WO2019051665A1 - 一种智能终端的启动控制方法及启动控制系统 - Google Patents

一种智能终端的启动控制方法及启动控制系统 Download PDF

Info

Publication number
WO2019051665A1
WO2019051665A1 PCT/CN2017/101567 CN2017101567W WO2019051665A1 WO 2019051665 A1 WO2019051665 A1 WO 2019051665A1 CN 2017101567 W CN2017101567 W CN 2017101567W WO 2019051665 A1 WO2019051665 A1 WO 2019051665A1
Authority
WO
WIPO (PCT)
Prior art keywords
smart terminal
face
face recognition
camera
preset
Prior art date
Application number
PCT/CN2017/101567
Other languages
English (en)
French (fr)
Inventor
王周丹
骆海涛
王雪蓉
杨康
Original Assignee
深圳传音通讯有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳传音通讯有限公司 filed Critical 深圳传音通讯有限公司
Priority to PCT/CN2017/101567 priority Critical patent/WO2019051665A1/zh
Priority to CN201780096728.0A priority patent/CN111344701A/zh
Publication of WO2019051665A1 publication Critical patent/WO2019051665A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/725—Cordless telephones
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/441—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card
    • H04N21/4415—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card using biometric characteristics of the user, e.g. by voice recognition or fingerprint scanning

Definitions

  • the present invention relates to the field of intelligent terminals, and in particular, to a startup control method and a startup control system for an intelligent terminal.
  • the booting or shutting down of various smart terminals is basically realized by the user pressing the power button of the power switch of the smart terminals, when the smart terminal After detecting that the power switch key is pressed, the power supply module converts the smart terminal battery voltage into a voltage suitable for each part of the intelligent terminal circuit, and supplies it to the corresponding power supply module.
  • the clock circuit receives the power supply voltage, the vibration signal is generated and sent.
  • the CPU executes the boot process after obtaining the voltage and clock signals, and performs subsequent boot operations.
  • Such a method of turning on and off the smart terminal by pressing the power button of the power switch has such a technical defect that the presence of the power button of the power switch causes an obstacle to the miniaturization of the smart terminal, which is disadvantageous to the lightness and miniaturization of the smart terminal.
  • the process of opening and shutting down the smart terminal by pressing the power button of the power switch of these smart terminals is cumbersome and complicated for the user who pursues efficiency; in addition, since the power button of the power switch is frequently used, the button is easily aged, resulting in aging. The sensitivity of the button is reduced or even disabled.
  • the present invention provides a startup control method and a startup control system for an intelligent terminal.
  • the facial image is recorded, and the face recognition template is preset.
  • the smart terminal is used.
  • the camera is aimed at the face, the camera collects the face recognition information, and the face recognition template is matched with the preset face recognition template.
  • the smart terminal can be started.
  • the power button of the smart terminal can be omitted, and the overall layout of the smart terminal is more compact, compact, and beautiful, which makes the smart terminal more technical and improves the user experience; and can be better.
  • an object of the present invention is to provide a startup control method and a startup control system for an intelligent terminal.
  • the invention discloses a startup control method for an intelligent terminal, comprising the following steps:
  • the front distance sensor of the smart terminal is invoked to detect a contour of the face
  • the camera of the smart terminal is called to acquire the face recognition information collected by the camera;
  • the step of establishing a face recognition template in the smart terminal includes:
  • the camera of the smart terminal is invoked to acquire a face image collected by the camera;
  • the face feature information of the face image is extracted, and the face recognition template is established.
  • the step of calling the camera of the smart terminal to acquire the face recognition information collected by the camera includes:
  • the camera of the smart terminal using a living body detecting means to determine that the data source of the face contour is a living body data source of the human body or a non-living data source of a photo, a video, or a mask;
  • the data source of the face contour is a non-living data source of photos, videos, and masks, the subsequent steps are stopped.
  • the step of calling the camera of the smart terminal to acquire the face recognition information collected by the camera includes:
  • the smart terminal setting a preset number of times and a preset time
  • the smart terminal sends an alarm signal.
  • the invention discloses a startup control system for an intelligent terminal, which comprises a preset module, a detection module, an acquisition module, a matching module and a control module;
  • the preset module is configured to establish a face recognition template in the smart terminal
  • the detecting module when the smart terminal is in a shutdown state, invokes a front distance sensor of the smart terminal to detect a contour of a human face;
  • the acquiring module is connected to the detecting module, and when the front distance sensor detects a human face contour, the camera of the smart terminal is invoked to acquire face recognition information collected by the camera;
  • the matching module is communicably connected to the preset module and the collection module, and matches the face recognition information with the face recognition template;
  • the control module is communicably connected to the matching module, and when the face recognition information matches the face recognition template, sends a power-on command to a power-on detection circuit provided in the smart terminal to control start The intelligent terminal.
  • the preset module includes a template acquiring unit and a template preset unit;
  • the template obtaining unit when the smart terminal is in a power-on state, invokes a camera of the smart terminal to acquire a face image collected by the camera;
  • the template preset unit is communicably connected to the template acquiring unit, extracts face feature information of the face image, and establishes the face recognition template.
  • the collection module includes a living body detecting unit and an acquisition control unit;
  • the living body detecting unit calls the camera of the smart terminal, and uses a living body detecting means to determine that the data source of the face recognition information is a living body data source of the human body or a non-living data source of a photo, a video, or a mask;
  • the acquisition control unit collects the face recognition information when the data source of the face recognition information is a living body data source of the human body; when the data source of the face recognition information is a photo, a video, or a mask When living data sources, Controlling the startup control system to shut down.
  • the acquisition module includes a signal preset unit, a signal acquisition unit, and a signal control unit;
  • the signal preset unit sets a voice signal in the smart terminal
  • the signal acquisition unit is communicably connected to the signal preset unit, and when the front distance sensor detects a face contour, the microphone of the smart terminal is called to detect whether the voice signal is input;
  • the signal control unit is in communication with the signal acquisition unit.
  • the camera of the smart terminal is invoked to acquire face recognition information collected by the camera.
  • the signal preset unit is configured to set a preset number of times and a preset time in the smart terminal;
  • the signal collecting unit determines, in the preset time, whether the number of times that the voice signal is started to start the smart terminal fails exceeds the preset number of times;
  • the signal control unit controls the smart terminal to send an alarm signal when the number of times the voice signal is started to start the smart terminal fails to exceed the preset number of times during the preset time.
  • the present invention provides a startup control method and a startup control system for an intelligent terminal.
  • the facial image is recorded, and the face recognition template is preset.
  • the smart terminal camera is aligned.
  • the face and the camera collect facial recognition information, and the face recognition template is used to match the preset facial recognition template.
  • the smart terminal can be activated.
  • the power button of the smart terminal can be omitted, and the overall layout of the smart terminal is more compact, compact, and beautiful, which makes the smart terminal more technical and improves the user experience; and can be better.
  • FIG. 1 is a schematic flow chart of a startup control method in accordance with a preferred embodiment of the present invention
  • FIG. 2 is a schematic flowchart of a step of establishing a face recognition template in the startup control method of FIG. 1;
  • FIG. 3 is a schematic flow chart of a living body detecting step of the startup control method of FIG. 1;
  • FIG. 4 is a schematic flow chart of a voice signal detecting step of the startup control method of FIG. 1;
  • FIG. 5 is a schematic flow chart of an alarm step of the startup control method of FIG. 4;
  • Figure 6 is a block diagram showing the structure of a start control system in accordance with a preferred embodiment of the present invention.
  • Reference numerals 100-start control system; 11-preset module; 12-detection module; 13-acquisition module; 14-matching module; 15-control module.
  • module or "unit” for indicating an element is merely an explanation for facilitating the present invention, and does not have a specific meaning per se. Therefore, “module” and “unit” can be used in combination.
  • the startup control method and the startup control system of the present invention can be applied to an intelligent terminal, and the intelligent terminal can be implemented in various forms.
  • the liquid crystal display terminal described in the present invention may include, for example, a mobile phone, a smart phone, a notebook computer, a PDA (Personal Digital Assistant), a PAD (Tablet), a PMP (Portable Multimedia Player), a navigation device, a smart watch, or the like.
  • Mobile terminals, as well as fixed terminals such as digital TVs, desktop computers, and the like.
  • the present invention will be described assuming that the terminal is a mobile terminal and assuming that the mobile terminal is a smart phone.
  • a method for controlling startup of a smart terminal includes the following steps:
  • S100 Establish a face recognition template in the smart terminal.
  • S200 When the smart terminal is in a shutdown state, calling a front distance sensor of the smart terminal to detect a contour of a human face;
  • S300 when the front distance sensor detects a face contour, calling a camera of the smart terminal to acquire face recognition information collected by the camera;
  • S400 Match the face recognition information with the face recognition template.
  • Step S100 establishing a face recognition template in the smart terminal
  • step S100 in the smart terminal, the step of establishing a face recognition template includes:
  • S120 Extract face feature information of the face image, and establish the face recognition template.
  • a face recognition template is created, and the face recognition template can be created in various ways, for example, by calling the camera of the smart phone, entering the facial image of the user, and, for example, acquiring the photo album application in the smart terminal.
  • the right to obtain photos, videos, etc. of the user's facial image in the smart terminal album, perform facial feature analysis on the acquired images, photos, videos, etc., extract face feature data, and establish a face recognition template the specific process will be Explained in detail below.
  • Step S200 When the smart terminal is in a shutdown state, the front distance sensor of the smart terminal is called to detect a contour of the face;
  • the camera of the smart phone is aimed at the face, and the front distance sensor of the smart phone senses the contour information of the face within a certain distance from the front of the smart phone.
  • the front distance sensor is generally disposed on both sides of the smartphone earpiece or in the groove of the smart phone earphone, so that the front distance sensor is convenient to work.
  • the mobile phone When the user picks up or makes a call, the mobile phone is placed close to the head or the ear, and the front distance sensor can measure the distance between the human head or the ear and the smart phone, and when the distance is reduced to a certain extent, the touch screen is controlled.
  • the backlight is off and the touch screen is turned off. This prevents the wrong operation of the touch screen during the call state. Secondly, it can save the power of the smart phone.
  • the backlight of the touch screen is turned on again.
  • a front distance sensor is disposed under the elliptical aperture, including an infrared emitting lamp and an infrared receiver.
  • the working principle is that the infrared emitting light emits infrared light when the human ear or other object approaches. In this aperture, the infrared light will be reflected back.
  • the infrared emitter receives the infrared intensity beyond a certain range, it will think that there is an object close to it, and it will be off when the call is in progress. Conversely, when the infrared intensity received by the infrared receiver is weaker than a certain range, the object will be considered to be far away and will be bright during the call.
  • the front distance sensor originally used to detect the distance during the call to control the off-screen and bright-screen operation can be used as the perception. Detection tool for face contour information.
  • Step S300 When the front distance sensor detects the contour of the face, the camera of the smart terminal is called to acquire the face recognition information collected by the camera;
  • the camera of the smart phone is activated to perform face detection.
  • step S300 when the front distance sensor detects a human face contour
  • the step of acquiring the face recognition information collected by the camera includes:
  • S310 Calling the camera of the smart terminal, using a living body detecting means to determine that the data source of the face contour is a living body data source of the human body or a non-living data source of a photo, a video, or a mask;
  • the living body detection means is first used to distinguish that the collected data source is a human body, rather than a non-living data source such as a photo, a video or a mask.
  • the face is focused, the AF point is automatically adjusted, the sharpness of the face is improved, the image is enlarged, the face feature is analyzed, and the face recognition information is extracted.
  • Step S500 When the face recognition information matches the face recognition template, send a power-on command to a power-on detection circuit provided in the smart terminal to control activation of the smart terminal.
  • Step S400-500 performs matching of the face recognition information and the face recognition template.
  • the process of positioning and determining the portrait elements mainly includes four components: face image acquisition and detection, face image preprocessing, face image feature extraction, and matching and recognition.
  • Different face images can be captured by the camera, such as still images, dynamic images, different positions, different expressions, etc., can be well collected.
  • the camera automatically searches for and captures the user's face image.
  • Face detection is mainly used for pre-processing of face recognition, that is, the position and size of the face are accurately calibrated in the image.
  • the pattern features contained in the face image are very rich, such as histogram features, color features, template features, structural features, and Haar features. Face detection is to pick out the useful information and use these features to achieve face detection.
  • the -Adaboost algorithm is used in the face detection process to select some rectangular features (weak classifiers) that can represent the face.
  • the weak classifier is constructed as a strong classifier according to the weighted voting method, and then some strong classifications are obtained.
  • the devices are connected in series to form a cascaded classifier of the cascade structure, which effectively improves the detection speed of the classifier.
  • Image preprocessing for faces is based on face detection results, processing the images and ultimately serving the feature extraction process.
  • the original image acquired by the system is often not directly used due to various conditions and random interference. It must be pre-processed with grayscale correction and noise filtering in the early stage of image processing.
  • the preprocessing process mainly includes ray compensation, gradation transformation, histogram equalization, normalization, geometric correction, filtering and sharpening of face images.
  • Face image feature extraction The features that can be used are usually divided into visual features, pixel statistical features, and face image changes. Change coefficient features, face image algebra features, and so on. Face feature extraction is performed on certain features of the face. Face feature extraction, also known as face representation, is a process of character modeling a face. The methods of face feature extraction are summarized into two categories: one is based on knowledge representation methods; the other is based on algebraic features or statistical learning.
  • the knowledge-based representation method mainly obtains the feature data which is helpful for face classification according to the shape description of the face organs and the distance characteristics between them.
  • the feature components usually include the Euclidean distance, curvature and angle between the feature points.
  • the human face is composed of parts such as eyes, nose, mouth, chin, etc. The geometric description of these parts and the structural relationship between them can be used as important features for recognizing human faces. These features are called geometric features.
  • Knowledge-based face representation mainly includes geometric feature-based methods and template matching methods.
  • Face image matching and recognition The feature data of the extracted face image is searched and matched with the feature template stored in the database. By setting a threshold, when the similarity exceeds the threshold, the result of the matching is output. Face recognition is to compare the face features to be recognized with the obtained face feature templates, and judge the identity information of the faces according to the degree of similarity. This process is divided into two categories: one is confirmation, one-to-one image comparison process, and the other is recognition, which is a one-to-many image matching process.
  • the face is composed of portrait elements such as eyes, nose, mouth, and chin. Because of the differences in the shape, size, and structure of these portrait elements, each face in the world varies widely, so the shape of these portrait elements and The geometric description of the structural relationship can be used as an important feature of face recognition.
  • the geometric feature was first used for the description and recognition of the side profile of the face. First, several significant points were determined according to the side profile curve, and a set of feature metrics such as distance, angle, etc. for identification were derived from these significant points.
  • the use of geometric features for frontal face recognition is generally performed by extracting the location of important feature points such as the human eye, mouth, nose, and the geometry of important organs such as the eye as classification features.
  • the deformable templating method can be regarded as an improvement of the geometric feature method.
  • the basic idea is to design an organ model with adjustable parameters (ie, deformable template), define an energy function, and minimize the energy function by adjusting the model parameters.
  • the model parameters at this time serve as the geometric features of the organ.
  • the weighting coefficients of various costs in the energy function can only be determined by experience, which is difficult to generalize.
  • the energy function optimization process is very time consuming and difficult to apply.
  • Parameter-based face representation can achieve an efficient description of the salient features of the face, but it requires a lot of pre-processing and fine parameter selection.
  • the general geometric features only describe the basic shape and structure relationship of the components, ignoring the local fine features, resulting in the loss of part of the information, more suitable for rough classification, and the existing feature point detection technology in the accuracy rate Far from Can meet the requirements, the amount of calculation is also large.
  • the representation of the principal subspace is compact, the feature dimension is greatly reduced, but it is non-localized, the support of the kernel function is extended in the entire coordinate space, and it is non-topological, the point adjacent to an axis projection. It has nothing to do with the proximity of points in the original image space. Locality and topologicality are ideal characteristics for pattern analysis and segmentation. It seems that this is more in line with the mechanism of neural information processing. Therefore, it is very important to find expressions with such characteristics.
  • the feature face method is one of the most popular algorithms proposed by Turk and Pentland in the early 1990s. It has simple and effective features, also called face recognition method based on principal component analysis (PCA).
  • PCA principal component analysis
  • the basic idea of the feature face face technology is to find the face image of the face image set covariance matrix from the statistical point of view, and to approximate the face image. These feature vectors are called Eigenfaces.
  • the eigenface reflects the information that is implicit in the set of face samples and the structural relationship of the face.
  • the feature vectors of the sample set covariance matrix of the eyes, cheeks, and lower jaws are called feature eyes, feature jaws, and feature lips, collectively referred to as feature face faces.
  • the feature face generates a subspace in the corresponding image space, called a child face space.
  • the projection distance of the test image window in the sub-face space is calculated, and if the window image satisfies the threshold comparison condition, it is determined to be a human face.
  • the method based on feature analysis that is, the relative ratio of the face reference point and other shape parameters or class parameters describing the facial face feature are combined to form the recognition feature vector, and the overall face-based recognition not only retains the face portion
  • the topological relationship between the pieces, and also the information of each component itself, and the component-based recognition is to design a specific recognition algorithm by extracting the local contour information and the gray information.
  • the method first determines the size, position, distance and other attributes of the facial iris, nose, mouth angle and the like, and then calculates their geometric feature quantities, and these feature quantities form a feature vector describing the image.
  • the core of the technology is actually "local body feature analysis” and "graphic/neural recognition algorithm.” This algorithm is a method that utilizes various organs and features of the human face.
  • the corresponding geometric relationship multi-data formation identification parameter is compared, judged and confirmed with all the original parameters in the database.
  • feature face On the basis of the traditional feature face, the researchers noticed that the feature vector with large feature value (ie, feature face) is not necessarily the direction of good classification performance, and accordingly, various feature (subspace) selection methods, such as Peng's, have been developed.
  • the eigenface method is an explicit principal component analysis face modeling.
  • Some linear self-association and linear compression BP networks are implicit principal component analysis methods. They all represent faces as some vectors.
  • Weighted sums are the main eigenvectors of the training set cross product matrix.
  • the eigenface method is a simple, fast and practical algorithm based on transform coefficient features, but because it is essentially It depends on the gray correlation of the training set and the test set image, and requires the test image to be compared with the training set, so it has great limitations.
  • the feature face recognition method based on KL transform is an optimal orthogonal transform in image compression. It is used for statistical feature extraction, which forms the basis of subspace method pattern recognition. If KL transform is used For face recognition, it is assumed that the face is in a low-dimensional linear space, and different faces are separable. Since the high-dimensional image space KL transform can obtain a new set of orthogonal bases, the partial orthogonal basis can be preserved. To generate low-dimensional face space, and the basis of low-dimensional space is obtained by analyzing the statistical characteristics of the face training sample set.
  • the generation matrix of the KL transform can be the overall scatter matrix of the training sample set, or it can be a training sample.
  • the inter-class scatter matrix of the set can be trained by using the average of several images of the same person, so that the interference of light and the like can be eliminated to some extent, and the calculation amount is also reduced, and the recognition rate is not decreased.
  • a dynamic link model (DLA) is proposed for object recognition with distortion invariance.
  • the object is described by sparse graphs.
  • the vertices are marked by multi-scale description of the local energy spectrum, and the edges represent topological connections and are marked by geometric distance.
  • Plastic pattern matching techniques are applied to find the most recent known patterns.
  • the surface deformation is performed by the method of finite element analysis, and it is judged whether the two pictures are the same person according to the deformation condition. This method is characterized by placing the space (x, y) and the gray scale I (x, y) in a 3D space and considering it. Experiments show that the recognition result is significantly better than the feature face method.
  • the face is encoded into 83 model parameters by automatically locating the salient features of the face, and the face recognition based on the shape information is performed by the method of discrimination analysis.
  • Elastic image matching technology is a recognition algorithm based on geometric features and wavelet texture analysis for gray distribution information. Because the algorithm makes good use of face structure and gray distribution information, it also has automatic and precise positioning. The function of the facial feature points has a good recognition effect, and the adaptive recognition rate is high.
  • Artificial neural network is a nonlinear dynamic system with good self-organization and self-adaptation ability.
  • the research of neural network methods in face recognition is in the ascendant. First, extract 50 principals of the face, then map it to the 5-dimensional space with the autocorrelation neural network, and then use a common multi-layer perceptron to discriminate, which is better for some simple test images;
  • a hybrid neural network for face recognition in which unsupervised neural networks are used for feature extraction and supervised neural networks are used for classification.
  • the application of neural network methods in face recognition has certain advantages over the above-mentioned methods, because it is quite difficult to explicitly describe many rules or rules of face recognition, and the neural network method can be learned.
  • the process of obtaining implicit expressions of these laws and rules its More adaptable and generally easier to implement. Therefore, artificial neural network recognition is fast, but the recognition rate is low.
  • the neural network method usually needs to input the face as a one-dimensional vector, so the input node is huge, and one of the important targets for recognition is dimension reduction processing.
  • the Gabor filter limits the Gaussian network function to the shape of a plane wave, and has a preference for the orientation and frequency in the filter design, which is characterized by sensitivity to line edge responses.
  • the method is to store a number of standard face image templates or face image organ templates in the library.
  • the sample face image is matched with all the pixels in the library using normalized correlation metrics.
  • the eigenface method treats the image as a matrix, and calculates the eigenvalues and the corresponding eigenvectors as algebraic features for recognition. It has the advantage of not having to extract geometric features such as the nose and mouth, but the recognition rate is not high in a single sample, and When the number of face patterns is large, the amount of calculation is large.
  • This technique is derived from, but essentially different from, the traditional eigenface face recognition method.
  • the feature face method all people share a face subspace, and the method creates a face subspace that is private to the individual face for each individual face, thereby not only better describing the difference between different individual faces. And, to the greatest extent, it discards the intra-class differences and noises that are unfavorable for recognition, and thus has better discriminating ability than the traditional feature face algorithm.
  • a technique for generating multiple training samples based on a single sample is proposed, so that the individual face subspace method requiring multiple training samples can be applied to the single Training sample face recognition problem.
  • the camera when the front distance sensor of the smart phone senses the contour of the face, the camera is activated to perform face tracking detection, and the image is automatically adjusted to obtain the face recognition information and the preset face recognition template for analysis and matching.
  • the command is sent to the power-on key, and the power-on channel is automatically turned on, and the voltage of the smart phone battery is converted into a voltage suitable for each part of the smart phone circuit, and supplied to the corresponding power supply module, and the vibration is generated when the clock circuit receives the power supply voltage.
  • the signal is sent to the logic circuit, and the CPU executes the boot process after obtaining the voltage and the clock signal to perform the subsequent boot operation.
  • S300 when the front distance sensor detects a human face contour, the step of calling the smart terminal's camera to obtain the face recognition information collected by the camera includes:
  • the voice recognition is combined with the facial recognition technology, and a voice signal is first preset in the smart terminal, such as “power on”, and the front distance sensor detects the contour of the face when the smart terminal is in the off state.
  • the microphone of the smart terminal is called to detect whether the voice signal is input, that is, whether the user says "power on” to the smart terminal, and when the user is detected to say "power on” to the smart terminal
  • the camera of the smart terminal is called to acquire the face recognition information collected by the camera. In this way, the camera is activated and the face recognition information is collected only when the front distance sensor detects the contour of the user's face and the user inputs the voice signal accurately.
  • the power of the smart terminal can be saved, and the user's misoperation can be effectively prevented. At the same time, improve the confidentiality of the privacy information of the smart terminal.
  • a predetermined number of times and a preset time are set in the smart terminal
  • the smart terminal sends an alarm signal.
  • the number of times the user inputs the voice signal to start the smart terminal fails more than a preset value.
  • the number of times for example, the preset number of times is three times, and the preset number of times can be adjusted according to the actual situation, that is, whether the number of times the voice signal error is determined exceeds the preset three times, and if the result of the determination is yes, an alarm is issued. signal.
  • the on/off operating system of the smartphone sends a voice alarm signal, such as “identify the error, please stop using the mobile phone”, and can send an alert email to the specified mailbox to inform the user or the owner that the smart phone is intrusive, so as to take it in time.
  • a voice alarm signal such as “identify the error, please stop using the mobile phone”
  • the measure solves the problem that the button is easily aged, resulting in decreased sensitivity or even failure, low security performance of single speech recognition, and large amount of data for single face recognition processing.
  • the present invention further discloses a startup control system 100 for an intelligent terminal, comprising a preset module 11, a detection module 12, an acquisition module 13, a matching module 14, and a control module 15;
  • the preset module 11 is configured to establish a face recognition template in the smart terminal
  • the detecting module 12 when the smart terminal is in a shutdown state, invokes a front distance sensor of the smart terminal to detect a contour of a human face;
  • the collecting module 13 is connected to the detecting module 12, and when the front distance sensor detects the contour of the face, the camera of the smart terminal is called to acquire the face recognition information collected by the camera;
  • the matching module 14 is communicably connected to the preset module 11 and the collecting module 13 to match the face recognition information with the face recognition template.
  • the control module 15 is communicably connected to the matching module 14, and when the face recognition information matches the face recognition template, sends a power-on command to the power-on detection circuit provided in the smart terminal, Control launching the smart terminal.
  • the preset module 11 includes a template acquiring unit and a template preset unit.
  • the template obtaining unit when the smart terminal is in a power-on state, invokes a camera of the smart terminal to acquire a face image collected by the camera;
  • the template preset unit is communicably connected to the template acquiring unit, extracts face feature information of the face image, and establishes the face recognition template.
  • the collection module 13 includes a living body detecting unit and an acquisition control unit;
  • the living body detecting unit calls the camera of the smart terminal, and uses a living body detecting means to determine that the data source of the face recognition information is a living body data source of the human body or a non-living data source of a photo, a video, or a mask;
  • the acquisition control unit collects the face recognition information when the data source of the face recognition information is a living body data source of the human body; when the data source of the face recognition information is a photo, a video, or a mask
  • the live control data source is controlled to shut down the startup control system 100.
  • the acquisition module 13 includes a signal preset unit, a signal acquisition unit, and a signal control. Unit
  • the signal preset unit sets a voice signal in the smart terminal
  • the signal acquisition unit is communicably connected to the signal preset unit, and when the front distance sensor detects a face contour, the microphone of the smart terminal is called to detect whether the voice signal is input;
  • the signal control unit is in communication with the signal acquisition unit.
  • the camera of the smart terminal is invoked to acquire face recognition information collected by the camera.
  • the signal preset unit is configured to set a preset number of times and a preset time in the smart terminal;
  • the signal collecting unit determines, in the preset time, whether the number of times that the voice signal is started to start the smart terminal fails exceeds the preset number of times;
  • the signal control unit controls the smart terminal to send an alarm signal when the number of times the voice signal is started to start the smart terminal fails to exceed the preset number of times during the preset time.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Security & Cryptography (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Collating Specific Patterns (AREA)

Abstract

本发明提供了一种智能终端的启动控制方法及启动控制系统，在用户首次使用智能终端时，录入面部影像，预设为面部识别模板，当用户需要开机时，将智能终端摄像头对准面部，摄像头采集面部识别信息，通过面部识别技术，与预设的面部识别模板进行匹配，匹配成功时，即可启动智能终端。通过上述启动控制方法及启动控制系统，可省去智能终端的电源键，是智能终端总体布局更叫轻便、小巧、美观，使得智能终端更加科技化，提高用户的使用体验；而且可以更好的保护智能终端内用户的隐私信息，防止智能终端内用户隐私信息的泄露。

Description

一种智能终端的启动控制方法及启动控制系统 技术领域
本发明涉及智能终端领域，尤其涉及一种智能终端的启动控制方法及启动控制系统。
背景技术
随着互联网技术的快速发展，具有多种应用功能的智能终端得以迅速普及，并成为深入至人类社会生活方方面面的终端产品。以手机为例，现有的手机大部分为智能手机，智能手机的功能也越来也强大。如今，用户不仅仅关注智能手机的功能，也越来也注重对智能手机的操作体验。
在智能终端的实际应用中，智能手机、平板电脑等各种智能终端的开机或关机(简称开关机)基本上都是由用户通过按压这些智能终端的开关机电源键来实现的，当智能终端的供电模块检测到电源开关键被按下后，会将智能终端电池电压转换为适合智能终端电路各部分使用的电压，供应给相应的电源模块，当时钟电路得到供电电压后产生震动信号，送入逻辑电路，CPU在得到电压和时钟信号后执行开机程序，进行后续开机操作。这种通过按压开关机电源键来实现智能终端开、关机的方式存在这样的技术缺陷，即开关机电源键的存在，对智能终端体积小型化造成了障碍，不利于智能终端轻便化、小型化；而且，通过按压这些智能终端的开关机电源键来实现的智能终端开、关机过程，对于追求效率的用户显得繁琐和复杂；另外，由于开关机电源键的使用非常频繁，按键容易老化，导致按键的灵敏度下降甚至失效。
随着智能终端用户的普及，如今，智能终端已不仅仅是用户的通讯工具，智能终端里面还包含了用户的隐私信息，智能终端在给用户带来越来越多便利的同时由于种种原因导致的用户信息泄密的事件也频频发生，由此带来的一系列严重后果让人无法回避，智能终端信息的安全性急需加强。当前智能终端一般都有一种非常简单的解锁机制，比如一组特殊组合的按键、一组密码或一组特别触屏滑动序列等，这种方式需要用户记住相应的密码，难免会造成无意泄密或暴力破解，有时用户还会忘记密码而造成很多不便和困扰。为了保护用户的个人信息不外漏，对智能终端持有者的识别更为重要。智能终端的摄像头功能已经具有普遍性和技术成熟性，利用摄像头对人脸识别更为便捷安全。
因此，本发明提供了一种智能终端的启动控制方法及启动控制系统，在用户首次使用智能终端时，录入面部影像，预设为面部识别模板，当用户需要开机时，将智能终端 摄像头对准面部，摄像头采集面部识别信息，通过面部识别技术，与预设的面部识别模板进行匹配，匹配成功时，即可启动智能终端。通过上述启动控制方法及启动控制系统，可省去智能终端的电源键，是智能终端总体布局更叫轻便、小巧、美观，使得智能终端更加科技化，提高用户的使用体验；而且可以更好的保护智能终端内用户的隐私信息，防止智能终端内用户隐私信息的泄露。
发明内容
为了克服上述技术缺陷，本发明的目的在于提供一种智能终端的启动控制方法及启动控制系统。
本发明公开了一种智能终端的启动控制方法，包括以下步骤：
于所述智能终端内，建立一人脸识别模板；
在所述智能终端处于关机状态时，调用所述智能终端的前置距离传感器，检测人脸轮廓；
当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息；
将所述人脸识别信息与所述人脸识别模板进行匹配；
当所述人脸识别信息与所述人脸识别模板匹配时，发送一开机指令至设于所述智能终端内的开机检测电路，以控制启动所述智能终端。
优选地，于所述智能终端内，建立一人脸识别模板的步骤包括：
在所述智能终端处于开机状态时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸图像；
提取所述人脸图像的人脸特征信息，建立所述人脸识别模板。
优选地，当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息的步骤包括：
调用所述智能终端的摄像头，采用活体检测手段，判断所述人脸轮廓的数据源是人体的活体数据源或照片、录像、面具的非活体数据源；
当所述人脸轮廓的数据源是人体的活体数据源时，采集所述人脸识别信息；
当所述人脸轮廓的数据源是照片、录像、面具的非活体数据源时，停止执行后续步骤。
优选地，当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息的步骤包括：
于所述智能终端内，设定一语音信号；
当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的麦克风，检测是否输入所述语音信号；
当检测到输入所述语音信号时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息。
优选地，于所述智能终端内，设定一预设次数及预设时间；
在所述预设时间内，判断输入所述语音信号启动所述智能终端失败的次数是否超过所述预设次数；
在所述预设时间内，当输入所述语音信号启动所述智能终端失败的次数超过所述预设次数时，所述智能终端发出报警信号。
本发明公开了一种智能终端的启动控制系统，包括预设模块、检测模块、采集模块、匹配模块、控制模块；
所述预设模块，于所述智能终端内，建立一人脸识别模板；
所述检测模块，在所述智能终端处于关机状态时，调用所述智能终端的前置距离传感器，检测人脸轮廓；
所述采集模块，与所述检测模块通信连接，当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息；
所述匹配模块，与所述预设模块、采集模块通信连接，将所述人脸识别信息与所述人脸识别模板进行匹配；
所述控制模块，与所述匹配模块通信连接，当所述人脸识别信息与所述人脸识别模板匹配时，发送一开机指令至设于所述智能终端内的开机检测电路，以控制启动所述智能终端。
优选地，所述预设模块包括模板获取单元、模板预设单元；
所述模板获取单元，在所述智能终端处于开机状态时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸图像；
所述模板预设单元，与所述模板获取单元通信连接，提取所述人脸图像的人脸特征信息，建立所述人脸识别模板。
优选地，所述采集模块包括活体检测单元、采集控制单元；
所述活体检测单元，调用所述智能终端的摄像头，采用活体检测手段，判断所述人脸识别信息的数据源是人体的活体数据源或照片、录像、面具的非活体数据源；
所述采集控制单元，当所述人脸识别信息的数据源是人体的活体数据源时，采集所述人脸识别信息；当所述人脸识别信息的数据源是照片、录像、面具的非活体数据源时， 控制所述启动控制系统关闭。
优选地，所述采集模块，包括信号预设单元、信号采集单元、信号控制单元；
所述信号预设单元，于所述智能终端内，设定一语音信号；
所述信号采集单元，与所述信号预设单元通信连接，当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的麦克风，检测是否输入所述语音信号；
所述信号控制单元，与所述信号采集单元通信连接，当检测到输入所述语音信号时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息。
优选地，所述信号预设单元，于所述智能终端内，设定一预设次数及预设时间；
所述信号采集单元，在所述预设时间内，判断输入所述语音信号启动所述智能终端失败的次数是否超过所述预设次数；
所述信号控制单元，在所述预设时间内，当输入所述语音信号启动所述智能终端失败的次数超过所述预设次数时，控制所述智能终端发出报警信号。
采用了上述技术方案后，与现有技术相比，具有以下有益效果：
1.本发明提供了一种智能终端的启动控制方法及启动控制系统，在用户首次使用智能终端时，录入面部影像，预设为面部识别模板，当用户需要开机时，将智能终端摄像头对准面部，摄像头采集面部识别信息，通过面部识别技术，与预设的面部识别模板进行匹配，匹配成功时，即可启动智能终端。通过上述启动控制方法及启动控制系统，可省去智能终端的电源键，是智能终端总体布局更叫轻便、小巧、美观，使得智能终端更加科技化，提高用户的使用体验；而且可以更好的保护智能终端内用户的隐私信息，防止智能终端内用户隐私信息的泄露。
附图说明
图1为符合本发明一优选实施例的启动控制方法的流程示意图；
图2为图1的启动控制方法的建立人脸识别模板步骤的流程示意图；
图3为图1的启动控制方法的活体检测步骤的流程示意图；
图4为图1的启动控制方法的语音信号检测步骤的流程示意图；
图5为图4的启动控制方法的报警步骤的流程示意图；
图6为符合本发明一优选实施例的启动控制系统的结构示意图。
附图标记：100-启动控制系统；11-预设模块；12-检测模块；13-采集模块；14-匹配模块；15-控制模块。
具体实施方式
以下结合附图与具体实施例进一步阐述本发明的优点。
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本发明相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本发明的一些方面相一致的装置和方法的例子。
在本发明使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本公开。在本发明和所附权利要求书中所使用的单数形式的“一”、“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。
在后续的描述中，使用用于表示元件的诸如“模块”或“单元”的后缀仅为了有利于本发明的说明，其本身并没有特定的意义。因此，“模块”与“单元”可以混合地使用。
本发明的启动控制方法及启动控制系统，可以应用于智能终端，智能终端可以以各种形式来实施。例如，本发明中描述的液晶显示终端可以包括诸如移动电话、智能电话、笔记本电脑、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、导航装置、智能手表等的移动终端，以及诸如数字TV、台式计算机等的固定终端。下面，假设终端是移动终端，并假设该移动终端为智能手机，对本发明进行说明。然而，本领域技术人员将理解的是，除了特别用于移动目的的元件之外，根据本发明的实施方式的构造也能够应用于固定类型的终端。为便于描述，本发明实施例均以智能手机为例进行说明，其它应用场景相互参照即可。
参考图1，一种智能终端的启动控制方法，包括以下步骤：
S100：于所述智能终端内，建立一人脸识别模板；
S200：在所述智能终端处于关机状态时，调用所述智能终端的前置距离传感器，检测人脸轮廓；
S300：当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息；
S400：将所述人脸识别信息与所述人脸识别模板进行匹配；
S500：当所述人脸识别信息与所述人脸识别模板匹配时，发送一开机指令至设于所述智能终端内的开机检测电路，以控制启动所述智能终端。
--步骤S100：于所述智能终端内，建立一人脸识别模板；
参考图2，在一优选实施例中，步骤S100：于所述智能终端内，建立一人脸识别模板的步骤包括：
S110：在所述智能终端处于开机状态时，调用所述智能终端的摄像头，获取所述摄 像头采集的人脸图像；
S120：提取所述人脸图像的人脸特征信息，建立所述人脸识别模板。
在用户首次使用智能手机时，建立一人脸识别模板，建立人脸识别模板的方式可以有多种，例如，通过调用智能手机的摄像头，录入用户的面部影像，又如，获取智能终端内相册应用的权限，从而获取智能终端相册内包含用户面部影像的照片、视频等，对获取的影像、照片、视频等进行人脸特征分析，提取人脸特征数据，建立人脸识别模板，其具体过程将在下面详细阐述。
--步骤S200：在所述智能终端处于关机状态时，调用所述智能终端的前置距离传感器，检测人脸轮廓；
当用户需要开机时，将智能手机的摄像头对准面部，智能手机的前置距离感应器感知智能手机正面一定距离内的人脸轮廓信息。
在通常的智能终端中，以现代最常见的触摸屏智能手机为例，前置距离传感器一般设置在智能手机听筒的两侧或者设置在智能手机听筒凹槽中，这样便于前置距离传感器的工作，当用户在接听或拨打电话时，将手机靠近头部或耳朵，前置距离传感器就可以测出人头部或耳朵与智能手机之间的距离，当该距离减小到一定程度后便控制触摸屏背景灯熄灭，触摸屏关闭，这样，一来可以防止在通话状态下对触摸屏的误操作，二来可以节约智能手机电量，当用户通话完毕拿开智能手机时，再度点亮触摸屏的背景灯，开启触摸屏，这样更方便用户挂断电话进行其他操作，也更为节省电量。通常地，智能手机正面上方，椭圆形光孔下面配置有前置距离传感器，包括一个红外发射灯，一个红外接收器，工作原理是红外发射灯向外发射红外线，当人的耳朵或者其他物体靠近这个光孔时，会将红外线反射回去，红外发射器接收到红外线强度超出某一范围后，就会认为有物体靠近，当在通话时就会熄屏。反之，当红外接收器接收到的红外强度弱于某一范围后就会认为物体远离，在通话过程中就会亮屏。
基于此，在通常的智能终端上，已经有了精确的前置距离传感器可用，因此，可以将原本用来检测通话时距离以控制熄屏、亮屏操作的前置距离传感器，用来作为感知人脸轮廓信息的检测工具。
--步骤S300：当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息；
当智能手机的前置距离传感器感知人脸轮廓信息时，激活智能手机的摄像头，进行人脸检测。
参考图3，在一优选实施例中，步骤S300：当所述前置距离传感器检测到人脸轮廓 时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息的步骤包括：
S310：调用所述智能终端的摄像头，采用活体检测手段，判断所述人脸轮廓的数据源是人体的活体数据源或照片、录像、面具的非活体数据源；
S320：当所述人脸轮廓的数据源是人体的活体数据源时，采集所述人脸识别信息；当所述人脸轮廓的数据源是照片、录像、面具的非活体数据源时，停止执行后续步骤。
在步骤S300采集人脸识别信息之前，首先采用活体检测手段，以区别采集的数据源是人体，而不是照片、录像或面具等非活体的数据源。活体检测完成之后，以人脸为焦点，自动对焦点，提高人脸的清晰度，调整影像放大，进行人脸特征分析，提取人脸识别信息。
--步骤S400：将所述人脸识别信息与所述人脸识别模板进行匹配；
--步骤S500：当所述人脸识别信息与所述人脸识别模板匹配时，发送一开机指令至设于所述智能终端内的开机检测电路，以控制启动所述智能终端。
步骤S400-500进行人脸识别信息与人脸识别模板进行匹配。具体地，人像要素的定位及确定的流程主要包括四个组成部分，分别为：人脸图像采集及检测、人脸图像预处理、人脸图像特征提取以及匹配与识别。
-人脸图像采集：不同的人脸图像都能通过摄像头采集下来，比如静态图像、动态图像、不同的位置、不同表情等方面都可以得到很好的采集。当用户在摄像头的拍摄范围内时，摄像头会自动搜索并拍摄用户的人脸图像。
-人脸检测：人脸检测在实际中主要用于人脸识别的预处理，即在图像中准确标定出人脸的位置和大小。人脸图像中包含的模式特征十分丰富，如直方图特征、颜色特征、模板特征、结构特征及Haar特征等。人脸检测就是把这其中有用的信息挑出来，并利用这些特征实现人脸检测。
-人脸检测过程中使用Adaboost算法挑选出一些最能代表人脸的矩形特征(弱分类器)，按照加权投票的方式将弱分类器构造为一个强分类器，再将训练得到的若干强分类器串联组成一个级联结构的层叠分类器，有效地提高分类器的检测速度。
-人脸图像预处理：对于人脸的图像预处理是基于人脸检测结果，对图像进行处理并最终服务于特征提取的过程。系统获取的原始图像由于受到各种条件的限制和随机干扰，往往不能直接使用，必须在图像处理的早期阶段对它进行灰度校正、噪声过滤等图像预处理。对于人脸图像而言，其预处理过程主要包括人脸图像的光线补偿、灰度变换、直方图均衡化、归一化、几何校正、滤波以及锐化等。
-人脸图像特征提取：可使用的特征通常分为视觉特征、像素统计特征、人脸图像变 换系数特征、人脸图像代数特征等。人脸特征提取就是针对人脸的某些特征进行的。人脸特征提取，也称人脸表征，它是对人脸进行特征建模的过程。人脸特征提取的方法归纳起来分为两大类：一种是基于知识的表征方法；另外一种是基于代数特征或统计学习的表征方法。
基于知识的表征方法主要是根据人脸器官的形状描述以及他们之间的距离特性来获得有助于人脸分类的特征数据，其特征分量通常包括特征点间的欧氏距离、曲率和角度等。人脸由眼睛、鼻子、嘴、下巴等局部构成，对这些局部和它们之间结构关系的几何描述，可作为识别人脸的重要特征，这些特征被称为几何特征。基于知识的人脸表征主要包括基于几何特征的方法和模板匹配法。
-人脸图像匹配与识别：提取的人脸图像的特征数据与数据库中存储的特征模板进行搜索匹配，通过设定一个阈值，当相似度超过这一阈值，则把匹配得到的结果输出。人脸识别就是将待识别的人脸特征与已得到的人脸特征模板进行比较，根据相似程度对人脸的身份信息进行判断。这一过程又分为两类：一类是确认，是一对一进行图像比较的过程，另一类是辨认，是一对多进行图像匹配对比的过程。
实现时，可通过以下算法实现：
1.基于几何特征的方法
正是由于人脸由眼睛、鼻子、嘴巴、下巴等人像要素构成，因为这些人像要素的形状、大小和结构上的各种差异才使得世界上每个人脸千差万别，因此对这些人像要素的形状和结构关系的几何描述，可以作为人脸识别的重要特征。几何特征最早是用于人脸侧面轮廓的描述与识别，首先根据侧面轮廓曲线确定若干显著点，并由这些显著点导出一组用于识别的特征度量如距离、角度等。
采用几何特征进行正面人脸识别一般是通过提取人眼、口、鼻等重要特征点的位置和眼睛等重要器官的几何形状作为分类特征。可变形模板法可以视为几何特征方法的一种改进，其基本思想是：设计一个参数可调的器官模型(即可变形模板)，定义一个能量函数，通过调整模型参数使能量函数最小化，此时的模型参数即作为该器官的几何特征。
这种方法存在两个问题，一是能量函数中各种代价的加权系数只能由经验确定，难以推广，二是能量函数优化过程十分耗时，难以实际应用。基于参数的人脸表示可以实现对人脸显著特征的一个高效描述，但它需要大量的前处理和精细的参数选择。同时，采用一般几何特征只描述了部件的基本形状与结构关系，忽略了局部细微特征，造成部分信息的丢失，更适合于做粗分类，而且目前已有的特征点检测技术在精确率上还远不 能满足要求，计算量也较大。
2.局部特征分析方法(Local Face Analysis)
主元子空间的表示是紧凑的，特征维数大大降低，但它是非局部化的，其核函数的支集扩展在整个坐标空间中，同时它是非拓扑的，某个轴投影后临近的点与原图像空间中点的临近性没有任何关系，而局部性和拓扑性对模式分析和分割是理想的特性，似乎这更符合神经信息处理的机制，因此寻找具有这种特性的表达十分重要。
3.特征脸方法(Eigenface或PCA)
特征脸方法是90年代初期由Turk和Pentland提出的目前最流行的算法之一，具有简单有效的特点，也称为基于主成分分析(principal component analysis，简称PCA)的人脸识别方法。
特征子脸技术的基本思想是：从统计的观点，寻找人脸图像分布的基本人像元素，即人脸图像样本集协方差矩阵的特征向量，以此近似地表征人脸图像。这些特征向量称为特征脸(Eigenface)。
实际上，特征脸反映了隐含在人脸样本集合内部的信息和人脸的结构关系。将眼睛、面颊、下颌的样本集协方差矩阵的特征向量称为特征眼、特征颌和特征唇，统称特征子脸。特征子脸在相应的图像空间中生成子空间，称为子脸空间。计算出测试图像窗口在子脸空间的投影距离，若窗口图像满足阈值比较条件，则判断其为人脸。
基于特征分析的方法，也就是将人脸基准点的相对比率和其它描述人脸脸部特征的形状参数或类别参数等一起构成识别特征向量，这种基于整体脸的识别不仅保留了人脸部件之间的拓扑关系，而且也保留了各部件本身的信息，而基于部件的识别则是通过提取出局部轮廓信息及灰度信息来设计具体识别算法。该方法是先确定眼虹膜、鼻翼、嘴角等面像五官轮廓的大小、位置、距离等属性，然后再计算出它们的几何特征量，而这些特征量形成一描述该面像的特征向量。其技术的核心实际为“局部人体特征分析”和“图形/神经识别算法。”这种算法是利用人体面部各器官及特征部位的方法。如对应几何关系多数据形成识别参数与数据库中所有的原始参数进行比较、判断与确认。在传统特征脸的基础上，研究者注意到特征值大的特征向量(即特征脸)并不一定是分类性能好的方向，据此发展了多种特征(子空间)选择方法，如Peng的双子空间方法、Weng的线性歧义分析方法、Belhumeur的FisherFace方法等。事实上，特征脸方法是一种显式主元分析人脸建模，一些线性自联想、线性压缩型BP网则为隐式的主元分析方法，它们都是把人脸表示为一些向量的加权和，这些向量是训练集叉积阵的主特征向量。总之，特征脸方法是一种简单、快速、实用的基于变换系数特征的算法，但由于它在本质上依 赖于训练集和测试集图像的灰度相关性，而且要求测试图像与训练集比较像，所以它有着很大的局限性。
基于KL变换的特征人脸识别方法，是图象压缩中的一种最优正交变换，人们将它用于统计特征提取，从而形成了子空间法模式识别的基础，若将KL变换用于人脸识别，则需假设人脸处于低维线性空间，且不同人脸具有可分性，由于高维图像空间KL变换后可得到一组新的正交基，因此可通过保留部分正交基，以生成低维人脸空间，而低维空间的基则是通过分析人脸训练样本集的统计特性来获得，KL变换的生成矩阵可以是训练样本集的总体散布矩阵，也可以是训练样本集的类间散布矩阵，即可采用同一人的数张图像的平均来进行训练，这样可在一定程度上消除光线等的干扰，且计算量也得到减少，而识别率不会下降。
4.基于弹性模型的方法
针对畸变不变性的物体识别提出了动态链接模型(DLA)，将物体用稀疏图形来描述，其顶点用局部能量谱的多尺度描述来标记，边则表示拓扑连接关系并用几何距离来标记，然后应用塑性图形匹配技术来寻找最近的已知图形。将人脸图像(I)(x，y)建模为可变形的3D网格表面(x，y，I(x，y))，从而将人脸匹配问题转化为可变形曲面的弹性匹配问题。利用有限元分析的方法进行曲面变形，并根据变形的情况判断两张图片是否为同一个人。这种方法的特点在于将空间(x，y)和灰度I(x，y)放在了一个3D空间中同时考虑，实验表明识别结果明显优于特征脸方法。
通过自动定位人脸的显著特征点将人脸编码为83个模型参数，并利用辨别分析的方法进行基于形状信息的人脸识别。弹性图匹配技术是一种基于几何特征和对灰度分布信息进行小波纹理分析相结合的识别算法，由于该算法较好的利用了人脸的结构和灰度分布信息，而且还具有自动精确定位面部特征点的功能，因而具有良好的识别效果，适应性强识别率较高。
5.神经网络方法(Neural Networks)
人工神经网络是一种非线性动力学系统，具有良好的自组织、自适应能力。目前神经网络方法在人脸识别中的研究方兴未艾。首先提取人脸的50个主元，然后用自相关神经网络将它映射到5维空间中，再用一个普通的多层感知器进行判别，对一些简单的测试图像效果较好；还提出了一种混合型神经网络来进行人脸识别，其中非监督神经网络用于特征提取，而监督神经网络用于分类。神经网络方法在人脸识别上的应用比起前述几类方法来有一定的优势，因为对人脸识别的许多规律或规则进行显性的描述是相当困难的，而神经网络方法则可以通过学习的过程获得对这些规律和规则的隐性表达，它的 适应性更强，一般也比较容易实现。因此人工神经网络识别速度快，但识别率低。而神经网络方法通常需要将人脸作为一个一维向量输入，因此输入节点庞大，其识别重要的一个目标就是降维处理。
6.其它方法：
除了以上几种方法，人脸识别还有其它若干思路和方法，包括以下一些：
1)隐马尔可夫模型方法(Hidden Markov Model)
2)Gabor小波变换+图形匹配
(1)精确抽取面部特征点以及基于Gabor引擎的匹配算法，具有较好的准确性，能够排除由于面部姿态、表情、发型、眼镜、照明环境等带来的变化。
(2)Gabor滤波器将Gaussian网络函数限制为一个平面波的形状，并且在滤波器设计中有优先方位和频率的选择，表现为对线条边缘反应敏感。
(3)但该算法的识别速度很慢，只适合于录象资料的回放识别，对于现场的适应性很差。
3)人脸等密度线分析匹配方法
(1)多重模板匹配方法
该方法是在库中存贮若干标准面像模板或面像器官模板，在进行比对时，将采样面像所有象素与库中所有模板采用归一化相关量度量进行匹配。
(2)线性判别分析方法(Linear Discriminant Analysis，LDA)
(3)本征脸法
本征脸法将图像看作矩阵，计算本征值和对应的本征向量作为代数特征进行识别，具有无需提取眼嘴鼻等几何特征的优点，但在单样本时识别率不高，且在人脸模式数较大时计算量大。
(4)特定人脸子空间(FSS)算法
该技术来源于但在本质上区别于传统的特征脸人脸识别方法。特征脸方法中所有人共有一个人脸子空间，而该方法则为每一个体人脸建立一个该个体对象所私有的人脸子空间，从而不但能够更好的描述不同个体人脸之间的差异性，而且最大可能地摈弃了对识别不利的类内差异性和噪声，因而比传统的特征脸算法具有更好的判别能力。另外，针对每个待识别个体只有单一训练样本的人脸识别问题，提出了一种基于单一样本生成多个训练样本的技术，从而使得需要多个训练样本的个体人脸子空间方法可以适用于单训练样本人脸识别问题。
(5)奇异值分解(singular value decomposition，简称SVD)
是一种有效的代数特征提取方法。由于奇异值特征在描述图像时是稳定的，且具有转置不变性、旋转不变性、位移不变性、镜像变换不变性等重要性质，因此奇异值特征可以作为图像的一种有效的代数特征描述。奇异值分解技术已经在图像数据压缩、信号处理和模式分析中得到了广泛应用。
综上，当智能手机的前置距离传感器感知人脸轮廓时，激活摄像头进行人脸追踪侦测，自动调整影像放大，获取人脸识别信息与预设的人脸识别模板进行分析匹配，确实是机主面部时，发送指令到电源开关键，自动接通开机通道，将智能手机电池电压转换为适合智能手机电路各部分使用的电压，供应给相应电源模块，当时钟电路得到供电电压后产生震动信号，送入逻辑电路，CPU在得到电压和时钟信号后执行开机程序，进行后续的开机操作。
参考图4，在一优选实施例中，S300：当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息的步骤包括：
于所述智能终端内，设定一语音信号；
当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的麦克风，检测是否输入所述语音信号；
当检测到输入所述语音信号时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息。
在该实施例中，将语音识别与面部识别技术结合，在智能终端内首先预设一语音信号，如“开机”，在智能终端处于关机状态时，所述前置距离传感器检测到人脸轮廓，此时，调用所述智能终端的麦克风，检测是否输入所述语音信号，即检测用户是否对智能终端说出“开机”二字，当检测到用户对对智能终端说出“开机”二字时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息。通过这种方式，只有在前置距离传感器检测到用户人脸轮廓且用户准确输入语音信号时，才激活摄像头，采集人脸识别信息，一方面可以节省智能终端的电量，有效防止用户的误操作，同时提高智能终端隐私信息的保密程度。
参考图5，在一优选实施例中，于所述智能终端内，设定一预设次数及预设时间；
在所述预设时间内，判断输入所述语音信号启动所述智能终端失败的次数是否超过所述预设次数；
在所述预设时间内，当输入所述语音信号启动所述智能终端失败的次数超过所述预设次数时，所述智能终端发出报警信号。
该实施例中，判断用户输入语音信号启动智能终端失败的次数是否超过预先设定的 次数，例如，预先设定的次数为三次，预先设定的次数可根据实际情况进行相应调整，也就是判断语音信号错误的次数是否超过预设的三次，如果判断的结果为是，则发出报警信号。
智能手机的开关机操作系统发出语音报警信号，例如“识别错误，请停止使用本手机”，同时可发送预警邮件给指定的邮箱，从而告知用户或主人该智能手机存在被入侵行为，以便及时采取措施，解决了按键容易老化导致灵敏度下降甚至失效、单一语音识别安全性能低和单一人脸识别处理数据量大的问题。
参考图6，本发明还公开了一种智能终端的启动控制系统100，包括预设模块11、检测模块12、采集模块13、匹配模块14、控制模块15；
所述预设模块11，于所述智能终端内，建立一人脸识别模板；
所述检测模块12，在所述智能终端处于关机状态时，调用所述智能终端的前置距离传感器，检测人脸轮廓；
所述采集模块13，与所述检测模块12通信连接，当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息；
所述匹配模块14，与所述预设模块11、采集模块13通信连接，将所述人脸识别信息与所述人脸识别模板进行匹配；
所述控制模块15，与所述匹配模块14通信连接，当所述人脸识别信息与所述人脸识别模板匹配时，发送一开机指令至设于所述智能终端内的开机检测电路，以控制启动所述智能终端。
在一优选实施例中，所述预设模块11包括模板获取单元、模板预设单元；
所述模板获取单元，在所述智能终端处于开机状态时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸图像；
所述模板预设单元，与所述模板获取单元通信连接，提取所述人脸图像的人脸特征信息，建立所述人脸识别模板。
在一优选实施例中，所述采集模块13包括活体检测单元、采集控制单元；
所述活体检测单元，调用所述智能终端的摄像头，采用活体检测手段，判断所述人脸识别信息的数据源是人体的活体数据源或照片、录像、面具的非活体数据源；
所述采集控制单元，当所述人脸识别信息的数据源是人体的活体数据源时，采集所述人脸识别信息；当所述人脸识别信息的数据源是照片、录像、面具的非活体数据源时，控制所述启动控制系统100关闭。
在一优选实施例中，所述采集模块13，包括信号预设单元、信号采集单元、信号控 制单元；
所述信号预设单元，于所述智能终端内，设定一语音信号；
所述信号采集单元，与所述信号预设单元通信连接，当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的麦克风，检测是否输入所述语音信号；
所述信号控制单元，与所述信号采集单元通信连接，当检测到输入所述语音信号时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息。
在一优选实施例中，所述信号预设单元，于所述智能终端内，设定一预设次数及预设时间；
所述信号采集单元，在所述预设时间内，判断输入所述语音信号启动所述智能终端失败的次数是否超过所述预设次数；
所述信号控制单元，在所述预设时间内，当输入所述语音信号启动所述智能终端失败的次数超过所述预设次数时，控制所述智能终端发出报警信号。
对于上述启动控制系统100实施例而言，由于其与方法实施例基本相似，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
应当注意的是，本发明的实施例有较佳的实施性，且并非对本发明作任何形式的限制，任何熟悉该领域的技术人员可能利用上述揭示的技术内容变更或修饰为等同的有效实施例，但凡未脱离本发明技术方案的内容，依据本发明的技术实质对以上实施例所作的任何修改或等同变化及修饰，均仍属于本发明技术方案的范围内。

Claims (10)

  1. 一种智能终端的启动控制方法，其特征在于，包括以下步骤：
    于所述智能终端内，建立一人脸识别模板；
    在所述智能终端处于关机状态时，调用所述智能终端的前置距离传感器，检测人脸轮廓；
    当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息；
    将所述人脸识别信息与所述人脸识别模板进行匹配；
    当所述人脸识别信息与所述人脸识别模板匹配时，发送一开机指令至设于所述智能终端内的开机检测电路，以控制启动所述智能终端。
  2. 如权利要求1所述的启动控制方法，其特征在于，
    于所述智能终端内，建立一人脸识别模板的步骤包括：
    在所述智能终端处于开机状态时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸图像；
    提取所述人脸图像的人脸特征信息，建立所述人脸识别模板。
  3. 如权利要求1所述的启动控制方法，其特征在于，
    当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息的步骤包括：
    调用所述智能终端的摄像头，采用活体检测手段，判断所述人脸轮廓的数据源是人体的活体数据源或照片、录像、面具的非活体数据源；
    当所述人脸轮廓的数据源是人体的活体数据源时，采集所述人脸识别信息；
    当所述人脸轮廓的数据源是照片、录像、面具的非活体数据源时，停止执行后续步骤。
  4. 如权利要求1所述的启动控制方法，其特征在于，
    当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息的步骤包括：
    于所述智能终端内，设定一语音信号；
    当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的麦克风，检测是否输入所述语音信号；
    当检测到输入所述语音信号时，调用所述智能终端的摄像头，获取所述摄像头采集的 人脸识别信息。
  5. 如权利要求4所述的启动控制方法，其特征在于，
    于所述智能终端内，设定一预设次数及预设时间；
    在所述预设时间内，判断输入所述语音信号启动所述智能终端失败的次数是否超过所述预设次数；
    在所述预设时间内，当输入所述语音信号启动所述智能终端失败的次数超过所述预设次数时，所述智能终端发出报警信号。
  6. 一种智能终端的启动控制系统，其特征在于，包括预设模块、检测模块、采集模块、匹配模块、控制模块；
    所述预设模块，于所述智能终端内，建立一人脸识别模板；
    所述检测模块，在所述智能终端处于关机状态时，调用所述智能终端的前置距离传感器，检测人脸轮廓；
    所述采集模块，与所述检测模块通信连接，当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息；
    所述匹配模块，与所述预设模块、采集模块通信连接，将所述人脸识别信息与所述人脸识别模板进行匹配；
    所述控制模块，与所述匹配模块通信连接，当所述人脸识别信息与所述人脸识别模板匹配时，发送一开机指令至设于所述智能终端内的开机检测电路，以控制启动所述智能终端。
  7. 如权利要求6所述的启动控制系统，其特征在于，
    所述预设模块包括模板获取单元、模板预设单元；
    所述模板获取单元，在所述智能终端处于开机状态时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸图像；
    所述模板预设单元，与所述模板获取单元通信连接，提取所述人脸图像的人脸特征信息，建立所述人脸识别模板。
  8. 如权利要求6所述的启动控制系统，其特征在于，
    所述采集模块包括活体检测单元、采集控制单元；
    所述活体检测单元，调用所述智能终端的摄像头，采用活体检测手段，判断所述人脸识别信息的数据源是人体的活体数据源或照片、录像、面具的非活体数据源；
    所述采集控制单元，当所述人脸识别信息的数据源是人体的活体数据源时，采集所述人脸识别信息；当所述人脸识别信息的数据源是照片、录像、面具的非活体数据源时， 控制所述启动控制系统关闭。
  9. 如权利要求6所述的启动控制系统，其特征在于，
    所述采集模块，包括信号预设单元、信号采集单元、信号控制单元；
    所述信号预设单元，于所述智能终端内，设定一语音信号；
    所述信号采集单元，与所述信号预设单元通信连接，当所述前置距离传感器检测到人脸轮廓时，调用所述智能终端的麦克风，检测是否输入所述语音信号；
    所述信号控制单元，与所述信号采集单元通信连接，当检测到输入所述语音信号时，调用所述智能终端的摄像头，获取所述摄像头采集的人脸识别信息。
  10. 如权利要求9所述的启动控制系统，其特征在于，
    所述信号预设单元，于所述智能终端内，设定一预设次数及预设时间；
    所述信号采集单元，在所述预设时间内，判断输入所述语音信号启动所述智能终端失败的次数是否超过所述预设次数；
    所述信号控制单元，在所述预设时间内，当输入所述语音信号启动所述智能终端失败的次数超过所述预设次数时，控制所述智能终端发出报警信号。
PCT/CN2017/101567 2017-09-13 2017-09-13 一种智能终端的启动控制方法及启动控制系统 WO2019051665A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2017/101567 WO2019051665A1 (zh) 2017-09-13 2017-09-13 一种智能终端的启动控制方法及启动控制系统
CN201780096728.0A CN111344701A (zh) 2017-09-13 2017-09-13 一种智能终端的启动控制方法及启动控制系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/101567 WO2019051665A1 (zh) 2017-09-13 2017-09-13 一种智能终端的启动控制方法及启动控制系统

Publications (1)

Publication Number Publication Date
WO2019051665A1 true WO2019051665A1 (zh) 2019-03-21

Family

ID=65723238

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/101567 WO2019051665A1 (zh) 2017-09-13 2017-09-13 一种智能终端的启动控制方法及启动控制系统

Country Status (2)

Country Link
CN (1) CN111344701A (zh)
WO (1) WO2019051665A1 (zh)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110732781A (zh) * 2019-11-19 2020-01-31 南京科仁电力科技有限公司 一种导线激光清障仪安全控制装置
CN112052731A (zh) * 2020-07-30 2020-12-08 广州市标准化研究院 一种智能人像识别打卡考勤系统及方法
CN112241663A (zh) * 2019-07-18 2021-01-19 上汽通用汽车有限公司 一种对多个车载资源进行调配的装置以及系统
CN112399140A (zh) * 2020-09-27 2021-02-23 平安信托有限责任公司 办公终端监控处理方法、装置、设备及存储介质
CN112447013A (zh) * 2020-11-13 2021-03-05 深圳市瑞意博医疗设备有限公司 一种多人取药的人脸跟踪智能识别装置
CN112733738A (zh) * 2021-01-12 2021-04-30 深圳市飞瑞斯科技有限公司 一种用于人脸识别数据比对的方法
CN113115116A (zh) * 2021-03-11 2021-07-13 广州朗国电子科技有限公司 一种通过人脸识别自动开机控制方法、装置及应用
CN113158834A (zh) * 2021-03-31 2021-07-23 中北大学南通智能光机电研究院 一种多感知的人脸识别魔方
CN113810505A (zh) * 2021-10-21 2021-12-17 上海德林威信息科技有限公司 一种用于人脸识别摄像头数据云端同步的系统及其使用方法
CN114187690A (zh) * 2021-11-30 2022-03-15 深圳市研锐智能科技有限公司 一种基于集控探针系统的企业网络安全保护装置
CN117428290A (zh) * 2023-12-15 2024-01-23 杭州三信网络技术有限公司 一种具有安全监测功能的焊机以及焊机的监测方法

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112836226B (zh) * 2021-02-07 2023-04-18 重庆满集网络科技有限公司 用于外勤业务员的任务管理系统及方法
CN113282900A (zh) * 2021-05-20 2021-08-20 读书郎教育科技有限公司 一种可解锁学生平板的智能台灯及方法
CN113436386A (zh) * 2021-06-24 2021-09-24 上海酒贝乐信息技术有限公司 一种智能售酒机用的人工智能系统
CN114344050A (zh) * 2022-01-20 2022-04-15 盐城市第一人民医院 一种智能骨科手术系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101393598A (zh) * 2007-09-21 2009-03-25 希姆通信息技术（上海）有限公司 利用手机摄像头对人脸识别来决定允许开机/解锁的方法
TW201344490A (zh) * 2012-04-27 2013-11-01 Chung Shan Inst Of Science 一種具有共同身分辨識之電腦開機方法及其系統
KR101362597B1 (ko) * 2007-03-19 2014-02-12 엘지전자 주식회사 사용자 인증기능을 갖는 이동통신단말기 및 그 사용자인증방법
CN104202483A (zh) * 2014-08-20 2014-12-10 厦门美图移动科技有限公司 移动终端的显示屏开关控制
CN204669463U (zh) * 2015-03-26 2015-09-23 咸阳师范学院 一种人脸识别加密的智能手机

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103973892B (zh) * 2014-05-12 2016-01-20 深圳市威富多媒体有限公司 一种基于语音及人脸识别的移动终端开关机的方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101362597B1 (ko) * 2007-03-19 2014-02-12 엘지전자 주식회사 사용자 인증기능을 갖는 이동통신단말기 및 그 사용자인증방법
CN101393598A (zh) * 2007-09-21 2009-03-25 希姆通信息技术（上海）有限公司 利用手机摄像头对人脸识别来决定允许开机/解锁的方法
TW201344490A (zh) * 2012-04-27 2013-11-01 Chung Shan Inst Of Science 一種具有共同身分辨識之電腦開機方法及其系統
CN104202483A (zh) * 2014-08-20 2014-12-10 厦门美图移动科技有限公司 移动终端的显示屏开关控制
CN204669463U (zh) * 2015-03-26 2015-09-23 咸阳师范学院 一种人脸识别加密的智能手机

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112241663B (zh) * 2019-07-18 2023-07-25 上汽通用汽车有限公司 一种对多个车载资源进行调配的装置以及系统
CN112241663A (zh) * 2019-07-18 2021-01-19 上汽通用汽车有限公司 一种对多个车载资源进行调配的装置以及系统
CN110732781A (zh) * 2019-11-19 2020-01-31 南京科仁电力科技有限公司 一种导线激光清障仪安全控制装置
CN112052731A (zh) * 2020-07-30 2020-12-08 广州市标准化研究院 一种智能人像识别打卡考勤系统及方法
CN112052731B (zh) * 2020-07-30 2024-03-29 广州市标准化研究院 一种智能人像识别打卡考勤系统及方法
CN112399140A (zh) * 2020-09-27 2021-02-23 平安信托有限责任公司 办公终端监控处理方法、装置、设备及存储介质
CN112447013A (zh) * 2020-11-13 2021-03-05 深圳市瑞意博医疗设备有限公司 一种多人取药的人脸跟踪智能识别装置
CN112733738A (zh) * 2021-01-12 2021-04-30 深圳市飞瑞斯科技有限公司 一种用于人脸识别数据比对的方法
CN113115116A (zh) * 2021-03-11 2021-07-13 广州朗国电子科技有限公司 一种通过人脸识别自动开机控制方法、装置及应用
CN113158834A (zh) * 2021-03-31 2021-07-23 中北大学南通智能光机电研究院 一种多感知的人脸识别魔方
CN113810505A (zh) * 2021-10-21 2021-12-17 上海德林威信息科技有限公司 一种用于人脸识别摄像头数据云端同步的系统及其使用方法
CN114187690A (zh) * 2021-11-30 2022-03-15 深圳市研锐智能科技有限公司 一种基于集控探针系统的企业网络安全保护装置
CN117428290A (zh) * 2023-12-15 2024-01-23 杭州三信网络技术有限公司 一种具有安全监测功能的焊机以及焊机的监测方法
CN117428290B (zh) * 2023-12-15 2024-03-15 杭州三信网络技术有限公司 一种具有安全监测功能的焊机以及焊机的监测方法

Also Published As

Publication number Publication date
CN111344701A (zh) 2020-06-26

Similar Documents

Publication Publication Date Title
WO2019051665A1 (zh) 一种智能终端的启动控制方法及启动控制系统
US11288504B2 (en) Iris liveness detection for mobile devices
Ma et al. Iris recognition based on multichannel Gabor filtering
US9613200B2 (en) Ear biometric capture, authentication, and identification method and system
Tao et al. Biometric authentication system on mobile personal devices
Kak et al. A review of person recognition based on face model
KR101185525B1 (ko) 서포트 벡터 머신 및 얼굴 인식에 기초한 자동 생체 식별
WO2019051777A1 (zh) 一种基于智能终端的提醒方法和提醒系统
Kepenekci et al. Occluded face recognition based on Gabor wavelets
Arora Real time application of face recognition concept
Bagherian et al. Facial feature extraction for face recognition: a review
Olivares-Mercado et al. Face recognition system for smartphone based on lbp
WO2019090503A1 (zh) 一种智能终端的图像拍摄方法及图像拍摄系统
Boodoo et al. Robust multi biometric recognition using face and ear images
Zhang et al. Fusion of face and iris biometrics on mobile devices using near-infrared images
Dwivedi et al. A new hybrid approach on face detection and recognition
Sutoyo et al. Unlock screen application design using face expression on android smartphone
CN111880848A (zh) 一种操作系统的切换方法、装置、终端以及可读存储介质
Olufade et al. Biometric authentication with face recognition using principal component analysis and feature based technique
Odinokikh et al. Iris feature extraction and matching method for mobile biometric applications
Wei Unconstrained face recognition with occlusions
Peng et al. A software framework for PCa-based face recognition
Patil et al. Iris recognition using fuzzy system
Adebayo et al. Combating Terrorism with Biometric Authentication Using Face Recognition
Castellanos et al. An Approach to Improve Mouth-State Detection to Support the ICAO Biometric Standard for Face Image Validation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17925270

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17925270

Country of ref document: EP

Kind code of ref document: A1