Home  Semiconductor Information

Nov 5 2018

Iris Recognition Technology:Principle and Application

Warm hints: The word in this article is about 3000 words and reading time is about 15 minutes.

Summary

        Biometric recognition is the most convenient and safe identification technology at present. It does not need to carry any certificates or remember any password. It is a convenient, fast and reliable identification method. Biometric identification is a technique to identify individuals by their inherent physiological or behavioral characteristics. Common biometric features include fingerprints, palmprint, iris, retina, face shape, voice, handwriting and DNA.

Iris Recognition Technology:Principle and Application

        Iris recognition technology is a kind of perception recognition technology that we are at once familiar and strange, very mysterious but relatively common. We often see it in science fiction, even may meet it in our daily life. Iris recognition technology is claimed to be the most accurate and unfake perceptual recognition technology, which adds its mystery.

Article core

Iris Recognition Technology

Keywords

Iris Recognition Technology, Biometric recognition, Eye Image.

Article name

Iris Recognition Technology:Principle and Application

Category

Semiconductor Information

Application

Determines People's Identity

Purpose

Introduce Iris Recognition Technology


Catalog

What Is Iris?

Characteristics of Iris

Uniqueness  

Stability  

Anti-counterfeiting Property   

Noncontact   

Convenient Signal Processing   

The Principle of Iris Recognition Technology

Iris Image Acquisition   

Image Preprocessing 

Feature Extraction  

Feature Matching  

Application Field of Iris Recognition Technology 

Power / Nuclear Power / Military Field  

Industry / Enterprise / Institution Field  

Prisons / Detention Centres / Counter-terrorism / Public Security Field

NCMS / Urban and Rural Old-age Insurance / Health Care / Disease Control / Illicit Drugs / Virus Laboratory Field 

Finance/ Banking/ Tax Field

Civil Aviation / Airport / Customs / Port Field   



What Is Iris?

        The appearance of human eye is composed of sclera, iris and pupil. The sclera is the white part of the periphery of the eyeball, and the center of the eye is the pupil part. The iris lies between the sclera and the pupil, and contains the most abundant texture information. Apparently, the iris is one of the most unique structures in the human body, consisting of many glandular fossa, folds and pigmented spots. 

Iris Recognition Technology:Principle and Application

         Between the cornea and lens of a vertebrate eyeball, the membrane, globular and colored, is part of the vascular membrane and its center is the pupil. The front of the iris is covered with a layer of endothelium; the middle layer is a loose connective tissue rich in blood vessels and pigment cells. Different pigment content can make iris appear different color, iris is blue when no pigment;and iris may appear gray, brown to brown-black when the pigments are from less to more. There are two layers of pigmented epithelium behind the iris, whose inner epithelium differentiates into smooth muscle. The muscle fibers which arranged radially from the inside to outside, is called the pupillary opening muscles. Innervated by sympathetic nerves, the pupils dilate;the muscle fibers arranged in a circular pattern around the edge of the pupil, is called Pupillary sphincter. Innervated by parasympathetic nerves, the pupils shrinks. 


Characteristics of Iris

1.Uniqueness 

        The information contained in each iris is different, and the possibility of identical iris tissues is much lower than that of other tissues. The iris phase feature proposed by Professor John Daugman of the University of Cambridge in the United Kingdom confirms that the iris image has 244 independent degrees of freedom, that is, the average amount of information per square millimeter is 3.2 bits. The details of iris fibrous tissue are complex and abundant, and its formation is related to the local physical and chemical conditions of the tissue during embryogenesis. It has great randomness. Even cloning technology can not replicate an iris. The iris texture information of identical twins is different, and the iris texture of the same person's left and right eyes will be different from each other. The test results of the National Physics Laboratory show that iris recognition has the lowest error rate among all biometric recognition methods.

 Iris Recognition Technology:Principle and Application

2.Stability   

        The iris begins to develop from the third month of the embryonic period, and the main texture structure of the iris has been formed by the eighth month. Unless experienced surgery that endangers the eye, the iris will remain unchanged for almost the rest of the life. Because of the protective effect of the cornea, the developed iris is not easily injured by the outside world.

3.Anti-counterfeiting Property   

        The iris is the visible part of the human eye. The iris is protected by sclera and has strong biological activity. For example, the size of the pupil varies with the intensity of light; there is an unconscious adjustment process when looking at objects; there are more than ten times of unconscious pupil zooming per second; when the human brain dies, in a deep coma state or when the eyeball tissue is separated from the human body, the iris tissue shrinks completely and the pupil dilates. These biological activities are symbiotic with human life phenomena, so it is impossible to replace living iris images with photographs, videos or iris of corpses, which ensures the authenticity of physiological tissues. 

4.Noncontact   

        The iris is an externally visible internal organ that can obtain qualified iris images without clinging to a collection device. The identification method is cleaner and healthier than fingerprints, hand shapes, and other biological features requiring contact perception, and does not degrade the imaging device or influence others' identification.

5.Convenient Signal Processing   

        In the eye image, the area adjacent to the iris are the pupil and sclera. There are obvious gray scale changes between this two and the iris area, both boundaries of the area are close to the circle, so Iris region is easy to be fitted, segmented and normalized. The iris structure is conducive to a pattern representation with translation, scaling and rotation invariance.         

        Uniqueness, stability and anti-counterfeiting are incomparable with other perceptual recognition technologies such as two-dimensional codes, RFID and so on. Additionally, iris, as the only human internal organization that can be directly observed from outside, contains rich information. Iris recognition has become a very important environmental-aware recognition technology, especially for high confidentiality requirements.


The Principle of Iris Recognition Technology

        Iris recognition determines people's identity by comparing the similarities between iris image features. The core of iris recognition is to describe and match iris features of human eyes using pattern recognition and image processing methods, so as to realize automatic personal identity authentication. The main steps of iris recognition include iris image acquisition, preprocessing, feature extraction, coding and classification.

  Iris Image Acquisition   

        Iris image acquisition refers to the use of specific digital camera equipment to take pictures of the entire human eye, and the captured image is transmitted to the computer through the image acquisition card for storage. The acquisition of iris image is the first step in iris recognition, and it is also a difficult step. It needs the comprehensive application of optical, mechanical and electrical technology. Because the area of people's eyes is small, if we want to meet the image resolution requirement of recognition algorithm, we must improve the magnification factor of optical system, which leads to a smaller depth of field of iris imaging. Therefore, the existing iris recognition system requires users to stop at the appropriate location, while the eyes stare at the lens (Stop and Stare). In addition, the Oriental iris is darker and can not capture recognizable iris images with ordinary cameras. Different from image acquisition of biological features such as face image and gait, iris image acquisition needs to design a reasonable optical system, equipped with the necessary light source and electronic control unit.

Iris Recognition Technology:Principle and Application


  Image Preprocessing   

        Image preprocessing refers to the need for image smoothing, edge detection, image separation and other preprocessing operations because the captured eye image contains a lot of redundant information and can not meet the requirements in clarity and other aspects. 

        The process of iris image preprocessing usually includes iris localization, iris image normalization and image enhancement.

1. Iris localization  

        It is generally believed that the inner and outer boundaries of the iris can be approximately fitted by circles. The inner circle represents the boundary between the iris and the pupil, and the outer circle represents the boundary between the iris and the sclera, but these two circles are not concentric circles. Usually, the part of the iris near the upper and lower eyelids is always covered by the eyelids, so it is necessary to detect the boundary between the iris and the upper and lower eyelids, so as to accurately determine the effective area of the iris. The boundary between the iris and the upper and lower eyelids can be represented by a two degree curve. The purpose of iris localization is to determine the location of these two circles and the two degree curves in the image. The commonly used location methods can be roughly divided into two categories: one is the combination of edge detection and Hough transform; the other is the method based on edge search. The common disadvantage of these two methods is that the operation time is long, so there are some improved methods based on the above two strategies, but the speed has not increased by an order of magnitude. Localization is still one of the longest operation steps in iris recognition. 

Iris Recognition Technology:Principle and Application

2. Iris image normalization 

        The purpose of iris image normalization is to adjust the iris to a fixed size. So far, the exact mathematical model of iris texture changes with illumination has not been obtained. Therefore, researchers engaged in iris recognition mainly use the mapping method to normalize iris images. If the process of iris texture changing with illumination intensity can be modeled or simulated approximately, it will be helpful to improve the performance of iris recognition system.

Iris Recognition Technology:Principle and Application

3. Photographic enhancement  

        The purpose of image enhancement is to solve the problem of low contrast of normalized image caused by uneven illumination of human eye image. In order to improve the recognition rate, it is necessary to enhance the normalized image. 


  Feature Extraction    

        Feature extraction is to extract unique feature points from the separated iris image by a certain algorithm and encode them.  The main iris feature extraction and recognition methods can be divided into eight categories.

1.Based on the image, the iris image is regarded as a two-dimensional quantity field, and the gray value of the pixels forms a joint distribution, and the correlation between the image matrices measures the similarity.

2.Based on phase, this method considers that most of the important details in the image, such as the location information of "events" such as points, lines and edges, are contained in phase, so the amplitude information reflecting illumination intensity and contrast is discarded in feature extraction.

3.Based on singular points, there are two kinds of singularities in iris images: zero crossing and extreme points.       

4.Based on the statistical features of multi-channel texture filtering, iris image can be regarded as two-dimensional texture, and there will be strong discriminant statistical features in different scales and directions in the frequency domain for recognition, which is also a commonly used method in texture analysis. 

5.Based on the decomposition coefficients in frequency domain, an image can be regarded as a base consisting of many different frequencies and directions. By analyzing the distribution of each base projection value of image, we can deeply understand the regularity of the information in the image.

6.Based on the shape feature of iris signal, the shape feature of iris signal includes two aspects: two-dimensional shape information of concave and convex iris surface and one-dimensional shape information along iris circumference. 

7.Based on directional feature, directional or oriented is a relative value, which is robust to illumination and contrast changes, and can describe local gray level features. It is a more suitable form for iris image feature expression. 

8.Based on subspace, the subspace method needs to find several optimal bases on a large training data set according to the defined optimal criteria, and then take the projection coefficients of the original image on the optimal basis as image features of dimensionality reduction.


  Feature Matching    

        Feature matching refers to comparing and verifying the feature coding of iris image acquired from the current with that  stored in the database in advance, so as to achieve the purpose of recognition.


Application Field of Iris Recognition Technology 

 Power / Nuclear Power / Military Field    

        In order to improve the networking, intellectualization, informationization, management efficiency and safety of power plants, the advanced iris recognition technology in the world is adopted, and the advantages of computer network in data acquisition, data communication, data retrieval and system control are combined to realize the access control management of main channels (entrances and exits) and personnel attendance management. According to the equipment status of substation, it can be transformed into an anti-mistake locking system with iris identity authentication, which greatly improves the operation safety. 

 Industry / Enterprise / Institution Field    

        The mine iris attendance system is an important part of the coal mine safety production management. It can make the enterprise managers know the underground production condition and personnel composition in time, and effectively improve the safety production management and labor organization mode. It is an important means to improve the efficiency of production safety. What is common in the market is the attendance machine realized by magnetic card, IC card, radio frequency card, etc. It can't solve the substitution problem, and the biometric identification technology, such as fingerprint, can't adapt to the harsh underground environment because of its insufficient recognition precision. Equipment maintenance difficulties and other problems can not meet the needs. The iris recognition attendance system can eliminate the substitution phenomenon of attendance fundamentally, and its high safety. Performance, rapid identification and its unique utility in underground mines are unmatched by other biometric systems. 

Iris Recognition Technology:Principle and Application

  Prisons / Detention Centres / Counter-terrorism / Public Security Field  

  • Prison:Buffer access control: iris authentication and identification of entry and exit areas.

  • Management of mobile personnel:collect iris and identify iris after visiting to determine whether the is the same person

  • Criminal investigation: accurate identification of criminal suspects; rapid identification of criminals; verification of the identity of death row.

  • Exit and Entry Administration: identity card / Passport: identification by iris.

  • Road patrol system: checking suspicious persons

  • Anti terrorism: capture iris information and compare with anti terrorist information.

  NCMS / Urban and Rural Old-age Insurance / Health Care / Disease Control / Illicit Drugs / Virus Laboratory Field        

  • After the socialization of social security, because of the relocation, change and closure of the unit, the insured personnel flow and disperse. Therefore, it is always a difficult problem to determine the survival status of the insured in the social insurance payment and settlement work. The only way to solve this problem is to use biometric identification technology to identify the insured. 

  • After socialization of social security, because of unit relocation, change, close reason, cause insurant flow, disperse. So to determine the living condition of the insured is always a difficult problem in the social security payment and claim settlement. The only way to solve this problem is to use biometric identification technology to identify. 

  • There are a variety of biometric techniques that can be used, such as fingerprints, palmprint, voiceprint, iris, face, ear shape, body taste, DNA (human cell genetic genes), and so on. Biological characteristics are objective and unique, people are different, they are invariable throughout their lives, and they can not be copied.

  • Compared with other biometric technologies, from the point of view of technology maturity and convenience, iris automatic recognition is especially suitable for the use of social security system, and it is also the safest and most accurate biotechnology.

  • New rural cooperative medical system: the iris collection is carried out during the management of the new rural cooperative medical system, and then each time the iris verification is carried out, only though the verification can the relevant business be handled.

   Finance/ Banking/ Tax Field   

  • With the development of financial industry, the competition of financial market is becoming more and more serious, the management of banks is becoming more and more standardized, and the security problem is becoming the most important issue. The application of iris recognition in banking is the trend of the times.

  • Bank vault access Control: The iris information of the person who has the right to enter the bank vault can be saved, and iris verification should be carried out every time he enters the vault, which can only be accessed through verification. Multi person verification and remote verification can also be set up to enhance the safety management of bank vaults.

  • The management of cash truck: collect and save the iris information of the related personnel of the cash carrier, carry on the iris verification while on duty, at the same time can also set the authority to open the cash cabinet, only the person with the authority can open the cash cabinet, which effectively ensure the safety of funds.

  • Credit personnel's identity verification: Iris verification will be carried out first for each borrower. If there is iris information of the borrower, it means that the borrower has already borrowed and should stop issuing loans. It can prevent another borrowing and effectively stop the loss of funds. If there is no iris information of this person, save it. 

  Civil Aviation / Airport / Customs / Port Field   

Iris Recognition Technology:Principle and Application

        Iris recognition system has been playing a more and more important role in many fields, such as the automatic biometric customs clearance system between airport and harbour customs, detection system and the identity detection device used by police, etc. The iris identification system can be used in key defensive areas, channels and ports where it needs, granting different authority to the authenticated personnel, and automatically taking measures to enclose the unauthorized personnel, who try to force to pass, into alert space. Automatic rapid customs clearance is a typical application of iris recognition. It will not only increases the airport security level, alleviates the pressure of passenger flow, but also brings economic benefits to the airport. Today, public safety has become a hot issue, the application of iris recognition technology in airports will become a trend of development internationally. 


You May Like:

What Is Facial Recognition Technology?



0 comment

Leave a Reply

Your email address will not be published.

 
 
   
Rating: