Image analysis – Applications – Animal – plant – or food inspection
Reexamination Certificate
1998-03-27
2001-09-04
Mehta, Bhavesh (Department: 2621)
Image analysis
Applications
Animal, plant, or food inspection
C382S117000
Reexamination Certificate
active
06285780
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to an individual animal identification apparatus for storing data for identification of individual animals and collating the features of the animals with stored data in organizations which individually manage animals, such as horses (for horse racing) or cattle (for livestock farming) and so on.
2. Prior Art
The identification of thoroughbreds in the racing tracks, auctions or breeding farms is done under the leadership of pedigree management organizations. The current identification method in Japan is by colors, white marks of the legs and the head. There are other methods, such as by blood types, brands or tattoos, which are used in some countries of the world. (References: “Uma no Chishiki” (Knowledge about the Horse)
11-3,
“Uma no Miwakekata” (How to Identify Horses) pp. 153-154)
In identifying cattle, identification tags, such as collars or ear tags, brands or tattoos have been adopted in stock farms in general. An identification method of animals currently drawing attention is by the use of a micro chip (MC). A micro chip in this case is encapsulated in a glass tube, and buried in the body of an animal by using some injecting means, such as a syringe, and when an animal is identified, the buried micro chip is scanned with a non-contact detector to detect an output signal from which ID information of the animal is obtained.
In the above-mentioned prior art, there is a problem which must be solved. Identification by the colors, white marks, and whorls tends to be incomplete with horses without salient features or horses with similar features. Furthermore, there are possibilities that the brands or tattoos wear off or are falsified. It has been desired that those methods be improved partly from a viewpoint of prevention of cruelty to animals, such as, causing a pain or a festering wound to the animals. The identification by blood types is accurate, but the process takes time until a decision is made, and is expensive.
The use of identification plates entails the risk of being lost or stolen. As in the case of horses, brands or tattoos made on animals have possibilities of wearing off or being falsified. Even if falsification is found, it is difficult to prove where the animal belongs.
The MC method has advantages of semi-permanent effectiveness once a micro chip is planted in the body of an animal and also high convenience. This MC method, however, involves many problems: the workability of the MC and an acute pain during implantation, the local reactions, such as swelling, oppressive pain, festering, hypokinesia of the animal, clinical abnormality, the MC's tendency to move in the animal body, the operability, stability and reliability of the detector, and the variation of detection sensitivity. Many people have shown opposition to the adoption of the MC method from nothing other than the standpoint of preventing cruelty to animals. So, there has been demand for a more convenient identification method to replace the MC method.
SUMMARY OF THE INVENTION
To solve the above problems, the present invention adopts the following arrangements.
<Arrangement 1>
An individual animal identification apparatus comprising: an eye region image pick-up unit for obtaining an input image by taking a picture of an eye, including the iridial granule, of an animal to be registered and identified; a geometric normalizer for performing a coordinate transformation process by using a specified parameter to move the iridial granule region of the input image onto predetermined coordinates; a feature extractor for extracting the feature of the normalized iridial granule; a dictionary memory for recording data on the feature of the iridial granule regions corresponding to animals to be registered, namely, the data having been extracted by the feature extractor; and a collator for checking whether or not an animal to be identified has been registered by comparing data on the feature of the iridial granule region corresponding to the animal under identification, the feature having been extracted by the feature extractor, with the feature data registered in the dictionary memory.
<Arrangement 2>
An individual animal identification apparatus according to Arrangement 1, wherein the geometric normalizer decides the position of the center of gravity of the iridial granule region as a predetermined parameter and performs a coordinate transformation process by using this parameter.
<Arrangement 3>
An individual animal identification apparatus according to Arrangement 1, wherein the geometric normalizer decides the inclination of a principal component of the iridial granule region to a reference line as the parameter and performs a coordinate transformation process by using this parameter.
<Arrangement 4>
An individual animal identification apparatus according to Arrangement 1, wherein the geometric normalizer decides a longitudinal length of the iridial granule region as the parameter and performs a coordinate transformation by using this parameter.
<Arrangement 5>
An individual animal identification apparatus according to Arrangement 1, further comprising a density normalizer for calculating a mean value of the density of the iridial granule region in connection with the contrast, and normalizing the density of the iridial granule region on the basis of the mean value.
<Arrangement 6>
An individual animal identification apparatus according to Arrangement 5, wherein the density normalizer calculates a standard deviation of the density of the iridial granule region by regarding the standard deviation as the contrast, and normalizes the density by using the standard deviation and the mean value.
<Arrangement 7>
In an individual animal identification apparatus according to Arrangement 1, the feature extractor divides an iridial granule region into a plurality of subdivisions, converts the subdivisions into compressed regions each having a mean value of pixel densities, and uses the density values of the compressed regions as data on the feature.
<Arrangement 8>
In an individual animal identification apparatus according to Arrangements 1 and 7, the collator performs an arithmetic operation on differences between the density values of the compressed regions extracted by the feature extractor and the density values of the compressed regions registered in the dictionary memory, and uses an obtained difference as a difference for identification of the animal.
<Arrangement 9>
An individual animal identification apparatus according to Arrangement 8, wherein the collator calculates a mean density difference of the compressed regions by dividing the total sum of the density values by the number of the compressed regions, and uses the mean density difference as a difference.
<Arrangement 10>
An individual animal identification apparatus according to Arrangement 1, further comprising a plurality of geometric normalizers, wherein the geometric normalizers respectively perform a coordinate transformation process on the iridial granule region by using a parameter which is different from the parameters used by the other normalizers.
<Arrangement 11>
An individual animal identification apparatus comprising:
an eye region image pick-up unit for capturing an image of an eye, including an iridial granule, of an animal at camera angles to obtain an input image, the animal to be registered in a registration mode of the apparatus while identified in an identification mode of the apparatus;
a camera angle determining section for deriving data on the camera angles;
a feature extracting section for extracting a feature of a region of the iridial granule from the input image to derive corresponding feature data;
a dictionary memory for, in the registration mode, registering the feature data of the animal to be registered along with the corresponding camera angle data; and
a collating section for, in the identification mode, collating the feature data of the animal to be identified, de
Kuno Yuji
Yamakita Osamu
Frank Robert J.
Mehta Bhavesh
OKI Electric Industry Co., Ltd.
Venable
Wood Allen
LandOfFree
Apparatus for identifying individual animals and image... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Apparatus for identifying individual animals and image..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Apparatus for identifying individual animals and image... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2511260