JP4712576B2 - Image layout apparatus and method, and program - Google Patents

Description

  The present invention relates to an image layout apparatus and method for laying out a plurality of images, and a program for causing a computer to execute the image layout method.

  With the widespread use of digital cameras, anyone can easily acquire images and print them out. Also, it is easy to process the image with its own personal computer. For example, a plurality of images are appropriately laid out to create a single layout image, which can be stored in a personal computer or printed out. When creating a layout image in this way, it is common to arrange a plurality of images so as to improve the appearance as much as possible in consideration of the overall balance of the obtained layout images.

  However, since the layout work is performed manually by the user who performs the work, the appearance of the layout image often depends on the user's design sense and experience, and a satisfactory layout image is not always obtained. In addition, the burden on the user who performs the work is large.

For this reason, various methods for automatically laying out a plurality of images have been proposed. For example, in Patent Document 1, when an image is laid out in a plurality of predetermined layout areas, layout is performed in consideration of the balance of the image by using the area and variance value of the face area of the image to be arranged. A method has been proposed. Japanese Patent Application Laid-Open No. 2004-228620 proposes a method of calculating a degree of attraction that is an eye-catching index for an image to be laid out and generating a layout image having high game performance and entertainment based on the degree of attraction. Further, Patent Document 3 proposes a method for evaluating the balance of images such as the face orientation, the acquired age, and the like, and generating a layout image using a genetic algorithm.
JP-A-2005-190401 JP 2005-284597 A JP 2002-288669 A

  However, the technique described in Patent Document 1 has a predetermined layout area, so that the obtained layout image often lacks interest. Further, although the method described in Patent Document 2 can obtain a layout image having high game performance and entertainment, the layout image feels noisy particularly when game performance and entertainment are not desired. Further, since the method described in Patent Document 3 uses a genetic algorithm, it is necessary to perform a lot of learning before a layout image having a good appearance can be obtained.

  The present invention has been made in view of the above circumstances, and an object thereof is to easily obtain a layout image having a good appearance when laying out a plurality of images.

An image layout apparatus according to the present invention detects a face area for each of a plurality of images for creating a layout image, and detects a size and a center of gravity of the face area;
The first image to be placed first in the base image as the background, and the second image to be placed in the second image, the center of gravity of the face area included in the first image, and the second image The second image is used as the base image so that the distance between the center of gravity between the center and the center of the face area included in the image of the first image becomes a predetermined distance at which the entire face area of the first image can be visually recognized. When there is an image to be arranged and further arranged, for the image to be further arranged, the centroid of each face area of the plurality of images already arranged in the base image and the centroid of the face area of the further arranged image Layout processing for arranging the further image to be arranged on the base image so that the distance between the center of gravity is a predetermined distance at which all face areas of all the already arranged images can be visually recognized. Layout means to do And it is characterized in that there was example.

  In some cases, a single image includes a plurality of face areas. In this case, the sizes of all the face areas are detected, and the centroids of all the face areas are detected.

  “Make all the face areas of the image visible” means that all face areas of all the already arranged images do not overlap with the image to be placed, that is, This means that all face regions of the image are not hidden by the image to be further arranged.

  In the image layout device according to the present invention, the base image in which all the images are laid out is cut out into an area including all the laid out images and having a specified aspect ratio, and the cut out area A final processing means for obtaining a layout image by changing the size to a designated size may be further provided.

The image layout apparatus according to the present invention further includes an image processing means for obtaining a processed image by performing at least one of resizing and rotation on a desired image among the plurality of images. Shall be prepared,
The layout unit may be a unit that performs the layout process on the processed image.

  The “desired image of the plurality of images” may be an image designated in advance or all images. Moreover, the image selected at random may be sufficient.

  Regarding “at least one process of resizing and rotating”, since the appearance of the layout image deteriorates if the degree of resizing and rotating is too large, a parameter range for specifying the degree of resizing and rotating is defined. It is preferable to keep it. Note that the size change and rotation processing may be performed on all desired images, or may be performed on an image designated in advance or an image selected at random. The parameters may be different or the same for each image to be processed. The parameters may be set randomly.

In the image layout apparatus according to the present invention, a person number detecting means for detecting the number of persons included in each of the plurality of images,
The image processing apparatus further includes size changing means for changing a size of a predetermined image of the plurality of images so as to increase a size as the number of persons increases, and obtaining a resized image.
The layout unit may be a unit that performs the layout process on the resized image.

  In this case, it is preferable that the predetermined image is an image having the largest number of persons.

  In the image layout apparatus according to the present invention, the predetermined distance may be a distance based on a minimum value of the distance between the centers of gravity. In particular, it is preferable that the predetermined distance is a minimum value of the distance between the centers of gravity.

  The “distance based on the minimum value of the distance between the centers of gravity” may be the minimum value of the distance between the centers of gravity if the entire face area of the image already arranged is visible, and is slightly larger than the minimum value. It may be a large distance (for example, about 10%). Further, it may be changed according to the number of images to be laid out. Specifically, it is preferable to decrease this distance as the number of images to be laid out increases.

The image layout method according to the present invention detects a face area for each of a plurality of images, detects the size and center of gravity of the face area,
Place the first image to be placed first on the base image that becomes the background,
For the second image to be placed on the second image, the distance between the center of gravity between the center of gravity of the face area included in the first image and the center of gravity of the face area included in the second image is The second image is arranged on the base image so that the entire face area of the first image becomes a predetermined distance that can be visually recognized.
When there is an image to be further arranged, the image to be further arranged is between the centroid of each face area of the plurality of images already arranged in the base image and the centroid of the face area of the further image to be arranged. The image to be further arranged is arranged in the base image so that the distance between the center of gravity of the image becomes a predetermined distance at which all face areas of all the images already arranged can be visually recognized. It is.

  The image layout method according to the present invention may be provided as a program for causing a computer to execute the image layout method.

  According to the present invention, the input of a plurality of images to be laid out is accepted, the face area is detected for each of the plurality of images, and the size and the center of gravity of the face area are detected. First, the first image to be arranged first is arranged on the background base image. Subsequently, for the second image to be placed on the second image, the distance between the center of gravity between the center of gravity of the face area included in the first image and the center of gravity of the face area included in the second image is It arrange | positions in a base image so that it may become the predetermined distance which the whole face area | region of a 1st image becomes visually recognizable. If there is an image to be further arranged, for the image to be further arranged, the centroid of each face area of the plurality of images already arranged in the base image and the centroid of the face area of the image to be further arranged The distance between the centers of gravity is arranged in the base image so that the distance between the centers of gravity becomes a predetermined distance at which all the face areas of all the already arranged images can be visually recognized.

  Therefore, it is possible to obtain a layout image having an unexpected arrangement of images according to the position of the face area and the number of face areas included in the plurality of images to be laid out. In addition, since the entire face area of the arranged image is visible, the face of the person included in the image to be laid out is not hidden by another image. Further, since the images are arranged so that all the face areas of all the already arranged images are visible based on the distance between the centers of gravity of the face areas included in the image, it is described in Patent Document 3. A layout image can be obtained without using a complicated algorithm. Therefore, a good-looking layout image can be easily obtained.

  In addition, the base image in which all the images are laid out is cut out into an area including all the laid out images and having a specified aspect ratio, and the cut out area is changed to a specified size. A layout image having a desired aspect ratio and a desired size can be obtained.

  Further, by performing at least one process of resizing and rotating on a desired image among a plurality of images to obtain a processed image, and performing layout processing on the processed image, A good-looking layout image can be obtained.

  Here, the size of the face of the person included in the image decreases as the number of persons included in the image increases. For this reason, by performing layout processing by changing the size so that the larger the number of persons, the larger the size, the layout image can be obtained by laying out the images so that the face of the person can be seen more easily.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a schematic block diagram showing the configuration of an image layout apparatus according to the first embodiment of the present invention. As shown in FIG. 1, the image layout apparatus 1 according to the first embodiment performs various controls such as recording control and display control of image data, and controls each part of the apparatus 1 and operates the CPU 12. A system memory 14 including a program to be executed, a viewer software for viewing images, a ROM in which various constants are recorded, and a RAM serving as a work area when the CPU 12 executes processing, and various instructions to the apparatus 1. An input unit 16 including a keyboard and a mouse for performing the display and a display unit 18 including a liquid crystal monitor for performing various displays are provided.

  The image layout apparatus 1 also includes a card slot 20 for reading image data from the memory card 2 on which image data is recorded, and recording image data on the memory card 2, and a technique represented by JPEG. A compression / decompression unit 22 that compresses or decompresses compressed image data; a hard disk 24 that records image data and various programs executed by the CPU 12; and a memory control that controls the system memory 14, the card slot 20, and the hard disk 24 Part 26.

  In addition, the image layout apparatus 1 detects a face area from each of a plurality of images used to create a layout image, and detects a position, size, and center of gravity of the detected face area, as will be described later. Are provided with a layout unit 30 that performs layout processing and a final processing unit 32 that acquires a final layout image, as will be described later. A display control unit 34 that controls the display of the display unit 18 is also provided.

  Hereinafter, processing performed by the face detection unit 28, the layout unit 30, and the final processing unit 32 in the first embodiment will be described. FIG. 2 is a flowchart showing processing performed in the first embodiment. It is assumed that a plurality of images to be laid out (hereinafter referred to as layout target images) have already been selected from a plurality of images read from the memory card 2 and stored in the hard disk 24. Further, it is assumed that the layout order is specified in advance for the layout target image.

  When the user issues an instruction to create a layout image from the input unit 16, the CPU 12 starts processing, and the face detection unit 28 detects a face area from all layout target images (step ST1). As a method for detecting a face area from an image, for example, as described in Japanese Patent Laid-Open No. 2005-157964, the image is binarized with a threshold value set based on the standard deviation of skin color information. A method of detecting both eyes from a digitized image and detecting a face area based on the detected information of both eyes, and skin color information and luminance information of an image as described in JP-A-2005-190400 Is used to determine whether or not a face area exists in the image, and for an image determined to have a face area, the detection target area is divided into a plurality of blocks, and the face area is determined using the feature vector of the block. Any known method such as a detection method can be used. Further, all face areas are detected from the layout target image including a plurality of faces. The face area is a rectangular area surrounding the face included in the layout target image.

  Subsequently, the face detection unit 28 detects the position, size, and center of gravity of the face area for all layout target images (step ST2). Here, the position of the face area is a coordinate value of the upper left corner of the face area when two-dimensional coordinates having the origin at the upper left corner of the layout target image are set. The size of the face area is the number of pixels in the vertical and horizontal directions of the face area. Hereinafter, detection of the center of gravity of the face area will be described.

  FIG. 3 is a diagram for explaining the detection of the center of gravity of the face area. When the layout target image includes only one face area F1 as shown in FIG. 3A, the center of gravity G1 of the face area F1 is an intersection of diagonal lines of the face area F1. As shown in FIG. 3B, when a plurality of (here, two) face areas F1 are included in the layout target image, the centroid G1 of the face area F1 is a line connecting the centroids G1 of the face areas F1. The minutes are internally divided according to the size of the face area F1. When there are three face areas F1, the center of gravity of a triangle whose vertex is the center of each of the three face areas F1 is set as the center of gravity of the face area F1. When more face areas F1 exist, the centroids G1 of all the face areas F1 are detected by combining the techniques of detecting the centroids in the case of two face areas F1 and three. Note that the detected position, size, and center of gravity of the face area are temporarily stored in the system memory 14 or the hard disk 24 in association with the layout target image.

  Here, when the layout target image does not include a person, the face area is not detected. In this case, as shown in FIG. 3C, layout processing described later is performed assuming that the center of gravity of the layout target image is the center of gravity G1 of the face region. In this case, the face area F1 has a predetermined proportion of size with respect to the layout target image, and the layout process described later is performed assuming that the aspect ratio is the same area as the layout target image.

  Here, in the present embodiment, the following description will be made assuming that the images shown in FIGS. 3A and 3B and the three layout target images shown in FIG. 3D are arranged.

  Subsequently, the layout unit 30 sets the image to be placed as the first layout target image (step ST3), and places the layout target image on the base image that is the background of the layout image (step ST4). FIG. 4 is a diagram illustrating a state in which the first layout target image (L1) is arranged in the base image B0. The base image B0 is a virtual plane having an infinite size. Next, the layout unit 30 sets the image to be placed as the second layout target image (step ST5), and places the second layout target image in consideration of the position, size, and center of gravity of the face area of the layout target image. (Step ST6). Hereinafter, the arrangement of the second layout target image will be described.

  First, for the second layout target image (referred to as L2), the face area F1 of the first layout target image L1 and the second layout target image L2 do not overlap and are arranged in the base image B0. The layout unit 30 searches for a position where the distance between the center of gravity G1 of the face area F1 of the first layout target image L1 and the center of gravity G1 of the face area F1 of the second layout target image L2 is the shortest. A second layout target image L2 is arranged.

  FIG. 5 is a diagram illustrating a state in which the first layout target image L1 and the second layout target image L2 are arranged in the base image B0. As shown in FIG. 5, the face area F1 of the first layout target image L1 does not overlap the second layout target image L2, and the center G1 of the face area F1 of the first layout target image L1 and the second sheet The second layout target image L2 is arranged at a position where the center of gravity G1 of the face area F1 of the layout target image L2 is the shortest.

  Next, the layout unit 30 determines whether there is a layout target image to be further arranged (step ST7). If step ST7 is affirmed, the layout target image to be arranged is set as the next layout target image (step ST8), the process returns to step ST6, and the processes after step ST6 are repeated.

  Here, when the third and subsequent layout target images are arranged, the layout unit 30 includes the face areas F1 of all the layout target images L1 and L2 already arranged in the base image B0 and the layout target images to be arranged. A position where the face area does not overlap and the distance between the centroid G1 of the face area F1 of all layout target images arranged in the base image B0 and the centroid G1 of the face area F1 of the layout target image arranged is the shortest. Search and place the layout target image.

  Here, in the state where two layout target images are arranged as shown in FIG. 5, the center of gravity G1 of the face area of the two layout target images is at the position shown in FIG. Therefore, when the layout target image (referred to as L3) shown in FIG. 3D is arranged in a state where the two layout target images L1 and L2 are arranged in the base image B0 as shown in FIG. 5, FIG. As shown, three layout target images L1, L2, and L3 are arranged. In this case, the center of gravity G1 of the face area of the three layout target images L1, L2, and L3 is as shown in FIG.

  On the other hand, if step ST7 is negative, the final processing unit 32 includes all the layout target images L1, L2, and L3 laid out in the base image B0 and has the designated aspect ratio as shown in FIG. The base image B0 is trimmed by the rectangular region S0 having the minimum size (step ST9). Here, the minimum-sized rectangular area S0 is an area inscribed in the three layout target images L1, L2, and L3 as shown in FIG.

  Subsequently, the final processing unit 32 changes the trimmed rectangular area S0 to the designated size (step ST10), and ends the creation of the layout image. As a result, as shown in FIG. 10, a layout image in which three layout target images L1, L2, and L3 are arranged can be obtained. The layout image is used for print output and monitor display.

  As described above, in the first embodiment, the centroid G1 of the face area F1 of the layout target image already arranged in the base image B0 and the centroid G1 of the face area F1 of the layout target image to be further arranged. The layout target images are arranged such that the distance between the centers of gravity is the shortest and the face area F1 of all layout target images that have already been arranged do not overlap with the layout target images to be arranged.

  Therefore, it is possible to obtain a layout image that is unexpected in the arrangement of the images according to the position of the face area F1 and the number of face areas included in the layout target image. Further, since all the face areas F1 of the arranged layout target images are not hidden by other layout target images, the face of a person included in the layout target images is not hidden by other images. Moreover, since a layout image can be obtained without using a complicated algorithm as described in Patent Document 3, a layout image having a good appearance can be easily obtained.

  Next, a second embodiment of the present invention will be described. FIG. 11 is a schematic block diagram showing the configuration of an image layout apparatus according to the second embodiment of the present invention. Note that in the second embodiment, the same reference numerals are assigned to the same components as those in the first embodiment, and detailed description thereof is omitted. As shown in FIG. 11, the image layout apparatus 1A according to the second embodiment has been processed by performing at least one process of size change and rotation on a desired layout target image among a plurality of layout target images. The point provided with the image process part 36 which acquires a layout object image differs from 1st Embodiment.

  Here, it is assumed that the image processing unit 36 performs a size change and rotation process on all layout target images at random to obtain processed layout target images. At this time, since the appearance of the layout image deteriorates if the size is changed or rotated extremely, the size change and rotation are performed within a predetermined parameter range. Specifically, the size change is preferably performed within a range of about ± 20% of the original image size, and the rotation is preferably performed within a range of about ± 15 degrees. Here, the size change and rotation are performed on all layout target images, but the size change and rotation may be performed only on a layout target image designated in advance. Further, only one of the size change and the rotation may be performed. Note that the size change and rotation are not random, and may be performed by designated parameters.

  Next, processing performed in the second embodiment will be described. FIG. 12 is a flowchart showing processing performed in the second embodiment. When the user gives an instruction to create a layout image from the input unit 16, the CPU 12 starts processing, and the face detection unit 28 detects a face area from all layout target images (step ST21). Next, the image processing unit 36 performs a size change and rotation process on all layout target images at random, and acquires processed layout target images (step ST22). Subsequently, the face detection unit 28 detects the position, size, and center of gravity of the face area for all processed layout target images (step ST23).

  Subsequently, the layout unit 30 sets the image to be placed as the first layout target image (step ST24), and places the layout target image on the base image that is the background of the layout image (step ST25). Next, the layout unit 30 sets the image to be arranged as the second layout target image (step ST26), and places the second layout target image in consideration of the position, size, and center of gravity of the face area of the layout target image. (Step ST27).

  Next, the layout unit 30 determines whether there is a layout target image to be further arranged (step ST28). If step ST28 is affirmed, the layout target image to be arranged is set as the next layout target image (step ST29), the process returns to step ST27, and the processes after step ST27 are repeated. At this time, as in the first embodiment, the face area F1 of the layout target image that has already been arranged and the layout target image to be arranged in the future do not overlap with the processed layout target image, and the base image The layout unit 30 searches for the position where the distance between the centroid G1 of the face area F1 of all the layout target images arranged in B0 and the centroid G1 of the face area F1 of the layout target image arranged in the future is the shortest. Arrange the layout target image.

  On the other hand, if step ST28 is negative, the final processing unit 32 includes the base image B0 by the rectangular region S0 of the minimum size that includes all the layout target images laid out in the base image B0 and has the specified aspect ratio. Trimming is performed (step ST30).

  Subsequently, the final processing unit 32 changes the trimmed rectangular area S0 to the designated size (step ST31), and ends the creation of the layout image. As a result, as shown in FIG. 13, it is possible to obtain a layout image in which three layout target images L1, L2, and L3 whose size is changed and rotated are arranged.

  As described above, in the second embodiment, the layout target image is subjected to at least one process of size change and rotation, and the layout process is performed on the processed layout target image. A good-looking layout image can be obtained.

  Next, a third embodiment of the present invention will be described. FIG. 14 is a schematic block diagram showing the configuration of an image layout apparatus according to the third embodiment of the present invention. Note that in the third embodiment, the same reference numerals are assigned to the same configurations as those in the first embodiment, and detailed description thereof is omitted. As illustrated in FIG. 13, the image layout device 1B according to the third embodiment includes a person number detection unit 38 that detects the number of persons included in the layout target image, and a layout target image that increases in size as the number of persons increases. This embodiment differs from the first embodiment in that it includes a size changing unit 40 that changes the size.

  Here, the size changing unit 40 changes the size of the single layout target image having the largest number of persons. However, the size changing unit 40 can change the size of the layout target image so that the size of the layout target image is different. The size of the layout target image may be changed.

  Next, processing performed in the third embodiment will be described. FIG. 15 is a flowchart showing processing performed in the third embodiment. When the user gives an instruction to create a layout image from the input unit 16, the CPU 12 starts processing, and the face detection unit 28 detects a face area from all layout target images (step ST41). Next, the number-of-persons detection unit 38 detects the number of people in the layout target image using the detection result of the face detection unit 28 (step ST42). Then, the size changing unit 40 changes the size of the layout target image having the largest number of persons (step ST43).

  Subsequently, the face detection unit 28 detects the position, size, and center of gravity of the face area for all layout target images (including the layout target image whose size has been changed) (step ST44).

  Subsequently, the layout unit 30 sets the image to be placed as the layout target image whose size has been changed (step ST45), and places the layout target image on the base image serving as the background of the layout image (step ST46). Next, the layout unit 30 sets the image to be arranged as the second layout target image (step ST47), and places the second layout target image in consideration of the position, size, and center of gravity of the face area of the layout target image. (Step ST48).

  Next, the layout unit 30 determines whether there is a layout target image to be further arranged (step ST49). If step ST49 is affirmed, the layout target image to be arranged is set as the next layout target image (step ST50), the process returns to step ST48, and the processes after step ST48 are repeated. At this time, as in the first embodiment, the face area F1 of the layout target image that has already been arranged does not overlap with the layout target image to be arranged in the future, and all the layout target images arranged in the base image B0. The layout unit 30 searches for a position where the distance between the center of gravity G1 of the face area F1 of the face and the center of gravity G1 of the face area F1 of the layout target image to be arranged is the shortest, and places the layout target image at that position.

  On the other hand, if step ST49 is negative, the final processing unit 32 adds the base image B0 to the rectangular region S0 of the minimum size that includes all the layout target images laid out in the base image B0 and has the specified aspect ratio. Trimming is performed (step ST51).

  Subsequently, the final processing unit 32 changes the trimmed rectangular area S0 to the designated size (step ST52), and ends the creation of the layout image. Thereby, as shown in FIG. 16, a layout image in which the layout target image L4 having the largest number of persons is enlarged can be obtained.

  Here, the size of the face of the person included in the image decreases as the number of persons included in the image increases. For this reason, by performing layout processing by changing the size of a layout target image having a large number of people to be large, a layout image in which images are laid out so that the faces of people can be seen more easily can be obtained.

  Next, a fourth embodiment of the present invention will be described. FIG. 17 is a schematic block diagram showing the configuration of an image layout apparatus according to the fourth embodiment of the present invention. In the fourth embodiment, the same reference numerals are assigned to the same components as those in the first embodiment, and detailed description thereof is omitted. As shown in FIG. 17, the image layout device 1 </ b> C according to the fourth embodiment includes the image processing unit 36 in the second embodiment, and the person number detection unit 38 and the size changing unit 40 in the third embodiment. The processing performed in the first to third embodiments can be switched by an instruction from the input unit 16. In the following description, the processes performed in the first to third embodiments are referred to as first to third processes, respectively.

  FIG. 18 is a flowchart showing processing performed in the fourth embodiment. The CPU 12 starts the process when the user gives an instruction to create a layout image from the input unit 16, and the CPU 12 determines whether any of the first to third processes is designated (step ST61). When the first process is designated, the first process similar to the first embodiment is performed to create a layout image (step ST62). When the second process is designated, a second process similar to that of the second embodiment is performed to create a layout image (step ST63). If the third process is designated, the third process similar to that of the third embodiment is performed to create a layout image (step ST64).

  As described above, by making it possible to switch the processing performed in the first to third embodiments, a layout image can be created in a manner desired by the user.

  In the first to fourth embodiments, the face area F1 of the layout target image that has already been arranged and the layout target image to be arranged in the future do not overlap, and all the layout objects arranged in the base image B0. The layout target image is arranged so that the distance between the centroid G1 of the face area F1 of the image and the centroid G1 of the face area F1 of the layout target image to be arranged will be shortest, but the distance between the centroids G1 is limited to the shortest. Instead, the face area F1 of the layout target image that has already been arranged and the layout target image to be arranged in the future may be increased to some extent from the shortest distance. In this case, the smaller the number of layout target images is, the more space can be provided between the images. Therefore, the distance between the centroids G1 can be increased with a relatively large margin.

  As described above, the apparatus according to the embodiment of the present invention has been described. However, the computer is connected to the face detection unit 28, the layout unit 30, the final processing unit 32, the image processing unit 36, the number of people detection unit 38, and the size changing unit 40. A program that functions as a corresponding means and performs processing as shown in FIGS. 2, 12, 15, and 18 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 a schematic block diagram showing the configuration of an image layout apparatus according to a first embodiment of the present invention. The flowchart which shows the process performed in 1st Embodiment The figure for demonstrating the detection of the gravity center of a face area | region The figure which shows the state by which the first layout object image was arrange | positioned at the base image The figure which shows the state which has arrange | positioned the first layout object image and the 2nd layout object image to the base image The figure which shows the gravity center of the face area in the state which has arrange | positioned the first layout object image and the 2nd layout object image to the base image The figure which shows the state which has arrange | positioned three layout object images to a base image The figure which shows the gravity center of the face area in the state which has arrange | positioned three layout object images to a base image Diagram for explaining trimming The figure which shows the layout image obtained in 1st Embodiment Schematic block diagram showing the configuration of an image layout apparatus according to a second embodiment of the present invention The flowchart which shows the process performed in 2nd Embodiment. The figure which shows the layout image obtained in 2nd Embodiment The schematic block diagram which shows the structure of the image layout apparatus by the 3rd Embodiment of this invention. The flowchart which shows the process performed in 3rd Embodiment The figure which shows the layout image obtained in 3rd Embodiment The schematic block diagram which shows the structure of the image layout apparatus by the 4th Embodiment of this invention. The flowchart which shows the process performed in 4th Embodiment

Explanation of symbols

1, 1A, 1B, 1C Image layout device 2 Memory card 12 CPU
DESCRIPTION OF SYMBOLS 14 System memory 16 Input part 18 Display part 20 Card slot 22 Compression / decompression part 24 Hard disk 26 Memory control part 28 Face detection part 30 Layout part 32 Final process part 34 Display control part 36 Image processing part 38 Person detection part 40 Size change part

Claims (9)

Detecting a face area for each of a plurality of images for creating a layout image, and detecting a size and a center of gravity of the face area;
The first image to be arranged first in the base image as the background, and the second image to be arranged in the second sheet, the entire face area of the first image becomes visible, and the first image The distance between the center of gravity between the center of gravity of the face area included in one image and the center of gravity of the face area included in the second image is a distance based on the minimum value of the distance between the center of gravity. When the arrangement position of the second image is searched, the second image is arranged at the searched arrangement position, and there is an image to be further arranged, the images to be further arranged are all already arranged. The distance between the centroids between the centroid of each face area of a plurality of images already arranged in the base image and the centroid of the face area of the further image to be arranged , where the entire face area of the image is visible distance but relative to the minimum value of the polymerization inter-axis distance And so that, searches for the position of the image to be the further arrangement, an image layout apparatus that is characterized in that a layout means performing the layout process to place the image of the further arranged in the arrangement positions the search.   A base image on which all the images are laid out is cut out into an area including all the laid out images and having a specified aspect ratio, and the cut out area is changed to a specified size to be a layout image. The image layout apparatus according to claim 1, further comprising a final processing unit that acquires the image data. Image processing means for obtaining a processed image by performing at least one process of resizing and rotating on a desired image of the plurality of images,
The image layout apparatus according to claim 1, wherein the layout unit is a unit that performs the layout process on the processed image. Person number detecting means for detecting the number of persons included in each of the plurality of images;
Resize means for obtaining a resized image by changing the size of a predetermined image of the plurality of images so that the image has a larger size as the number of persons increases.
The image layout apparatus according to claim 1, wherein the layout unit is a unit that performs the layout process on the resized image.   The image layout apparatus according to claim 4, wherein the predetermined image is an image having the largest number of persons. Distance relative to the minimum value of the distance between centers of gravity are, the image layout apparatus according to any one of claims 1 to 5, wherein the minimum value of the distance between center of gravity.   The said layout means is a means to make the distance on the basis of the minimum value of the distance between the centers of gravity the larger the number of the plurality of images, the smaller one of the plurality of images. Image layout device. The computer detects a face area for each of a plurality of images for creating a layout image, and detects the size and center of gravity of the face area,
Place the first image to be placed first on the base image that becomes the background,
For the second image to be placed on the second image, the entire face area of the first image is visible, and the center of the face area included in the first image is included in the second image. Searching for the arrangement position of the second image so that the distance between the center of gravity of the face area to be determined is a distance based on the minimum value of the distance between the center of gravity ,
The second image is arranged at the searched arrangement position ,
When there is an image to be further arranged, for the image to be further arranged , all the face regions of all the images already arranged are visible and each of the plurality of images already arranged in the base image is displayed. and the center of gravity of the face area, the centroid distance between the centroid of the face area of the image to be the further arrangement, so that the distance relative to the minimum value of the polymerization inter-axis distance, position of the image to be the further arranged And laying out the image to be further arranged at the searched arrangement position . Detecting a face area for each of a plurality of images for creating a layout image, and detecting a size and a center of gravity of the face area;
A procedure for placing a first image to be placed first on a background base image;
For the second image to be placed on the second image, the entire face area of the first image is visible, and the center of the face area included in the first image is included in the second image. A procedure for searching for an arrangement position of the second image so that a distance between the center of gravity between the center of the face area to be determined is a distance based on a minimum value of the distance between the center of gravity ;
Placing the second image at the searched placement position ;
When there is an image to be further arranged, for the image to be further arranged , all the face regions of all the images already arranged are visible and each of the plurality of images already arranged in the base image is displayed. and the center of gravity of the face area, the centroid distance between the centroid of the face area of the image to be the further arrangement, so that the distance relative to the minimum value of the polymerization inter-axis distance, position of the image to be the further arranged And an image layout program for causing a computer to execute a procedure for arranging the image to be further arranged at the searched arrangement position .

Images