151 results about "Mouth region" patented technology

A face feature analysis which begins by generating multiple face feature candidates, e.g., eyes and nose positions, using an isolated frame face analysis. Then, a nostril tracking window is defined around a nose candidate and tests are applied to the pixels therein based on percentages of skin color area pixels and nostril area pixels to determine whether the nose candidate represents an actual nose. Once actual nostrils are identified, size, separation and contiguity of the actual nostrils is determined by projecting the nostril pixels within the nostril tracking window. A mouth window is defined around the mouth region and mouth detail analysis is then applied to the pixels within the mouth window to identify inner mouth and teeth pixels and therefrom generate an inner mouth contour. The nostril position and inner mouth contour are used to generate a synthetic model head. A direct comparison is made between the inner mouth contour generated and that of a synthetic model head and the synthetic model head is adjusted accordingly. Vector quantization algorithms may be used to develop a codebook of face model parameters to improve processing efficiency. The face feature analysis is suitable regardless of noise, illumination variations, head tilt, scale variations and nostril shape.

An unsatisfactory scene is disqualified as an image acquisition control for a camera. An image is acquired. One or more mouth regions are determined. The mouth regions are analyzed to determined whether they are frowning, and if so, then the scene is disqualified as a candidate for a processed, permanent image while the mouth is completing the frowning.

A method of digitally adding the appearance of makeup to a videoconferencing participant. The system and method for applying digital make-up operates in a loop processing sequential video frames. For each input frame, there are typically three general steps: 1) Locating the face and eye and mouth regions; 2) Applying digital make-up to the face, preferably with the exception of the eye and open mouth areas; and 3) Blending the make-up region with the rest of the face. In one embodiment of the invention, the background in the frame containing a video conferencing participant can also be modified so that other video conferencing participants cannot clearly see the background behind the participant in the image frame. In one such embodiment of the invention, the video conferencing participant tries to make his or her own image look comical or altered. In another embodiment of the invention, a particular remote participant tries to make another participant look funny to the other participants.

The invention relates to a voice-and-facial-expression-based identification method for dual-modal emotion fusion. The method comprises: S1, audio data and video data of a to-be-identified object are obtained; S2, a face expression image is extracted from the video data and segmentation of an eye region, a nose region, and a mouth region is carried out; S3, a facial expression feature in each regional image is extracted from images of the three regions; S4, PCA analysis and dimensionality reduction is carried out on voice emotion features and the facial expression features; and S5, naive Bayesian emotion voice classification is carried out on samples of two kinds of modes and decision fusion is carried out on a conditional probability to obtain a final emotion identification result. According to the invention, fusion of the voice emotion features and the facial expression features is carried out by using a decision fusion method, so that accurate data can be provided for corresponding conditional probability calculation carried out at the next step; and an emotion state of a detected object can be obtained precisely by using the method, so that accuracy and reliability of emotion identification can be improved.

The invention discloses a face multi-area fusion expression recognition method based on depth learning, which comprises the following steps of detecting a face position with a detection model; obtaining the coordinates of the key points by using the key point model; aligning the eyes according to the key points of the eyes, then aligning the face according to the coordinates of the key points of the whole face, and clipping the face region by affine transformation; cutting the eye and mouth areas of the image to a certain proportion; dividing the convolution neural network into one backbone network and two branch networks; carrying out the feature fusion in the last convolution layer, and finally obtaining the expression classification results by the classifier. The method of the inventionutilizes the priori information, besides the whole face, the eyes and mouth regions are also used as the input of the network, and the network can learn the whole semantic features of facial expressions and the local features of facial expressions through model fusion, so that the method simplifies the difficulty of facial expression recognition, reduces the external noise, and has strong robustness, high accuracy, low complexity of the algorithm and so on.

An invention for eliminating the noise generated by a user speaking into a microphonic instrument is disclosed herein. In a first embodiment, the invention comprises a soundproofed housing arranged to cover a user's mouth region and a loudspeaker that outputs a processed sound wave having a phase that is opposite of the user's voice thereby canceling out the user's voice that was confined inside the housing. In a second embodiment, the invention comprises a soundproofed housing arranged to enclose a user's mouth area, a microphone to capture the user's speech, and a loudspeaker that outputs a processed sound wave having a phase that is opposite of the user's voice thereby canceling out the user's voice that was confined inside the housing.

A balaclava designed for covering a wearer's head and at least part of their neck has a face opening, and a removable, face conforming mask is releasably securable to the balaclava to cover part of the face opening corresponding to the part of a wearer's face below the eyes. The mask is designed to conform to the general contours of a wearer's lower face including the nose and mouth region, and has appropriate openings for breathing purposes.

A combination sealing and restraint system for an as-cast ductile iron fitting is shown for both sealing and preventing separation of an iron pipe fitting and a mating male pipe. A ring-shaped body is installed within a mating groove provided in a mouth region of the as-cast fitting after the fitting has been cast at the manufacturing plant. The ring-shaped body is formed of an injection molded elastomeric material and carries a series of gripping segments which have teeth on an inner surface thereof which are designed to engage an outer surface of a mating male pipe. The teeth are oriented to allow movement of the male pipe in a first direction relative to an end opening o f the fitting during assembly, but to resist movement in a opposite direction after the fitting joint has been assembled. The gripping segments are mechanically bonded to the elastomeric body of the gasket during the injection molding operation. The ring-shaped body also includes a relatively flexible portion formed of an elastomer which forms a lip seal region with the mating male pipe.

An embodiment of the invention discloses a method for detecting states of drivers in real time. The method includes detecting face regions from video images of the drivers; detecting eye regions and mouth regions from the face regions; normalizing the detected eye regions and the detected mouth regions and matching the eye regions and the mouth regions with preliminarily trained eye and mouth templates so as to determine fatigue states of the drivers; detecting face feature points from the face regions by the aid of local constraint models in real time; three-dimensionally modeling the detected face feature points by means of converting world coordinate systems, camera coordinate systems, image physical coordinate systems and image pixel coordinate systems so as to determine head poses of the drivers and judging whether the drivers are in the states of being tired or not on the basis of the fatigue states and the head poses of the drivers. The video images of the drivers are taken by a camera.

The invention provides a yawning action detection method for detecting fatigue driving. The yawning action detection method comprises the following steps: relative position relations of facial feature regions in a facial image region in a video image are respectively determined in a matched manner by virtue of feature region contours respectively corresponding to the facial feature regions of a face matching template, so as to well ensure the accuracy of mouth location, quick matching location of the mouth regions in the facial image region in the video image is carried out by adopting an active shape model matching algorithm, the data operation amount is small, the processing speed is high, and the real-time performance of the mouth location is ensured; then, the actual shapes of mouth feature region counters are determined by carrying out matching location on the mouth regions in the facial image region in the video image to recognize the mouth opening or closing state. The yawning action detection method realizes the detection of the yawning action, is high in detection accuracy, fast in speed, provides an effective and high-real-time-performance solution for the detection of the yawning action, and can provide an alerting signal with timeliness for the fatigue driving detection.

The invention discloses a method and device for human face in-vivo detection, and belongs to the field of human face recognition. The method comprises the following steps: acquiring a 3D human face image; selecting a first group of feature points on the whole region of the 3D human face image; selecting a second group of feature points on a local region of the 3D human face image, and acquiring a three-dimensional coordinate of the second group of feature points, wherein the local region is a nose region, an eye region or a mouth region; using the three-dimensional coordinate of the first group of feature points to compute a first human face feature for representing depth information of the first group of feature points; using the three-dimensional coordinates of the first group of feature points and the second group of feature points to compute a second human face feature for representing the depth information of the first group of feature points and the second group of feature points; using the first human face feature and/or the second human face feature to judge whether the 3D human face image is a living body. The method disclosed by the invention is capable of judging whether the human face image is the living body; the recognition precision is high, and the recognition result has robustness and stability.

A method and system for detecting temporal segments of talking faces in a video sequence using visual cues. The system detects talking segments by classifying talking and non-talking segments in a sequence of image frames using visual cues. The present disclosure detects temporal segments of talking faces in video sequences by first localizing face, eyes, and hence, a mouth region. Then, the localized mouth regions across the video frames are encoded in terms of integrated gradient histogram (IGH) of visual features and quantified using evaluated entropy of the IGH. The time series data of entropy values from each frame is further clustered using online temporal segmentation (K-Means clustering) algorithm to distinguish talking mouth patterns from other mouth movements. Such segmented time series data is then used to enhance the emotion recognition system.

The invention discloses a dimension emotion recognition method based on multi-scale time sequence modeling. The method includes performing face detection and tracking on each frame image of a video sequence, and extracting face key points as first class face features; extracting gray values of pixels of a face region image, mouth region image and eye region image as second, third and fourth class face features; performing dimension emotion initial prediction according to the four classes of face features of the multiple frame image in a unit period t; performing time sequence and modality combination through a linear regression device according to the emotion initial prediction results of N unit periods t, and outputting an emotion prediction value of the video sequence. According to the method, time sequence modeling with different scales is performed on video sequence signals, and the precision prediction of each time sequence unit is implemented; the method is adaptive to emotion recognition of face signals of videos and has the advantages of fine real-time performance and greatly improved recognition precision.

A method, for electronic face recognition using geodesic representations, of processing such a geodesic representation of a face having a mouth and being able to adopt open-mouthed or closed mouth states, so that the electronic recognition works regardless of whether the mouth in the representation is open or closed. The method comprises: identifying a mouth region within a face; applying a topological constraint to the mouth region, and representing the face with the constraint. The topological constraint is chosen to render the geodesic representation invariant to the mouth state being open or closed.

Disclosed herein is a protective helmet that includes a protective outer shell, a head cavity and a computer processor housed within the protective helmet. Further disclosed is a transmitter and a receiver located in the protective helmet that is configured to establish a communication with a mobile communicator. Further disclosed is a microphone connected to the computer processor and located in a mouth region of the head cavity, the microphone configured to convert sound to an electronic transmission and provide the electronic transmission to the computer processor. Additionally, at least one speaker connected to the computer processor and located in an ear region of the head cavity. The computer processor is configured to receive verbal instructions from the microphone. The instructions are configured to control the mobile communicator. Moreover, the computer processor is configured to receive information from the mobile communicator and provide this information to the speakers in the form of an audio transmission.