), every time the
controller 7 transmits a frame image to the facedetection processing unit 15, the facedetection processing unit 15 repeatedly performs face detection operations through the routines from steps SA10 to SA23 shown inFIG. 4 .FIG. 5 is an explanatory diagram showing aface searching region 101 in aframe image 100 and parameters used in a face detection operation. - As shown in
FIG. 4 , first, the facedetection processing unit 15 sets sizes Xf, Yf of aface detection region 102 subjected to a pattern matching to the initial values (Xmin, Ymin) set by the controller 7 (step SA10). The facedetection processing unit 15 sets the value of a detection counter to “0” (step SA11). Further, the facedetection processing unit 15 sets the values of start points Xs, Ys of theface detection region 102 to “0”, and sets the values of end points Xe, Ye of theface detection region 102 to values corresponding to the start points Xs, Ys and the sizes Xf, Yf (step SA12). In this manner, the facedetection processing unit 15 executes a parameter initialization process. Note that the start points Xs, Ys and the end points Xe, Ye are coordinates within theface searching region 101 in theframe image 100. Thereafter, the facedetection processing unit 15 executes a face detection process through a pattern matching on theface detection region 102 having the sizes Xf, Yf (step SA13). The facedetection processing unit 15 repeats the same face detection process through the following procedures while updating the position and size of aface detection region 102. - First, the face
detection processing unit 15 sets shift units ΔX and ΔY of theface detection region 102 in the X direction and the Y direction to 20% of the sizes Xf, Yf of the face detection region at the time (step SA17). Thereafter, the facedetection processing unit 15 updates the start point Xs and the end point Xe to shift theface detection region 102 by what corresponds to the shift unit ΔX in the X direction (step SA18). Until the end point Xe in the X direction crosses a coordinate position of the right end of the face searching region 101 (in the embodiment, 290) (step SA19: NO), the facedetection processing unit 15 executes a face detection process every time theface detection region 102 is shifted in the X direction through the foregoing process. - Every time the end point Xe of the
face detection region 102 in the X direction crosses the right end coordinate position (290) of the face searching region 101 (step SA19: YES), the facedetection processing unit 15 shifts theface detection region 102 in the Y direction by what corresponds to the shift unit ΔY, and updates the start points Xs, Ys, and the end points Xe, Ye to move the position of theface detection region 102 in the X direction to the left end (step SA20). The facedetection processing unit 15 repeats shifting in the X direction from a new position in the Y direction, and executes a face detection process every time theface detection region 102 is shifted. In this manner, the facedetection processing unit 15 repeatedly shifts theface detection region 102 until a new end point Ye in the Y direction crosses over the bottom end coordinate position (in the embodiment, 220) of the face searching region 101 (step SA21: NO). Namely, the facedetection processing unit 15 repeats the face detection process while shifting theface detection region 102 little by little (by the shift units ΔX, ΔY) from the left to the right, and the top to the bottom of theface searching region 101. - Every time the end point Ye of the
face detection region 102 in the Y direction crosses over the bottom end coordinate position of the face searching region 101 (step SA21: YES), the facedetection processing unit 15 enlarges the sizes Xf, Yf of theface detection region 102 in the X direction and the Y direction at that time to sizes of 1.2 times (step SA22). Afterward, the facedetection processing unit 15 repeats the face detection process while shifting theface detection region 102 of a new size (Xf, Yf) from the left to the right, top to the bottom of theface searching region 101 as explained before (step SA23: NO). - Further, every time a face is detected while the foregoing face detection process is repeated (step SA14: YES), the face
detection processing unit 15 counts up the value of the detection counter (step SA15). When the value of the detection counter, i.e., the number of faces detected reaches the maximum value (face Max) (step SA16: YES), or when the size (Xf, Yf) of theface detection region 102 set in the step SA22 exceeds the maximum size (Xmax, Ymax) set beforehand (step SA23: YES), the facedetection processing unit 15 terminates the face detection operation to theframe image 100. The process returns to the step SA5 inFIG. 3 . - When there is no operation of changing over the face detection mode or a shutter key half-press operation (steps SA5, SA7: NO), the face detection operation from the step SA10 to the step SA23 shown in
FIG. 4 is repeatedly performed on a new frame image. - It is not shown in the flowcharts, but when counting up the value of the detection counter in the step SA15 of the face detection operation, the face
detection processing unit 15 transmits coordinate information (start points Xs, Ys and end points Xe, Ye) of theface detection region 102 at that time to thecontroller 7. Thecontroller 7 successively displays a face detection frame indicating a face region overlapped on a through image based on the transmitted coordinate information.FIGS. 6A and 6B are diagrams showing an example of a throughimage 110 with a face detection frame A being displayed at a time when the face detection operation to a frame image, i.e., the face detection process of a cycle is completed. - The face detection frame A is displayed by the
controller 7 synthesizing OSD (On Screen Display) data of the face detection frame A with YUV data of a through image stored in theSDRAM 9. A face region detected by the facedetection processing unit 15 is used as, for example, a photometric region when thecontroller 7 performs AE control, and an acquisition region of a contrast value (AF evaluation region) when thecontroller 7 performs AF control. - As shown in
FIG. 3 , when the user changes over the face detection mode (step SA5: YES), thecontroller 7 changes the setting values set for the facedetection processing unit 15, i.e., the value of face sizes (Xmin, Ymin) and the maximum value of the number of faces to be detected (face Max) to values corresponding to a new mode (speed preference mode, or person-number preference mode) (step SA6). Thereafter, the facedetection processing unit 15 executes the foregoing face detection operation based on the changed setting values. - When the user operates a predetermined key for setting (changing) a mode, the
controller 7 displays a mode selection screen exemplified inFIG. 7 on thedisplay unit 10 in response to the operation of the user. As the user selects a face detection mode (speed preference mode or person-number preference mode) through an operation like moving a cursor, thecontroller 7 sets the mode selected by the user as a new face detection mode. - Further, when the user presses the shutter key halfway (step SA7: YES), the
controller 7 determines whether the face detection mode set at the time is the speed preference mode or not (step SA8). When determining that the speed preference mode is set (step SA8: YES), thecontroller 7 causes the facedetection processing unit 15 to stop the face detection operation at the time, and temporarily changes the values of the face sizes (Xmin, Ymin) and the maximum value (face Max) of the number of faces to be detected to the values corresponding to the person-number preference mode (step SA9). Thereafter, while the shutter key is being pressed halfway, thecontroller 7 causes the facedetection processing unit 15 to perform the face detection operation to a frame image in the person-number preference mode. It is not illustrated in the flowchart, but when the setting values are temporarily changed to the values corresponding to the person-number preference mode, thecontroller 7 sets back the setting values to the setting values for the speed preference mode at a time when the half-pressing of the shutter key is released. Afterward, in the image-pickup standby state, the operations from the step SA5 to the step SA23 are repeated while the face detection function is being enabled. - In the foregoing embodiment, when the speed preference mode is set as the face detection mode, the maximum value of the number of detected faces (face Max) is set to “5”, and the initial value of the size of the
face detection region 102 is set to “36, 36” (16% in face size). When the person-number preference mode is set, the maximum value of the number of detected faces (face Max) is set to “10”, and the initial value of the size of theface detection region 102 is set to “22, 22” (10% in face size). - Therefore, when the speed preference mode is set, the face detection performances, such as the number of faces to be detected (the number of detected faces) and the face size, are small in comparison with the person-number preference mode, but a process speed necessary for a cycle of face detection becomes fast, so that the face detection operation ensures a high responsiveness. Namely, when an angle of view changes or when a person in an angle of view moves, it is possible to promptly move the face detection frame A (see,
FIGS. 6A , 6B) following to such a change or such a movement. In contrast, when the person-number preference mode is set, the responsiveness thereof is less than that of the speed preference mode, but it is possible to detect a small face far away, and it is possible to detect faces of a large number of persons. That is, it is possible to do face detection in detail. - As explained above, according to the digital camera of the embodiment, the user (photographer) can cause the digital camera to perform efficient face detection corresponding to specific contents of an object, such as the number of persons in an angle of view, and a face size, by just selecting the kind of the face detection mode.
- In a case where the user individually sets the parameters, such as a detectable face size, and the number of detectable faces, it is necessary that the user should have a proficiency in setting of those parameters (combination of parameter values). For example, when the user wants to detect only a large face, it is desirable to reduce the number of faces to be detected (maximum number of persons). In a case where the user does not have a proficiency in setting of those parameters, but sets the maximum number of persons largely, this results in an achievement of an unintentional responsiveness. On the other hand, according to the digital camera of the embodiment, a user needs to only select the kind of the face detection mode, so that everyone can cause the digital camera to do efficient face detection in accordance with specific contents of an object.
- During a period from when the shutter key is pressed halfway and until when the shutter key is released, the face detection mode is forcibly set to the person-number preference mode regardless of the kind of the face detection mode so far. Accordingly, most appropriate AF control and AE control are always performed through a detailed face detection operation in picking up an image.
- Note that a change to the person-number preference mode through the foregoing half-pressing of the shutter key may be carried out temporarily only when the shutter key is pressed halfway. The foregoing effectiveness can be also achieved in this case.
- In the foregoing embodiment, the face detection mode has the two kinds: the speed preference mode where a preference is given to a process speed in detecting a face; and the person-number preference mode where a preference is given to the number o face to be detected (detection of faces in detail), but the kinds of the face detection mode set beforehand may be greater than or equal to three. Individual face detection modes may have different conditions for detecting a face region by combining the values of greater than or equal to two parameters. That is, a mode which has a preference (importance) to an operational content other than a process speed in detecting a face and the number of faces to be detected may be set.
- In a case where, for example, another mode in addition to the speed preference mode and the person-number preference mode is set as a face detection mode, like the foregoing embodiment, by setting a mode which has the highest detection precision of a face region in plural face detection modes during a period from when the shutter key is pressed halfway and until when the shutter key is released, further appropriate AF control and AE control are enabled in picking up an image.
- Next, the second embodiment of the invention will be explained. The embodiment relates to a digital camera which automatically sets (changes) the foregoing face detection mode. The digital camera has the same basic structure as that of the first embodiment, but the
flash memory 16 stores a program for causing thecontroller 7 to execute the following process. - The contents of the process by the
controller 7 relating to a face detection will be explained with reference to the flowcharts ofFIGS. 9 and 10 . As shown inFIG. 9 , as the face detection function is enabled in the recording mode or as the recording mode is set with the face detection function being set enabled, thecontroller 7 performs an initializing process of setting a person-number preference flag OFF (step SB1). Next, thecontroller 7 sets the person-number preference mode as the face detection mode. Namely, thecontroller 7 reads out the setting parameters corresponding to the person-number preference mode from the preference setting table T (see,FIG. 2 ), and set those values as initial values used for a face detection operation in the face detection processing unit 15 (step SB2). Thecontroller 7 causes the facedetection processing unit 15 to do the face detection operation like that of the first embodiment (step SB3). - Thereafter, until a cycle of face detection to a frame image is completed through the face detection processing unit 15 (step SB8: NO), every time the face
detection processing unit 15 detects a face (step SB4: YES), thecontroller 7 determines whether or not the size of the detected face is less than 16% and whether or not the number of detected faces (number of detected faces) reaches the maximum, i.e., “10” which is the maximum value (face Max) in the person-number preference mode based on coordinate information (start points Xs, Ys, and end points Xe, Ye) of the face detection region 102 (see,FIG. 5 ) transmitted from the face detection processing unit 15 (steps SB5, SB7). - When it is determined that the size of the detected face is less than 16%, and when a relatively small face is detected in a frame image (step SB5: YES), the
controller 7 sets the person-number preference flag in an ON state (step SB6). - When the number of detected faces reaches the maximum (step SB7: YES) or when the number of detected faces does not reach the maximum but a cycle of the face detection process is completed (step SB8: YES), the
controller 7 displays one or plural face detection frames on a through image based on all coordinate information transmitted from the facedetection processing unit 15 until that time (step SB9). - Subsequently, when the person-number preference flag is set ON (step SB10: YES), the
controller 7 once sets back the person-number preference flag OFF (step SB11). Thereafter, thecontroller 7 returns the process to the step SB3, and causes the facedetection processing unit 15 to perform the face detection process on a next frame image while keeping the face detection mode being in the person-number preference mode (step SB3). Namely, in a case where at least one face having a size less than 16% is included in one or plural faces detected in a most recent frame image, when the size of the detected face does not satisfy the detection condition of a face region in the speed preference mode, thecontroller 7 keeps the facedetection processing unit 15 to perform the face detection process in the person-number preference mode. Therefore, it is possible to do effective face detection in accordance with the specific contents of an object. - In contrast, when the person-number preference flag is not set ON (step SB10: NO), as shown in
FIG. 10 , thecontroller 7 changes over the face detection mode from the person-number preference mode to the speed preference mode (step SB12). That is, in a case where the sizes of faces detected from a most recent frame is all greater than or equal to 16% in the person-number preference mode, thecontroller 7 changes over the face detection mode from the person-number preference mode to the speed preference mode. Thecontroller 7 reads out the setting parameters corresponding to the speed preference mode from the preference setting table T (see,FIG. 2 ), and sets those parameters as initial values used for the face detection operation to the facedetection processing unit 15. At the same time, thecontroller 7 starts a timing counter operation to acquire an operation timing every predetermined time (three seconds) after the change over of the face detection mode (step SB13). Next, thecontroller 7 causes the facedetection processing unit 15 to do the face detection operation in the speed preference mode (step SB14). - Thereafter, until the face
detection processing unit 15 completes a cycle of the face detection process to a frame image (step SB17: NO), every time the facedetection processing unit 15 detects a face (step SB15: YES), thecontroller 7 determines whether or not the number of faces detected (number of detected faces) at the time reaches the maximum, i.e., whether or not the number of faces detected at the time reaches “five” which is the maximum value (face Max) of the speed preference mode (step SB16). - When the number of detected faces reaches the maximum value (step SB16: YES), or when the number of detected faces does not reach the maximum, but when a cycle of the face detection process is completed (step SB17: YES), the
controller 7 displays one or plural face detection frames on a through image based on all coordinate information transmitted from the face detection processing unit 15 (step SB18). - Subsequently, when it is not an operation timing acquired every three seconds as explained above (step SB19: NO), the process returns to the step SB14. That is, the
controller 7 causes the facedetection processing unit 15 to perform the face detection process on a next frame image in the speed preference mode not changed as it is. Accordingly, it is possible to do effective face detection in accordance with an object. - In contrast, while repeating the foregoing process, when it becomes an operation timing acquired every three seconds (step SB19: YES), the process returns to the step SB2 in
FIG. 9 . Thecontroller 7 changes over the face detection mode from the speed preference mode to the person-number preference mode. Thereafter, thecontroller 7 executes the process to the step SB10. When there is a change in the state of an object, such that any person in the angle of view moves away from the digital camera, or a person newly enters in the angle of view so that a relatively small size of a face less than 16% is detected after the face detection has been previously carried out through the person-number preference mode (step SB5: YES), thecontroller 7 sets the person-number preference flag ON (step SB6). By setting the person-number preference flag ON, thecontroller 7 can cause the facedetection processing unit 15 to repeat the detailed face detection process in the person-number preference mode not changed as it is. - When no face having a relatively small size less than 16% is detected at all in the person-number preference mode carried out once every three seconds (steps SB5 to SB10), the
controller 7 sets back the face detection mode to the speed preference mode (step SB12). Thereafter, thecontroller 7 causes the facedetection processing unit 15 to repeat the fast-speed face detection process again. - As explained above, according to the embodiment, the kind of the face detection mode is automatically set. Thereby, it enables an effective face detection in accordance with the specific contents of an object, such as the number of persons in the angle of view, and the largeness of a face, without placing an operational load on the user (photographer) at all.
- In addition, as the face detection mode is temporarily changed from the speed preference mode to the person-number preference mode, it is determined at all times whether or not a change to the person-number preference mode is necessary based on a result of face detection in the person-number preference mode. When it is determined that a change to the person-number preference mode is necessary, the face detection mode is automatically changed to the person-number preference mode, so that even if the specific contents of an object change at an arbitrary time, it is possible to cope with such a change promptly.
- In the embodiment, predetermined detection information of the invention is a size of a face detected through the face detection operation in the person-number preference mode. The face detection mode is changed over to the speed preference mode in a case where the predetermined information satisfies the detection condition in the speed preference mode, but the face detection mode may be changed over as follows.
- For example, in a case where the number of persons detected through the face detection operation in the person-number preference mode satisfies the detection condition of a face region in the speed preference mode, the face detection mode may be changed over to the speed preference mode. Furthermore, in a case where either one of the size of a face detected through the face detection operation or the number of detected faces in the person-number preference mode satisfies the detection condition of a face region in the speed preference mode, or both of the size of a face detected through the face detection operation or the number of detected faces in the person-number preference mode satisfy the detection condition of a face region in the speed preference mode, the face detection mode may be changed over to the speed preference mode. In particular, according to the latter case, it is possible to control the face detection mode which is further surely appropriate for the specific contents of an object.
- Further, in the embodiment, the explanation has been given of the case where the face detection modes are the speed preference mode and the person-number preference mode, and the detection condition of a face region in each mode is based on the values of plural parameters, such as the size of a smallest detectable face (minimum value of a face size), and a maximum number of faces detectable (maximum value of the number of detected faces). The detection condition of a face region in each face detection mode, however, may be based on the value of a single parameter.
- For example, each of the face detection modes may be a mode having a detection condition which is based on only the size of the smallest face detectable, or a mode having a detection condition which is based on the maximum number of faces should be detected, as long as individual modes have different detection condition of a face region.
- The detection condition of a face region in each face detection mode is not limited to one which is based on a single or two parameter values, and may be one which is based on more than or equal to three kinds of parameters. In this case, however, the specific operation of automatically determining a necessity of changing the face detection mode, and of changing over the face detection mode as needed becomes complex, as the kinds of the face detection mode are large numbers.
- In a case where a mode different from the foregoing speed preference mode and person-number preference mode is employed as a face detection mode, depending on a parameter deciding the detection condition of a face region in each mode, but the following operation may be applied. Namely, after the face detection mode is changed from one mode to the other mode, while a face detection is repeated through the other mode without temporarily changing the face detection mode to the one mode, it is determined at all times whether or not a change to the one mode is necessary based on predetermined detection information acquired through the face detection process. In a case where it is determined that a mode change is necessary, the face detection mode may be automatically changed over to the one mode from the other mode.
- The explanation has been given of the digital camera having the face
detection processing unit 15 which performs face detection on a frame image and acquires coordinate information on a face region in the first and second embodiments, but the invention is not limited to such a digital camera. For example, the invention can be applied to a digital camera having no facedetection processing unit 15, and structured in such a way that acontroller 7 performs face detection on a frame image and acquires coordinate information on a face region. Further, the explanation has been given of the case where the invention is applied to the digital camera having a general structure, but the invention is not limited to such a case, and can be applied to a digital camera built in another information device like a cellular phone, another image pickup device like a digital video camera, and another device like an image processing device as long as those have a face detection function. - Various embodiments and changes may be made thereunto without departing from the broad spirit and scope of the invention. The above-described embodiments are intended to illustrate the present invention, not to limit the scope of the present invention. The scope of the present invention is shown by the attached claims rather than the embodiments. Various modifications made within the meaning of an equivalent of the claims of the invention and within the claims are to be regarded to be in the scope of the present invention.
Claims (9)
1. An image pickup device comprising:
an image sensor which picks up an object image;
a selection control unit which selects any one of plural face detection modes set beforehand as an operation mode in detecting a face region; and
a face detection unit which detects a face region from the object image picked up by the image sensor in accordance with values of a first parameter and a second parameter, the first parameter and the second parameter corresponding to the face detection mode selected by the selection control unit and defining a detection condition for detecting a face region.
2. The image pickup device according to claim 1 , wherein the selection control unit selects any one of the plural face detection modes set beforehand as an operation mode in detecting a face region in response to a selection operation of a user.
3. The image pickup device according to claim 1 , further comprising a parameter setting unit which sets the values of the first parameter and the second parameter, the first parameter and the second parameter corresponding to a face detection mode selected by the selection control unit, and defining a detection condition for detecting a face region,
wherein the face detection unit detects a face region from the object image picked up by the image sensor in accordance with the values of the first and second parameters set by the parameter setting unit.
4. The image pickup device according to claim 1 , further comprising:
a parameter storing unit which stores the values of the first parameter and the second parameter in association with each face detection mode; and
a parameter read-out unit which reads out the values of the first parameter and the second parameter, corresponding to a face detection mode selected by a user through the selection control unit, from the parameter storing unit,
wherein the face detection unit detects a face region from the object image picked up by the image sensor in accordance with the values of the first parameter and the second parameter read out by the parameter read-out unit.
5. The image pickup device according to claim 1 , wherein the first parameter is a number of detected face regions from the object image, and the second parameter is a minimum size of a face region set as detectable from the object image.
6. The image pickup device according to claim 1 , further comprising:
an image recording unit which records an object image picked up by the image sensor;
an operation unit through which a user gives an image-pickup instruction of recording the object image in the image recording unit and sets an image-pickup preparation prior to the image pickup instruction; and
a mode control unit which always sets a face detection mode of the face detection unit to a face detection mode having the relatively highest detection precision in the plural face detection modes regardless of a face detection mode at a time when the image-pickup preparation is set, in response to the image-pickup preparation set by the user through the operation unit.
7. The image pickup device according to claim 1 , further comprising a display unit which displays the object image picked up by the image sensor together with an image representing a face region detected by the face detection unit.
8. A face detection method of detecting a face region from an object image picked up by an image sensor, comprising:
selecting any one of plural face detection modes as an operation mode in detecting a face region; and
detecting a face region from the object image picked up by the image sensor in accordance with values of a first parameter and a second parameter, the first parameter and the second parameter corresponding to the selected face detection mode and defining a detection condition for detecting a face region.
9. A non-transitory computer-readable recording medium recording a face detection control program that controls a computer of an image processing device having a face detection function of detecting a face region from an object image picked up by an image sensor to execute processes comprising:
selecting any one of plural face detection modes set beforehand as an operation mode in detecting a face region; and
detecting a face region from the object image picked up by an image sensor in accordance with values of a first parameter and a second parameter, the first parameter and the second parameter corresponding to the selected face detection mode and defining a detection condition for detecting a face region.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/191,927 US20110279701A1 (en) | 2007-05-18 | 2011-07-27 | Image pickup device, face detection method, and computer-readable recording medium |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2007-133353 | 2007-05-18 | ||
JP2007133353A JP4315215B2 (en) | 2007-05-18 | 2007-05-18 | Imaging apparatus, face detection method, and face detection control program |
US12/152,890 US8019129B2 (en) | 2007-05-18 | 2008-05-16 | Image pickup device, face detection method, and computer-readable recording medium |
US13/191,927 US20110279701A1 (en) | 2007-05-18 | 2011-07-27 | Image pickup device, face detection method, and computer-readable recording medium |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/152,890 Continuation US8019129B2 (en) | 2007-05-18 | 2008-05-16 | Image pickup device, face detection method, and computer-readable recording medium |
Publications (1)
Publication Number | Publication Date |
---|---|
US20110279701A1 true US20110279701A1 (en) | 2011-11-17 |
Family
ID=40027516
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/152,890 Active 2030-07-11 US8019129B2 (en) | 2007-05-18 | 2008-05-16 | Image pickup device, face detection method, and computer-readable recording medium |
US13/178,055 Active US8111881B2 (en) | 2007-05-18 | 2011-07-07 | Image pickup device, face detection method, and computer-readable recording medium |
US13/191,927 Abandoned US20110279701A1 (en) | 2007-05-18 | 2011-07-27 | Image pickup device, face detection method, and computer-readable recording medium |
Family Applications Before (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/152,890 Active 2030-07-11 US8019129B2 (en) | 2007-05-18 | 2008-05-16 | Image pickup device, face detection method, and computer-readable recording medium |
US13/178,055 Active US8111881B2 (en) | 2007-05-18 | 2011-07-07 | Image pickup device, face detection method, and computer-readable recording medium |
Country Status (5)
Country | Link |
---|---|
US (3) | US8019129B2 (en) |
JP (1) | JP4315215B2 (en) |
KR (1) | KR100951515B1 (en) |
CN (2) | CN101383905B (en) |
TW (1) | TWI373008B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100033592A1 (en) * | 2008-08-07 | 2010-02-11 | Canon Kabushiki Kaisha | Image pickup device and method of controlling same |
US10917563B2 (en) * | 2018-12-07 | 2021-02-09 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and non-transitory computer-readable storage medium |
US20210306556A1 (en) * | 2020-03-25 | 2021-09-30 | Casio Computer Co., Ltd. | Image processing device, image processing method, and non-transitory recording medium |
Families Citing this family (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5099488B2 (en) | 2007-08-31 | 2012-12-19 | カシオ計算機株式会社 | Imaging apparatus, face recognition method and program thereof |
JP2009089174A (en) * | 2007-10-01 | 2009-04-23 | Fujifilm Corp | Digital camera and photographing method thereof |
JP2009277027A (en) * | 2008-05-15 | 2009-11-26 | Seiko Epson Corp | Detection of organ area corresponding to facial organ image in image |
KR100965320B1 (en) * | 2008-10-08 | 2010-06-22 | 삼성전기주식회사 | Automatic controlling device of a continuous auto focus and Automatic controlling method of the same |
CN102150181A (en) * | 2008-12-05 | 2011-08-10 | 松下电器产业株式会社 | Face detection device |
JP2010147808A (en) * | 2008-12-18 | 2010-07-01 | Olympus Imaging Corp | Imaging apparatus and image processing method in same |
JP4760918B2 (en) * | 2009-01-23 | 2011-08-31 | カシオ計算機株式会社 | Imaging apparatus, subject tracking method, and program |
WO2010109613A1 (en) * | 2009-03-25 | 2010-09-30 | 富士通株式会社 | Playback control program, playback control method, and playback device |
JP2010251817A (en) * | 2009-04-10 | 2010-11-04 | Sony Corp | Imaging apparatus and method, and program |
JP2011022203A (en) * | 2009-07-13 | 2011-02-03 | Fujifilm Corp | Af frame automatic follow-up system and method for automatically following up af frame |
KR20110060295A (en) * | 2009-11-30 | 2011-06-08 | 삼성전자주식회사 | Digital photographing apparatus and controlling method thereof |
KR20120068078A (en) * | 2010-10-26 | 2012-06-27 | 삼성전자주식회사 | Image photographing apparatus and method for connecting audio data to image data thereof |
JP5182352B2 (en) * | 2010-11-16 | 2013-04-17 | カシオ計算機株式会社 | Imaging apparatus, image composition method, and program |
KR20140114832A (en) | 2012-01-20 | 2014-09-29 | 톰슨 라이센싱 | Method and apparatus for user recognition |
CN103489107B (en) * | 2013-08-16 | 2015-11-25 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus making virtual fitting model image |
RU2613852C2 (en) * | 2014-10-03 | 2017-03-21 | Юрий Николаевич Хомяков | Method of personal identification by digital facial image |
US9986289B2 (en) | 2015-03-02 | 2018-05-29 | The Nielsen Company (Us), Llc | Methods and apparatus to count people |
CN106210514B (en) * | 2016-07-04 | 2019-04-12 | Oppo广东移动通信有限公司 | It takes pictures the method, apparatus and smart machine of focusing |
KR102488563B1 (en) * | 2016-07-29 | 2023-01-17 | 삼성전자주식회사 | Apparatus and Method for Processing Differential Beauty Effect |
EP3355243A1 (en) | 2017-01-30 | 2018-08-01 | Canon Kabushiki Kaisha | Information processing apparatus, information processing method, and program |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040207743A1 (en) * | 2003-04-15 | 2004-10-21 | Nikon Corporation | Digital camera system |
US20070076979A1 (en) * | 2005-10-03 | 2007-04-05 | Microsoft Corporation | Automatically cropping an image |
US7583294B2 (en) * | 2000-02-28 | 2009-09-01 | Eastman Kodak Company | Face detecting camera and method |
Family Cites Families (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7415126B2 (en) * | 1992-05-05 | 2008-08-19 | Automotive Technologies International Inc. | Occupant sensing system |
JP2000048184A (en) | 1998-05-29 | 2000-02-18 | Canon Inc | Method for processing image, and method for extracting facial area and device therefor |
US6445819B1 (en) * | 1998-09-10 | 2002-09-03 | Fuji Photo Film Co., Ltd. | Image processing method, image processing device, and recording medium |
US6226409B1 (en) * | 1998-11-03 | 2001-05-01 | Compaq Computer Corporation | Multiple mode probability density estimation with application to sequential markovian decision processes |
US6639998B1 (en) * | 1999-01-11 | 2003-10-28 | Lg Electronics Inc. | Method of detecting a specific object in an image signal |
US7092569B1 (en) * | 1999-07-29 | 2006-08-15 | Fuji Photo Film Co., Ltd. | Method and device for extracting specified image subjects |
US20040051336A1 (en) * | 2002-09-17 | 2004-03-18 | Dah-Shiarn Chiao | Conformal weather shield and garments |
KR100474312B1 (en) * | 2002-12-12 | 2005-03-10 | 엘지전자 주식회사 | Automatic zooming method for digital camera |
US7362919B2 (en) * | 2002-12-12 | 2008-04-22 | Eastman Kodak Company | Method for generating customized photo album pages and prints based on people and gender profiles |
JP4461789B2 (en) * | 2003-03-20 | 2010-05-12 | オムロン株式会社 | Image processing device |
JP3845867B2 (en) * | 2003-03-27 | 2006-11-15 | ソニー株式会社 | Imaging apparatus and imaging method |
JP4338560B2 (en) | 2003-04-14 | 2009-10-07 | 富士フイルム株式会社 | Image feature portion extraction method, feature portion extraction program, imaging apparatus, and image processing apparatus |
US7616233B2 (en) * | 2003-06-26 | 2009-11-10 | Fotonation Vision Limited | Perfecting of digital image capture parameters within acquisition devices using face detection |
US7920723B2 (en) * | 2005-11-18 | 2011-04-05 | Tessera Technologies Ireland Limited | Two stage detection for photographic eye artifacts |
US8948468B2 (en) * | 2003-06-26 | 2015-02-03 | Fotonation Limited | Modification of viewing parameters for digital images using face detection information |
US7574016B2 (en) * | 2003-06-26 | 2009-08-11 | Fotonation Vision Limited | Digital image processing using face detection information |
US7440593B1 (en) * | 2003-06-26 | 2008-10-21 | Fotonation Vision Limited | Method of improving orientation and color balance of digital images using face detection information |
FR2857481A1 (en) * | 2003-07-08 | 2005-01-14 | Thomson Licensing Sa | METHOD AND DEVICE FOR DETECTING FACES IN A COLOR IMAGE |
JP2005117242A (en) * | 2003-10-06 | 2005-04-28 | Canon Inc | Imaging apparatus and control method therefor |
JP4046079B2 (en) * | 2003-12-10 | 2008-02-13 | ソニー株式会社 | Image processing device |
JP2005182196A (en) * | 2003-12-16 | 2005-07-07 | Canon Inc | Image display method and image display device |
JP2005215750A (en) * | 2004-01-27 | 2005-08-11 | Canon Inc | Face detecting device and face detecting method |
US7620242B2 (en) * | 2004-04-06 | 2009-11-17 | Fujifilm Corporation | Particular-region detection method and apparatus, and program therefor |
JP2006018805A (en) | 2004-06-02 | 2006-01-19 | Fuji Photo Film Co Ltd | Particular region detection method, particular region detection apparatus and program |
JP4757559B2 (en) | 2004-08-11 | 2011-08-24 | 富士フイルム株式会社 | Apparatus and method for detecting components of a subject |
KR20060035198A (en) * | 2004-10-21 | 2006-04-26 | 주식회사 팬택앤큐리텔 | Auto zooming system used face recognition technology and mobile phone installed it and auto zooming method used face recognition technology |
JP2008236645A (en) * | 2007-03-23 | 2008-10-02 | Fujifilm Corp | Photographing device |
JP2008244804A (en) * | 2007-03-27 | 2008-10-09 | Fujifilm Corp | Image-taking device and method, and control program |
JP5418991B2 (en) * | 2008-07-10 | 2014-02-19 | 日本電気株式会社 | Personal authentication system, personal authentication method |
JP2010171797A (en) * | 2009-01-23 | 2010-08-05 | Nikon Corp | Imaging apparatus and program |
-
2007
- 2007-05-18 JP JP2007133353A patent/JP4315215B2/en not_active Expired - Fee Related
-
2008
- 2008-05-15 TW TW097117769A patent/TWI373008B/en not_active IP Right Cessation
- 2008-05-16 KR KR1020080045596A patent/KR100951515B1/en active IP Right Grant
- 2008-05-16 US US12/152,890 patent/US8019129B2/en active Active
- 2008-05-16 CN CN200810173701XA patent/CN101383905B/en active Active
- 2008-05-16 CN CN2010105056768A patent/CN101945222B/en active Active
-
2011
- 2011-07-07 US US13/178,055 patent/US8111881B2/en active Active
- 2011-07-27 US US13/191,927 patent/US20110279701A1/en not_active Abandoned
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7583294B2 (en) * | 2000-02-28 | 2009-09-01 | Eastman Kodak Company | Face detecting camera and method |
US20040207743A1 (en) * | 2003-04-15 | 2004-10-21 | Nikon Corporation | Digital camera system |
US20070076979A1 (en) * | 2005-10-03 | 2007-04-05 | Microsoft Corporation | Automatically cropping an image |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100033592A1 (en) * | 2008-08-07 | 2010-02-11 | Canon Kabushiki Kaisha | Image pickup device and method of controlling same |
US8223253B2 (en) * | 2008-08-07 | 2012-07-17 | Canon Kabushiki Kaisha | Image pickup device and method of controlling same |
US10917563B2 (en) * | 2018-12-07 | 2021-02-09 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and non-transitory computer-readable storage medium |
US20210306556A1 (en) * | 2020-03-25 | 2021-09-30 | Casio Computer Co., Ltd. | Image processing device, image processing method, and non-transitory recording medium |
Also Published As
Publication number | Publication date |
---|---|
US20080285817A1 (en) | 2008-11-20 |
CN101383905A (en) | 2009-03-11 |
JP2008289006A (en) | 2008-11-27 |
CN101945222B (en) | 2013-03-13 |
US8019129B2 (en) | 2011-09-13 |
US20110261222A1 (en) | 2011-10-27 |
US8111881B2 (en) | 2012-02-07 |
KR20080101779A (en) | 2008-11-21 |
TW200903384A (en) | 2009-01-16 |
CN101945222A (en) | 2011-01-12 |
CN101383905B (en) | 2013-04-03 |
KR100951515B1 (en) | 2010-04-07 |
JP4315215B2 (en) | 2009-08-19 |
TWI373008B (en) | 2012-09-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8111881B2 (en) | Image pickup device, face detection method, and computer-readable recording medium | |
US8144230B2 (en) | Camera, storage medium having stored therein camera control program, and camera control method | |
JP4591325B2 (en) | Imaging apparatus and program | |
JP4919160B2 (en) | Imaging apparatus and program thereof | |
US20090027515A1 (en) | Image pickup apparatus | |
JP5182253B2 (en) | Imaging device | |
JP5045731B2 (en) | Imaging apparatus, white balance setting method, and program | |
US8181121B2 (en) | Display unit and display method | |
JP4632417B2 (en) | Imaging apparatus and control method thereof | |
JP2006276683A (en) | Imaging apparatus and program | |
US20050057678A1 (en) | Digital camera and control method for digital camera | |
US20210029291A1 (en) | Apparatus, method, and storage medium | |
JP6143181B2 (en) | Imaging apparatus, moving image shooting method, and program | |
JP4307061B2 (en) | Imaging device | |
JP2009049639A (en) | Image pick-up device | |
JP4983672B2 (en) | Imaging apparatus and program thereof | |
JP4556968B2 (en) | Face detection device, face detection method, and face detection program | |
JP4872801B2 (en) | Imaging apparatus, imaging method, and imaging program | |
JP2008071150A (en) | Image processor, image processing program, and photographing device | |
US20120154617A1 (en) | Image capturing device | |
JP3466912B2 (en) | Digital camera, image processing method, storage medium | |
JP2017050591A (en) | Imaging controller, imaging control method, and program | |
JP2010087760A (en) | Imaging apparatus, display method and program | |
JP2007221680A (en) | Camera |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |