JP2007140897A - Image search device and method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To enable the selection of, for example, images to be printed out from a plurality of images while dispensing with complicated operations. <P>SOLUTION: A face detection part 32 detects face areas from a plurality of images read out from a memory card 2. A person identification part 34 identifies persons included in the plurality of images according to the detected face areas. A search part 36 searches the plurality of images for images including the person out of the identified persons who is included most frequently in the plurality of images. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to an image search apparatus and method for searching for an image to be used for printing or the like from a plurality of images, and a program for causing a computer to execute the image search method.

  An image acquired by photographing using a digital camera or the like or an image acquired by reading from a negative film is printed out by a home printer or a printer of a photo shop. Various methods for printing out images more easily have been proposed. For example, Patent Document 1 describes a method of selecting and outputting a paper size to be printed according to the size of an image when printing an image read from a document such as a negative film.

By the way, when printing out an image, all of a plurality of acquired images may be printed. In many cases, a user selects an image desired to be printed from a plurality of images, and only the selected image is printed. Output. In this case, a list of a plurality of images is displayed using viewer software or the like, and an image desired to be printed is selected while viewing the displayed list.
JP-A-5-292262

  However, the operation of selecting a desired image from a plurality of images is very complicated. In particular, thumbnail images with reduced images are displayed in the list, so it is difficult to check the person included in the image. To check the person, it is necessary to enlarge each image and check it. Yes, making the work of selecting images more complicated.

  The present invention has been made in view of the above circumstances, and an object of the present invention is to make it possible to select, for example, an image used for print output from a plurality of images without performing complicated operations.

A first image search apparatus according to the present invention includes a face detection unit that detects a face region from each of a plurality of images,
A person specifying means for specifying a person included in the plurality of images based on the detected face area;
Search means for searching the plurality of images for an image including the person most frequently included in the plurality of images among the specified persons is provided.

  In the first image search apparatus according to the present invention, the search means may be means for further searching for an image not including a person from the plurality of images.

A second image search device according to the present invention includes a specifying unit that receives a specification of at least one person to be searched among persons included in a plurality of images.
Face detecting means for detecting a face area from each of the plurality of images;
The image processing apparatus includes a search unit that searches the plurality of images for an image including the specified at least one person based on the detected face area.

  The “image including at least one designated person” is an image including that person when the designated person is one person. In addition, when there are a plurality of designated persons, any of an image including the specified individual person, an image including only the specified individual person, and an image including all the specified persons may be used. .

  In the second image retrieval apparatus according to the present invention, the retrieval means retrieves, from the plurality of images, an image whose facial expression matches that of the designated person when the designated person is one person. It is good.

  In the second image search apparatus according to the present invention, the search means may be means for further searching for an image not including a person from the plurality of images.

A first image search method according to the present invention detects a face region from each of a plurality of images,
Based on the detected face area, the person included in the plurality of images is identified,
Among the identified persons, an image including the person most frequently included in the plurality of images is searched from the plurality of images.

The second image search method according to the present invention accepts designation of at least one person to be searched among persons included in a plurality of images,
Detecting a face region from each of the plurality of images;
Based on the detected face area, an image including the designated at least one person is searched from the plurality of images.

  In addition, you may provide as a program for making a computer perform the 1st and 2nd image search method by this invention.

  When a user selects an image to be used for printing or the like from a plurality of images, the user often selects an image included in the user, and the image owned by the user includes the most users. It is what.

  According to the first image search device and method of the present invention, a face area is detected from each of a plurality of images, a person included in the plurality of images is identified based on the detected face area, and the identified person's Among them, the image including the person most frequently included in the plurality of images is searched from the plurality of images, so that the user can select an image to be used for printing or the like from the plurality of images without performing the operation of selecting the image. Can do.

  On the other hand, when the user selects an image to be used for printing or the like from a plurality of images, for example, when the user wants to give a print to a friend, it is necessary to print an image including the friend.

  According to the second image search apparatus and method of the present invention, the designation of at least one person to be searched among the persons included in the plurality of images is accepted, the face area is detected from each of the plurality of images, and the detection is performed. Since the image including at least one specified person is searched from a plurality of images based on the face area, the user can display the image especially when he / she wants to print and pass an image showing a friend to a friend. An image used for printing or the like can be selected from a plurality of images without performing a selection operation.

  Further, when the designated person is one person, the image of the person having the desired facial expression is selected from the plurality of images by searching the plurality of images for images that match the expression of the designated person. be able to.

  In addition, when selecting an image to be used for printing or the like from a plurality of images, an image such as a landscape that does not include a person is often selected. Therefore, by further searching for an image that does not include a person from a plurality of images, an image such as a landscape that does not include a person can be selected from the plurality of images without performing complicated operations.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is an external perspective view of an image print order receiving apparatus to which an image selection apparatus according to an embodiment of the present invention is applied. As shown in FIG. 1, a print order receiving apparatus 1 according to the present embodiment is installed at a photo shop in order to receive an image print order by a user, and an image for ordering a print is recorded. Various memory cards 2 are loaded, a plurality of card slots 4 for reading out images from the memory card 2 and recording images on the memory card 2, and a display unit 6 for performing various displays for ordering prints. And is connected to a printer 8 installed in the photo shop. The display unit 6 includes a touch panel type input unit, and the user can input necessary for the print order by touching the display unit 6 according to the display on the monitor 6.

  FIG. 2 is a schematic block diagram showing the configuration of the print order receiving apparatus according to the first embodiment of the present invention. As shown in FIG. 2, the print order receiving apparatus 1 performs various controls such as recording control and display control of image data representing an image, and operates the apparatus 1 and a CPU 12 that controls each part of the apparatus 1. A system memory 14 composed of a ROM in which a basic program and various constants for recording are recorded, and a RAM serving as a work area when the CPU 12 executes processing, and various instructions to the device 1 Touch panel type input unit 16 and the display unit 6 described above.

  The print order receiving apparatus 1 also includes the card slot 4 described above, a compression / decompression unit 22 that compresses image data by a technique typified by JPEG, and decompresses the compressed image data, and an image read from the memory card 2. A hard disk 24 that records various programs executed by the CPU 12 such as a print ordering program for ordering data and images, a memory control unit 26 that controls the system memory 14, the card slot 4, and the hard disk 24, and a display unit 6, and a printer interface 30 for connecting the printer 8 to the apparatus 1.

  Although a plurality of card slots 4 are prepared according to the type of the memory card 2, only one card slot 4 is shown in FIG.

  The print order receiving apparatus 1 also detects a face detection unit 32 that detects all face areas from each of a plurality of images recorded on the memory card 2 and a plurality of images based on the detected face areas, as will be described later. Are provided with a person specifying unit 34 for specifying the person most frequently included, and a search unit 36 for searching for an image including the specified person from a plurality of images.

  Hereinafter, functions of the face detection unit 32, the person identification unit 34, and the search unit 36 will be described together with processing performed in this embodiment.

  FIG. 3 is a flowchart showing processing performed at the time of image reading performed in the first embodiment. When the user loads the memory card 2 into the card slot 4 and issues an image reading instruction from the input unit 16, the CPU 12 starts processing, and reads a plurality of images recorded on the memory card 2 (step ST1). Next, the face detection unit 32 detects all face areas of the person from each of the plurality of images (step ST2). Specifically, for example, an area having a flesh color in an image and forming a face outline shape is detected as a face area. Note that a face area is not detected for an image such as a background or a still life that does not include a face area.

  Next, the person specifying unit 34 specifies the person in the face area for the image in which the face area is detected in the order of the file names of the images (step ST3). As a method for identifying a person, for example, a plurality of feature amounts representing facial features such as contour shapes, face parts constituting the face such as eyes, mouth and nose, and skin color are obtained from the face region. The file name associates the person included in the first image with the obtained feature quantity, and assigns an identification number to the person included in the image according to the number of persons included.

  Specifically, first, with respect to the image whose file name is the first, identification numbers are sequentially assigned from 1 to the person whose feature value has been obtained. For the second and subsequent images, the feature quantities obtained from the face area are compared with the feature quantities of the already identified person, and the obtained feature quantities and the feature quantities of the already identified person are compared. If the difference between and is within a predetermined range, the person in the detected face area is regarded as a person corresponding to the feature amount for which the difference is within the predetermined range. The identification number of the person who obtained the corresponding feature amount is assigned. In addition, when the difference with the feature-value corresponding to all the already detected persons does not become in a predetermined range, a new identification number is provided to the person of the detected face area.

  A person may be specified by obtaining a correlation value between extracted face areas and assigning the same identification number to face areas having a correlation value equal to or greater than a predetermined value.

  The person specifying unit 34 creates a person information file describing the number of persons and an identification number corresponding to the included person for all the images, and stores them in the hard disk 24 in association with the images (step ST4). An image in which no face area is detected is described as the number of persons = 0 in the person information file.

  When the person is specified for all the images, the person specifying unit 34 creates an aggregation file in which the identification number is associated with the number of images including the person corresponding to the identification number, and this is stored in the hard disk 24. (Step ST5), and the process ends.

  FIG. 4 is a diagram showing the contents of an image, a person information file, and a total file when there are seven images read from the memory card 2. As shown in FIG. 4, each image is an image in JPEG format, and is associated with a person information file having the same file name and a text extension. Here, by referring to the person information file associated with each image, for example, the file name is DSCF0727. Since the JPG image is described as “number of persons = 0”, no person is included, and the file name is DSCF0740. Since the JPG image is described as “number of persons = 3, person 1: identification number = 1, person 2: identification number = 2, person 3: identification number = 3”, three persons are included. It can be seen that the respective identification numbers are 1, 2, and 3. In addition, by referring to the summary file whose file name is info.txt, the number of persons included in the seven images to be processed is 3, and the person whose identification number is 1 is included in one image. It can be seen that the person with the identification number 2 is included in the four images, and the person with the identification number 3 is included in the three images.

  Next, processing performed at the time of printing in the first embodiment will be described. FIG. 5 is a flowchart showing processing performed at the time of printing in the first embodiment. When the user issues a print execution instruction from the input unit 16, the CPU 12 starts processing. First, the search unit 36 sets the processing target to the first image with the file name (step ST11), and the total file and processing target image. Referring to the person information file, it is determined whether or not the image to be processed includes a person (step ST12). In this case, if “number of persons = 0” is described in the person information file attached to the image to be processed, step ST12 is negative, and if a number other than 0 is described in the number of persons. Step ST12 is affirmed. If step ST12 is negative, a processing target image is selected from a plurality of images (step ST13).

  When step ST12 is affirmed, the search unit 36 compares the description of the summary file with the description of the person information file given to the processing target image, so that the person specifying unit 34 specifies the processing target image. It is determined whether or not the included person includes the person most frequently captured in a plurality of images read from the memory card 2 (step ST14). If step ST14 is affirmed, the process proceeds to step ST13, and an image to be processed is selected from a plurality of images.

  Subsequent to step ST13 and when step ST14 is negative, it is determined whether or not the processing of all images has been completed (step ST15). When step ST15 is negative, the image to be processed is set to the next image. (Step ST16), the process returns to step ST12, and the processes after step ST12 are repeated. If step ST15 is affirmed, the selected image is printed out from the printer 8 (step ST17), and the process ends.

  As a result, only an image that does not include a person and an image that includes a person who is captured most frequently are retrieved and printed out. Specifically, as shown in FIG. 4, since the person most frequently included in the plurality of images is the person with the identification number = 2, the file name in which the person with the identification number = 2 is shown is DSCF0740. JPG, DSCF0741. JPG, DSCF07443. JPG, DSCF0747. JPG images and file names that do not contain people are DSCF0727. JPG, DSCF0728. A JPG image is retrieved from a plurality of images and printed out.

  As described above, according to the first embodiment, a face area is detected from each of a plurality of images, a person included in the plurality of images is identified based on the detected face area, and a plurality of the identified persons are identified. Since the image including the person most frequently shown in the image is searched from a plurality of images, the user can select an image to be used for printing or the like from the plurality of images without performing an operation of selecting the image. .

  In addition, when selecting an image to be used for printing or the like from a plurality of images, an image such as a landscape that does not include a person is often selected. For this reason, by further searching for an image that does not include a person from a plurality of images, it is possible to select an image such as a landscape that does not include a person from the plurality of images without performing complicated operations.

  Next, a second embodiment of the present invention will be described. FIG. 6 is a schematic block diagram showing the configuration of the print order receiving apparatus according to the second embodiment of the present invention. In the second embodiment, the same components as those in the first embodiment are denoted by the same reference numerals, and detailed description thereof is omitted here. The print order receiving apparatus 1A according to the second embodiment includes a person specifying unit 34A and a searching unit 36A that perform processing different from the person specifying unit 34 and the searching unit 36 in the first embodiment.

  Next, processing performed in the second embodiment will be described.

  FIG. 7 is a flowchart showing processing performed at the time of image reading performed in the second embodiment. When the user loads the memory card 2 into the card slot 4 and issues an image reading instruction from the input unit 16, the CPU 12 starts processing, and reads a plurality of images recorded on the memory card 2 (step ST21). Next, the face detection unit 32 detects a human face area from each of the plurality of images (step ST22).

  Next, the person specifying unit 34A specifies a person in the order of the file names of the images in the same manner as in the first embodiment with respect to the image including the face area (step ST23).

  Then, the person specifying unit 34 creates a person information file describing the number of persons and an identification number when the person is included for the image specifying the person, and stores it in the hard disk 24 in association with the image (step ST24), the process ends. The person information file is the same as that in the first embodiment.

  Next, processing for designating a person to be searched in the second embodiment will be described. FIG. 8 is a flowchart of person designation processing in the second embodiment. When the user issues a person designation instruction from the input unit 16, the CPU 12 starts processing, and a person designation screen for allowing the user to designate a person is displayed on the display unit 18 (step ST31).

  FIG. 9 is a diagram showing a person designation screen in the second embodiment. As shown in FIG. 9, the person designation screen 40 includes an image area 40A for displaying an image for designating a person, a setting button 40B for setting the designated person as a search target, and designating a plurality of persons. And an AND button 40C for setting an image including all the specified persons as a search target, and when a plurality of persons are specified, an image including only the specified person is set as a search target. or button 40D is displayed.

  Here, the image displayed in the image area 40A is a minimum image including all persons included in the plurality of images read from the memory card 2. For example, when images similar to those in the first and the above-described embodiments are recorded on the memory card 2, a plurality of images include a total of three persons, and therefore a file in which all three persons are shown. The name is DSCF0740. A JPG image is displayed in the image area 40A.

  The user designates a desired person in the displayed image using the input unit 16. In addition, as a method of designating a person, a technique such as enclosing a person's face with a rectangular area can be used. When a person is specified and the setting button 40B is selected, the person specifying unit 34A generates a specified person file describing an identification number representing the selected person, stores it in the hard disk 24 (step ST33), and ends the process. . FIG. 10A shows the description content of the designated person file when only one person is designated. As shown in FIG. 10A, in the designated person file, information (search candidate = 1) indicating that there is one search candidate and the identification number of the designated person are described.

  At this time, a plurality of persons may be designated. When a plurality of persons are specified and the setting button 40B is selected and then the and button 40C is selected, the person specifying unit 34A selects the image including all the specified persons as a search target to be described later. A designated person file in which identification numbers representing persons are collectively described is generated. The description content of the designated person file in this case is shown in FIG. As shown in FIG. 10B, in the designated person file, information indicating that there is one search candidate and identification numbers of a plurality of designated persons are described.

  When the or button 40D is selected after selecting the setting button 40B when a plurality of persons are specified, the person specifying unit 34A selects an image including only the specified person as a search target to be described later in units of persons. A designated person file in which an identification number representing the selected person is individually described is generated. The description content of the designated person file in this case is shown in FIG. As shown in FIG. 10C, the designated person file is searched for information including a plurality of search candidates (here, two), an identification number of the designated person, and an image including only the designated person. Information of “or = 1” is described.

  When the setting button 40B is selected when a plurality of persons are specified, the person specifying unit 34A sets an identification number representing the selected person so that an image including the specified person is a search target to be described later in units of persons. Generate individually specified person files. The description content of the designated person file in this case is shown in FIG. As shown in FIG. 10D, the designated person file includes information indicating that there are a plurality of search candidates (here, two), the identification number of the designated person, and the designated person (not only). Information of “or = 0” representing image search is described.

  Next, processing performed at the time of printing in the second embodiment will be described. FIG. 11 is a flowchart showing processing performed at the time of printing in the second embodiment. In the following description, it is assumed that the user designates only one person. When the user issues a print execution instruction from the input unit 16, the CPU 12 starts processing. First, the search unit 36A sets the processing target as the first image (step ST41), and designates the designated person file and the processing target. With reference to the person information file of the image, it is determined whether or not the image to be processed includes a person (step ST42). If step ST42 is negative, an image to be processed is selected from a plurality of images (step ST43).

  If step ST42 is positive, the search unit 36A determines whether or not the processing target image includes a person designated by the user (step ST44). If step ST44 is affirmed, the process proceeds to step ST43, and an image to be processed is selected from a plurality of images. As a result, an image not including a person and an image including a person designated by the user are searched from a plurality of images.

  Subsequent to step ST43 and when step ST44 is negative, it is determined whether or not the processing of all images has been completed (step ST45). When step ST45 is negative, the image to be processed is set to the next image. (Step ST46), the process returns to step ST42, and the processes after step ST42 are repeated. If step ST45 is affirmed, the selected image is printed out from the printer 8 (step ST47), and the process is terminated.

  As a result, only an image including no person and an image including a person designated by the user are printed out. Specifically, if the person designated by the user is a person with identification number = 2, the file name in which the person with identification number = 2 is shown is DSCF0740. JPG, DSCF0741. JPG, DSCF0744. JPG, DSCF0747. JPG images and file names that do not contain people are DSCF0727. JPG, DSCF0728. A JPG image is retrieved from a plurality of images and printed out.

  When the designated person file designates a search for an image including both persons having identification numbers = 2 and 3 as shown in FIG. 10B, both persons having identification numbers = 2 and 3 are specified. Is the file name DSCF0740. JPG, DSCF0741. JPG images and file names that do not contain people are DSCF0727. JPG, DSCF0728. A JPG image is retrieved from a plurality of images and printed out.

  Further, when the designated person file designates a search for an image including only the persons with identification numbers = 2 and 3 as shown in FIG. 10C, only the person with the identification number = 2 is first selected. The file name shown is DSCF0744. JPG, DSCF0747. JPG images and file names that do not contain people are DSCF0727. JPG, DSCF0728. A JPG image is retrieved from a plurality of images and printed out. Next, the file name in which only the person with the identification number = 3 is shown is DSCF0742. JPG images and file names that do not contain people are DSCF0727. JPG, DSCF0728. A JPG image is retrieved from a plurality of images and printed out.

  If the designated person file designates a search for an image including each of the persons with identification numbers = 2 and 3 as shown in FIG. 10D, the person with the identification number = 2 is shown first. File name is DSCF0740. JPG, DSCF0741. JPG, DSCF0744. JPG, DSCF0747. JPG images and file names that do not contain people are DSCF0727. JPG, DSCF0728. A JPG image is retrieved from a plurality of images and printed out. Next, the file name in which the person with the identification number = 3 is shown is DSCF0740. JPG, DSCF0741. JPG, DSCF0742. JPG images and file names that do not contain people are DSCF0727. JPG, DSCF0728. A JPG image is retrieved from a plurality of images and printed out.

  As described above, according to the second embodiment of the present invention, the designation of at least one person to be searched is accepted, the face area is detected from each of the plurality of images, and the designation is made based on the detected face area. Since the image including at least one person is searched from a plurality of images, the user does not need to select the image, especially when the image showing the friend is printed and given to the friend. Images to be used for printing can be selected from a plurality of images.

  In the second embodiment, when an or button 40D is selected subsequent to the setting button 40B after one person is designated, an image including only the designated person may be selected.

  Next, a third embodiment of the present invention will be described. FIG. 12 is a schematic block diagram showing a configuration of a print order receiving apparatus according to the third embodiment of the present invention. In the third embodiment, the same components as those in the second embodiment are denoted by the same reference numerals, and detailed description thereof is omitted here. The print order receiving apparatus 1B according to the third embodiment includes a person specifying unit 34B and a search unit 36B that perform processing different from the person specifying unit 34A and the search unit 36A in the second embodiment.

  Next, processing performed in the third embodiment will be described. Note that the processing performed at the time of reading an image in the third embodiment is the same as that in the second embodiment, so detailed description thereof will be omitted here, and processing from designating a person to be searched will be described. FIG. 13 is a flowchart of person designation processing in the third embodiment. When the user gives an instruction to specify a person from the input unit 16, the CPU 12 starts processing, and displays a person specifying screen for specifying the user's person on the display unit 18 (step ST51).

  FIG. 14 is a diagram showing a person designation screen in the third embodiment. As shown in FIG. 14, the person designation screen 42 displays an image area 42A for displaying an image for designating a person, and a setting button 42B for setting the designated person as a search target.

  As shown in FIG. 14, the image displayed in the image area 42 </ b> A is an image including a person among a plurality of images read from the memory card 2.

  The user uses the input unit 16 to specify an image in which one person having a desired facial expression is shown in the displayed image. In addition, as a method of designating a person, a technique such as enclosing a person's face with a rectangular area can be used. When the setting button 42B is selected surrounding the person, the person specifying unit 34B generates a designated person file in which an identification number representing the selected person is registered, stores it in the hard disk 24 (step ST53), and ends the process. The description content of the designated person file in this case is as shown in FIG.

  Next, processing performed at the time of printing in the third embodiment will be described. FIG. 15 is a flowchart showing processing performed at the time of printing in the third embodiment. When the user issues a print execution instruction from the input unit 16, the CPU 12 starts processing. First, the search unit 36B sets the processing target as the first image (step ST61), and designates the designated person file and the processing target. With reference to the person information file of the image, it is determined whether or not the image to be processed includes a person (step ST62). If step ST62 is negative, an image to be processed is selected from a plurality of images (step ST63).

  If step ST62 is positive, the search unit 36B determines whether or not the processing target image includes a person designated by the user (step ST64). At this time, the search unit 36B compares the plurality of feature amounts obtained from the face area of the person included in the image designated by the user with the plurality of feature amounts obtained from the face area included in the processing target image, When the difference between the feature amounts is within a predetermined range, it is determined that the processing target image includes a person designated by the user. Note that the “predetermined range” in the third embodiment is smaller than the “predetermined range” in the second embodiment. Thereby, for example, when the person designated by the user has a smiling expression, even if the person designated by the user is included in the image to be processed, it is included in the image to be processed. Only when the person's facial expression is a laughing expression, the image to be processed is selected from a plurality of images.

  When step ST64 is affirmed, the process proceeds to step ST63, and an image to be processed is selected from a plurality of images. Thereby, an image including no person and an image including a person designated by the user are searched from a plurality of images.

  Subsequent to step ST63 and when step ST64 is denied, it is determined whether or not all the images have been processed (step ST65). When step ST65 is denied, the image to be processed is set to the next image. (Step ST66), the process returns to step ST62, and the processes after step ST62 are repeated. If step ST65 is positive, the selected image is printed out from the printer 8 (step ST67), and the process ends.

  As a result, only an image including no person and an image including a person designated by the user are printed out. Specifically, when the person designated by the user is a person with identification number = 2 and the person has a laughing expression, the person including the person with identification number = 2 has a laughing expression. An image that does not include a person and an image that does not include a person are retrieved from a plurality of images and printed out.

  In the first to third embodiments, an image that does not include a person is retrieved and printed out. However, an image that does not include a person may not be searched and printed out.

  In the above embodiment, the image search apparatus according to the present invention is used as a print order receiving apparatus. However, the image search apparatus according to the present invention may be used alone or provided in a device that handles images such as a digital camera. Also good.

  Although the apparatus according to the embodiment of the present invention has been described above, the computer functions as a unit corresponding to the face detection unit 32, the person identification units 34, 34A, 34B, and the search units 36, 36A, 36B. A program that performs processing as shown in 3, 5, 7, 8, 11, 13, and 15 is also one embodiment of the present invention. A computer-readable recording medium in which such a program is recorded is also one embodiment of the present invention. Further, such a program may be incorporated in viewer software for browsing images.

1 is an external perspective view of a print order receiving apparatus to which an image selection apparatus according to a first embodiment of the present invention is applied. 1 is a schematic block diagram showing the configuration of a print order receiving apparatus according to a first embodiment of the present invention. The flowchart which shows the process performed at the time of the image reading performed in 1st Embodiment Diagram showing contents of image, person information file and summary file The flowchart which shows the process performed at the time of printing in 1st Embodiment. Schematic block diagram showing the configuration of a print order receiving apparatus according to a second embodiment of the present invention The flowchart which shows the process performed at the time of the reading of the image performed in 2nd Embodiment Flowchart of person designation processing in the second embodiment The figure which shows the person designation | designated screen in 2nd Embodiment Diagram showing the contents of the specified person file The flowchart which shows the process performed at the time of printing in 2nd Embodiment Schematic block diagram showing the configuration of a print order receiving apparatus according to a third embodiment of the present invention Flowchart of person designation processing in the third embodiment The figure which shows the person designation | designated screen in 3rd Embodiment The flowchart which shows the process performed at the time of printing in 3rd Embodiment

Explanation of symbols

1, 1A, 1B Print order acceptance device 2 Memory card 4 Card slot 6 Display unit 8 Printer 12 CPU
14 System memory 16 Input unit 22 Compression / decompression unit 24 Hard disk 26 Memory control unit 28 Display control unit 30 Printer interface 32 Face detection unit 34, 34A, 34B Person identification unit 36, 36A, 36B Search unit

Claims (9)

Face detection means for detecting a face area from each of a plurality of images;
A person specifying means for specifying a person included in the plurality of images based on the detected face area;
An image search apparatus comprising: search means for searching the plurality of images for an image including the person most frequently included in the plurality of images among the specified persons.   2. The image search apparatus according to claim 1, wherein the search means is means for further searching for an image not including a person from the plurality of images. A designation means for accepting designation of at least one person to be searched among persons included in the plurality of images;
Face detecting means for detecting a face area from each of the plurality of images;
An image search apparatus comprising: search means for searching an image including the specified at least one person from the plurality of images based on the detected face area.   4. The image search according to claim 3, wherein, when the designated person is one person, the retrieval means is a means for retrieving an image whose facial expression matches the designated person from the plurality of images. apparatus.   5. The image search apparatus according to claim 3, wherein the search means is means for further searching for an image not including a person from the plurality of images. Detect the face area from each of multiple images,
Based on the detected face area, the person included in the plurality of images is identified,
An image search method, wherein an image including a person most frequently included in the plurality of images among the specified persons is searched from the plurality of images. Accept the designation of at least one person to search among people included in multiple images,
Detecting a face region from each of the plurality of images;
An image search method, wherein an image including the specified at least one person is searched from the plurality of images based on the detected face area. A procedure for detecting a face area from each of a plurality of images;
A procedure for identifying a person included in the plurality of images based on the detected face area;
A program for causing a computer to execute an image search method, comprising: a step of searching the plurality of images for an image including a person most frequently included in the plurality of images among the specified persons. A procedure for accepting designation of at least one person to be searched among persons included in a plurality of images,
Detecting a face region from each of the plurality of images;
A program for causing a computer to execute an image search method comprising: searching for an image including the specified at least one person from the plurality of images based on the detected face area.

Images