JPH10340345A - Individual identification device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an individual identification device capable of surely perform individual identifying processing even when an identification object is not still. SOLUTION: Image storage means 1-4 respectively store different images photographing the same identification object. An image selecting means 5 discriminates the presence/absence of image directly usable for an individual identifying means 8 out of images in the image storage means 1-4 and when there is such an image, this is outputted to the individual identifying means 8. When there is not such an image, image composition is instructed to a composite image generating means 6. The composite image generating means 6 generates the composite image usable for individual identifying processing at the individual identifying means 8 from images in the image storage means 1-4 and stores the result in a synthetic image storage means 7. The individual identifying means 8 performs individual identification by analyzing either the image selected by the image selecting means 5 or the composite image stored in the composite image storage means 7.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to an individual identification device for identifying an individual by performing image processing on an input image.

[0002]

2. Description of the Related Art There is known a technique for identifying an individual by photographing biological information (face, iris, fingerprint, etc.) of a human or an animal with a camera or a scanner and analyzing the obtained image. For example, such a technique is disclosed in US Pat.
There is one shown in the specification of 91560.

In the technique disclosed in the above document, an iris image of a human eye is analyzed, image data of the iris is converted into 0 and 1 codes, and the codes are stored in advance as a dictionary. Similarly, when actually performing identification, the input iris image is converted into codes of 0 and 1, and individual identification is performed by comparing the converted code with the code of the dictionary. .

[0004]

However, in the above-described conventional individual identification technology, when the object to be identified is not still, the object captured by the camera does not show the object to be identified, Even if
There is a problem that a part of the identification target may be missing, and the degree of failure in identification increases. For example, in the technique of the above-mentioned document, when a person to be photographed moves or walks around when capturing an iris image of a person with a camera, a part of the iris is captured in the obtained input image. In the worst case, or in the worst case, no iris may be present in the image. In such a case, there is a problem that the accuracy of identification is reduced.

Similarly, when the object to be identified is an animal, it is not always necessary to stay still, which increases the possibility that an image convenient for the identification system cannot be obtained.

[0006] In view of the above, it has been desired to realize an individual identification device that can reliably perform individual identification processing even when the identification target is not stationary.

[0007]

The present invention employs the following structure to solve the above-mentioned problems. <Structure of Claim 1> An image storage means for photographing the same identification target and separately storing a plurality of images different from each other, and a plurality of images stored in the image storage means for direct individual identification. Judge whether there is an image that can be used, if there is an image that can be used directly, select that image as an image for individual identification, and if there is no image that can be used directly, select an image that outputs an image synthesis instruction Means, a composite image generating means for synthesizing an image usable for individual identification from a plurality of images stored in the image storage means when an image synthesizing instruction is output from the image selecting means, and an individual selected by the image selecting means. If the identification image or the individual identification image does not exist, the synthesized image generated by the synthesized image generating means is analyzed, and the characteristic amount obtained by the analysis is compared with the previously stored characteristic amount. The Rukoto an individual identification apparatus which is characterized in that a individual identification means for performing identification of individuals.

<Explanation of Claim 1> According to the invention of claim 1, a plurality of images are photographed from the same object to be identified, and if any of them can be used as they are, individual identification is performed based on these images. If not, the image is synthesized.

The object to be identified is, for example, a human or an animal.
The photographed image is an eye image, but is also applicable to various other individuals and images photographed of the individual. Further, as for the image synthesis, any synthesis method may be used as long as an image that can be used for individual identification can be obtained. Further, the characteristic amount in the individual identification means is, for example, an iris code in the iris recognition process, but may be another characteristic amount depending on the individual.

According to the first aspect of the present invention, it is possible to increase the possibility of obtaining an image that can be used for individual identification even when the identification target is not stationary. Further, even when there is no image directly usable for individual identification among a plurality of images, an image for identification can be obtained by image synthesis, and thus the possibility of identification in individual identification processing can be further increased. .

<Structure of Claim 2> In Claim 1, there is provided individual identification means for performing individual identification processing while excluding a region in which a pixel value is not obtained from the composite image generated by the composite image generation means. An individual identification device characterized in that:

<Explanation of Claim 2> According to the invention of claim 2, a portion in which a pixel value is not obtained even in a synthesized image is excluded from a target of the identification processing. As a result, it is possible to suppress a decrease in the processing accuracy even in the identification processing using the composite image.

<Structure of Claim 3> In Claim 1 or 2, a unique portion common to a plurality of images of the object to be identified is used as a reference point, and the images are synthesized so that the reference points match. An individual identification device comprising a composite image generation unit.

<Explanation of Claim 3> In the invention of claim 3, in the image synthesizing process, a plurality of images are synthesized based on reference points in the images. Here, the reference point may be any point as long as it is a part that is commonly present in a plurality of images.

(Structure of Claim 4) In any one of Claims 1 to 3, an image storage means for photographing the eyes of the same individual and separately storing a plurality of images each different from each other, and photographing the eyes A composite image generating means for composing an image so that the reference point coincides with a portion of the illumination for photographing present in the plurality of images, and an individual identification unit for performing individual identification by iris recognition processing Means for identifying an individual.

<Explanation of Claim 4> According to a fourth aspect of the present invention, a plurality of images are taken as images of the eyes, and individual identification is performed by iris recognition processing. It is a reflection of the lighting of the. Here, the individual includes not only humans but also animals such as horses. According to the fourth aspect of the present invention, with such a configuration, the iris recognition process can be reliably performed even in the case where, for example, an animal such as a horse often stays still during photographing. In addition, since the reference point is a reflection of illumination, it is easy to detect the reference point from the image, and the processing load is light, so that a high-performance individual identification process can be performed.

[0017]

Embodiments of the present invention will be described below in detail with reference to the drawings. << Specific Example >> In this specific example, an object to be identified is photographed by a plurality of cameras, and an image suitable for individual identification is selected from a plurality of images obtained by photographing. Also, in the image obtained by shooting,
Even when there is no image suitable for individual identification, a composite image is generated from a plurality of obtained images, and an image suitable for individual identification is generated, thereby improving the accuracy of individual identification.

<Configuration> FIG. 1 is a configuration diagram showing a specific example of an individual identification device of the present invention. The apparatus shown in the figure is constituted by a computer and comprises image storage means 1, 2, 3, 4, image selection means 5, composite image generation means 6, composite image storage means 7, and individual identification means 8. In this specific example, a case will be described in which iris recognition is performed as individual identification. In this specific example, a case will be described in which four cameras for photographing the identification target are prepared. However, the present invention is not necessarily limited to a configuration in which four cameras are used for photographing.

The image storage means 1 to 4 are provided in an auxiliary storage device such as a semiconductor memory or a disk, and are functional units for individually recording images taken by the four video cameras for individual identification at the same moment. is there. Further, these image storage means 1 to 4 need not be independent memories or disks, but may be independent memory areas. Furthermore,
Each image can be obtained by A / D converting an image obtained by a video camera.

The image selection means 5 is the most effective image among the images stored in the image storage means 1 to 4 as an image to be used by the individual identification means 8 based on the position of the reflection of the illumination present in the image. It has a function of selecting a suitable image.
However, if it is determined that none of the images stored in the image storage units 1 to 4 is suitable for use by the individual identification unit 8, the configuration is such that the composite image generation unit 6 is instructed to generate a composite image. Have been.

The composite image generation means 6 operates when the image selection means 5 determines that there is no image which can be used as it is for the individual identification processing, and reflects the illumination detected by the image selection means 5. Is a functional unit that synthesizes images based on the position of. The composite image storage unit 7 is a functional unit that is provided in an auxiliary storage device such as a semiconductor memory or a disk and stores the composite image generated by the composite image generation unit 6.

The individual identifying means 8 analyzes the image selected by the image selecting means 5 or, if the image does not exist, the synthesized image generated by the synthesized image generating means 6, and analyzes the feature quantity obtained by the analysis. This is a functional unit for identifying an individual by comparing the feature amount of an identification dictionary provided in advance.

<Operation> Assume that four cameras shoot the same object at the same moment, and the respective images are stored in the image storage means 1 to 4.

FIG. 2 is an explanatory diagram showing an example of an input image stored in the image storage means 1-4. As shown in the figure, the video cameras that capture the identification target are arranged so as to obtain different images. Therefore, the images stored in the image storage units 1 to 4 are different images.

When the images shown in FIG. 2 are stored in the image storage units 1 to 4, the image selection unit 5 first selects the most suitable image among the images used by the individual identification unit 8. Select an image. However, when it is determined that none of the images is suitable for use by the individual identification unit 8, the image processing unit 6 instructs the composite image generation unit 6 to generate a composite image.

The operation of the image selecting means 5 when the identification target is an iris image will be described below. FIG. 3 shows an example of the iris image. The black circles in the pupils in the figure indicate that the illumination illuminated during imaging is reflected in the image. In this specific example, an image selection process is performed using the position information of the reflection of the illumination. In this specific example,
It is assumed that the system is such that when the object to be identified is illuminated, the reflected part is located in the pupil.

Various methods can be considered as a method of detecting the position of the reflection of the illumination in the image. For example, when the light is reflected, the pixel at the position where the light is reflected is very bright. Therefore, first, the brightest area in the image is found, and if the brightness of the area is brighter than a preset threshold, the area is determined to be the reflection of illumination.
On the other hand, if the brightness of the area is darker than a preset threshold, it is determined that there is no reflection of illumination.

As described above, first, the image storage means 1 to 1
For each of the images stored in step 4, the presence or absence of the reflection of the illumination and, if it is, the position of the illumination are detected.

Next, the image selecting means 5 performs an image selecting process using the position information of the reflection. FIG. 4 is an explanatory diagram of the image selection determination using the position of the reflection. When the position of the reflection is present in the area 1 shown in the figure, the individual identification means 8 determines that the image cannot be used as it is. On the other hand, when the position of the reflection of the light exists in the area 2, it is determined that the image is an image that can be directly used by the individual identification unit 8. That is, as described above, the position where the illumination is reflected is the pupil portion, which is the center of the eye. Therefore, the case where the position of the reflection exists in the central part as in the region 2 means that the image of the eye is located substantially in the central part of the screen, and thus there is a high possibility that a complete iris image is obtained. Is the case. On the other hand, the case where the position of the reflection is located at the periphery of the screen as in the region 1 is the case where the iris image is also located at the periphery of the screen and a complete image may not be obtained. .

The image selecting means 5 instructs the individual identifying means 8 to perform individual identification using the image when the position of the reflected light is one image in the area 2.
For example, in the example of FIG. 2, the image stored in the image storage unit 2 is selected. When there are a plurality of images in which reflection of illumination exists in the area 2, an image whose reflection of illumination is closest to the reference point of the reflection determination shown in FIG. 4 is selected, and individual images are selected using the image. The individual identification means 8 is instructed to perform identification.

On the other hand, when there is no image in which the reflection of the illumination exists in the area 2, the image processing unit 6 instructs the synthetic image generating means 6 to generate a synthetic image.

Next, the operation of the composite image generating means 6 will be described. The composite image generation unit 6 operates when the image selection unit 5 determines that there is no image that can be directly used for the individual identification processing. The composite image generation unit 6 performs image synthesis using the position information of the reflection of the illumination detected by the image selection unit 5. And
The composite image generation unit 6 uses only the image in which the reflection of the illumination exists in the area 1 in FIG. 4 among the images stored in the image storage units 1 to 4.

FIG. 5 shows an example of an image processed by the composite image generating means 6. In the example shown in the figure, since the reflection of the illumination of the images stored in the image storage unit 1, the image storage unit 2, and the image storage unit 3 exists in the area 1 in FIG. Combine one image. Since the position of the reflected light was not detected in the image stored in the image storage means 4, this image is excluded from the processing target.

The composite image generation means 6 includes image storage means 1 to
The images are synthesized by superimposing the positions of the reflections of the illuminations of the images stored in the image 3.

FIG. 6 is an explanatory diagram of a synthesized image. In the illustrated example, the position of the reflection of the illumination is superimposed on the reference point of the reflection determination in FIG. In FIG. 6, various methods can be considered as a method of calculating a pixel value of a region where a plurality of images overlap. For example, a method of using the average value of the overlapping images, a method of using the pixel values of the images in which the position of the reflection of the illumination is close to the reference point of the reflection determination in FIG. There is. In addition, as a pixel value of an area where a pixel value is not obtained as in the lower left portion of the composite image illustrated in FIG. 6, a value set in advance according to an identification target or an identification method is employed. Further, the position information of the area where the pixel value is not obtained is output to the individual identification means 8. The individual identification means 8 performs processing by excluding the area where the pixel value is not obtained from the target of the identification processing. Thus, it is possible to suppress a decrease in identification accuracy.

The composite image generated by the composite image generation means 6 is stored in the composite image storage means 7. When there is no image in which the reflection of the light exists, the composite image generating means 6 does not perform the image compositing process. Therefore, in this case, the individual identification means 8 does not perform the identification processing.

Next, the operation of the individual identification means 8 will be described. If there is an image selected by the image selection means 5, the individual identification means 8 outputs the image based on the image. If no image is selected by the image selection means 5, the composite image generation means 6 A characteristic amount is obtained by analyzing a composite image (image stored in the composite image storage means 7) obtained by the composition, and the characteristic amount is compared with the characteristic amount registered in advance in an identification dictionary or the like. By comparing with, individual identification is performed. However, if neither the image selecting unit 5 nor the composite image generating unit 6 can obtain an image, the individual identification processing is not performed.

Here, a case where iris recognition is used as the individual identification processing will be described. The individual identification means 8 is an eye image stored in the image storage means 1 to 4 selected by the image selection means 5 or a composite image stored in the composite image storage means 7 generated by the composite image generation means 6 Is analyzed to determine the circumcircle of the pupil and the circumcircle of the iris.
Next, polar coordinates are set based on the two circles, the iris region is divided into several regions, and codes 0 and 1 (hereinafter, referred to as iris codes) are output by filtering and thresholding. . Individual identification is performed by comparing the iris code generated in this manner with an iris code stored in advance in an identification dictionary or the like.

For example, in the literature described in the prior art, a Hamming distance between an iris code generated from an input image and an iris code stored in an identification dictionary is calculated, and a dictionary having the smallest Hamming distance is selected. I do. Further, when the Hamming distance at that time is smaller than a preset threshold value, it is determined that the user is the principal.

When the individual identification means 8 uses the composite image stored in the composite image storage means 7 for identification, an area where a composite image is not obtained (for example, FIG. 6).
(Lower left area) is excluded from the target of the individual identification processing to improve the identification accuracy.

As described above, the case where iris recognition is used as the individual identification means by image analysis has been described in the above specific example. However, the present invention can be applied to various techniques for identifying individuals by analyzing images. Also, the identification target is not limited to humans, and is a technology applicable to animals in general, such as dogs, cats, and horses. Furthermore, an example in which four images are used as a plurality of images has been described, but even if the number of images increases or decreases,
By preparing an image storage means in response to this, it can be easily handled.

Further, in the above specific example, as the plurality of images to be identified, images photographed at the same moment are used. Thus, even if the position of the identification target in the screen is different, the size can be made substantially the same. Therefore, even when the synthesized image is generated by the synthesized image generating means 6, processing for adjusting the size of the iris portion is not required, and the load of the image synthesis processing can be reduced. In addition, as long as a plurality of images are images of the same identification target, not all images need to be always shot at the same moment. However, if there is a temporal difference between the plurality of images, the size of the identification target itself may be different between the plurality of images. It is necessary to perform a process of adjusting the values.

<Effects> As described above, according to the specific example, since a plurality of different images obtained by photographing the same object to be identified are used, even if the object to be identified is not stationary, it can be used for individual identification. It is possible to increase the possibility of obtaining a possible image.

Even when there is no image directly usable for individual identification among a plurality of images stored in the image storage means 1 to 4, an image usable for individual identification is synthesized from those images. With this configuration, the possibility of identification in the individual identification processing can be further improved.

In the individual identification processing, when the composite image is used for identification, the area where no pixel value is obtained is excluded from the object of identification, and the processing is performed.
Even in such a case, it is possible to suppress a decrease in individual identification accuracy. Therefore, high-performance individual identification can be realized as a system.

Further, all the operations of the above specific example can be realized by control by a program of a computer which plays a role of an individual identification device. Therefore, a method of recording the program on a recording medium such as a floppy disk or a CD-ROM and then installing the program on a computer, or downloading and installing the program from a network, or a method of previously installing the program on a hard disk or the like Thereby, the individual identification device of the present invention can be realized.

[Brief description of the drawings]

FIG. 1 is a configuration diagram showing a specific example of an individual identification device of the present invention.

FIG. 2 is an explanatory diagram of an input image of an image storage unit in a specific example of the individual identification device of the present invention.

FIG. 3 is an explanatory diagram showing an example of an iris image in a specific example of the individual identification device of the present invention.

FIG. 4 is an explanatory diagram of an image selection determination using a reflection position in a specific example of the individual identification device of the present invention.

FIG. 5 is an explanatory diagram illustrating an example of an image processed by a synthetic image generation unit in a specific example of the individual identification device of the present invention.

FIG. 6 is an explanatory diagram of a combined image in a specific example of the individual identification device of the present invention.

[Explanation of symbols]

 1-4 Image storage means 5 Image selection means 6 Synthetic image generation means 7 Synthetic image storage means 8 Individual identification means

Claims (4)

[Claims] 1. An image storage means for photographing the same identification target and separately storing a plurality of different images, and directly using the plurality of images stored in the image storage means for individual identification. Image selecting means for judging whether there is an image which can be used, and when there is an image which can be directly used, selecting the image as an image for individual identification, and when there is no image which can be used directly, outputting an image synthesis instruction And when an image combining instruction is output from the image selecting means,
A composite image generation unit that synthesizes an image that can be used for individual identification from a plurality of images stored in the image storage unit; and an individual identification image selected by the image selection unit, or when the individual identification image does not exist. Comprises individual identification means for identifying the individual by analyzing the composite image generated by the composite image generation means, and comparing the characteristic amount obtained by the analysis with the characteristic amount stored in advance. An individual identification device characterized in that: 2. The apparatus according to claim 1, further comprising: an individual identification unit that performs an individual identification process by excluding a region in which no pixel value is obtained from the composite image generated by the composite image generation unit. Individual identification device. 3. The composite image generating means according to claim 1, wherein a unique portion common to a plurality of images of the object to be identified is used as a reference point, and the images are synthesized so that the reference points match. An individual identification device, comprising: 4. The image storage device according to claim 1, wherein an image of the same individual is photographed, and a plurality of images each of which is different from each other are separately stored; A composite image generating means for composing an image in such a manner that a portion of the illumination for photographing existing in the image is included as a reference point and combining the reference points, and an individual identification means for identifying an individual by iris recognition processing An individual identification device characterized in that: