JP2002358316A - Image processing apparatus, its method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processing apparatus, its method and program capable of classifying images efficiently and appropriately. SOLUTION: In an image processing apparatus, images are inputted from an image input part 1 and a CPU 2 decides an image to be compared to classify images to be processed based on the input time of the images. Meanwhile, an operating part 7 designates preconditions showing classification of the images. The CPU 2 sets a threshold to discriminate similarity between the images of the processing object and the images of comparison object based on the designated classification preconditions. Next, it discriminates the similarity between the images of the processing object and the images of the comparison object based on the threshold. Then, the CPU 2 imparts group attributes indicating a group to which the images belong of the processing object based on the result of discrimination.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus for classifying a plurality of images, a method therefor, and a program.

[0002]

2. Description of the Related Art Conventionally, in classifying images captured by a camera or an electronic camera, or a plurality of image-processed images, as a method of grouping unknown images by purpose, a user is required to group individual images. Check and change to an arbitrary file name to have regularity, or specify an arbitrary folder to store multiple images in one place,
There is a method that can be considered.

In Japanese Patent Application Laid-Open No. 2000-207405, there is a method in which a specified image group is automatically rearranged according to the attribute of the image.
In order to group images by purpose, a user must specify an image group to be rearranged each time.

[0004]

In the above prior art, for example, a plurality of images may be photographed under the same conditions for the same subject. In some cases, a series of these files may be extracted from an image and grouped.

However, in the conventional method, it is necessary for the user to confirm each image and perform the above-described processing, and the work load on the user is large.

SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and has as its object to provide an image processing apparatus, an image processing method, and a program capable of efficiently and appropriately classifying images. .

[0007]

An image processing apparatus according to the present invention for achieving the above object has the following arrangement.
That is, an image processing apparatus for classifying a plurality of images, wherein input means for inputting an image and a comparison target image to be compared for classifying the processing target image are determined based on the input time of the processing target image. Determining means, specifying means for specifying a classification precondition for classifying the processing target image, and a similarity between the processing target image and the comparison target image based on the classification precondition specified by the specifying means. Setting means for setting a threshold for determination, based on the threshold,
Determining means for determining the degree of similarity between the processing target image and the comparison target image, based on a determination result of the determining means,
An assigning unit that assigns a group attribute indicating a group to which the processing target image belongs to the processing target image.

Preferably, when the similarity between the image to be processed and the image to be compared is less than the predetermined value, the determination means preferably includes input condition data of the image to be processed and input of the image to be compared. An error determination unit that determines an error of a difference from the condition data, and a processing unit that processes the processing target image based on an error determination result of the error determination unit.

Preferably, the setting means sets the threshold value based on the classification precondition.

Preferably, the input condition data is an angle value of an image, and the processing means performs the processing in accordance with a difference between an angle value of the image to be processed and an angle value of the image to be compared. Process the target image.

Preferably, the input condition is a zoom value of an image, and the processing means is configured to determine the processing object in accordance with a difference between a zoom value of the image to be processed and a zoom value of the image to be compared. Process the image.

Preferably, the input condition is a value indicating whether or not the image is to be flashed, and the processing means is configured to determine whether or not the image to be processed is to be flashed and to determine whether or not the image to be compared is to be flashed. The processing target image is processed according to the difference from the value indicating the presence or absence of the image.

An image processing method according to the present invention for achieving the above object has the following arrangement. That is, an image processing method for classifying a plurality of images, wherein an input step of inputting an image and a comparison target image to be compared for classifying the processing target image are determined based on the input time of the processing target image. A determining step, a specifying step of specifying a classification precondition for classifying the processing target image, and a similarity between the processing target image and the comparison target image based on the classification precondition specified in the specifying step. A setting step of setting a threshold value for determination, and a determination step of determining a similarity between the processing target image and the comparison target image based on the threshold value,
Providing a group attribute indicating a group to which the processing target image belongs to the processing target image based on the determination result of the determination step.

A program according to the present invention for achieving the above object has the following configuration. That is, a program for causing a computer to perform image processing for classifying a plurality of images, the program code of an input step of inputting an image, and a comparison target image to be compared for classifying a processing target image, The program code of the determining step to determine based on the input time of the target image, the program code of the specifying step to specify a classification precondition for classifying the processing target image, and the classification precondition specified in the specifying step A program code of a setting step for setting a threshold value for determining a similarity between the processing target image and the comparison target image, based on the threshold value, and a similarity between the processing target image and the comparison target image based on the threshold value The program code of the discriminating step for discriminating and the group to which the image to be processed belongs are indicated based on the discrimination result of the discriminating step. The group attribute and a program code of step of applying to the processing target image.

[0015]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present invention will be described below in detail with reference to the drawings.

FIG. 1 is a block diagram showing a hardware configuration of the image processing apparatus according to the present embodiment.

In this embodiment, a digital camera is given as a specific example of the image processing apparatus. In this digital camera, at least an angle value, a zoom value, a value indicating whether or not a flash is turned on, as shooting condition data to be described later. It is possible to acquire various values relating to shooting conditions including a focus shift value. In addition, it is possible to input classification preconditions (for example, the same person image, a traveling image, a plant observation record image, and the like) for classifying captured images. Further, it is possible to input an error condition for determining an error of a difference between the shooting condition data of the shot image and the shooting condition data of the comparison target image to be compared in order to classify the shot image according to the classification precondition. .

In FIG. 1, reference numeral 1 denotes an image input unit for inputting an image by photographing / reading the image. 2 is CPU
It performs calculations, logical decisions, and the like for various types of processing including image processing, which will be described later, and controls each component connected to the bus 6. Reference numeral 3 denotes an image output unit for outputting an image input by the image input unit 1, and is usually constituted by a liquid crystal display.

Reference numeral 4 denotes a program memory for storing various control programs executed by the CPU 2 including a flowchart described later. Note that the program memory 4 may be a ROM or a RAM into which a program is loaded from an external storage device.

Reference numeral 5 denotes a data memory for storing input images and data generated in various processes. 6 is CPU
2 is a bus for transferring an address signal indicating a component to be controlled, a control signal for controlling each component, and a data exchange between components. Reference numeral 7 denotes an operation unit including an operation panel for instructing various processes including a photographing / reading operation.

Next, an outline of the processing executed in this embodiment will be described with reference to FIG.

FIG. 2 is a flowchart showing an outline of the processing executed in the present embodiment.

When the system is started, step S20
At 1, the system boot process is started. Next, in step S202, an event waiting process is started, and
Wait for an event to occur. Next, in step S203, it is determined whether or not the event that has occurred is power off. When the power is off (step S203)
Then, the process proceeds to step S208 to activate the system termination process and terminate the process. On the other hand, when the power is not turned off (NO in step S203), the process proceeds to step S204.

Next, in step S204, it is determined whether or not the event that has occurred is shooting. If it is not shooting (NO in step S204), the flow advances to step S207 to start other processing. On the other hand, in the case of photographing (YES in step S204), the photographing operation is executed, the photographed image and the photographing time are stored in the data memory 5, and the process proceeds to step S205. In addition, when the user specifies a prerequisite for classification of a photographed image, the prerequisite for classification is also stored in the data memory 5 in association with the photographed image and the photographing time.

It should be noted that a unique image file name is given to a photographed image, and is usually stored in the data memory 5 in the order of photographing time.

Next, in step S205, a photographing condition acquisition process is started, and photographing condition data of a photographed image is acquired, and stored in the data memory 5 in association with the photographed image. Subsequently, in step S206, the image classification process is started, group attribute data indicating the classification of the captured image is added to the captured image, and the process returns to step S202.

Next, details of the photographing condition acquisition processing in step S205 will be described with reference to FIG.

FIG. 3 is a flowchart showing details of the photographing condition acquisition processing of this embodiment.

When the photographing condition acquisition processing is started, in step S301, the presence or absence of an angle difference between photographed images is determined. If there is no angle difference (NO in step S301), the process proceeds to step S303. On the other hand, if there is an angle difference (YES in step S301),
Proceeding to 302, the angle data indicating the angle difference is stored.

The angle difference is a difference between a predetermined angle reference value and an angle value of a photographed image.

In step S303, it is determined whether or not the photographed image has a zoom difference. If there is no zoom difference (NO in step S303), the process proceeds to step S305. On the other hand, if there is a zoom difference (YE in step S303)
S), the process proceeds to step S304, and zoom data indicating the zoom difference is stored.

The zoom difference is a difference between the zoom value of the photographed image and a predetermined zoom reference value.

Next, in step S305, it is determined whether or not there is a flash lighting difference in the captured image. If there is no flash lighting difference (NO in step S305), the process proceeds to step S307. On the other hand, if there is a flash lighting difference (YES in step S305), step S306
The flash lighting data indicating the flash lighting difference is stored.

The flash lighting difference is a difference between a predetermined reference value indicating the flash lighting status and a value indicating the flash lighting status of the captured image.

Next, in step S307, it is determined whether or not there is a focus shift difference between the captured images. If there is no focus movement difference (NO in step S307), the process ends.
On the other hand, if there is a focus movement difference (Y in step S307)
ES), the flow advances to step S308 to store focus movement data indicating the focus movement difference.

Note that the focus shift difference is a difference between a focus shift value of a photographed image and a predetermined focus shift reference value.

Next, details of the image classification processing in step S206 will be described with reference to FIG.

FIG. 4 is a flowchart showing the details of the image classification processing of this embodiment.

When the image classification processing is started, step S4
In step 01, a comparison target determination process is started, and a comparison target list including a group of images (reference images) already stored in the data memory 5 to be compared with the image (photographed image) to be processed is created.

Next, in step S402, a pointer is set at the head of the comparison target list in order to select a reference image to be compared with the processing target image from the comparison target list.

In step S403, it is determined whether or not the pointer indicates the end of the comparison target list. If the pointer indicates the end of the comparison target list (YES in step S403), the process ends. On the other hand, if the pointer does not indicate the end of the comparison target list (NO in step S403), the process proceeds to step S404.

Next, in step S404, similarity determination processing is started, and the similarity between the reference image in the comparison target list indicated by the pointer and the processing target image is determined. Based on the determination result, in step S405, it is determined whether the reference image and the processing target image are similar. If the processing target images are similar (Y in step S405)
ES), the process advances to step S407 to start a group attribute assigning process, and assigns group attribute data indicating the classification to the image to be processed. On the other hand, if the reference image and the processing target image are not similar (NO in step S405),
Proceeding to step S406, the position of the pointer on the comparison target list is next advanced, and the process returns to step S403.

Next, the details of the comparison object determination processing in step S401 will be described with reference to FIG.

FIG. 5 is a flowchart showing details of the comparison object determination processing of this embodiment.

The process of FIG. 5 is a process of determining an image within the approximate range of the photographing time from the photographing time of the photographed image as a comparison target image. The images existing up to the shooting time approximate value are added to the comparison target list one by one.

When the comparison object determination processing is started, in step S501, an approximate value of the photographing time with respect to the photographing time of the photographed image is set in the minus direction.

In step S502, the presence or absence of an image corresponding to the set photographing time approximate value is determined. If there is no image (NO in step S502), the process ends. On the other hand, if there is an image (YE in step S502)
S), and proceed to step S503.

In step S503, the image is stored in the comparison target list. Next, in step S504, the shooting time approximate value is advanced by one in the negative direction, and the process returns to step S502.

Next, details of the similarity determination processing in step S404 will be described with reference to FIG.

FIG. 6 is a flowchart showing details of the similarity determination processing of this embodiment.

When the similarity determination processing is started, step S
In 601, a threshold acquisition process is started, and a threshold for an image to be processed is acquired. Next, in step S602, similarity acquisition processing is started, and the similarity between the reference image selected from the comparison target list and the processing target image is acquired.
The similarity is calculated, for example, by comparison with an image feature amount calculated from a color distribution, brightness, and the like in the image.

Next, in step S603, it is determined whether or not the obtained similarity is equal to or larger than a threshold. If the similarity is equal to or greater than the threshold (YES in step S603), T
return, and the process ends. On the other hand, if the similarity is less than the threshold (NO in step S603), the process proceeds to step S603.
Proceed to 604.

In step S604, an error determination process is started, and the difference between the photographing condition data of the image to be processed and the photographing condition data of the reference image is calculated. Step S
In step 605, it is determined whether or not the calculated error is within an error range with reference to an error determination table described later. If not within the error range (N in step S605)
O), False is returned and the process ends. On the other hand, if it is within the error range (YES in step S605), the process proceeds to step S606.

Here, an example of the error determination table will be described with reference to FIG.

FIG. 18 is a diagram showing an example of the error determination table of the present embodiment.

The error determination table is stored in the data memory 5, and as shown in FIG. 18, error range conditions which can be specified by the user from the operation unit 7 and corresponding error range contents are managed. If the error range is satisfied,
True (T) is returned as the determination result, and it is determined that the processing target image is similar to the reference image. On the other hand, when the content of the error range is not satisfied, Fa
1se (F) is returned, and it is determined that the processing target image is not similar to the reference image.

In step S606, the processing is started, the error of the difference is adjusted, and the processing target image is processed. Subsequently, in step S607, similarity acquisition processing is started, and the similarity between the reference image selected from the comparison target list and the processed image is acquired. In step S608, it is determined whether the acquired similarity is equal to or greater than a threshold. If the similarity is equal to or greater than the threshold (YES in step S608), True is returned and the process ends. On the other hand, when the similarity is less than the threshold (N in step S608)
O), False is returned and the process ends.

Next, the details of the threshold value acquiring process in step S601 will be described with reference to FIG.

FIG. 7 is a flowchart showing details of the threshold value acquisition processing of this embodiment.

When the threshold acquisition process is started, step S7
In step 01, a threshold initial value acquisition process is started, and a threshold initial value is set based on classification preconditions for an image to be processed.
Next, in step S702, a pointer is set at the head of the weight determination list in order to select a threshold to be processed from the weight determination list.

In step S703, it is determined whether or not the pointer indicates the end of the weight determination list. If the pointer indicates the end of the weight determination list (YES in step S703), step S707
Proceed to. If the pointer does not indicate the end of the threshold initial value list (NO in step S703), the process advances to step S704.

In step S704, a comparison is made between each piece of numerical data used as a classification precondition attached to the image to be processed and the corresponding numerical data in the weight determination list. Based on the comparison result, step S
In 705, it is determined whether or not they match as classification preconditions. If the classification preconditions match (YES in step S705), the flow advances to step 708 to calculate an optimal threshold based on threshold coefficient data and a threshold initial value corresponding to the classification precondition, and terminate the process. . on the other hand,
If the classification preconditions do not match (N in step S705)
O) The process advances to step S706, and the pointer is advanced to the next.
It returns to step S703.

On the other hand, if the pointer indicates the end of the weight determination list in step S703, the threshold coefficient data is set to 1 in step S707. Subsequently, in step S708, an optimum threshold is calculated based on the threshold coefficient data and the threshold initial value, and the process ends.

Here, an example of the threshold initial value list will be described with reference to FIG.

FIG. 8 is a diagram showing an example of a threshold initial value list according to the present embodiment.

As shown in FIG. 8, a threshold initial value is set according to the classification precondition specified by the user from the operation unit 7, and according to the above-described processing, the threshold initial value corresponds to the specified classification precondition. The threshold initial value will be selected.
The threshold initial value corresponding to each classification precondition is determined by the user's intention to classify the image to be processed, and is multiplied by various numerical data of each classification precondition itself to determine an optimal threshold. There is weight determination list data for calculating.

Next, an example of the weight determination list data will be described with reference to FIG.

FIG. 9 is a diagram showing an example of the weight determination list data of the present embodiment.

The weight determination list is composed of numerical data indicating the relationship between the image to be processed and the image to be compared in order to determine a coefficient for adjusting the threshold.
In FIG. 9, “time distance”, “date distance”, “movement distance”, “angle”, “focus movement”, and the like are managed, and weighting is performed using a characteristic difference between the two images represented by these numerical data. Is set. The combination of the configuration of the numerical data and the threshold coefficient is updated every time the classification precondition of the processing target image changes.

The “moving distance” can be determined by a position detection function such as a GPS in the image processing apparatus (digital camera), which can detect the position information of the image processing apparatus, or by the communication function. When the position information of the image processing apparatus can be received more, the position information is managed as numerical data of the weight determination list.

Next, the details of the error determination processing in step S604 will be described with reference to FIG.

FIG. 10 is a flowchart showing the details of the error judgment processing of this embodiment.

When the error determination process is started, step S1
In 001, the difference between the imaging condition data of the reference image selected from the comparison target list and the imaging condition data of the processing target image is calculated. Subsequently, in step S1002, an error determination is performed according to the designated condition with reference to the error determination table. If the determination result is within the error range (YES in step S1002), True is returned and the process ends. On the other hand, if the determination result is outside the error range (NO in step S1002), False is returned and the process ends.

Next, an example of the photographing condition data will be described with reference to FIG.

FIG. 11 is a view showing an example of the photographing condition data of the present embodiment.

As shown in FIG. 11, an angle value, a zoom value, a value indicating whether or not a flash is lit, a focus shift value, and the like at the time of photographing are taken as photographing condition data with respect to the photographing time of the photographed image and the image file name. Is managed.

Next, the processing in step S606 will be described with reference to FIG.

FIG. 12 is a flowchart showing the processing of this embodiment.

When the processing is started, step S120
In 1, it is determined whether or not there is an angle difference between the angle value of the captured image and the angle value of the reference image to be compared. If there is no angle difference (NO in step S1201),
Proceed to step S1203. On the other hand, if there is an angle difference (YES in step S1201), step S12
In step 02, the angle processing is started, and the angle value of the processing target image (captured image) is changed to the angle value of the reference image image according to the angle difference.

Next, in step S1203, it is determined whether there is a zoom difference between the zoom value of the captured image and the zoom value of the reference image to be compared. If there is no zoom difference (NO in step S1203), the process advances to step S1205. On the other hand, when there is a zoom difference (step S1203)
In step S1204, the zoom processing is started, and the zoom value of the processing target image is changed to the zoom value of the reference image according to the zoom difference.

Next, in step S1205, it is determined whether or not there is a flash lighting difference between the value indicating whether the captured image is flashed and the value indicating whether the reference image to be compared is flashed. If there is no flash lighting difference (NO in step S1205), step S1207
Proceed to. On the other hand, if there is a flash lighting difference (YES in step S1205), the flow advances to step S1206.
The brightness processing is started, and the brightness of the processing target image is changed to the brightness value of the reference image according to the flash lighting difference.

Next, in step S1207, the center of gravity determination processing is started, and the center of gravity of the overlapping area between the reference image and the image to be processed is determined. Next, in step S1208, the clipping process is started, and the image of the overlapping area is clipped.

Next, a specific example of the angle processing in step S1202 will be described with reference to FIG.

FIG. 13 is a diagram showing a specific example of the angle processing according to the present embodiment.

As shown in FIG. 13, in the angle processing, an angle difference is detected according to the angle value (90 degrees) of the photographed image A and the angle value (0 degrees) of the reference image B to be compared. The captured image A is rotated so that the captured image A (the positional relationship between the subject and the frame) matches the angle value of the reference image B according to the angle difference.

Thus, the photographed image A and the reference image B can have the same angle value.

Next, a specific example of the zoom processing in step S1204 will be described with reference to FIG.

FIG. 14 is a diagram showing a specific example of the zoom processing according to the present embodiment.

As shown in FIG. 14, in the zoom processing, a zoom difference is detected according to the zoom value (100) of the photographed image A and the zoom value (0) of the reference image B to be compared. The scale of the image A is adjusted so that (the subject) matches the zoom value of the reference image B.

Thus, the photographed image A and the reference image B can have the same zoom value.

Next, a specific example of the brightness processing in step S1206 will be described with reference to FIG.

FIG. 15 is a diagram showing a specific example of the brightness processing of this embodiment.

As shown in FIG. 15, in the brightness processing,
A value (off) indicating whether or not the flash of the captured image A is turned on
And a value indicating whether the flash of the reference image B is turned on (on)
, The brightness of the captured image A is adjusted to the reference image B.

Thus, the captured image A and the reference image B can have the same brightness.

Next, the details of the group attribute assignment processing in step S407 will be described with reference to FIG.

FIG. 16 is a flowchart showing details of the group attribute assignment processing of the present embodiment.

When the group attribute determination process is started, in step S1601, it is determined whether or not group attribute data exists in the reference image B to be compared. If there is group attribute data (YE in step S1601)
S), the process proceeds to step S1605, the acquired group attribute data is added to the captured image A, and stored in the group folder on the data memory 5 having the group attribute data. On the other hand, if there is no group attribute data (NO in step S1601), the process advances to step S1602.

In step S1602, group attribute data indicating a new group is generated, and a new group folder is additionally created in the data memory 5. Next, in step S1603, the generated group attribute data is added to the captured image A and stored in the new group folder created on the data memory 5. Subsequently, step S1
At 604, the generated group attribute data is added to the reference image B to be compared, and stored in the new group folder created on the data memory 5.

Although FIG. 16 shows a configuration in which images having the same group attribute data are stored in folders, storage areas corresponding to the group attributes may be configured and stored in the data memory 5 respectively. good.

Next, a specific example of the processing executed in this embodiment will be described with reference to FIG.

FIG. 17 is a diagram showing a specific example of the processing executed in this embodiment.

In the following specific example, first, in step S
By the group attribute assigning process of 407, FIG.
As shown in FIG. 7, it is assumed that a group of captured images 00001 to 00005 is stored in the data memory 5, and each has the same group attribute 00001.

FIG. 17A shows, for example, a group of photographed images 00001 to 00005 in which the movement of the sunrise is photographed in chronological order. (For example, image 0000
2) and a captured image (for example, image 0
0005), the captured image (image 00001) before and after the target captured image (image 00002)
And the image 00003). As a result, the images 00001 to 00005 belong to the same group. In this manner, by determining the similarity between the processing target image and the comparison target image based on the shooting condition data and determining the group attribute, apparently different images such as a group of images that change in a time series can be obtained. Even in a group of images that may occur, those images can be grouped as the same image.

In this state, it is assumed that a new image is shot by the digital camera and the image 00006 is stored in the data memory 5. Also, the shooting time at this time is
October 10, 2000 (20001010), 7: 4
It is assumed that the time is 5 minutes and 11 seconds (0745111).

In this case, first, step S205 in FIG.
In the photographing condition acquisition processing of, an angle value (90 degrees) and a zoom value (-
10) is stored in the data memory 5.

Next, among the image classification processing in step S206 in FIG. 2, in the comparison target determination processing in step S401 in FIG. 4, the group of images 00001 to 00005 is stored in the comparison target list.

Next, in the threshold initial value acquisition processing of step S701 in FIG. 7 of the similarity degree determination processing in step S404, for example, the threshold initial value from the threshold initial value list in FIG. To get. Subsequently, in step S702, the processing target is set in the weight determination list of FIG. 9. In this case, the difference between the numerical data of the processing target image and the numerical data of the comparison target image is only the time distance, and the time distance of the weight determination list is determined. The threshold coefficient is set to 1 in accordance with the combination of the numerical data and the threshold coefficient data that have only changed. As a result, step S
At 708, a threshold 90% is set based on the threshold initial value 90% and the threshold coefficient 1.

Next, in step S602, image 0
The similarity between the image 0005 and the image 00006 is acquired. In this case, since the similarity is smaller than the threshold value, the process proceeds to step S604, and the error of the imaging condition data of both images is determined by the error determination process. Here, assuming that the error determination condition is the error determination condition 1 in FIG. 18, the error is within the error range as a result of the determination, and the process proceeds to step S606.

In the processing shown in FIG. 12, since there is an angle difference in step S1201, step S1201 is performed.
In step 1202, the angle processing is started, and the image 00006 is rotated by the angle difference as described with reference to FIG.
Next, since there is a zoom difference in step S1203, zoom processing is started in step S1204, and the scale of the image 00006 is reduced to the image 00005 as described with reference to FIG.
Adjust according to.

Subsequently, in step S1207, the center of gravity is determined from the overlapping area of both images, and in step S1208, the overlapping area of the processed image is cut out.

Subsequently, in the similarity acquisition processing in step S607, the similarity between the images processed by the processing is obtained. In this case, since the similarity is equal to or larger than the threshold, the image 00006 is replaced with the image in step S405. 000
05 is determined to be similar.

Subsequently, the group attribute assigning process in step S407 is started, and in step S1601, the image 0000 is added.
Since there are 5 group attributes 00001, the image 0000
60001 is assigned to the group attribute of No. 6.

In this way, the input image 00006 is given the same group attribute as the group of images 00001 to 00005. As a result, the image 00001 to the image 000
06 are classified as the same group.

As described above, according to the present embodiment, the images are classified based on the photographing condition data between the images, separately from the similarity between the images. Even for a group of images that may be apparently different, those images can be grouped as the same image.

In the above embodiment, an example has been described in which a group of images taken by a digital camera is classified based on the photographing time. However, the present invention is not limited to this. By classifying the electronic images based on the input time, the same effect as in the above-described embodiment can be obtained. Alternatively, as a condition replacing the input time, the input image may have an attribute of a file name, a classification symbol given to the input image at the time of shooting or input, or the like.
However, in this case, the classification preconditions and the photographing condition data described in the above embodiment are set by the user.

The present invention can be applied to a system composed of a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), but can be applied to a single device (for example, a copying machine, a facsimile machine). Etc.).

Further, an object of the present invention is to provide a storage medium storing a program code of software for realizing the functions of the above-described embodiments to a system or an apparatus, and to provide a computer (or CPU) of the system or apparatus.
And MPU) read and execute the program code stored in the storage medium.

In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiment, and the storage medium storing the program code constitutes the present invention.

As a storage medium for supplying the program code, for example, a floppy disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD
-R / RW, DVD-ROM / RAM, magnetic tape, non-volatile memory card, ROM and the like can be used.

When the computer executes the readout program code, not only the functions of the above-described embodiment are realized, but also the OS (Operating System) running on the computer based on the instruction of the program code. ) May perform some or all of the actual processing, and the processing may realize the functions of the above-described embodiments.

Further, after the program code read from the storage medium is written into a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, based on the instruction of the program code, It goes without saying that the CPU included in the function expansion board or the function expansion unit performs part or all of the actual processing, and the processing realizes the functions of the above-described embodiments.

When the present invention is applied to the storage medium, the storage medium stores program codes corresponding to the flowcharts shown in the above-described drawings.

[0123]

As described above, according to the present invention,
An image processing apparatus, an image processing method, and a program capable of efficiently and appropriately classifying images can be provided.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a hardware configuration of an image processing apparatus according to an embodiment.

FIG. 2 is a flowchart illustrating an outline of a process executed in the embodiment.

FIG. 3 is a flowchart illustrating details of a shooting condition acquisition process according to the embodiment;

FIG. 4 is a flowchart illustrating details of an image classification process according to the present embodiment.

FIG. 5 is a flowchart illustrating details of a comparison target determination process according to the embodiment.

FIG. 6 is a flowchart illustrating details of a similarity determination process according to the embodiment;

FIG. 7 is a flowchart illustrating details of a threshold acquisition process according to the embodiment;

FIG. 8 is a diagram illustrating an example of a threshold initial value list according to the present embodiment.

FIG. 9 is a diagram illustrating an example of weight determination list data according to the present embodiment.

FIG. 10 is a flowchart illustrating details of an error determination process according to the embodiment.

FIG. 11 is a diagram illustrating an example of photographing condition data according to the present embodiment.

FIG. 12 is a flowchart illustrating the processing according to the present embodiment.

FIG. 13 is a diagram illustrating a specific example of the angle processing according to the embodiment;

FIG. 14 is a diagram illustrating a specific example of zoom processing according to the embodiment;

FIG. 15 is a diagram illustrating a specific example of the brightness processing according to the embodiment;

FIG. 16 is a flowchart illustrating details of a group attribute assigning process according to the present embodiment.

FIG. 17 is a diagram showing a specific example of a process executed in the embodiment.

FIG. 18 is a diagram illustrating an example of an error determination table according to the present embodiment.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Image input part 2 CPU 3 Image output part 4 Program memory 5 Data memory 6 Bus 7 Operation part

──────────────────────────────────────────────────の Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) H04N 5/907 H04N 5/907 B // H04N 101: 00 101: 00 F term (Reference) 5B050 BA15 DA04 EA04 EA09 EA18 GA08 5B075 ND06 NR12 QM08 UU40 5C052 AA17 DD04 GA02 GB01 GB09 5L096 AA02 AA06 CA02 JA03 JA11 KA09 KA11

Claims (13)

[Claims] 1. An image processing apparatus for classifying a plurality of images, comprising: input means for inputting images; and a comparison target image to be compared for classifying the processing target image, based on an input time of the processing target image. Determining means for determining the image to be processed; specifying means for specifying a classification precondition for classifying the processing target image; and, based on the classification precondition specified by the specifying means, the processing target image and the comparison target image. Setting means for setting a threshold value for determining the degree of similarity; determining means for determining the degree of similarity between the processing target image and the comparison target image based on the threshold value; and An image processing apparatus, comprising: an assigning unit that assigns a group attribute indicating a group to which the processing target image belongs to the processing target image. 2. The image processing apparatus according to claim 2, wherein the similarity between the processing target image and the comparison target image is less than the predetermined value, and the input condition data of the processing target image and the input condition data of the comparison target image are determined. Based on the error determination results of the error determination means and the error determination means for performing the error determination of the difference,
The image processing apparatus according to claim 1, further comprising: a processing unit configured to process the image to be processed. 3. The apparatus according to claim 1, wherein the setting unit sets the threshold based on the classification precondition.
An image processing apparatus according to claim 1. 4. The input condition data is an angle value of an image, and the processing means converts the image to be processed according to a difference between an angle value of the image to be processed and an angle value of the image to be compared. The image processing apparatus according to claim 2, wherein the image processing is performed. 5. The input condition is a zoom value of the image, and the processing means processes the image to be processed according to a difference between a zoom value of the image to be processed and a zoom value of the image to be compared. The image processing apparatus according to claim 2, wherein: 6. The input condition is a value indicating whether or not the image is flashed, and the processing means is configured to determine whether or not the processing target image is flashed and whether or not the comparison target image is flashed. The image processing apparatus according to claim 2, wherein the processing target image is processed according to a difference from the indicated value. 7. An image processing method for classifying a plurality of images, comprising: an input step of inputting images; and a comparison target image to be compared for classifying the processing target image, based on an input time of the processing target image. A determination step of determining the classification target condition for classifying the processing target image, and a designation step of specifying a classification precondition for classifying the processing target image. A setting step of setting a threshold for determining a similarity; a determining step of determining a similarity between the processing target image and the comparison target image based on the threshold; and a determination result of the determining step. Providing a group attribute indicating a group to which the processing target image belongs to the processing target image. 8. The input condition data of the processing target image and the input condition data of the comparison target image when the similarity between the processing target image and the comparison target image is less than the predetermined value. Based on the error determination result of the error determination step and the error determination step of performing the error determination of the difference of,
The image processing method according to claim 7, further comprising: a processing step of processing the processing target image. 9. The method according to claim 7, wherein the setting step sets the threshold based on the classification precondition.
The image processing method according to 1. 10. The input condition data is an angle value of an image. In the processing step, the processing target image is processed in accordance with a difference between an angle value of the processing target image and an angle value of the comparison target image. The image processing method according to claim 8, wherein the image processing is performed. 11. The input condition is a zoom value of the image, and the processing step processes the image to be processed according to a difference between a zoom value of the image to be processed and a zoom value of the image to be compared. The image processing method according to claim 8, wherein: 12. The input condition is a value indicating whether or not the image is to be flashed, and the processing step includes determining whether or not the image to be processed is to be flashed and whether to flash the image to be compared. The image processing method according to claim 8, wherein the processing target image is processed according to a difference from the indicated value. 13. A program for causing a computer to perform image processing for classifying a plurality of images, comprising: a program code of an input step of inputting an image; and a comparison target image to be compared for classifying the processing target image. A program code of a determining step of determining based on the input time of the processing target image; a program code of a specifying step for specifying a classification precondition for classifying the processing target image; and a classification specified in the specifying step. Based on preconditions, a program code of a setting step of setting a threshold for determining the similarity between the processing target image and the comparison target image, and based on the threshold, the processing target image and the comparison target image, A program code of a discriminating step for discriminating the degree of similarity, and the processing target image belongs based on a discrimination result of the discriminating step. A program code for an application step of applying a group attribute indicating a group to the image to be processed.