CN112101275A

CN112101275A - Human face detection method, device, equipment and medium for multi-view camera

Info

Publication number: CN112101275A
Application number: CN202011016048.3A
Authority: CN
Inventors: 姚志强; 周曦; 陈福财; 肖春林; 朱鹏; 刘林赟
Original assignee: Guangzhou Yunconghonghuang Intelligent Technology Co Ltd
Current assignee: Guangzhou Yunconghonghuang Intelligent Technology Co Ltd
Priority date: 2020-09-24
Filing date: 2020-09-24
Publication date: 2020-12-18
Anticipated expiration: 2040-09-24
Also published as: CN112101275B

Abstract

The invention provides a face detection method, a face detection device, face detection equipment and a face detection medium for a multi-view camera, wherein the face detection method, the face detection device, the face detection equipment and the face detection medium comprise the following steps: acquiring at least two images of a target object acquired under the same or different illumination conditions by using a multi-view camera; acquiring the position of a first face frame of the target object in any one of the images; and mapping the position of the first face frame into another image to form a second face frame, and adjusting the position and the size of the second face frame according to the face characteristic point in the other image. The invention not only greatly reduces the calculation amount of face detection, but also is beneficial to embedding or transplanting the face detection mode to various platforms, thereby expanding the application range of the face detection mode.

Description

Human face detection method, device, equipment and medium for multi-view camera

Technical Field

The invention relates to the technical field of image processing, in particular to a human face detection method, a human face detection device, human face detection equipment and a human face detection medium for a multi-view camera.

Background

With the continuous updating of security technologies, face recognition technologies are also more and more widely applied in life. Especially in government departments, face access control, gate machines and financial industries, the intelligent security monitoring function irreplaceable to the security protection is provided.

However, in the process of recognizing the human face, the human face detection module is a time-consuming module. The face detection method of the existing multi-view camera at least needs to carry out face detection on two paths of images, compared with a monocular camera, the face detection method of the multi-view camera greatly increases the calculated amount, and meanwhile, the huge calculated amount enables the face detection method of the multi-view camera not to be transplanted to an embedded platform or causes the phenomenon that the face detection method of the multi-view camera is stuck after being transplanted to affect normal use.

Disclosure of Invention

In view of the above drawbacks of the prior art, an object of the present invention is to provide a method, an apparatus, a device and a medium for detecting a face of a multi-view camera, which are used to solve the problem of a large amount of calculation caused by a face detection method of a multi-view camera in the prior art.

In order to achieve the above and other related objects, the present invention provides a face detection method for a multi-view camera, comprising the following steps:

acquiring at least two images of a target object acquired under the same or different illumination conditions by using a binocular camera or a multi-view camera;

acquiring the position of a first face frame of the target object in any one of the images;

and mapping the position of the first face frame into another image to form a second face frame, and adjusting the position and the size of the second face frame according to the face characteristic point in the other image.

The invention also provides a face detection device of the multi-view camera, which comprises:

the acquisition module acquires at least two images of a target object acquired under the same or different illumination conditions by using the multi-view camera;

the acquisition module is used for acquiring the position of a first face frame of the target object in any one of the images;

and the mapping adjustment module is used for mapping the position of the first face frame into another image to form a second face frame, and adjusting the position and the size of the second face frame according to the face characteristic point in the other image.

The present invention also provides an apparatus comprising:

one or more processors; and

one or more machine-readable media having instructions stored thereon that, when executed by the one or more processors, cause the apparatus to perform a method as described in one or more of the above.

The present invention also provides one or more machine-readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform the methods as described in one or more of the above.

As described above, the face detection method, device, equipment and medium for a multi-view camera provided by the invention have the following beneficial effects:

when the multi-view camera carries out face detection, a first face frame in any image is obtained, the first face frame is mapped to another image or other images to form a second face frame, and the position and the size of the second face frame are adjusted according to face characteristic points in the another image or other images until the second face frame frames each face characteristic point. The invention not only greatly reduces the calculation amount of face detection, but also is beneficial to embedding or transplanting the face detection mode to various platforms, thereby expanding the application range of the face detection mode.

Drawings

Fig. 1 is a schematic flow chart of a face detection method of a multi-view camera according to an embodiment;

fig. 2 is a schematic flow chart of a face detection method of a multi-view camera according to another embodiment;

fig. 3 is a schematic flowchart of step S3 in the face detection method of the multi-view camera according to an embodiment;

fig. 4 is a schematic hardware structure diagram of a face detection apparatus of a multi-view camera according to an embodiment;

fig. 5 is a schematic diagram of a hardware structure of a face detection apparatus of a multi-view camera according to another embodiment;

fig. 6 is a schematic diagram of a hardware structure of an adjustment module in the face detection apparatus of the multi-view camera according to an embodiment;

fig. 7 is a flowchart of a conventional binocular camera face detection method according to an embodiment;

fig. 8 is a flowchart of a binocular camera face detection method according to an embodiment of the present invention;

fig. 9 is a schematic hardware structure diagram of a terminal device according to an embodiment;

fig. 10 is a schematic diagram of a hardware structure of a terminal device according to another embodiment.

Element number description:

0 correction module

1 acquisition Module

2 acquisition module

3 mapping adjustment module

31 first adjusting unit

32 calculation unit

33 second adjusting unit

1100 input device

1101 first processor

1102 output device

1103 first memory

1104 communication bus

1200 processing assembly

1201 second processor

1202 second memory

1203 communication assembly

1204 Power supply Assembly

1205 multimedia assembly

1206 voice assembly

1207 input/output interface

1208 sensor assembly

Detailed Description

The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.

It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.

In the related technologies in the field, with the continuous updating of security technologies, the face recognition technology is applied more and more widely in life. Especially in government departments, face access control, gate machines and financial industries, the intelligent security monitoring function irreplaceable to the security protection is provided. The face recognition technology is mature day by day, the commercial application is wider, however, in the process of recognizing the face, the face detection module is a module which consumes more time. The face detection method of the existing multi-view camera at least needs to carry out face detection on two paths of images, compared with a monocular camera, the face detection method of the multi-view camera greatly increases the calculated amount, and meanwhile, the huge calculated amount enables the face detection method of the multi-view camera not to be transplanted to an embedded platform or causes the phenomenon that the face detection method of the multi-view camera is stuck after being transplanted to affect normal use.

Based on the problems existing in the above schemes, the invention discloses a face detection method of a multi-view camera, a face detection device of the multi-view camera, an electronic device and a storage medium.

Near infrared image, an image formed by a remote sensor receiving the reflected or radiated near infrared spectrum of a target object.

The human face feature points are also called human face landmark points, and a plurality of mark points are drawn on the face, the mark points are generally drawn at key positions such as edges, corners, contours, intersections, equal parts and the like, the shapes of the human faces can be described by means of the mark points, and the aligned human faces can be obtained after twisting, stretching and zooming.

The method comprises the steps of living body detection and living body identification, wherein the living body detection is a method for determining the real physiological characteristics of an object in some identity verification scenes, and in the application of face identification, the living body detection can verify whether a user operates for the real living body by combining actions of blinking, mouth opening, head shaking, head pointing and the like by using techniques of face characteristic point positioning, face tracking and the like. Can effectively resist common attack means such as photos, face changing, masks, sheltering, screen copying and the like, thereby helping users to discriminate fraudulent behaviors and ensuring the benefits of users

Referring to fig. 1, the present invention provides a face detection method for a multi-view camera, which includes the following steps:

step S1, acquiring at least two images of a target object collected under the same or different illumination conditions by using a multi-view camera;

taking a binocular camera as an example, when the binocular camera is used for collecting two images, wherein one image is a color image generated under the condition of natural light or white light; the other image is a near-infrared image generated under a near-infrared light condition; or, one of the images is a near-infrared image generated under a near-infrared light condition, and one of the images is a color image generated under a natural light or white light condition. The binocular camera face detection mode in the scene is mainly applied to living body detection, and whether an acquired target object is a living body or not is judged according to a detected face image.

It should be noted that, when the multi-view camera shoots the target object under the same illumination condition, at least two images are obtained, and the number of the cameras in the used camera module is increased, so that the obtained images are correspondingly increased. For example, at present, in order to improve the photographing effect, a terminal such as a smart phone or a smart tablet has three cameras, four cameras or five cameras installed on the back of the terminal. Therefore, the present application can be widely applied to photographing a target object (person).

Step S2, acquiring the position of a first face frame of the target object in any one of the images;

the number of the first face frame and the number of the second face frame are the same and are at least one, when one image has a plurality of faces (main bodies), the corresponding another image definitely also has a plurality of faces, and therefore the number of the first face frame and the number of the second face frame are the same and are all a plurality.

Specifically, the first face frame and the second face frame may be circular, oval, or rectangular, which is not limited herein.

Step S3, mapping the position of the first face frame into another image to form a second face frame, and adjusting the position and size of the second face frame according to the face feature point in another image;

specifically, the position and size of the second face frame are adjusted according to the face feature points in another image until the second face frame frames all the face feature points.

In this embodiment, when the multi-view camera performs face detection, a first face frame in any image is obtained, the first face frame is mapped to another image or images to form a second face frame, and the position and size of the second face frame are adjusted according to face feature points in the another image or images until the second face frame frames each of the face feature points. The method not only greatly reduces the calculated amount of face detection, but also is beneficial to embedding or transplanting face detection modes into various platforms, and enlarges the application range of the method.

In another embodiment, the adaboost algorithm is used to detect the position of the first face frame of the target object in any of the images.

Specifically, the detection of the face region may adopt a feature-based face detection method, a template matching method, and an adaboost algorithm. The face detection method based on the characteristics comprises an overall contour method, a skin color detection method and an organ distribution method; the template matching method includes a mosaic method (also called mosaic method), a predetermined template matching method, and a deformed template method.

The face detection algorithm based on skin color has high encounter rate, misjudgment is easily generated on non-face skin color areas (hands, feet, neck and the like) and skin color areas in the background, and meanwhile, the algorithm has poor robustness due to a single fixed threshold value and is not suitable for environments with changed external factors such as illumination, shadow and the like, so that the algorithm is limited and can only be applied to skin color detection under a simple background.

The face detection algorithm based on the Gabor + BP neural network has the advantages of being simple to understand, strong in learning capacity, small in calculated amount and strong in anti-noise capacity, accuracy can be improved by expanding a training sample set, but the face detection algorithm has the problems that the convergence speed is low due to long training time, the learning efficiency is low, the selection of the number of middle layers and the number of nodes of each middle layer is not guided by theory, and old samples cannot be well remembered while new samples are learned.

Compared with other face detection algorithms, the face detection algorithm based on adaboost has higher robustness on the face with a certain rotation angle and illumination change of people with different skin colors, and is high in detection rate and low in false detection rate. Therefore, in the present embodiment, it is preferable to perform face region detection using the adaboost algorithm.

In this embodiment, adaboost is an iterative method, and the core idea is to train the same weak classifier for different training sets, and then to assemble the weak classifiers obtained on different training sets to form a final strong classifier.

Based on the features, the Adaboost learning algorithm is adopted, the Adaboost algorithm is used for selecting some rectangular features (weak classifiers) which can represent the human face most in the human face detection process, the weak classifiers are constructed into a strong classifier according to a weighted voting mode, and then a plurality of strong classifiers obtained through training are connected in series to form a cascade-structured cascade classifier, so that the detection speed of the classifier is effectively improved.

In an exemplary embodiment, please refer to fig. 2, which is a flowchart of a face detection method of a multi-view camera according to another embodiment of the present invention, and the difference from fig. 1 is that before step S1, the method further includes:

and step S0, correcting the internal and external parameters configured by the multi-view camera.

Specifically, the multi-view camera is corrected by configuring internal and external parameters of the camera, wherein the internal and external parameters can be one or more of definition, resolution and brightness; the definition refers to the definition of each detail shadow and the boundary thereof on the image; the resolution refers to the precision of the screen image; the brightness is the brightness of the picture.

For another example, when an image is acquired under the same lighting condition, the internal and external parameters of the camera may further include level correction, automatic white balance, color restoration, automatic exposure, gamma correction, demosaicing, RGB2YUV, noise reduction, and the like, so that the image signal in the Bayer RAW format obtained by the RGB camera can be restored to a photosensitive image closer to the current real environment.

In the present embodiment, the error between the collected multiple images is made extremely small through step S0, which facilitates the reduction of the error in the image mapping of the subsequent face frame, and at the same time, the color image generated even under natural light or white light conditions; and the near-infrared image generated under the near-infrared light condition, and the two images obtained by adopting the method have only a tiny pixel error.

In an exemplary embodiment, please refer to fig. 3, which is a flowchart of a face detection method of a multi-view camera according to another embodiment of the present invention, further including:

step S30, mapping the position of the first face frame to another image to form a second face frame;

wherein, because the pixel error between the images is very small, a second face frame is formed by mapping the position and size of the first face frame in one image to another or other images.

Step S31, increasing the framing area of the second face frame according to the position of the face feature point of the other image according to the preconfigured parameters to form an increased second face frame, or decreasing the framing area of the second face frame according to the position of the face feature point of the other image according to the preconfigured parameters to form a decreased second face frame.

When the images are mapped from one image to another image or other images to form a second face frame according to the hardware difference of the cameras, a face frame drift phenomenon (that is, the error of the face frame obtained by mapping is large) may occur, so that the second face frame cannot cover all face feature points in the images, therefore, according to the position coordinates of the face feature points of the other image, the framing area of the second face frame needs to be increased according to the preset parameters to form the expanded second face frame, for example, the second face frame is expanded from the upper direction, the lower direction, the left direction and the right direction by 5-20% in amplitude.

For example, the position coordinates of the left corner of the left eye are compared with the left frame of the face frame, the position coordinates of the right corner of the right eye are compared with the right frame of the face frame, the position coordinates corresponding to the highest position of the eyebrows are compared with the upper frame of the face frame, the position coordinates corresponding to the lowest position of the lower lip of the mouth are compared with the lower frame of the face frame, and the second face frame is expanded in the above manner only if any one of the face feature points is not in the face frame.

Of course, another extreme case may also occur, where the difference between the images of the same subject is large, the first face frame may frame the face feature points, the second face frame obtained by mapping in another or other images may also frame the face feature points, and the area framed by the second face frame in the image is too large, then the framed area of the second face frame is reduced according to the position coordinates of the face feature points of another image according to the pre-configured parameters to form a reduced second face frame, for example, the second face frame is reduced by 5-10% in the up, down, left, and right directions.

The second face frame can accurately frame the face feature points, and the detection precision of the face frame is improved.

Step S32, calculating facial feature points framed by the second facial frame after the image is amplified or reduced, and confidence degrees corresponding to the facial feature points; calculating the distance from each face characteristic point to an average position; and removing the one or more face characteristic points with the largest distance, calculating a surrounding frame of the face characteristic points which are remained after removal, and regarding the surrounding frame as an adjusted second face frame.

Specifically, 68 feature points of the face are obtained by using a face feature point detection module, wherein the positions of the face feature points in the face frame are accurately positioned by calculating the face feature points in another or other images, so that the position of a second face frame can be adjusted subsequently, whether the face feature points are disturbed or not can be judged by subsequent detection, and meanwhile, living body detection can be realized by comparing the confidence degrees corresponding to the face feature points, particularly when the face of a binocular camera is detected, with a preset confidence degree threshold value.

Specifically, the method effectively avoids the disturbance image of a certain wrong face characteristic point in the face characteristic points, and improves the precision of framing the face characteristic points by the second face frame. Meanwhile, redundant outlines of the frames in the second face frame can be effectively reduced, and the face characteristic points can be accurately framed.

In this embodiment, since the facial feature points at least include the facial contour features of the outer contour, the left eye, the right eye, the nose, and the mouth, the steps S30 to S32 are adopted, on one hand, the calculated amount of the face detection is greatly reduced, which is beneficial to embedding or transplanting the face detection mode into various platforms, and the application range is expanded; on the other hand, the detection precision and the detection range of the face frame are also improved.

On the basis of the embodiment, when the face characteristic points only comprise five characteristic points including a left eye, a right eye, a nose and a mouth, the following steps are adopted to perform outward expansion of the bounding box, so that the framed face frame is bounded with contour characteristics, and the face frame can be detected more intuitively and beautifully.

And step S33, expanding the surrounding frame according to a preset proportion to form an adjusted second face frame.

In other embodiments, taking a binocular camera as an example, in a conventional face detection process, as shown in fig. 7, face detection and face feature point detection are performed on a color image and a near-infrared image respectively, so as to obtain a face frame and face feature points correspondingly.

In this embodiment, the human face can be obtained by using the human face detection on the near-infrared image, but because the existing human face detection algorithms are all neural networks with deep network layers, more neural weights, huge floating point calculation quantity and large time consumption, real-time processing cannot be achieved even if the neural networks are executed on an embedded chip, and industrialization is difficult, the calculation amount of the human face detection is greatly increased.

In other embodiments, as shown in fig. 8, the face detection method implemented by the present invention maps a first face frame into another or other images using a space to form a second face frame, and performs fast secondary face detection by re-estimating after searching for feature points in the second face frame, and uses a low computation to replace high computation face detection by using a feature of a binocular module with a small difference in image space.

In the embodiment, for the whole system platform, the calculation amount is greatly reduced, and the time of in-vivo detection is reduced, so that the method and the system are conveniently popularized and applied on an embedded platform.

Referring to fig. 4, a face detection device of a multi-view camera provided by the present invention includes:

the system comprises an acquisition module 1, a display module and a control module, wherein the acquisition module is used for acquiring at least two images of a target object acquired under the same or different illumination conditions by using a multi-view camera;

the acquisition module 2 is used for acquiring the position of a first face frame of the target object in any one of the images;

and detecting the first image by using an adaboost algorithm, and acquiring the position of a first face frame in the first image.

And the mapping adjustment module 3 is configured to map the position of the first face frame into another image to form a second face frame, and adjust the position and size of the second face frame according to a face feature point in the another image.

In an exemplary embodiment, one of the images is a color image produced under natural or white light conditions; another of the images is a near infrared image generated under a near infrared light condition.

In an exemplary embodiment, the number of the first face frame and the second face frame is the same and is at least one.

In an exemplary embodiment, the first image is a color image generated under natural or white light conditions; the second image is a near-infrared image generated under a near-infrared light condition.

In an exemplary embodiment, please refer to fig. 5, which is a schematic diagram of a hardware structure of a face detection apparatus of a multi-view camera according to another embodiment of the present invention, and on the basis of fig. 4, the face detection apparatus further includes:

and the correction module 0 is used for correcting the internal and external parameters configured by the multi-view camera.

In an exemplary embodiment, please refer to fig. 6, which is a schematic diagram of a hardware structure of an adjustment module in a face detection apparatus of a multi-view camera according to an embodiment of the present invention, including:

a mapping unit 30, configured to map the position of the first face frame into another image to form a second face frame;

a first adjusting unit 31, configured to increase the framing area of the second face frame according to a preconfigured parameter according to the position of the face feature point of the other image to form an expanded second face frame, or decrease the framing area of the second face frame according to a preconfigured parameter according to the position of the face feature point of the other image to form a reduced second face frame.

A calculating unit 32, configured to calculate facial feature points framed by the second face frame after being amplified or reduced on another image, and confidence degrees corresponding to the respective facial feature points; the average position of all human face characteristic points in the second human face frame after amplification or reduction is calculated; calculating the distances from all the human face characteristic points to an average position; and removing the one or more human face characteristic points with the largest distance, and calculating the surrounding frame of the human face characteristic points left after removal as the adjusted second human face frame.

Specifically, the face feature points at least include an outer contour, a left eye, a right eye, a nose, and a mouth, and the adjusted second face frame can be obtained by means of the second adjusting unit.

In other embodiments, if the face feature points include only left eye, right eye, nose, and mouth, the third adjusting unit is used on the basis of the second adjusting unit to obtain the adjusted second face frame.

And the second adjusting unit 33 is configured to expand the bounding box to form an adjusted second face frame according to a preset ratio.

In this embodiment, the face detection device of the multi-view camera and the face detection method of the multi-view camera are in a one-to-one correspondence, and please refer to the above embodiment for details of technical details, technical functions, and technical effects, which are not described herein any more.

In summary, the present invention provides a face detection apparatus for a multi-view camera, which obtains a first face frame in any one of images when the multi-view camera performs face detection, maps the first face frame to another image or another image to form a second face frame, and adjusts a position and a size of the second face frame according to a face feature point in the another image or another image until the second face frame frames each of the face feature points. The invention not only greatly reduces the calculation amount of face detection, but also is beneficial to embedding or transplanting the face detection mode to various platforms, thereby expanding the application range of the face detection mode.

An embodiment of the present application further provides an apparatus, which may include: one or more processors; and one or more machine readable media having instructions stored thereon that, when executed by the one or more processors, cause the apparatus to perform the method of fig. 1. In practical applications, the device may be used as a terminal device, and may also be used as a server, where examples of the terminal device may include: the mobile terminal includes a smart phone, a tablet computer, an electronic book reader, an MP3 (Moving Picture Experts Group Audio Layer III) player, an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop, a vehicle-mounted computer, a desktop computer, a set-top box, an intelligent television, a wearable device, and the like.

Embodiments of the present application also provide a non-transitory readable storage medium, where one or more modules (programs) are stored in the storage medium, and when the one or more modules are applied to a device, the device may execute instructions (instructions) included in the method in fig. 1 according to the embodiments of the present application.

Fig. 9 is a schematic diagram of a hardware structure of a terminal device according to an embodiment of the present application. As shown in fig. 9, the terminal device may include: an input device 1100, a first processor 1101, an output device 1102, a first memory 1103, and at least one communication bus 1104. The communication bus 1104 is used to implement communication connections between the elements. The first memory 1103 may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and the first memory 1103 may store various programs for performing various processing functions and implementing the method steps of the present embodiment.

Alternatively, the first processor 1101 may be, for example, a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, and the first processor 1101 is coupled to the input device 1100 and the output device 1102 through a wired or wireless connection.

Optionally, the input device 1100 may include a variety of input devices, such as at least one of a user-oriented user interface, a device-oriented device interface, a software programmable interface, a camera, and a sensor. Optionally, the device interface facing the device may be a wired interface for data transmission between devices, or may be a hardware plug-in interface (e.g., a USB interface, a serial port, etc.) for data transmission between devices; optionally, the user-facing user interface may be, for example, a user-facing control key, a voice input device for receiving voice input, and a touch sensing device (e.g., a touch screen with a touch sensing function, a touch pad, etc.) for receiving user touch input; optionally, the programmable interface of the software may be, for example, an entry for a user to edit or modify a program, such as an input pin interface or an input interface of a chip; the output devices 1102 may include output devices such as a display, audio, and the like.

In this embodiment, the processor of the terminal device includes a function for executing each module of the speech recognition apparatus in each device, and specific functions and technical effects may refer to the above embodiments, which are not described herein again.

Fig. 10 is a schematic hardware structure diagram of a terminal device according to an embodiment of the present application. FIG. 10 is a specific embodiment of the implementation of FIG. 9. As shown, the terminal device of the present embodiment may include a second processor 1201 and a second memory 1202.

The second processor 1201 executes the computer program code stored in the second memory 1202 to implement the method described in fig. 1 in the above embodiment.

The second memory 1202 is configured to store various types of data to support operations at the terminal device. Examples of such data include instructions for any application or method operating on the terminal device, such as messages, pictures, videos, and so forth. The second memory 1202 may include a Random Access Memory (RAM) and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

Optionally, a second processor 1201 is provided in the processing assembly 1200. The terminal device may further include: communication component 1203, power component 1204, multimedia component 1205, speech component 1206, input/output interfaces 1207, and/or sensor component 1208. The specific components included in the terminal device are set according to actual requirements, which is not limited in this embodiment.

The processing component 1200 generally controls the overall operation of the terminal device. The processing assembly 1200 may include one or more second processors 1201 to execute instructions to perform all or part of the steps of the data processing method described above. Further, the processing component 1200 can include one or more modules that facilitate interaction between the processing component 1200 and other components. For example, the processing component 1200 can include a multimedia module to facilitate interaction between the multimedia component 1205 and the processing component 1200.

The power supply component 1204 provides power to the various components of the terminal device. The power components 1204 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the terminal device.

The multimedia components 1205 include a display screen that provides an output interface between the terminal device and the user. In some embodiments, the display screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the display screen includes a touch panel, the display screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

The voice component 1206 is configured to output and/or input voice signals. For example, the voice component 1206 includes a Microphone (MIC) configured to receive external voice signals when the terminal device is in an operational mode, such as a voice recognition mode. The received speech signal may further be stored in the second memory 1202 or transmitted via the communication component 1203. In some embodiments, the speech component 1206 further comprises a speaker for outputting speech signals.

The input/output interface 1207 provides an interface between the processing component 1200 and peripheral interface modules, which may be click wheels, buttons, etc. These buttons may include, but are not limited to: a volume button, a start button, and a lock button.

The sensor component 1208 includes one or more sensors for providing various aspects of status assessment for the terminal device. For example, the sensor component 1208 may detect an open/closed state of the terminal device, relative positioning of the components, presence or absence of user contact with the terminal device. The sensor assembly 1208 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact, including detecting the distance between the user and the terminal device. In some embodiments, the sensor assembly 1208 may also include a camera or the like.

The communication component 1203 is configured to facilitate communications between the terminal device and other devices in a wired or wireless manner. The terminal device may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In one embodiment, the terminal device may include a SIM card slot therein for inserting a SIM card therein, so that the terminal device may log onto a GPRS network to establish communication with the server via the internet.

As can be seen from the above, the communication component 1203, the voice component 1206, the input/output interface 1207 and the sensor component 1208 involved in the embodiment of fig. 10 can be implemented as the input device in the embodiment of fig. 9.

The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.

Claims

1. A face detection method of a multi-view camera is characterized by comprising the following steps:

acquiring at least two images of a target object acquired under the same or different illumination conditions by using a multi-view camera;

2. The method for detecting a face of a multi-view camera according to claim 1, wherein the step of adjusting the position and size of the second face frame according to the face feature point in the other image comprises: and increasing the framing area of the second face frame according to the position of the face characteristic point of the other image and the preset parameters to form an expanded second face frame, or decreasing the framing area of the second face frame according to the position of the face characteristic point of the other image and the preset parameters to form a reduced second face frame.

3. The face detection method of the multi-view camera according to claim 2, further comprising: calculating a face characteristic point framed by a second face frame after the amplification or reduction in another image and a confidence corresponding to each face characteristic point, wherein the confidence is used for detecting whether a face provider is a living body; calculating the average position of all human face characteristic points in the amplified or reduced second human face frame; calculating the distance from each face characteristic point to an average position; and removing the one or more face characteristic points with the largest distance, calculating a surrounding frame of the face characteristic points which are remained after removal, and regarding the surrounding frame as an adjusted second face frame.

4. The face detection method of the multi-view camera according to claim 3, further comprising: and expanding the surrounding frame according to a preset proportion to form an adjusted second face frame.

5. The face detection method of a multi-view camera according to claim 1, wherein one of the images is a color image generated under natural light or white light; another of the images is a near infrared image generated under a near infrared light condition.

6. The method for detecting the human face of the multi-view camera according to claim 1, wherein the number of the first human face frame is the same as that of the second human face frame, and the number of the first human face frame is at least one.

7. The face detection method of the multi-view camera according to claim 1, further comprising: and adjusting the position and the size of the second face frame according to the face characteristic points in the other image until the second face frame frames all the face characteristic points.

8. The method for detecting human face with multi-view camera according to claim 1, wherein the human face feature points at least comprise outer contour, left eye, right eye, nose, mouth.

9. The utility model provides a face detection device of many meshes camera which characterized in that includes:

10. The face detection device of the multi-view camera according to claim 9, wherein the first image is a color image generated under natural light or white light; the second image is a near-infrared image generated under a near-infrared light condition.

11. The face detection device of a multi-view camera according to claim 9, wherein the adjusting module further comprises: and the first adjusting unit is used for increasing the framing area of the second face frame according to the position of the face characteristic point of the other image according to a preset parameter to form an expanded second face frame, or reducing the framing area of the second face frame according to the position of the face characteristic point of the other image according to a preset parameter to form a reduced second face frame.

12. The face detection device of a multi-view camera of claim 11, wherein the adjusting module further comprises: a calculating unit, configured to calculate face feature points framed by the second face frame after the second image is amplified or reduced, and confidence degrees corresponding to the face feature points; the average position of all human face characteristic points in the second human face frame after amplification or reduction is calculated; calculating the distances from all the human face characteristic points to an average position; and removing the one or more face characteristic points with the largest distance, calculating a surrounding frame of the face characteristic points which are remained after removal, and regarding the surrounding frame as an adjusted second face frame.

13. The face detection device of a multi-view camera according to claim 12, further comprising: and the second adjusting unit is used for expanding the surrounding frame to form an adjusted second face frame according to a preset proportion.

14. An apparatus, comprising:

one or more processors; and

one or more machine-readable media having instructions stored thereon that, when executed by the one or more processors, cause the apparatus to perform the method recited by one or more of claims 1-8.

15. One or more machine-readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform the method recited by one or more of claims 1-8.