88 results about "Blink detection" patented technology

The invention discloses a view line tracking method and an assistant system for the handicapped by using the method. The method comprises the steps of image pretreatment, the orientation of a human eye area by utilizing Harr features, blinking recognition, the inspection and judgment of LED reflecting lightspot in pupils, the accurate position of pupil centre, the calculation of view line direction and so on. The system comprises an embedded-like platform, a camera, a display screen and four LED and wheelchair running control modules which are installed at the four corners of the display screen and arranged into a rectangular. The system is an embedded-type system, which carries out blinking inspection, the inspection of the reflecting lightspots against infrared light sources on corneas, the accurate position of the pupil centers and the judgment of view line directions by the camera and a processor, tracks the view line of human eyes and, meanwhile, carries out the recognition of the status of the human eyes by judging the view line directions of the human eyes when gazing on the screen, thus realizing the functions of wheelchair control, music play control, text reading and webpage rolling. The invention is convenient for use and has high accuracy, thereby being capable of bringing great convenience for the lives of the handicapped.

A blink detection algorithm and associated circuitry for an ophthalmic lens comprising an electronic system is described herein. The blink detection algorithm is implemented in the system controller which is part of an electronic system incorporated into the ophthalmic lens. The electronic system includes one or more batteries or other power sources, power management circuitry, one or more sensors, clock generation circuitry, control algorithms and circuitry, and lens driver circuitry. The blink detection algorithm implements the steps of sampling, at a predetermined rate, light incident on an eye of an individual and at least temporarily saving collected samples, determining when an eyelid is open or closed in order to divine the number, time period and pulse width of the blinks from the collected samples, calculating a number of blinks and the duration of the blinks in a given time period, and comparing the number of blinks, the durations of the blinks in the given time period, and the time between blinks in the given time period to a stored set of samples to determine patterns in blinking.

An imaging apparatus includes a focus control unit that sets an image area including eyes, which is included in an input image inputted in the imaging apparatus, as a range finding area for calculation of a subject distance and acquires an evaluation value based on contrast of the range finding area to detect a focus position and a blink detecting unit that detects presence or absence of a blink on the basis of image analysis in the range finding area. The focus control unit inputs blink detection information in the blink detection unit, identifies evaluation value data in a blink period and a non-blink period, and executes processing for detecting a focus position on the basis of only an evaluation value in a period judged as the non-blink period.

A contact lens for lens-to-lens communication includes blink detection circuitry, one or more electrodes, a logic engine, and data transmission circuitry. The blink detection circuitry is configured to generate a blink signal in response to a blinking of an eye. The logic engine is coupled to receive the blink signal from the blink detection circuitry. The data transmission circuitry is coupled between the one or more electrodes and the logic engine. The logic engine causes the data transmission circuitry to drive electrical data signals onto the one or more electrodes in response to the blink signal reaching a pre-determined threshold.

The invention discloses a living face recognition method based on blink detection. According to the living face recognition method, through reading an image in a face video which is detected by a camera, and calculating a distance between a upper eyelid characteristic point and a lower eyelid characteristic point in each image frame, when the number of read frames reaches a frame number threshold, whether a face in the face video is living according to the fluctuation condition of the distance between the upper eyelid characteristic point and the lower eyelid characteristic point in the read image; and if yes, face recognition is performed on the face in the face image. Therefore the living face recognition method has advantages of simple calculation method, low requirement for the image, and effective improvement of accuracy and efficiency in living detection.

A real-time low frame-rate video compression system and method that allows the user to perform face-to-face communication through an extremely low bandwidth network. The system and method employs novel eye tracking and blink detection techniques in order to select images for transmission. Experimental results show that the system is superior to more traditional video codecs for low bit-rate face-to-face communication.

The invention provides a human-computer interaction method. The human-computer interaction method comprises the following steps of: (1), detecting key points of eyes including upper and lower eyelids, inner circles and outer circles of irises and pupil centres, fitting to obtain position information of boundaries of the upper and lower eyelids, canthus and boundaries of the inner circles and outer circles of the irises, and obtaining accurate pupils and iris centres through information of the inner circles and outer circles of the irises; (2), calculating the direction of eyeball sight, and, in combination with the position of the sight correspondingly on a display screen of virtual reality equipment, completing eyeball sight tracking; (3), performing stare / blink detection of eyeballs including stare detection and blink detection, if stare / blink detection is passed, entering the step (4), and otherwise, entering the step (5); (4), executing corresponding operations for specific stare items in stare detection, and then, returning to the step (1) to perform detection of the key points of the eyes; and (5), according to the eyeball sight direction, updating a display content of the virtual reality equipment, and then, returning to the step (1) to perform detection of the key points of the eyes.

According to an exemplary embodiment, a blink device includes: a blink detector configured to detect a blink of a user from an image photographed by a camera; a period measurer configured to measure a time period between consecutive blinks of the user and determine whether the measured time period exceeds a reference time period; a real-time image capture unit configured to capture a real-time image of the user from the photographed image; and an image processor configured to perform the following if the measured time period exceeds the reference time period: generate from the real-time image a blink image for inducing the user to blink, delay the display of the blink image by a delay period from when the user's blink is detected, and display the blink image after the delaying.

The invention discloses a blink detection method based on an eye contour feature point aspect ratio, and the method comprises the steps: obtaining a video stream, and extracting a single-frame face image set from the video stream; Extracting a face rectangular frame in the face image from the single-frame face image set by using a deep neural network, and obtaining a face rectangular frame coordinate; Obtaining eye key point coordinates in the single-frame face image set according to the face rectangular frame coordinates; Calculating the eye aspect ratio of the single-frame face image set according to the eye key point coordinates so as to judge whether blinking occurs or not according to the eye aspect ratio. According to the method, whether blinking occurs or not is judged by calculating the double-eye aspect ratio, the influence of light intensity, character postures and the like on blinking judgment can be overcome, high robustness is achieved, and the method is simple in calculation, high in precision, high in efficiency and capable of being better applied to the fields of living body recognition, fatigue driving monitoring and the like.

An image processing apparatus is configured so that a combination of the processes that are performed is set for each of unit cycles (according to the value of a counter) in accordance with priorities individually set for the processes, and image processing is performed in a fundamental cycle that is constituted of six unit cycles. A face direction determination process, a line-of-sight direction determination process, a blink detection process, a dozing determination process, and a consciousness deterioration level determination process are selectively performed depending on the value of the counter, which varies from 1 to 6. According to the image processing apparatus, it is possible to more efficiently perform image processing that involves a plurality of processes.

The invention discloses a full-automatic webpage browsing control method based on a brain-computer interface. A P300 brain-computer potential is used for controlling the position of news that a user wants to watch in a browser, the news to be played is confirmed through blink detection, after the position of the news is confirmed, a news content interface is entered, and when relevant detailed content is read, steady state visual evoked potential (SSVEP) is used as an index of signal detecting and for conducting page-up, page-down and returning operation on the news, browsing interested news in detail, returning to a news list page and exiting the browser. The method has the advantages of being simple in operation and wide in application range, providing a chance for disabled people to browse internet information and being capable of being used under the condition that the body or a mouse can not be moved due to external or personal factors.

The invention discloses a face recognition method. The face recognition method includes: S1: acquiring a face image,; S2: positioning face photo key points; S3: tracking and detecting the face: assuming that the face key points performs uniform motion in a unit time interval, adopting a Kalman filter to track the face key points, wherein the Kalman filter performs optimal estimation on the next frame image state on the basis of a previous frame image state equation of a face key point dynamic system and obtains an observation equation for two adjacent frame images of the face key points acquired in the unit time interval; and S4: using the face blink detection to implement face detection. The invention adopts a Viola-Jones detector and the Kalman filter to perform face key point tracking detection, the detection speed is fast, the precision is high, and the stability is good; and the method is applied to the electronic medical record system, and the user login is more convenient and fast, and the safety performance is good.

This disclosure relates to proximity sensing for wink detection. An illustrative method includes receiving data from a receiver portion of a proximity sensor. The receiver portion is disposed at a side section of a head-mountable device (HMD). When a wearer wears the HMD, the receiver portion is arranged to receive light reflected from an eye area of the wearer, the proximity sensor detects a movement of the eye area, and the data represents the movement. The method includes determining that the data corresponds to a wink gesture. The method also includes selecting a computing action to perform, based on the wink gesture. The method further includes performing the computing action.

A method of blink detection in a laser eye surgical system includes providing a topography measurement structure having a geometric marker. The method includes bringing the topography measurement structure into a position proximal to an eye such that light traveling from the geometric marker is capable of reflecting off a refractive structure of the eye of the patient, and also detecting the light reflected from the structure of the eye for a predetermined time period while the topography measurement structure is at the proximal position. The method further includes converting the light reflected from the surface of the eye into image data and analyzing the image data to determine whether light reflected from the geometric marker is present is in the reflected light, wherein if the geometric marker is determined not to be present, the patient is identified as having blinked during the predetermined time.

The invention discloses a nerve plexus stimulation system, a nerve plexus stimulator and a nerve plexus stimulation method, which are designed to solve the problem of inaccurate nerve plexus positioning in the conventional peripheral nerve block operation. The nerve plexus stimulation system comprises the nerve plexus stimulator, an auxiliary electrode and a nerve plexus stimulating needle, wherein the auxiliary electrode and the nerve plexus stimulating needle are connected with the nerve plexus stimulator through connectors; and the nerve plexus stimulator comprises a working parameter regulating and setting module, a microprocessor, a simulative impulse transmission and control module, a display module and a power supply module. Based on the structure and simulation method, the system can position the nerve plexus objectively, directly and accurately, and thus, problems of the conventional subjective and unquantized blink detection method are solved.

The invention provides a human face recognition method based on blink detection. The method comprises the steps: taking a picture of a user through a camera, and detecting a human face image from the picture of the user through a human face detector; carrying out the matching of the human face image with a pre-stored registered human face image through a human face matching algorithm, and determining that the human face is registered when the similarity of the matching result is greater than a set matching threshold value; detecting whether a plurality of user images have the blink phenomenon or not through a blink detection algorithm, and determining that the user images are the images of a living body if the user images have the blink phenomenon. The method can detect whether the detected object is a picture, a sculpture or a living body well through blink detection. Compared with an ASM+Canny blind detection method which is higher in requirements for light, the method carries out the differential processing of the image through the morphology, and can be well suitable for a weak light detection condition.

The invention discloses a human face living body recognition method based on multi-classifier fusion of deep learning, which comprises the following steps of respectively training three classifiers byusing traditional edge features, eye features and the like and deep neural network features, and then carrying out the human face living body recognition by using the classifiers through a designed program process. The method aims at a living body identification problem in a real scene. Frame detection, blink detection and moire detection are designed, the three detection results are fused innovatively according to a certain logic to obtain a human face living body recognition result, and the method has the advantages of being good in anti-cheating capacity, excellent in anti-interference capacity, capable of being matched by a small number of users, only needing a common camera (without additional equipment) and the like. The method mainly comprises the steps of the border detection, theblink detection, the moire detection, the fusion judgment and the like, and makes a certain contribution to the application of practical popularization of human face living body recognition.

The invention provides a blink detection method and system which are suitable for the field of data processing. The blink detection method includes the steps that electromyographic signals and eye image information are collected, first blink information is obtained through the electromyographic signals, and second blink information is obtained through the eye image information; the first blink information is compared with the second blink information; the blink information is obtained according to the compared result. By means of the blink detection method and system, more accurate blink information can be obtained through the compared result.

A method of blink detection in a laser eye surgical system includes providing a topography measurement structure having a geometric marker. The method includes bringing the topography measurement structure into a position proximal to an eye such that light traveling from the geometric marker is capable of reflecting off a refractive structure of the eye of the patient, and also detecting the light reflected from the structure of the eye for a predetermined time period while the topography measurement structure is at the proximal position. The method further includes converting the light reflected from the surface of the eye into image data and analyzing the image data to determine whether light reflected from the geometric marker is present is in the reflected light, wherein if the geometric marker is determined not to be present, the patient is identified as having blinked during the predetermined time.

The invention discloses an MOOC online learning pattern recognition system and method. The recognition system comprises a head-wearable EEG collecting instrument, a blink detection and analyzing instrument and a pattern recognizing and classifying device. The head-wearable EEG collecting instrument is used for obtaining EEG signals of a tested object in the online learning process in real time and is provided with a wireless communication module for transmitting the EEG signals. The blink detection and analyzing instrument is used for receiving the EEG signals sent by the head-wearable EEG collecting instrument, processing the EEG signals through a standard time frequency analytical algorithm so as to obtain the blink time information and obtain the blink time sequence, conducting statistic analysis on the blink time sequence and obtaining feature parameters of online learning state patterns. The pattern recognizing and classifying device is used for conducting pattern recognizing and classifying on the online learning state of a user according to the spatial position where the feature parameters are located, and therefore real-time feedback information is provided for the user. According to the MOOC online learning pattern recognition system and method, the structure is simple, the application range is wide, the performance is superior, the pattern recognizing problem of the MOOC online learning state can be solved, and the good market prospect is achieved.

An optical imaging system, method, and medium for imaging a subject. Measure an aberration state of light from the subject is measured. Determine a condition of the subject based on the aberration state of the light, and if the subject is in a first condition or a second condition. An aberration correction device that adjusts a state of the light. In a first case if the subject is in the first condition than the light is adjusted based on the aberration state of the light used to determine that the subject is in the first condition. In a second case if the subject is in the second condition than the light is adjusted based on based on a most recent aberration state of the light that was used to determine that the subject was in the first condition prior to detecting that the subject is in the second condition.

An embodiment of the invention discloses a method and a device for detecting image information, and relates to the field of technologies for processing images. The method includes determining human eye regions in various video frames in video segments with preset durations; respectively computing light stream information of various pixel points in the human eye regions in the various video frames in the video segments; respectively counting the quantities of the downwardly moving pixel points and the upwardly moving pixel points in the human eye regions of the various video frames in the video segments according to the computed light stream information; acquiring human eye state characteristics of the various video frames in the video segments according to counting results; detecting to determine whether blinking phenomena are available in the video segments or not according to the acquired human eye state characteristics. The light stream information of the various pixel points in the human eye regions in each video frame in the corresponding video segment corresponds to a front frame of the video frame. According to the scheme, the method and the device in the embodiment of the invention have the advantages that the human eye state characteristics of the video frames are acquired by the aid of the image information among the video frames, and are utilized when whether the blinking phenomena are available in the video segments or not is detected, and accordingly the blinking detection accuracy can be improved.

The application provides a method for transmitting control information, which is executed in a communication system which uses at least two partitioning modes to partition time-frequency resources fortransmitting the control information. A plurality of time-frequency resource blocks partitioned in at least two partitioning modes are of a nested structure. The method comprises the steps of: from aplurality of time-frequency resource blocks, determining a first time-frequency resource block for sending first control information; partitioning the first control information into m information fragments; according to the m information fragments, generating m pieces of to-be-sent information, wherein each to-be-sent information comprises the corresponding information fragment, to-be-sent information i comprises an information fragment i and a check sequence i, the check sequence i is generated according to the information fragment i, and i is an element of a set [1,m]; carrying out polar code encoding on the m to-be-sent information to generate a symbol sequence; and by the first time-frequency resource block, sending the symbol sequence. Resource cost of transmitting the control information can be reduced, and blink detection calculation complexity and processing delay are reduced.

The invention discloses a blink detection method comprising the steps that an eye opening detector and an eye closing detector are trained; a first face area in the first video frame is acquired, andthe first positions of the eyes are located by using the eye opening detector in the first face area; if locating is successful, the first positions are saved; a second face area in the second video frame is acquired, and the second positions of the eyes are located by using the eye opening detector in the second face area; if locating is successful, the video frames are switched in turn to perform locating until locating fails, and the second positions acquired in the last time of successful locating act as the first positions; the eye closing positions of the eyes are located by using the eye closing detector at the first positions; and if locating is successful, successful blinking is outputted. According to the method, the problems of error detection caused by shielding can be effectively avoided and the acquired classifier model is small so that the detection efficiency can be further enhanced. The invention also discloses a blink detection device and equipment and a computer readable storage medium which have the beneficial effects.

The invention relates to an intelligent television user fatigue detection system and method based on face multi-feature fusion. The system is based on intelligent television application and mainly comprises a fatigue detection setting module, a video data acquisition module, a face feature point extraction module, an eye aspect ratio calculation module, a blinking detection module, a head posturedetection module and an intelligent fatigue detection module. The number of blinking times in unit time is determined according to the change of the eye aspect ratio. Through the occurrence of a sleepiness event determined by inclination of the head posture, and the duration of unit time, the fatigue state of the user is judged in a combined mode, an implementation method is provided based on thesystem, comprehensive multi-feature fusion analysis and combined decision making are conducted on fatigue detection multi-dimensional features in a smart television use scene, the accuracy of fatiguerecognition is improved, and the probability of false triggering is reduced.

The invention relates to a face recognition method with a living body detection function, and the method comprises the following steps: carrying out the face detection of an obtained image through image obtaining equipment, carrying out the blink detection in a face region when a face is detected, and judging whether the detected face is a living body or not; and when the detected human face is aliving body, recognizing the human face by using a human face recognition model. The method is simple in calculation and easy to implement, and the reliability and safety of face recognition are improved by adding a layer of protection mechanism.