100 results about "Closed eyes" patented technology

A driver's appearance recognition system comprises: a camera to capture a driver's face image; a near infrared ray LED to radiate near infrared ray to the driver's face; an LED current control circuit to control the amount of current supplied to the near infrared ray LED; and an image processing circuit to execute an individual authentication process and a closed-eye detection process. When the individual authentication process is executed, it is necessary to increase the illumination intensity during image capture by the camera. For this purpose, a setup current value for the LED current control circuit is set to a high current value. When the closed-eye detection process is executed, the illumination intensity needs to be ensured as much as required for the closed-eye detection process. For this purpose, a setup current value is set to a current value lower than that used for execution of the individual authentication process.

A container has an impermeable outer membrane sized to fit generally within the peri-orbital region and sufficiently flexible to mold to the structure of the closed eye. Heat which is generated by an exothermic reaction inside the container, which provides steady-state heat to the eyelids. A soft, non-abrasive, lint-free material is presoaked in a pH controlled (preferably antibacterial and hypoallergenic) detergent, with or without an ophthalmic antibiotic solution. The compress may also have a handle which makes holding and maneuvering the compress more feasible, while protecting the user's fingers from the heat, and preventing the contamination of the compress by the fingers. The compress may be packed in a watertight, sterile wrapper which will prevent drying of the detergent solution. Other embodiments are also described and claimed.

A container has an impermeable outer membrane sized to fit generally within the peri-orbital region and sufficiently flexible to mold to the structure of the closed eye. Heat which is generated by an exothermic reaction inside the container, which provides steady-state heat to the eyelids. A soft, non-abrasive, lint-free material is presoaked in a pH controlled (preferably antibacterial and hypoallergenic) detergent, with or without an ophthalmic antibiotic solution. The compress may also have a handle which makes holding and maneuvering the compress more feasible, while protecting the user's fingers from the heat, and preventing the contamination of the compress by the fingers. The compress may be packed in a watertight, sterile wrapper which will prevent drying of the detergent solution. Other embodiments are also described and claimed.

A driver's appearance recognition system comprises: a camera to capture a driver's face image; a near infrared ray LED to radiate near infrared ray to the driver's face; an LED current control circuit to control the amount of current supplied to the near infrared ray LED; and an image processing circuit to execute an individual authentication process and a closed-eye detection process. When the individual authentication process is executed, it is necessary to increase the illumination intensity during image capture by the camera. For this purpose, a setup current value for the LED current control circuit is set to a high current value. When the closed-eye detection process is executed, the illumination intensity needs to be ensured as much as required for the closed-eye detection process. For this purpose, a setup current value is set to a current value lower than that used for execution of the individual authentication process.

A system and method of eliminating closed or partially closed eyes of subject in photography, caused by subjects blinking at the moment of image capture. A digital camera is configured to capture two images in quick succession. The image processing unit of the camera identifies regions of difference between the two images that indicate that eyes are partially or fully closed in one of the two images, and creates a single composite image from the two original images, in which all eyes are open for all subjects in the image.

An applicator system for applying eye shadow is provided that includes flexible body, which may be a bundle of bristles, having a proximal end secured to a handle, and a distal end having a concave shape that is substantially complementary to a portion of a closed eye lid. The concave shape is asymmetrical so that one end of the bristle bundle extends farther out than the other end to facilitate the application of make-up under the brow region and in the corners of the eye area. Eye make-up is preferably applied to the concave brush by a convex-shaped pad of eye shadow in the shape of a cylindrical section having a convex profile that is complementary in shape to the concave profile of the distal end of the bristle bundle.

The invention discloses a fatigue driving detection method, an automobile data recorder and a storage device. The fatigue driving detection method comprises the following steps of: starting a camera to shoot face images; reading a frame of face image and preprocessing the face image; carrying out face detection on the preprocessed image by adoption of an Ada boost algorithm-based Haar classifier,and drawing a face box; predicting coordinate information of 16 key points around the eyes and mouth according to the face box; calculating eye areas according to the detected coordinate information of the key points, extracting HOG features of left and right eye areas, sending the HOG features into an SVM classifier and judging whether the eyes are in a closed state; and carrying out statistic onframe numbers of face images with closed eyes in a predetermined frames of face images, and if the frame number of the face images with closed eyes exceeds a predetermined threshold value, judging fatigue driving and outputting a fatigue alarm signal. The method has the advantages of suppressing interferences in the process of detecting the blink conditions of drivers and correctly judging the fatigue state of the drivers.

The image processing method and apparatus perform preset image processing on input image data and outputting processed image data as output image data. In the method and apparatus, the present image processing includes eye correction processing for correcting a closed eye image in a human image having an eye in a closed state into an eye image in an open state. The method and apparatus are capable of performing eye opening processing on a human image having an eye being closed, correcting a failure created at the time of shooting and then outputting the image having the eye being open.

The invention discloses an intelligent shooting method and a device based on intelligent composition and micro expression analysis. According to the method, the best composition angle is obtained through analysis of the preview image background of a camera, and prompt information is established. Thus, intelligent terminals can provide shooting suggestions for users, and users who do not have professional shooting skills can still find the best shooting angle. In addition, the micro facial expressions in a preview image are analyzed through a model trained in advance, so that a picture in accordance with the model threshold can be captured, and photos with closed eyes or weird facial expressions are avoided. On one hand, the method and the device can help users to enhance the shooting skill and shoot satisfactory photos. On the other hand, the method and the device can help users to capture a more desired expression, there is no need to delete unsatisfactory photos from a photo album manually, and the service experience of users is enhanced.

The present invention relates to a method and a device for treating opacities and / or hardenings of an unopened eye.It is a specific advantage of the solution according to the invention that the treamtment of the inner region of the eye is possible without the need to introduce a surgical instrument into the eye.

The invention relates to an image processing method and apparatus, a mobile terminal and a computer readable storage medium. The method comprises the following steps: obtaining multiple frames of human face images that are continuously shot; determining a target image according to human eye features of human faces in the human face images; separately matching the target image with the other imagesin the multiple frames of human face images; and performing fusion processing on the target image and the other images with matching rates exceeding a preset value. According to the method, in the multiple frames of human face images that are continuously shot, the mobile terminal can determine the target image according to the human eye features of the human faces, obtain the other images matched with the target image and perform the fusion processing on the target image and the other images. As the images are selected via the human eye features, the images in which the human faces with closed eyes can be screened out, and multiple images are fused, so that the noise in the image can be reduced, and the quality of the image can be improved.

The embodiment of the invention provides an image processing method and device, a computer readable storage medium and electronic equipment. The method comprises the steps that an image is acquired, and whether the image includes eyes is detected; if the detection result indicates that the image includes the eyes, whether each pair of eyes in the image are in the closed state is judged; and if thejudgment result indicates that one pair of eyes are in the closed state, the open eye image corresponding to the pair of eyes is acquired from a database according to the facial features containing the pair of eyes, and the open eye image substitutes the eye parts of the face corresponding to the pair of eyes. Only one photo requires to be photographed, the image features are analyzed as for theclosed eye image according to the facial features of the closed eye image if the photo includes the closed eye image and the open eye image corresponding to the closed eye image is acquired, and the open eye image is automatically adhered on the eye areas of the closed eye image so that eye closing can be eliminated by photographing one group photo and the photographing efficiency of the group photo can be enhanced.

An alarm clock control method comprises the following method: when a predetermined time is reached, emitting an alarm clock prompt signal; acquiring acceleration and direction signals; according to the acquired acceleration and direction signals, judging whether a swing is generated; and if a swing is generated, delaying or turning off the alarm clock prompt signal. The alarm clock control method provided by the invention can judge whether a swing is generated in accordance with the acquired acceleration and direction signals, and can further delay or turn off the alarm clock prompt signal. The user need not find the key or touch point of the touch screen, can operate the alarm clock with closed eyes. The operation is more rapid and convenient, the fun to interact with the alarm clock is increased, and the user experience is enhanced. The method can be used as a solo method to operate the alarm clock or can be used in combination with other alarm clock delaying or turning off methods.

The invention relates to a fatigue drive detecting method based on eye features. The fatigue drive detecting method based on the eye features comprises the following steps that a face detection classifier is established; drive state images of a driver are collected in real time; the eyes of the driver are accurately positioned in the drive state images; in continuous video images, according to the positions of the eyes in the image of the last frame, the positions of the eyes in the image of the current frame are accurately predicted; according to the predicated positions of the eyes, the positions of the eyes are accurately positioned, and the positions of the eyes on the last frame are replaced by the new positions of the eyes; whether the eyes of the driver are opened or closed is judged, and according to the ratio of the number of closed eye frames within unit time, whether the driver is in the fatigue drive state or not is judged; if the driver is in the fatigue drive state, an alarming reminding is conducted or a real-time video of the driver in the fatigue drive state is sent to a remote server, and a remote order is received. The fatigue drive detecting method based on the eye features has the advantages that the monitoring accuracy is high, the leak detection and false detection rate is low, the environmental influence is small, the speed is high, and the cost is low.

A doze detection method, which accurately detects a blink burst and improves speed and accuracy of doze detection, includes measuring a state where the eye is substantially open as an open eye time and another state as a closed eye time, defining a time shorter than an average blink interval of a healthy adult in an alert state as a first threshold time; defining a time longer than an average closed eye time of a healthy adult in an alert state as a second threshold time; and defining blinks as a blink burst when detecting an eye opening equal to or shorter than the first threshold time. A doze state is determined when the closed eye time of a blink among the blinks during the blink burst reaches at least the second threshold time, the blink occurring after an open eye time equal to at most the first threshold time.

Real-time video images of a human subject's face are processed by a plurality of classification algorithms developed in an off-line training process to determine the open vs. closed eye state of the subject. The off-line training process utilizes a genetic programming loop embedded within an adaptive boosting loop, and forms the classification algorithms and weighting factors for combining their classification scores. In the real-time process, the individual classification scores are combined and compared to a threshold to determine the open vs. closed eye state.

The invention relates to a method for photographing allowing closed eyes to be opened. The method comprises the following steps: conducting face identification on captured data, conducting detection and positioning on eyes, and conducting threshold statistics on the peripheries of the eyes to judge whether the eyes are closed or not and to determine whether the eyes are suitable for photographing; only when the condition that the eyes are ever closed and reopened is matched, further judging the open range of the eyes, then conducting data capturing by calling hardware, and finishing a photographed function. According to the method, the taken photo will not have the problem of eye closing and also will not have the problem that the eyes are lackluster, so that the effect of the photo is better.

The invention discloses a method and a device for recognizing a blink movement. The method comprises steps: texture features of an eye image in a predetermined image frame in a human face image frame sequence are acquired, wherein the texture features are used for characterizing biological features of the eye part corresponding to the eye image; according to the texture features, whether the eye image in the predetermined image frame is an opened eye image or a closed eye image is determined; whether the eye image in the human face image frame sequence contains the opened eye image and the closed eye image is judged; and if the eye image in the human face image frame sequence contains the opened eye image and the closed eye image, a blink movement existing in the human face corresponding to the human face image frame sequence is determined. The technical problem that the human eye movement state is inaccurately detected can be solved.

The embodiment of the invention discloses a method and a device for controlling rendering, and is applied to virtual reality equipment. The calculated amount of final rendering can be effectively reduced, and the power consumption of the virtual reality equipment is reduced. The method disclosed by the embodiment of the invention comprises the following steps: when a virtual scene picture is rendered by the virtual reality equipment and the rendered picture is exhibited for a user, detecting the eye state of the user; and if the eye state indicates that the user is at a closed-eye state, suspending the rendering for the virtual scene picture by the virtual reality equipment.

To reduce the number of erroneous operations, on an operation apparatus conducting mutually different operations such as opening and closing operations, a concretized human pictogram indicating mutually different state changes such as state changes represented by use of a face with opened eyes and a face with closed eyes associated with operation signals assigned to a pair of operation switches and a pictogram in which the human pictogram is combined with an operation pictogram representing a state in which a door concretizing an operation target to operate in response to an operation signal is opened or is being completely closed are respectively attached to the operation switches disposed adjacent to each other.

The invention discloses a balancing ability detection method which is realized by the following process: a tested person is allowed to stand on a balancing pressure plate, measuring is performed withfive postures comprising standing with open eyes and two feet, standing with closed eyes and two feet, standing with open eyes and left leg, standing with closed eyes and left leg, and standing with closed eyes and right leg; bluetooth receives digital signals from the balancing pressure plate and transmits the digital signals to a computer in real time; balancing ability analysis software converts the digital signals into real-time positions of center-of-gravity coordinates and draw a moving trajectory chart of the center of gravity, and the moving trajectory chart is displayed on a displayer; the indicators collected on the displayer are summarized and sorted out and are substituted into a balance ability calculation formula, and the balance ability score of the tested person is calculated; and according to a balance ability grade table, the corresponding balance level is divided. The method gives a set of standard specification measurement methods. At the same time, through the screening treatment of the indicators, the indicators that can comprehensively reflect the balance ability are selected out, so that the whole balance evaluation process becomes simple and reliable.

A system and method are provided for monitoring an eye to determine eye closure. The system includes a video imaging camera oriented to generate images of an eye, and a video processor for processing the images. The processor includes an edge detector for detecting edges of the eye in the image, and a line selector for generating lines at any of select angles representative of the detected edges. The processor determines the state of eye closure, such as an open eye or closed eye, based on an angle between two of the lines that select angles. The system may be employed on a vehicle to determine the eye closure state of a driver of the vehicle.

The invention discloses a fatigue driving detection method based on depth information. The fatigue driving detection method comprises the steps that a color data frame or an infrared data frame including a driver image, a depth data frame, a human body index frame and a face frame are acquired through Kinect; the human body index frame is mapped to the depth data frame, the data point depth values belonging to the same human body index number on the depth data frame are added to obtain a mean value, and the corresponding human body index number of the least mean value is taken as the driver index number; the corresponding face frame is acquired according to the driver index number; information of five sense organs is acquired from the face frame to be drawn on the color data frame or the infrared data frame; and the closed eye situation is acquired according to the eye image of the color data frame or the infrared data frame and the PERCLOS value is calculated, and the fatigue driving prompt is given when the PERCLOS value exceeds the preset threshold. The invention also discloses a fatigue driving detection device based on the depth information. According to the method, the interference of the human body data of other persons apart from the driver can be eliminated by using the depth data so that the accuracy of fatigue detection is high.

Provided is a health diagnosis apparatus and method in which brain waves are sequentially measured from the frontal lobe of a human body that is to be diagnosed when the eyes are in an eyes-open and eyes-closed state, the measured brain waves are fast Fourier transformed to then be accumulated, and then the health conditions of the respective portions of the human body can be determined according to the patterns with respective frequencies. The health condition diagnosis method includes measuring brain waves; performing a fast-Fourier-transform on the measured brain waves; classifying the frequency-based brain wave data into opened and closed eye state brain waves to thus accumulate the classified result; finding a specific frequency and a pattern thereof which repeats from the accumulated brain wave data; correspondingly connecting the frequency and the respective portions of the human body based on the specific frequency pattern; and determining the health condition of the human body. The frequency-based health condition determination is based on clinic test results.

The invention relates to a household integrated fitness machine for middle-aged and elderly people. The fitness machine comprises a main body, wherein the main body is composed of at least two vertical supporting pillars which are mutually parallel, and the bottoms of the two vertical supporting pillars are connected by virtue of a balance standing plate; and protecting devices are arranged in the middles of the vertical supporting pillars. The household integrated fitness machine provided by the invention has the beneficial effects that by arranging the balance standing plate at the bottom of the main body and by arranging the protecting devices which are matched with the balance standing plate, people, in particular the middle-aged and elderly people, can conveniently exercise closed-eye single-leg standing, and safety in an exercise process can be guaranteed; by arranging corresponding fitness mechanisms on proper positions in accordance with the structural characteristics of the main body of the fitness machine, various fitness devices outdoors can be gathered together, so that the occupied space of the devices is greatly diminished and indoor exercise is facilitated; and in addition, by designing the vertical supporting pillars as telescopic or adjustable structures and by arranging various exercise mechanisms in a detachable mode, the device can be mounted and carried conveniently.

A doze detection method, which accurately detects a blink burst and improves speed and accuracy of doze detection, includes measuring a state where the eye is substantially open as an open eye time and another state as a closed eye time, defining a time shorter than an average blink interval of a healthy adult in an alert state as a first threshold time; defining a time longer than an average closed eye time of a healthy adult in an alert state as a second threshold time; and defining blinks as a blink burst when detecting an eye opening equal to or shorter than the first threshold time. A doze state is determined when the closed eye time of a blink among the blinks during the blink burst reaches at least the second threshold time, the blink occurring after an open eye time equal to at most the first threshold time.

A digital photographing apparatus is provided that reduces the number of instances in which an image including a subject having closed eyes is obtained. A method of controlling the apparatus and a computer readable medium having recorded thereon a program for executing the method are also provided. The apparatus includes an image capture device that generates data from light incident thereon, and a blink determination unit that determines whether eyes are closed in an image from the generated data. The blink determination unit performs the determination as to whether eyes are closed only on an image from first still image data obtained in response to a signal received from a user. If the blink determination unit determines that eyes are closed in an image from still image data generated by the image capture device, still image data is obtained again from light incident on the image capture device.

The present application discloses a correction method for a closed-eye photograph, which comprises the following steps: identifying a human eye region in a current photograph and detecting whether theeye is open or closed; when the detection result is eye closure, the face of the recognized human eye region is determined, and an eye-opening face photograph matching the determined face is searchedin the terminal; utilizing the retrieved eye-opening face photos, the human eye region recognized in the current photos is corrected. Applying the present application, correction of the closed-eye photograph can be automatically performed.