23 results about "Iris detection" patented technology

The invention discloses a digital currency transaction system based on an iris and a block chain, and the system comprises an iris registration module which is used for collecting an iris image, extracting an iris feature vector based on a deep hash network, and generating a unique identity label; the iris identity authentication module is used for extracting a current iris feature and calculating an identity hash value when a digital currency transaction request is obtained; the anti-counterfeiting iris detection module is used for detecting a texture abnormal condition of the current iris feature based on the anti-counterfeiting sample detection module, and confirming the validity of the iris when the detection is passed; and the transaction validity verification module is used for verifying the validity of the digital currency transaction based on zero-knowledge proof verification. Based on the iris features and the block chain technology, the defects of traditional digital currency in the aspects of identity authentication, account security and privacy protection are overcome.

The invention discloses an ordering method and platform based on individual health, and the method comprises the steps: obtaining an iris image of a user, and recognizing the body health risk information of the user through iris detection, analysis and processing; generating a catering recommendation rule according to the obtained body health risk information of the user; the ordering platform screens a food list according to the ordering condition of the user and the catering recommendation rule, and then presents catering recommendation information; or the ordering platform screens the food list according to the ordering condition of the user, generates risk prompt information according to the catering recommendation rule, and presents the catering recommendation information and the risk prompt information; the user performs ordering selection; according to the scheme, by combining the iris detection technology and the Internet ordering platform, the health risk of the user can be effectively recognized, personalized diet recommendation and health risk prompt are provided, the user is helped to enjoy online ordering and online take-out convenience, diet health can be guaranteed, and chronic diseases can be prevented and controlled.

The present invention discloses an early screening system for autism based on human-computer interaction, comprising: a data acquisition module, which collects interactive action videos and audios of subjects through human-computer interaction; a data perception module, which performs limb backbone detection and body language recognition on the interactive action video data; performs face detection, facial key point detection and expression recognition on the interactive action video data; performs eye key point detection on the interactive action video data, and estimates the line of sight direction in combination with the facial key points; performs iris detection on the interactive action video data, and performs face distance measurement based on the iris size; a data analysis module, which counts the number of correct responses of the subjects based on the interactive scene guidance and the data perception results, and evaluates various abilities of the autism index; predicts the results of auxiliary diagnosis of autism based on the trained neural network model; and a data output module, which outputs the early screening results of autism.

The application discloses an image processing-based dry eye iris detection method, and relates to the technical field of dry eye detection, and comprises the following steps: 1, in the process of collecting the human eye iris projection image, four light supplementing white lamps are turned on, and the white lamps are projected onto the iris surface; 2, in the collecting process, the four points projected onto the iris are kept in the delimited green circle, and the relative position relationship of the four points is detected and calculated in real time; 3, before the comparison threshold value, whether the four white lamp projection images of the image reach the set clear range is judged first, when the clear range is reached, whether the relative position relationship of the four points is less than the threshold value of the preset value calibration is judged, and when the threshold value is less than the preset threshold value, the iris image is collected; 4, then, the image processing technology is applied to extract the iris position of the collected image and the position of the four LED projection white lamps; 5, finally, the size of the iris diameter is calibrated through the position relationship of the white lamps. The detection method has the advantages of fast detection speed and accurate detection result.

The application discloses an automatic iris pigment spot texture segmentation method, and relates to an eye pigment segmentation method, and specifically comprises the following steps: establishing an iris detection data set and preparing an iris pigment spot semantic segmentation data set, including normalizing and preprocessing the data set, histogram equalization, data set amplification, dividing the data set into a training set and a test set, processing the test set, building a DIPSnet semantic segmentation network, training the network to obtain an overall semantic segmentation model, obtaining weight parameters of the network model through a gradient back propagation method, inputting images in the test set into the DIPSnet semantic segmentation network model, outputting the images through a softmax layer to generate a classification probability graph, and obtaining a segmentation result graph of the images according to the category probability in the classification probability graph. The application is applied to an iris recognition system and a human health monitoring system based on the iris.

The application relates to an iris detection method and system based on knowledge review distillation, which comprises the following steps: collecting and pre-processing iris data to obtain a standard iris detection data set; training an iris detection model of a teacher network by using the iris detection data set to serve as a teacher model for knowledge review distillation; training an iris detection model of a student network by using the iris detection data set to serve as a student model for knowledge review distillation; performing pooling and loss calculation on output feature maps by a student network and a teacher network at multiple different stages through a fusion module and a hierarchical context loss module based on attention, and deep layer information also continuously outputs knowledge review to shallow layer information in the distillation process to obtain an optimal distilled student model as a final iris detection model. The application can make the precision of iris detection on a lightweight network close to the precision performance of a deep network and keep the lightweight characteristics of the lightweight network.

The invention discloses a healthy catering service system and method based on iris detection, and the system comprises an information interaction module which is used for displaying an interaction process to a user and receiving the input of the user; the iris detection and analysis module is used for acquiring an iris image of the user, analyzing the iris image and acquiring health condition information of the user; the nutrition catering module is used for recommending a catering scheme suitable for the health condition of the user according to the acquired health condition information; the intelligent ordering matching module is used for acquiring catering data of the third-party ordering platform, querying in the catering data according to the catering scheme, and matching food or shops meeting conditions; the scheme has the characteristics that the efficiency and convenience of obtaining healthy diet suggestions and services by the user are remarkably improved, the healthy diet habits of the user are promoted, and the life quality of the user is improved.

The present invention discloses a method for training an iris detection neural network, which includes the following steps: extracting pre-stored training sample images and marked coordinates from a sample library; inputting the extracted training sample images and marked coordinates into a neural network model for training; calculating the network output based on the current network connection weights; calculating the inference loss Loss = 1 - IOU + r 2 / c 2 +(1 - a 2 / b 2 ) Calculate the inference loss Loss; a is the length of the short side of the inference box; b is the length of the long side of the inference box; c is the length of the diagonal of the inference box; r is the distance from the center point of the inference box to the center point of the marked box; determine whether the output loss Loss meets the preset conditions. If not, adjust the network connection weights according to the feedback algorithm, and re-infer and calculate the inference loss; if so, stop the training. This method can achieve a lower false recognition rate, a more accurate positioning effect, and a faster convergence speed when detecting the iris.

A method for detecting an iris in a user eye image captured by a camera of an eye tracking system, the method comprising: processing the image to estimate a pupil position in a 3D coordinate system; estimating an approximate optical axis in the 3D coordinate system; estimating an iris center in the 3D coordinate system based on the pupil position in the 3D coordinate system; and estimating an iris contour in the 3D coordinate system as a circle with an estimated iris diameter centered at the iris center lying in a plane having a normal parallel to the approximate optical axis; and estimating an image iris contour by transforming the iris contour in the 3D coordinate system to an image coordinate system.

The utility model relates to the technical field of mine personnel access detection, in particular to a mine personnel access detection device which comprises a shading assembly, a lifting block, a lifting pile, a fixing groove, a threaded groove, an iris detection body, two fixing blocks, a fixing screw rod, a knob, a lifting groove, a lifting screw rod and a fine adjustment assembly. The shading assembly comprises a shading top plate, a fixing rod, a plurality of shading strips, a limiting lantern ring, a fixing hole and a fixing nut, the multiple shading strips are annularly arranged on the outer edge of the shading top plate in the shading assembly in a surrounding mode, external light can be preliminarily blocked, and meanwhile the shading assembly further comprises a low-brightness LED lamp arranged at the top in the shading top plate in a diffusion mode. In addition, the low-brightness LED lamp can provide a relatively stable and soft light environment, and is matched with the shading strip, so that the shading effect is further enhanced, the interference of external strong light on the iris recognition area is reduced, and the iris recognition accuracy is improved.

An iris detection method includes acquiring a first image; generating a second image including an eye section of the person from the first image; generating a third image where pixels having a gradation value smaller than a threshold value are represented by a first luminance value and pixels having a gradation value equal to or greater than the threshold value are represented by a second luminance value after binarizing the second image; generating a fourth image by replacing the pixel of the second luminance value come into existence in a first luminance area having the first luminance value and satisfying a predetermined condition with the pixel of the first luminance value in the third image; calculating iris information including information about at least one of a position and a size of the iris of the person by use of the fourth image; and outputting the iris information.

The invention discloses a personnel channel off-line identification method based on sound waves and UWB positioning, and the method comprises the following steps: S1, inputting personnel positioning data and biological information in a database of a biological detection machine, and setting the parameters of a card reader; s2, the person with the identification card enters the channel, and the iris detection machine extracts the biological characteristics of the person entering the channel; s3, after the person holding the identification card enters the channel and is located in the uniqueness detection range, the card reader sends a distance measurement instruction to the identification card, the identification card performs UWB and sound wave reply at the same time, and the card reader determines the position information of the identification card according to the time difference of UWB and sound wave reply and obtains identity information at the same time; s4, the controller of the gate machine judges whether the identity information obtained in the step S3 is consistent with the biological characteristics obtained in the step S2 or not, if yes, the gate machine is opened, and if not, an alarm is given. A personnel channel off-line identification system based on pure UWB positioning comprises a plurality of channels, biological detection machines and gates are correspondingly arranged in the channels, and the biological detection machines and the gates are connected with a local server through CAN buses; the identification card is used for being worn by a person; and the personnel wearing the identification card enter the channel, and identity information judgment is performed according to the personnel channel off-line identification method. According to the personnel channel off-line identification method and system based on sound waves and UWB positioning, the identification card can be rapidly detected by improving the distance measurement mode, and the identification precision is improved.

This application provides a fast binaural iris detection method, apparatus, and electronic device. The method, applied to a server, includes: acquiring an image to be detected; inputting the image to be detected into a trained fast detection model, and segmenting the image into a first image and a second image according to a preset method, wherein the first image contains a first iris and the second image contains a second iris; scanning the first image to detect a first iris bounding box containing the first iris; acquiring the coordinates and diameter of a first center point of the first iris bounding box, and determining the region where the second iris is located based on the coordinates and diameter of the first center point; and scanning the region where the second iris is located to detect a second iris bounding box containing the second iris. This application improves the efficiency of binaural iris detection.

AI-BASED IRIS DETECTION DEVICE FOR SECURITY

The invention discloses a school bus anti-omission system based on face recognition, which takes a control unit as a core and calls information contents stored in a storage module by logging in a communication terminal. Through a monitoring unit, a communication module, a spherical camera, an infrared camera, a positioning module, an identification unit, a display screen and a microprocessor, anti-omission safety detection is carried out. The system has the beneficial effects that a school bus driver controls the control unit, verifies the face and iris information of students getting on and off the bus by means of the face recognition camera and the iris detector, and obtains the getting on and off conditions of the students through feedback information, so that missing of the students is avoided, and the safety of the students is improved. A school bus driver can efficiently supervise, manage and use; the positioning module analyzes and records getting-on and getting-off places of students and family positions of the students, assists a school bus driver in timely parking, accurately picks up the students, avoids wrong routes or forgetting to park, and prevents the students from staying in the school bus.

The invention discloses a disease communication system and method based on iris detection, and the system comprises an iris image collection module which is used for capturing an iris image of a user and uploading the iris image to a server; the iris image analysis module is used for analyzing the user iris image received by the server and outputting an analysis result to the communication module matching recommendation module; the communication plate matching recommendation module is used for matching a communication plate and a communication partition suitable for the user according to the received analysis result, and sending the communication plate and the communication partition to the user interaction terminal; the user interaction terminal is used for displaying a recommendation result of the matching recommendation module of the communication module and allowing a user to select and operate; the scheme is simultaneously suitable for patients and non-patients, and solves the problems of disordered information, poor information reliability, low information utilization degree, difficulty in effective utilization and the like of an existing disease communication platform.

The invention discloses a first-aid data processing system and method based on iris detection. The first-aid data processing system comprises an iris detector, an iris detection analysis and preparation scheme platform and an institution IT platform, the iris detector is used for collecting an iris image and transmitting the image to the iris detection analysis and preparation scheme platform for analysis and processing, and the iris detection analysis and preparation scheme platform is used for processing and analyzing the iris image and generating a diagnosis and treatment preparation scheme according to diagnosis and treatment scheme basic data; the institution IT platform is used for receiving a diagnosis and treatment preparation scheme for medical staff to check; according to the scheme, by collecting the iris image and carrying out data analysis and processing on the iris image, a preparation scheme can be effectively appointed for emergency treatment and treatment, and the pertinence and timeliness of emergency treatment and treatment are improved.

The iris detection method of the present invention obtains a first image containing a human face; generates a second image containing an area of ​​the human eye from the first image; binarizes the second image to generate a third image, in which pixels having grayscale values ​​less than a threshold are represented by a first brightness value and pixels having grayscale values ​​greater than the threshold are represented by a second brightness value; replaces pixels of the second brightness value in the third image that appear within a first brightness area having the first brightness value and meet a specified condition with pixels of the first brightness value, thereby generating a fourth image; calculates iris information containing information related to at least one of the position and size of the human iris using the fourth image; and outputs the iris information.

The invention discloses a gamification platform and method based on iris detection, and the platform comprises a user interaction module which is used for interacting with a user and providing an iris image for the user; the iris image analysis module is used for analyzing the iris image provided by the user and generating a health risk standard answer; the competition issuing module is used for receiving the iris image and the health risk standard answer provided by the user and issuing competition information; the user guessing participation module is used for checking current competition information by a user, selecting a participated competition and submitting an iris image analysis result as a guessing answer; the result evaluation module is used for evaluating guessing answers submitted by the user and calculating guessing accuracy; the result feedback module is used for feeding back the guessing result to the user; according to the scheme, the interest and participation degree of the user in the iris diagnosis technology are improved; and the user is stimulated to actively learn and explore relevant knowledge of iris diagnosis.

The application discloses a pupil contraction wheel detection method based on a double-flow structure and relates to an eye iris detection method.The technical scheme of the application comprises iris image normalization, pupil contraction wheel boundary line detection, pupil contraction wheel fuzzy curve detection, determination of a detection area and area gradient detection (a preprocessing module, a texture flow module, a structure flow module, a fusion module and a detection module). In the iris normalized image, a double-flow network structure is used to extract structure features and texture features respectively. An edge gradient operator is used to detect in the initial positioning area to extract the pupil contraction wheel boundary. The application further reduces the pupil contraction wheel boundary fluctuation on the basis of ensuring the detection rate and the detection speed. Meanwhile, the application overcomes the unfavorable factors such as eyelashes, light spots and eyelids in the pupil contraction wheel detection process. The method is applied to an iris recognition system and a human body health monitoring system based on the iris.