57 results about "Iris detection" patented technology

The invention relates to a living iris detection method, which comprises the following steps of: S1, pre-treating a living iris image and an artificial iris image in a training image library; performing multi-scale characteristic extraction of local binary mode in an obtained interested area, and selecting the preferable one from the obtained candidate characteristics by using an adaptive reinforcement learning algorithm, and establishing a classifier for living iris detection; and S2, pre-treating the randomly input test iris image, and calculating the preferable local binary-mode characteristic in the obtained interested area; inputting the calculated characteristic value into the classifier for living iris detection obtained in step S1, and judging whether the test image is from the living iris according to the output result of the classifier. The invention can perform effective anti-forgery detection and alarm for the iris image and reduce error rate in iris recognition. The invention is widely applicable to various application systems for identification and safety precaution by using iris recognition.

Biometric iris detection systems are adaptable for control of alarm conditions through the systems scanner or reader by physical actions of a user's eye and / or eye lid. An alarm condition can be set in a biometric iris detection system following a predetermined blinking pattern by a user's eyelid. An alarm condition also can be set in a biometric iris detection system following closure of a user's eyelid for a predetermined time following user identification / acceptance by the system. An alarm condition can following a predetermined movement patter of a user's eyeball (e.g., a user looks at a particular area, or areas, within a biometric reader, e.g., upper left, upper right, lower left, lower right, during user identification and acceptance procedures. The embodiments of the present invention can be carried out using biometric iris detection hardware and image processing / control software.

The invention discloses an automobile anti-theft automatic control system based on biological information identification. The automobile anti-theft automatic control system consists of a vibration detection subsystem, a fingerprint identification subsystem, an iris information identification subsystem, a voice identification and control subsystem and an alarm subsystem, wherein when an owner of an automobile wants to open a door, a trunk cover and an oil tank cover, the door, the trunk cover and the oil tank cover are opened automatically through fingerprint identification; when the owner of the automobile enters the automobile, the voice identification and control subsystem is activated through the iris identification; an engine and a vehicle-mounted device are controlled to work through voice identification; when a thief wants to prize doors, windows, the trunk cover and the oil tank cover, an alarm device is used for alarming in wireless communication and bell ringing ways; when the fingerprint identification is wrong, an alarm is sent to the owner of the automobile; and if the iris information is wrong or a person entering the automobile does not perform the iris detection after being prompted, bell ringing alarm is made, and an alarm is sent to the owner of the automobile. Due to the adoption of the reliable anti-theft automatic control system, the possibility that the automobile is stolen is lowered to the maximum extent, and the property security of the owner of the automobile is effectively protected.

The invention provides a rapid iris collecting, judging and controlling method for iris identification. Iris quality detection comprises rapid primary detection after coarse positioning of a pupil and fine detection after the pupil is positioned. Speed of the primary iris quality detection method is high, and definition of an iris, motion blur, whether blinking occurs, the effective iris proportion, and whether an image is a living iris image are all detected. 95% of the iris image after primary quality detection meets the requirement for final fine iris detection, and therefore collecting speed is greatly improved. After iris positioning is completed, fine quality detection of the iris image mainly comprises detection for the definition and the deformation degree of the iris. In addition, the focal length of a CCD, light intensity of a near-infrared light source and a user display interface are controlled in a primary quality detecting process, magnification times of the CCD are controlled in the fine iris quality detecting process, and therefore a user can carry out the method conveniently.

The invention provides a mobile terminal iris detection method and a mobile terminal. The mobile terminal iris detection method comprises the following steps that: when iris detection indicating information is received, a controller of the mobile terminal acquires an iris image acquired by an iris scanner arranged in the mobile terminal; the controller partitions the iris image into iris subgraphs which correspond to each organ of a human body according to an iris map; the controller extracts specific characteristic information of each subgraph, and acquires health state information which correspond to the specific characteristic information from an iris information database; and the controller controls display equipment of the mobile terminal to display the health state information. Due to the adoption of the mobile terminal iris detection method and the mobile terminal provided by the invention, the iris image can be fully utilized, the iris detection function is integrated into the mobile terminal, inspection of the health state of a human body is realized while the communication function is realized, additional purchase of an iris detector or inspection in a hospital is not required, the occupied space is reduced, and the resource utilization ratio is increased.

The invention provides an image information processing method and apparatus which can accurately calculate the central position of the iris of the person based on the person image shot and can calculate the sightline direction with the high accuracy. An eye-gaze direction calculation unit (29) calculates the eye-gaze direction in an input facial image of a person by carrying out prescribed operation processing based on iris shape data output from an iris detection unit (25) and face-direction measurement data output from a face-direction measurement unit (27). The eye-gaze direction of the facial image of the person can be measured on the basis of accurate iris shape information obtained by an iris shape detection unit (19). The iris and sclera regions can be estimated on the basis of thedetected eyelid contour information, thereby making it possible to accurately estimate the shape of the iris.

The invention discloses a rapid iris detection method based on a convolutional neural network. The method comprises the following steps: (1) designing and training an iris detection network regressiondevice model; (2) obtaining a to-be-detected iris image and carrying out image preprocessing; (3) inputting the image obtained in the step (2) into the iris detection network regression device modelobtained in the step (1) to obtain the probability of belonging to the iris and the bias of the central point and the radius of the iris image; and (4) in order to obtain a more accurate iris position, outputting the iris center point and radius corresponding to the iris probability greater than a preset threshold in the result obtained in the step (3), and screening through a non-maximum suppression method to obtain the center point and radius of the iris of the final image, thereby obtaining the circular range corresponding to the iris area. According to the technical scheme, the compact convolutional neural network is adopted to carry out regression on the central point and radius offset of the iris image, the iris area is obtained according to the circular characteristics of the iris,the detection speed is high, the accuracy is high, and the method plays an important role in improving the iris recognition precision.

The embodiment of the invention discloses an iris detection method of living body, and a terminal. The method comprises: a plurality of iris photos are obtained; a position of a center of a pupil in each iris photo is determined; according to the position of the center of the pupil in each iris photo, a maximum displacement value of the center of the pupil is calculated; and according to the maximum displacement values of the centers of the pupils, an iris detection result is determined. According to the embodiment of the invention, the iris detection accuracy and identification efficiency are improved; and the eyes can be protected from being injured.

The invention provides a human health detecting and prompting method and system. The method includes: acquiring the number and identity of users entering an elevator according to one or more of face recognition, iris detection, fingerprint information, preset gestures, input target floor information acquiring and identity card recognition; acquiring the weight parameter, the heart rate parameter, the fat parameter and the blood pressure parameter of the users to perform health condition analysis, and using one or more of voice prompting in the elevator, visual prompting in the elevator and prompt information sending to the social account and mobile phone of the corresponding user to remind the corresponding user pay attention to health problems if abnormal health data is discovered; by a server, automatically contacting first-aid services conforming to preset conditions to perform first-aid on the corresponding user if the server judges that the discovered abnormal health data belongs to severe situations in a preset severe situation list. By the human health detecting and prompting method and system, human health detecting convenience is increased greatly.

The invention provides a model generation method and device and an iris detection method and device, and the method comprises the steps: obtaining a training sample set, wherein the training sample set comprises a plurality of training sample subsets, each training sample in each training sample subset comprises an iris image, a type label and real iris bounding box position information, and the type of the training sample in each training sample subset comprises a real person iris, a beauty pupil iris and a prosthesis iris; training the iris detection neural network by using each training sample of each training sample subset in the training sample set to obtain an iris detection model, wherein the iris detection neural network comprises a feature extraction layer, an iris positioning layer, a region of interest pooling layer, a beauty pupil detection layer and a prosthesis detection layer, the feature extraction layer, the iris positioning layer, the region-of-interest pooling layerand the beauty pupil detection layer are connected in sequence, and the output of the feature extraction layer is further connected with the region-of-interest pooling layer and the prosthesis detection layer. Through the scheme, the iris image processing efficiency can be improved.

The invention discloses a multi-task iris detection and visual angle classification method, comprising the following steps: S101, acquiring an iris image to be detected; S102, inputting the iris imageto First-Net detector to obtain a first output result; S103, inputting the first output result to Second-net detector to obtain a second output result; S104, inputting the second output result to Ultimate-net detector. After merging the overlapping iris candidate frames with non-maximal suppression algorithm, the remaining iris candidate frames, the probability corresponding to the remaining iriscandidate frames, and the probability that the remaining iris candidate frames belong to different iris perspectives are obtained. The invention has the advantages that the multi-task convolution neural network is used for detecting the iris image and the method for classifying the five angles of view of the iris. On the one hand, it ensures the accuracy of iris image detection, on the other hand, it improves the accuracy of iris classification from five angles of view.

The invention discloses an ellipse-detection-based iris detection method. The method comprises: step one, obtaining an image including an eye region; and step two, carrying out ellipse detection on the eye region; to be specific, step 2-1, carrying out ellipse detection on the eye region by using an ELSD algorithm; to be specific, changing the sensitivity of the ELSD for N times to obtain information of N groups of circles; step 2-2, according to the obtained circle information, constructing a circumference by using a point set of circumferential points in the circle information; step 2-3, for each point of the point set, constructing feature vectors of the point and selecting feature parameters, including a circle center coordinate, a radius, an arc degree, an arc length, and a circumferential point coordinate, of the point to carry out weighted processing to obtain feature vectors; step 2-4, classifying the feature vectors, using one class with the largest individual number as a target class, and storing circumferential point coordinates of all feature vectors; and step 2-5, carrying out circle fitting by using the circumferential point coordinates in the step 2-4.

The present invention discloses a live iris detection method for an electronic device. The electronic device includes an iris recognition module that performs iris recognition on the iris of the object to be recognized. The live iris detection method includes: acquiring a first iris image and a second iris image when the eye is at the front view and the side view of the iris recognition module by the iris recognition module; and according to the information difference between the first iris image and the second iris image, determining the iris images collected by the iris recognition module are live iris images. The present invention also discloses an electronic device and a computer readable storage medium. The live iris detection method, the electronic device and the computer readable storage medium in the embodiments of the present invention obtain the difference of the iris information by processing the iris images when the user faces the front and the side of the iris recognition module, and according to the difference, that whether the iris images acquired by the iris recognition module are live iris images are determined, thereby enhancing the safety of iris recognition.

A system and method of automatically prevents a cellular telephone operated by a driver from receiving or transmitting text and email messages while driving a motor vehicle. The system includes a first Bluetooth transceiver located inside a motor vehicle that is configured to create a link, such as a piconet, with a compatible second Bluetooth receiver located in the cellular telephone that has text and email messaging capabilities. The cellular telephone includes a software program loaded into its memory designed to automatically disable the device's text and mail messaging capabilities when the link is created. Upon entering and starting the motor vehicle, the link is established, which automatically blocks or deactivates the device's transmission and receiving message capabilities. In one embodiment, the software program provides a menu page that allows the driver to selectively turn ON or OFF different features when the two transceivers are linked. Access to the menu page may be controlled by passwords, or finger prints, or iris detection.

The invention discloses a combined verification system of a smart lock. The combined verification system comprises an iris detection module, a fingerprint detection module, a key input module, a pressure detection module, a master control module, a voice broadcast module, a display module, an alarm module, a wireless communication module, a door lock execution module and a vibration module, wherein the master control module is connected with the iris detection module, the fingerprint detection module, the key input module, the pressure detection module, the voice broadcast module, the display module, the alarm module, the wireless communication module, the door lock execution module and the vibration module respectively; the voice broadcast module comprises a voice collector, a data memory, a selector and a voice player. The system disclosed by the invention realizes single or combined unlocking verification through iris, fingerprint and keyboard information input; due to the pressure detection module and the vibration module arranged on the door body, the indoor user is effectively reminded of a guest outside; the system has the characteristics of fast verification and high accuracy, and greatly improves the safety of residents.

The invention discloses an iris center positioning method based on a cascade regression forest and image gray features, and relates to the technical field of iris detection. The invention is used forsolving the problems of real-time performance, accuracy, robustness and the like in the prior art, and provides an iris center positioning method based on a cascade regression forest and image gray feature. The method utilizes cascaded regression forests, grayscale weighted averages, and weighted-snakuscule energy value iterations and fully combines advantages of a method based on expressions anda multi-stage scheme based on machine learning. High accuracy and robustness are still kept under challenging low-resolution images.

The invention discloses an apparatus for monitoring on duty information of employees. The apparatus comprises a microcontroller, a power supply module for supplying power for each electric module, a reset circuit, a data storage chip, and a RS232 communication interface circuit; an input terminal of the microcontroller is connected to a first infrared detection circuit for acquiring door entering data information of employees, a second infrared detection circuit for acquiring leaving data information of employees, a high definition camera for acquiring entering or leaving real time image information of employees, an iris detection circuit for identifying employee identity information, a first timing circuit for acquiring specific time at which employees enter a company, a second timing circuit for acquiring specific time at which employees leave the company and a button setting circuit, and an output terminal of the microcontroller is connected to a liquid crystal display screen and a control indicating lamp; the power supply module comprises a power supply and a power switch. The apparatus has a function for monitoring on duty information of employees, and has the advantages of novel design, simple structure, simple operation, and practicality.

The invention provides a method for preventing cheating through iris recognition. The method comprises the steps of acquiring M iris characteristics of a tested person through an iris testing instrument, performing comparison with a database for acquiring information of the tested person; continuously tracking the eyes of the tested person by the iris testing instrument, and acquiring a leas N iris characteristics in each frame in a tracking process; in a time period between acquiring the information of the tested person and receiving the expired gas of the tested person for performing drinking testing, if the number of the continuous frames in which the iris characteristics cannot be acquired in the obtained image is larger than S, performing alarming or reminding the tested person of performing iris recognition testing again; and if the iris characteristics cannot be acquired or the number of the acquired iris characteristics is smaller than N in S continuous frames, determining no leaving of the tested person, and acquiring drinking testing information of the tested person. The method can realize in-time tracking for the iris of the tested person for preventing substitution in testing, and furthermore can judge whether substitution in testing occurs according to the iris recognition condition in the preset number of continuous frames.

The invention relates to a multifunctional auxiliary driving system based on artificial intelligence. The multifunctional auxiliary driving system comprises a driving position control terminal, a secondary driving position control terminal, a vehicle body monitoring terminal and an intelligent driving control terminal. The driving position control terminal comprises a steering wheel angle detection device, a first camera shooting device, a second camera shooting device, an iris detection device, a steering wheel adjusting device, an accelerator adjusting device, a clutch adjusting device and abrake adjusting device. The secondary driving position control terminal connection is provided with a control panel in a connected mode; the control panel comprises a gesture control system and an infrared detection device which are connected; an infrared sensor device is connected with a signal transmission device in a paired mode; the control panel is further provided with a simulation cockpitposition display system in a connected mode; the secondary driving position control terminal is further provided with a first touch element, a second touch element and a third touch element in a connected mode; and the intelligent driving control terminal comprises a standard vehicle speed control module and a standard rotation angle control module.

The invention discloses ophthalmic function inspection equipment based on a slit lamp platform. The ophthalmic function inspection equipment structurally comprises an eyepiece sleeve, a lens left wheel disc, a rotor beam shielding conical barrel, a handheld grip, a counterweight base block, a data display and an antenna column rod. A light receiving focusing matching effect is formed through a beam lamp bead ring and a rotor convex lens frame to avoid the fuzzy observation of astigmatism, so that the operation that the whole lens cone stretches, clamps and retracts a shading nipper plate and then shoots into the refracted beam line is improved; it is guaranteed that subsequent passing light and distance light adjust crystalline lens, and conical channel divergence iris examination adjusting effect is obtained through projection of a black point column core of an iris cover disc, so that the composite adjustment operation of a rotor ball block and a convex lens seat is singly performedon the cornea alignment after the iris detection and the crystalline lens adjustment; and the whole eye socket is effectively detected and adjusted step by step, the light scattering phenomenon is avoided, and the eyeball relaxing and sliding efficiency is improved.

The invention relates to the technical field of auxiliary mine personnel detection devices, and in particular to a unique device for getting into and out of a mine, which improves the accuracy of detection and can conveniently report workers with attendance problem in time, thus improving practicability. The unique device for getting into and out of a mine comprises a top plate, a bottom plate, aleft side plate, and a right side plate, a foot plate comprises an upper plate body, a lower plate body, and four sets of supports, each of the four sets of supports comprises a retractable rod, a piston, and a pressure pipe, the foot plate further comprises a rotary shaft, two sets of posts, and two sets of pulleys, the top end of the bottom plate is provided with a placement groove, and a ball bearing and a limit piece are arranged in the placement groove. The unique device for getting into and out of the mine further comprises an iris detection module, a fingerprint detection module, a master control module, a display module, a warning module, and a remote module, an iris detector is arranged on the right side wall of the left side plate, a fingerprint detector is arranged on the left side wall of the right side plate, a display screen is arranged on the front side wall of the top plate, and a warning lamp is arranged on the bottom end of the top plate. The unique device for gettinginto and out of the mine further comprises a client.

The invention provides a corpse iris recognition method and device, and the method comprises the following steps: collecting a corpse iris image, and carrying out the iris image quality evaluation ofthe collected corpse iris image; performing first corpse iris quality evaluation on the corpse iris image; carrying out iris detection and positioning on the iris images with the image quality meetingthe preset quality standard; matching the corpse iris image data positioned in the iris area with iris data in a living iris database, and obtaining at least one matching result and a corresponding confidence coefficient; and comprehensively analyzing and outputting a final identification result based on the quality evaluation result, the matching result and the corresponding confidence. The embodiment of the invention provides an effective means for efficient high-precision corpse identity confirmation.

The invention discloses a method for building a middle school student mental stress detection system based on an iris detection technology. The system comprises an iris image acquisition module, an iris image preprocessing module, an iris feature and pressure curve feature analysis module, an identity recognition and mental stress diagnosis module and a statistical analysis module. According to the method for building the middle school student mental stress detection system based on the iris detection technology, the mental stress of a student can be detected by detecting a mental stress line of an iris, so that metal health illness of the student can be directly diagnosed and found. The detection system is simple, easy to implement, high in reliability, high in accuracy and wide in application.

The invention discloses a human eye iris detection method and a device, and the method comprises the steps: receiving a face data set, and training a key point positioning neural network; carrying outcoarse positioning on the face key points by using a key point positioning neural network to obtain corresponding face key points, and selecting human eye region key points according to the obtainedface key points; calculating the angle of the iris not shielded by eyelids and the upper bound of the radius of the outer boundary of the iris of the human eye according to the key points of the humaneye area; and performing iterative optimization on the key points of the human eye area according to the angle of the iris which is not shielded by the eyelids and the upper bound of the radius of the outer boundary of the human eye iris, thereby realizing fine positioning of the key points and fine positioning of the outer boundary of the iris. According to the method, precise positioning of human eye key points and iris outer boundaries can be efficiently positioned, the accuracy and robustness are high, and the real-time processing efficiency can be achieved.

The invention discloses an intelligent identification system for an automobile applying an iris technology, the system comprising an iris detection device which is installed on a vehicle door, a wireless transmitter which is integrated with the iris detection device, and a data processing circuit, a central processor and an alarm device which are installed inside an in-car entertainment system; the data processing circuit comprises a wireless receiver which matches with the wireless transmitter, a signal amplification circuit which is connected to the wireless receiver, a filter circuit which is connected to the signal amplification circuit, and an A / D converting circuit which is connected to the filter circuit; the central processor is connected to the A / D converting circuit. The alarm device is connected to the central processor; and the central processor is connected to a control switch of a door lock. According to the intelligent identification system and an identification method thereof, an iris technology is applied in vehicle security and anti-theft fields, the locking and unlocking of a vehicle door lock are realized through an iris comparison. The problem of vehicle theft due to door lock being pried is effectively solved, so that security of vehicle usage is greatly increased.

The invention discloses a single-channel iris detection device, comprising a housing, wherein a collection window for iris image inputting is arranged on the housing; a detection device and an illumination device are respectively arranged inside the housing, the detection device comprises a camera plate, an image sensor for image acquisition is arranged on the camera plate, and an objective lens and an infrared filter are arranged at the front end of the image sensor in turn. Iris images of both eyes coming from the acquisition window pass through the infrared filter and are focused by the objective lens and imaged on the image sensor. The image sensor converts the iris image signals of both eyes into digital signals and transmits them to the camera board for processing. The single-channeliris detection device of the invention adopts a single channel to take photos of iris information of both eyes, and simultaneously captures images of two pairs of iris, which greatly simplifies the system structure and saves device cost.

The invention relates to a system (including hardware and software) for shooting an iris image with a cell phone and performing data analyzing treatment. The hardware is a cell phone additional mirror, when the cell phone additional mirror is connected with the cell phone, a human eye iris image can be shot. The resolution of the collected iris image can reach 14 million pixels or above, which conforms to the medical analysis standard. The software is an analysis system imbedded into the cell phone, and consists of background APP and a Sucheng server. Human organs corresponding to shot iris images can be directly subjected to immediate digital location and sign analysis, iris samples in the software database are compared, health judgment of a subject is formed, a corresponding recuperatingscheme is made, and an iris examining report is automatically transmitted to a client through the server. Through the adoption of the system disclosed by the invention, the technique bottleneck of shooting equipment on imaging is broken through, the difficulty that the iris cannot be shot by the cell phone is solved, the defects that a conventional iris detection device is large in size, complexto use, low in shooting pixels and not standard in analysis are overcome, and the cell phone long-range health-care diagnosis and treatment service is realized.

The invention discloses an iris detection method for a door lock device, and the door lock device comprises: an iris sensor which comprises a CCD imaging chip, a lens, and a lens rotating device for rotating the lens; a door lock processing modulewhich is used for processing iris data acquired by the iris sensor; a height acquisition module which is used for detecting the height range of the user. The iris detection method comprises the following steps: acquiring height data of a user; controlling the lens rotating device to rotate the angle of the lens relative to the imaging plane of the CCD imaging chip according to the user height data; and using the CCD imaging chip to collect iris data. The iris detection method of the door lock device has the beneficial effect that the detection range of the iris sensor can be intelligently adjusted according to the height of a user.

The invention discloses a living iris detection method based on dual wavebands, and belongs to the technical field of biological image processing. Comprising the following steps: performing living iris detection in a living body detection permission, acquiring a human eye region image I of a user in a 530-nanometer wave band and a human eye region image II of a user in a 700-nanometer wave band in a depth-of-field range of a camera, and preprocessing the human eye region images to obtain a grayed iris image; obtaining an interested iris and sclera region tissue feature map If1 and a blood vessel texture feature map If2; and calculating the difference degree between the tissue and blood vessel texture feature map of the I and the tissue and blood vessel texture feature map of the II by using a Hash algorithm, extracting living body detection features according to the difference between the tissue feature maps If1 and IIf1 and the blood vessel texture feature maps If2 and IIf2, and outputting an iris authenticity judgment result. According to the method, true and false distinguishing is carried out according to the difference of the absorption reflectivity of the blood vessels and tissues in the eyes of the living body and the biological texture simulated by the forged sample in different wavebands, and the attack of the forged iris can be well defended.