142 results about "Eyes pupils" patented technology

A system, apparatus, method, and machine readable medium are described for performing eye tracking during authentication. For example, one embodiment of a method comprises: receiving a request to authenticate a user; presenting one or more screen layouts to the user; capturing a sequence of images which include the user's eyes as the one or more screen layouts are displayed; and (a) performing eye movement detection across the sequence of images to identify a correlation between motion of the user's eyes as the one or more screen layouts are presented and an expected motion of the user's eyes as the one or more screen layouts are presented and/or (b) measuring the eye's pupil size to identify a correlation between the effective light intensity of the screen and its effect on the user's eye pupil size; capturing audio of the user's voice; and performing voice recognition techniques to determine a correlation between the captured audio of the user's voice and one or more voice prints.

Example embodiments of a large dynamic range sequential wavefront sensor for vision correction or assessment procedures are disclosed. An example embodiment optically relays a wavefront from an eye pupil or corneal plane to a wavefront sampling plane in such a manner that somewhere in the relaying process, the wavefront beam from the eye within a large eye diopter range is made to reside within a desired physical dimension over a certain axial distance range in a wavefront image space and/or a Fourier transform space. As a result, a wavefront beam shifting device can be disposed there to fully intercept and hence shift the whole beam to transversely shift the relayed wavefront.

A system, apparatus, method, and machine readable medium are described for performing eye tracking during authentication. For example, one embodiment of a method comprises: receiving a request to authenticate a user; presenting one or more screen layouts to the user; capturing a sequence of images which include the user's eyes as the one or more screen layouts are displayed; and (a) performing eye movement detection across the sequence of images to identify a correlation between motion of the user's eyes as the one or more screen layouts are presented and an expected motion of the user's eyes as the one or more screen layouts are presented and/or (b) measuring the eye's pupil size to identify a correlation between the effective light intensity of the screen and its effect on the user's eye pupil size.

An imaging apparatus for simultaneously determining optical parameters of the eye comprising: a light source for illuminating at least a portion of the eye pupil; an illumination optical system for directing light rays emitted from the light source into the eye; a light receiving optical system for guiding the light rays reflected from the eye to a detector unit, wherein the detector unit detects an image intensity distribution from the light rays reflected from the eye; and an arithmetic unit for determining optical characteristics of the eye by parameter estimation is provided.

An apparatus for detecting abnormalities in spatial perception that consists of a first transparent screen in a close-vision field and a second screen seen through the first one and located in a far-vision field of a person being tested. The apparatus is provided with devices for forming images selectively on the first or second screen and with a device for tracking trajectories of the eye pupils while following the images. The method is based on detecting specific irregularities in trajectories of the eye pupils, such as nystagmuses, cut-offs, sudden drops of the gaze, etc., when a person follows the smooth trajectory of a moving image on a selected screen, or when the size and position of the eye pupil change with certain irregularity in response to instantaneous switching of images between the screens without changing the position of the person's head.

The invention discloses a fixation point measurement device and method based on video images and an artificial neural network, and aims to provide a head freestyle fixation point measurement device and method. The measurement device comprises a host, a main display and an assistant display, and is characterized by further comprising a stereoscopic vision measuring system, wherein the stereoscopic vision measuring system comprises a light source, a direct current stabilized voltage power supply and two or more than two pick-up cameras. The measurement method comprises the step of adopting a manual neural network to establish a fixation point measurement mathematical model, wherein a manual neural network input layer comprises 12 input nodes, the input nodes respectively represent three dimensional coordinate components of a left eye pupil, three dimensional coordinate components of a right eye pupil, three dimensional coordinate components of a left eye Puer Qin hot spot and three dimensional coordinate components of a right eye Puer Qin hot spot, a manual neural network output layer comprises 2 output nodes serving as two dimension coordinate components of a fixation point.

A new beam deflection approach is provided for displaying images in autostereoscopic format. Conceptually, polarized light from a display is directed into specific viewing regions using a polarization-sensitive beam deflection sub-system that comprises, in exemplary embodiments, an active liquid crystal quarter-wave plate modulator and a passive cycloidal grating element, such as a diffractive waveplate. Specific embodiments may comprise an illumination system that both floods an LCD panel and creates a defined eye pupil region, from within which the display is viewable. Deflecting the pupil region between left and right eye positions in synchronization with displayed frame sequential stereo image data creates desirable autostereoscopic 3D viewing. Other embodiments employ a similar beam deflection sub-system in conjunction with a means of viewing subsets of pixels from different viewing positions, such as a parallax barrier or lenslet array, allowing freedom of head movement while maintaining stereo viewing.

The invention discloses a multi-strategy fraud-preventing face recognition method which comprises the following steps of: 1, in a face detection process, detecting whether bright pupils generated by anear-infrared device exist at eye pupil positions and detecting whether the variance meets a threshold value in a face complexion grayscale section at a face region position, and determining whethera fraudulent behavior attack exists; 2, based on the dynamic property of the face recognition process, in the process of face recognition verification, detecting a micro-expression based on Candide-3model 3D face reconstruction, determining the similarity between the face features in three adjacent frames and the 3D model, and setting a reasonable threshold to avoid an excessively approximate face.

The invention discloses a fundus camera for photographing retinas of human eyes and particularly relates to a portable variable camber liquid lens fundus camera. The portable variable camber liquid lens fundus camera comprises an eye positioning system, an imaging system, an illuminating system, an image acquisition unit, a control circuit and an intelligent remote control terminal, wherein the imaging system comprises an eyepiece lens group, an imaging objective lens group, a zoom liquid lens and the image acquisition unit, an intermediary image of a fundus image is formed by an eyepiece lens, the intermediary image is subjected to zooming through the liquid lens and finally imaged on a sensor target surface of the image acquisition unit by an imaging objective lens to be real-timely displayed through a screen, the illuminating system comprises a ring illuminator, a uniform light lens of a front group and the eyepiece lens of a back group, the illuminating system and the imaging system share the eyepiece lens, the ring illuminator is directly imaged at a position of an eye pupil by the illuminating system to pass through the eyepiece lens of an imaging light path and then enter a polarizing beam splitter (PBS), and the illuminating system and the imaging system are coaxial. Besides, with a wireless fidelity (Wi-Fi) connecting function, the fundus camera can be remotely operated through the intelligent remote control terminal.

The invention discloses a driver state monitoring method based on vision information fusion and a driver state monitoring system based on vision information fusion. The method comprises steps that: a driver face image and a road image in front of an automobile are acquired, and the images are pre-processed; face positioning on the pre-processed driver face image is carried out to acquire a face area; an eye pupil mass center and a pupil area in the face area are positioned to acquire eye state parameters, and eyes are tracked; track line detection and identification on the pre-processed road image in front of the automobile are carried out; according to a detected track line, an automobile driving direction and a navigation line included angle are calculated to determine whether the automobile deviates from the track; the driving state of the driver is discriminated according to the eye characteristics of the driver and the automobile deviation degree. The driver state monitoring method integrates two computer vision modes, improves detection efficiency, realizes real-time monitoring and alarm when the driver is under abnormal driving states, e.g., fatigue driving, after-drinking driving and driving with disperse attention, and thereby automobile safety driving is guaranteed.

A gaze tracker and a computer-implemented method for gaze tracking, comprising the steps of: recording video images of a being's eye such that an eye pupil and a glint on the eye ball caused by a light source ( ) are recorded; processing the video images to compute an offset between the position of the predetermined spatial feature and a predetermined position with respect to the glint; by means of the light source such as a display, emitting light from a light pattern at a location selected among a multitude of preconfigured locations of light patterns towards the being's eye; wherein the location is controlled by a feedback signal; controlling the location of the light pattern from one location to another location among the predefined locations of light patterns, in response to the offset, such that the predetermined position with respect to the glint caused by the light source tracks the predetermined spatial feature of the being's eye; wherein the above steps are repeated to establish a control loop with the location of the light pattern being controlled via the feedback signal.

The invention belongs to the technical field of image processing, and particularly relates to a region of interest detection method and device, a computer readable storage medium and terminal equipment. The method comprises the steps of obtaining a to-be-detected target face image; calculating the head posture of the target face image; extracting a left eye image and a right eye image in the target face image; determining a sight attention direction according to the left eye image, the right eye image and the head posture; carrying out eye key point detection in the left eye image and the right eye image to obtain coordinates of a left eye pupil center point and coordinates of a right eye pupil center point; and determining an eye attention area according to the sight attention direction,the coordinate of the left eye pupil center point and the coordinate of the right eye pupil center point. In the embodiment of the invention, an expensive precision instrument is not needed, and the eye region of interest is determined by analyzing and processing the face image, so that the cost is greatly reduced, and the method can be widely applied.

The invention belongs to the technical field of optics. Through refraction and transmission of a spherical lens group coaxially arranged, a binocular eye pupil at an exit pupil position divides outgoing light into a left beam and a right beam in a wavefront-splitting manner, and binocular observation for a shared single display image is achieved. The single-display-shared large-exit-pupil binocular eyepiece optical system to which the invention relates is the lens groups arranged between the display and a diaphragm. The lens group is characterized in that the lens group comprises n spherical lenses which are successively and coaxially arranged, and n is a natural number not less than 3; the display is placed on a front focal plane of the lens group, and the center of the display coincides with an optical axis of the lens group; and the lens group comprises 2n optical surfaces which are (2n) and (2n+1) taking a diaphragm surface (1) as a starting point, and a display surface is (2n+2). The binocular eyepiece optical system has the advantages of simple structure, comfortable observation, reliable performance, the large exit pupil diameter and the large exit pupil distance; free observation can be performed in a certain special scope, and an object image is easy to continuously observe; the binocular eyepiece optical system can be fixed to a vehicle body and does not increase a burden of a head, and people cannot feel fatigue easily; and the binocular eyepiece optical system is suitable for a vehicle-mounted binocular observation instrument to continuously observe surrounding scenery conditions or related information.

The invention discloses a human eye recognition system and method. The system comprises an identification module of a human eye area to be detected, a human eye detection module and a human eye weight recognition module, wherein the identification module of the human eye area to be detected is used for marking off the area to be detected of a left eye and a right eye on a human face area; the human eye detection module is used for detecting the target area of the left eye and the right eye from the area to be detected of a left eye and a right eye; the human eye weight recognition module is used for the weight calculation to the target area of the left eye and the right eye to obtain the human eye area; and the weight comprises the approximate degree of the size of the left eye and the right eye, the reasonable degree of the ratio of side length of the left eye area and the right eye area to the space between a left eye pupil and a right eye pupil, and an included angle between the ligature of the space between a left eye pupil and a right eye pupil and the horizontal direction. The human eye recognition system of the invention precisely positions the human eyes by three weights after detecting the target area of the left eye and the right eye, effectively solves the problem of positioning the target area of the human eyes and improves the accuracy of human eye recognition.

A method, a system, and a computer for identifying an object in augmented reality, the identification method includes: a computer receiving a user's left eye pupil position and right eye pupil position input by an input device, computing spatial coordinates of a visual focus of eyes according to the left eye pupil position and the right eye pupil position; the computer receiving spatial coordinates of each virtual object input by the input device, and comparing the spatial coordinates of each virtual object with the spatial coordinates of the visual focus of eyes to determine a virtual object to be operated by the user.

A system for generating a beam for retinal reflection detection includes a beam processor positioned to receive an illumination beam having a first spot size from a light source. The beam processor can alter the illumination beam to form a beam having a second spot size. Focusing optics focus this altered beam onto an eye, causing a spot to be formed on the retina. A detector receives reflected radiation from the retina passed through the pupil, and generates data indicative of a spatial extent of the eye pupil and an intensity map of the reflected radiation. A software package can determine from the data a pupil size and an intensity level in the intensity map. A controller in communication with the software signals the beam processor to vary the second spot size to optimize an accuracy of the determined pupil size and the intensity level.

The invention discloses a virtual reality interaction method on one hand. The method comprises the steps of shooting a reference image comprising user eye pupils; locating the position of the eye pupils in the reference image; based on a mapping relationship between the reference image and a coordinate system of a target screen, determining a watching position of the user eye pupils on the targetscreen; and if the watching position is located in an operable region, judging whether a watching state of a user meets a preset condition or not, and if the preset condition is met, executing corresponding interaction operation. The invention furthermore discloses a virtual reality interaction apparatus on the other hand. By tracking the watching position of the user on the target screen, the interaction operation is realized, so that the problems of complex operation and low interaction efficiency caused by frequently rotating the head of the user for performing virtual interaction are avoided; and a sight line-based interaction mode is simple and efficient, so that the user burden can be reduced and the user experience can be improved.

The embodiment of the invention discloses a sight line detection and video processing method and device, equipment and a storage medium. The sight line detection method comprises the steps that according to key feature points in a human face image, a corresponding human face posture and eye pupil rotation displacement are determined, and the eye pupil rotation displacement is the displacement of the pupil center relative to the eyeball center in the human face image; and according to a preset projection function and the human face posture, the eye pupil rotation displacement is projected to athree-dimensional space where an actual human face is located to obtain a sight line direction of the actual human face. According to the technical scheme provided by the embodiment of the invention,the processing amount of the eye data is reduced, the detection efficiency of the sight line direction is improved, the sight line direction of the actual face is analyzed directly through eye pupil rotation in the face image, and the detection accuracy of the sight line direction is improved.

The embodiment of the invention discloses a 3D (Three-dimensional) head raising display system, a design method thereof, and an automobile. The 3D head raising display system comprises a display unit,a 3D function unit, an optical imaging unit and a semi-transparent semi-reflection unit, wherein the display unit is used for displaying image information and emitting an image ray; the 3D function unit is positioned on one side of the light emitting side of the display unit and is used for independently focusing the image ray on a virtual left eye pupil and a virtual right eye pupil, or independently focusing the reverse extension cord of the image ray on the virtual left eye pupil and the virtual right eye pupil; and the optical imaging unit and the semi-transparent semi-reflection unit areused for independently reflecting the image ray to a left eye pupil window range and a right eye pupil window range. By use of the above technical scheme, 3D display can be realized in the head raising display system, and user experience is improved.