CN107239736A - Method for detecting human face and detection means based on multitask concatenated convolutional neutral net - Google Patents
Method for detecting human face and detection means based on multitask concatenated convolutional neutral net Download PDFInfo
- Publication number
- CN107239736A CN107239736A CN201710291289.0A CN201710291289A CN107239736A CN 107239736 A CN107239736 A CN 107239736A CN 201710291289 A CN201710291289 A CN 201710291289A CN 107239736 A CN107239736 A CN 107239736A
- Authority
- CN
- China
- Prior art keywords
- face
- neural networks
- convolutional neural
- sample
- multistage
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Abstract
The invention discloses a kind of method for detecting human face based on multitask concatenated convolutional neutral net and detection means, this method includes：Set up the multistage convolutional neural networks of cascade；The study of the task of multistage convolutional neural networks progress face classification, the recurrence of human face region position and the crucial point location of face is trained as training sample using face positive sample, face negative sample, part face and face key point sample；Face datection is carried out to image to be detected using the multistage convolutional neural networks trained；Wherein, in the training stage, while the face negative sample for combining to excavate hardly possible using online mode and offline two ways is as training sample.Multistage convolutional neural networks of the invention based on cascade, it can learn to the stronger feature of robustness, simultaneously by the way of two kinds of online mode and offline mode excavate difficult negative sample, the classification capacity of network can be improved, so as to improve the detectability and accuracy rate of network, and ensure the speed of service of this method in actual product.
Description
Technical field
The present invention relates to Face datection field, especially, it is related to a kind of people based on multitask concatenated convolutional neutral net
Face detecting method and detection means.
Background technology
Face datection (face detection) technology is all face correlation techniques (recognition of face, face alignment, face
Crucial point prediction of Expression Recognition, face etc.) basis.As human face detection tech is applied in increasing scene, especially
In the monitors environment of the non-cooperation of user, face yardstick, angle and light conditions change very greatly, this precision and speed to Face datection
Degree requires also more and more higher.
Deep learning (deep learning) technology has no the difference of essence with artificial neural network in those early years, from
From 2012, the increase of data and the enhancing of computing capability are benefited from, depth learning technology is rapidly developed.Convolutional Neural
Network (Convolutional neural networks, CNN) is one kind of deep learning network, in image domains, CNN side
Method has the raising of matter than conventional method in the ability for solving various problems.
Method for detecting human face was divided into two classes according to whether using deep learning method in recent years, not using deep learning method
Algorithm effect it is relatively good have joint cascade face detection and align (JDA) and Normalized
Pixel Difference(NPD).JDA methods combine Face datection and face critical point detection, are compared using one kind
Simple pixel difference feature and random forest method realize algorithm frame.Because feature is fairly simple, Shandong of the algorithm to illumination
Rod is poor, and in the case where backlight, uneven illumination are even, the effect of Face datection is poor.NPD methods and the overall frame of JDA methods
Frame is similar, and difference essentially consists in NPD and carried out normalized to pixel difference feature, has preferable improvement to backlight situation.
The algorithm detects effect on authoritative Face datection data set FDDB (Face Detection Data Set and Benchmark)
Fruit is slightly poorer than JDA, and JDA methods are slower than in speed.
Both the above detection algorithm is best one of several of effect in conventional method (not using deep learning), compares depth
Recall rate will low 5 to 10 points in the case of flase drop number identical for the Face datection algorithm of learning method.It is described below several
The relatively good deep learning face algorithm of effect.Face Detection with the Faster R-CNN are by vgg networks (16
Layer) and Faster R-CNN frame applications to Face datection, another method Boost strapping Face Detection
With hard Negative Examples are even more by 50 layers of residual error network application into Face datection.Although these methods
Good effect is achieved, but is due to that model file is too big, speed is too slow, basic is difficult to be used in actual product.
Conventional method monitors environment out of doors, the recall rate to face is inadequate.And the algorithm based on deep learning, use
Network is too deep, and model file is larger, and computational complexity is too high, it is difficult to be disposed in actual product.
The content of the invention
The invention provides a kind of method for detecting human face based on multitask concatenated convolutional neutral net and detection means, with
Solve the technical problem for being difficult to take into account computational complexity and accuracy of detection in the prior art.
The technical solution adopted by the present invention is as follows：
A kind of method for detecting human face based on multitask concatenated convolutional neutral net, including：Set up the multistage convolution of cascade
Neutral net；Trained using face positive sample, face negative sample, part face and face key point sample as training sample
Multistage convolutional neural networks carry out the study of the task of face classification, the recurrence of human face region position and the crucial point location of face；
Face datection is carried out to image to be detected using the multistage convolutional neural networks trained；Wherein, in the training stage, while using
The face negative sample that online mode and offline mode combine to excavate hardly possible is as training sample.
Further, online mode is：The gradient trained in each batch processing returns the stage, and a counting loss is more than setting
The gradient of the part face negative sample of threshold value, ignores remaining face negative sample.Offline mode is：By the model that trains come
The face negative sample of classification error is obtained, and one of score in setting range is selected from the face negative sample of classification error
Batch, it is added to predetermined probability in the face negative sample currently trained and continues to train the model.
Further, every one-level in multistage convolutional neural networks include be sequentially connected multiple convolutional layers, at least one
The feature and upper level of full articulamentum output in maximum pond layer and full an articulamentum, and rear stage convolutional neural networks
The feature of the full articulamentum output of convolutional neural networks is combined, then corresponds to different tasks by different full connection sublayers
Study.
Further, multistage convolutional neural networks include three-level convolutional neural networks, wherein, first order convolutional neural networks
Using the image of 10*10*3 sizes as input, first order convolutional neural networks include multiple convolutional layers and maximum pond layer with
And a full articulamentum, after convolution and pondization processing, image is changed into the feature of 1*1*32 sizes from 10*10*3, then is passed through
Two different full connection sublayers correspond to different tasks；Second level convolutional neural networks use the image of 24*24*3 sizes
As input, second level convolutional neural networks include multiple convolutional layers and two maximum pond layers and an output length is
128 full articulamentum, the feature of the full articulamentum output of this grade and the 1*1*32 of the first order convolutional neural networks output feature
It is stitched together and forms length and be 160 feature, then corresponds to by two different full connection sublayers the study of different task；The
Three-level convolutional neural networks are using the image of 48*48*3 sizes as input, and third level convolutional neural networks include multiple convolution
The full articulamentum that layer and three maximum pond layers and an output length are 256, the feature of the full articulamentum output of this grade with
The merging features that the length of second layer convolutional neural networks output is 160 get up to be formed the feature that length is 416, then pass through three
Different full connection sublayers corresponds to the study of different task.
Further, in the training stage, in the multistage convolutional neural networks of cascade, multistage convolutional neural networks above are defeated
Enter sample for face positive sample, face negative sample and part face sample, face is added in afterbody convolutional neural networks
Key point sample, and face positive sample and the ratio of face negative sample are improved in convolutional neural networks at different levels later.
Further, in the training stage, face classification task use cross entropy loss function, human face region position return and
Face key point location tasks use European loss function, and face classification task also uses middle body loss function, and will hand over
Entropy loss function, European loss function and middle body loss function is pitched to export by different Weights.
Further, in detection-phase, image per one-level convolutional neural networks after handling, to the same face area of identification
Domain, the individual face region clustering of K is merged into the people after k-th before using non-maxima suppression method, sample score is come
Face region, and adjust human face region position.When being ranked up using non-maxima suppression method to sample score, using multistage
The weight score of convolutional neural networks is used as sample score.Multistage convolutional neural networks include three-level convolutional neural networks, weighting
Score computing mechanism is：First order convolutional neural networks classification score is S1, second level convolutional neural networks classification score S2, the
Three-level convolutional neural networks classification score S3, in sequence, sample passes through the score T1=that first order convolutional neural networks are used
S1, score T2=S2+S1*0.5 of the sample after the convolutional neural networks of the second level, sample pass through third level convolutional neural networks
Score T3=S3+T2*0.5 afterwards.
According to another aspect of the present invention, a kind of Face datection based on multitask concatenated convolutional neutral net is additionally provided
Device, including：Module is set up, the multistage convolutional neural networks for setting up cascade；Training module, for multistage convolutional Neural
Network is trained, and training module is used as instruction using face positive sample, face negative sample, part face and face key point sample
Practicing sample, face classification, human face region position are returned and the crucial point location of face is appointed to train multistage convolutional neural networks to carry out
The study of business；Detection module, for carrying out Face datection using the multistage convolutional neural networks trained to image to be detected；Instruction
Practice module in the training stage, while the face negative sample for combining to excavate hardly possible using online mode and offline mode is used as training sample
This.
Further, online mode is：The gradient trained in each batch processing returns the stage, and a counting loss is more than setting
The gradient of the part face negative sample of threshold value, ignores remaining face negative sample；Offline mode is：By the model that trains come
The face negative sample of classification error is obtained, and one of score in setting range is selected from the face negative sample of classification error
Batch, it is added to predetermined probability in the face negative sample currently trained and continues to train the model.
Further, set up in the multistage convolutional neural networks that module is set up, include successively per one-level convolutional neural networks
In the multiple convolutional layers, at least one maximum pond layer and the full articulamentum, and rear stage convolutional neural networks that connect
The feature of full articulamentum output is combined with the feature of the full articulamentum output of upper level convolutional neural networks, then by different complete
Connection sublayer corresponds to the study of different tasks.
The invention has the advantages that：Multistage convolutional neural networks of the invention based on cascade, can learn to Shandong
The stronger feature of rod, while by the way of two kinds of online mode and offline mode excavate difficult face negative sample, can improve
The classification capacity of network, so as to improve the detectability and accuracy rate of network, and ensures operation of this method in actual product
Speed.
In addition to objects, features and advantages described above, the present invention also has other objects, features and advantages.
Below with reference to accompanying drawings, the present invention is further detailed explanation.
Brief description of the drawings
The accompanying drawing for constituting the part of the application is used for providing a further understanding of the present invention, schematic reality of the invention
Apply example and its illustrate to be used to explain the present invention, do not constitute inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is the flow of method for detecting human face of the preferred embodiment of the present invention based on multitask concatenated convolutional neutral net
Figure；
Fig. 2 is the structural representation of the first order convolutional neural networks of the preferred embodiment of the present invention；
Fig. 3 is the structural representation of the second level convolutional neural networks of the preferred embodiment of the present invention；
Fig. 4 is the structural representation of the third level convolutional neural networks of the preferred embodiment of the present invention；
Fig. 5 is the structure of the human face detection device based on multitask concatenated convolutional neutral net of the preferred embodiment of the present invention
Block diagram.
Embodiment
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the present invention in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Reference picture 1, the method for detecting human face of the invention based on multitask concatenated convolutional neutral net, idiographic flow bag
Include：
Step S100, sets up the multistage convolutional neural networks of cascade；
Step S200, training sample is used as using face positive sample, face negative sample, part face and face key point sample
Originally the multistage convolutional neural networks were trained to carry out face classification, the recurrence of human face region position and the crucial point location of face
The study of task；
Step S300, Face datection is carried out using the multistage convolutional neural networks trained to image to be detected.
The preferred embodiments of the present invention, by setting up and training the convolutional neural networks of three-level differentiation of cascade to realize people
The crucial positioning of face detection, face.The present invention ensures the speed of service of this method in actual product first, on this basis,
Image pyramid is constructed to input picture, the shallow-layer convolutional neural networks of three cascades is reapplied, greatly improves the performance of algorithm.
First order convolutional neural networks ensure that higher face recall rate while speed is ensured, second level convolutional neural networks and
3rd convolutional neural networks further obtain the position of accurate human face region positional information and face key point.Every grade of convolution
Neutral net is corrected while whether discriminant classification input picture is face to the position of human face region, is further improved
The accuracy rate of Face datection.
Specifically, first order convolutional neural networks are used as input using the image of 10*10*3 sizes.In first order convolution god
Training stage through network, by taking 8*8,9*9,10*10,11*11,12*12 respectively, totally five kinds of input sizes are tested,
The results show, as input, (can contrast 12*12*3) using the image of 10*10*3 sizes while very little precision is lost
Increase substantially the speed of first order convolutional neural networks.The structures of first order convolutional neural networks as shown in Fig. 2 it include according to
One 1*3*3 of secondary connection convolutional layer (C), 3*1*10 convolutional layer, 2*2 maximum pond max pooling
Layer (MP) and a 1*3*10 convolutional layer, the convolutional layer of 3*1*16 convolutional layer and 1*3*10 and one connect entirely
Connect layer.After convolution and pondization processing, image is changed into the feature (feature Map) of 1*1*32 sizes from 10*10*3, then is led to
Cross two full connection sublayers and correspond to different tasks, including face classification (face classification) and human face region
Position returns (bounding box regression).
For further optimal speed, core 3*3*10 convolutional layer is split into a core for 1*3*3 and one by the present invention
Core is 3*1*10 convolutional layer, and further optimal speed while performance hardly declines, the present invention is rolled up in two-stage below
Also apply the technology to optimize network in product neutral net.In detection-phase, the present invention is refreshing by the first order convolution trained
Arranged through the full articulamentum in network according to core for the form of 1*1 convolutional layer, can not so limit the size of input picture.It is defeated
Enter whole image and obtain the characteristic pattern after first network processes, judge which position for face area according to this feature figure
Domain.
Second level convolutional neural networks input is 24*24*3, as shown in figure 3, its structure includes a 1* being sequentially connected
3*3 convolutional layer, 3*1*28 convolutional layer, 3*3 maximum pond layer, 1*3*28 convolutional layer, a 3*
The maximum pond layer of 1*48 convolutional layer, 3*3, reconnects convolutional layer and a full articulamentum that a core is 2*2, exports
Length be 128.Merging features by this length for the 1*1*32 of 128 feature and the first order convolutional neural networks output rise
To form the feature that length is 160, the study of different tasks is corresponded to by two full connection sublayers on this basis, including
Face classification and human face region position are returned.Experiment proves to add after the feature of first order convolutional neural networks, can improve second
The classification capacity of level convolutional neural networks.
As shown in figure 4, the input of third level convolutional neural networks is 48*48*3, a 1* is sequentially connected after input layer
3*3 convolutional layer, 3*1*32 convolutional layer, 3*3 maximum pond layer, 1*3*32 convolutional layer, a 3*
1*64 convolutional layer, 3*3 maximum pond layer, a core for 3*3 convolutional layer and a 2*2 maximum pond layer, one
Individual core is for 2*2 convolutional layer, immediately following a full articulamentum, and output length is 256.It is similar with second level convolutional neural networks, this
The merging features that the feature and this level length that the length that invention also obtains preceding two-stage convolutional neural networks is 160 are 256 are one
Rise, characteristic length is 416 after splicing, then correspond to by three different full connection sublayers the study of different task, including people
Face classification, human face region position are returned and the crucial point location (landmark localization) of face.
The present invention is used as training data using WIDER FACE and CelebA.In the training stage, according to selected image district
Domain and the overlapping size of actual face marked region, training sample is divided into face positive sample, and (positives, overlapping region is big
In 0.7), face negative sample (negatives, overlapping region be less than 0.3), (part faces, overlapping region is more than part face
0.5 and less than 0.7), face key point sample (landmarks, have key point mark face positive sample).Wherein
Positives and negatives is used for face classification task；Positives and part faces are returned for human face region position
Return task；Landmarks is used for face key point location tasks.In the stage of training first order convolutional neural networks, control
Positives, negatives, part faces ratio are 1:3:1, in the stage control of training second level convolutional neural networks
It is 1 to make the ratio:2:1, trained finally adding landmarks in the stage of training third level convolutional neural networks, and control
Positives processed：negatives：part faces：Landmarks ratio is 1:1:1:1.In second level convolutional Neural net
Face positive sample and the ratio of face negative sample are improved in the training process of network and third level convolutional neural networks, can be effectively improved
The classification capacity of this two-level network.
When first order convolutional neural networks are trained, from the big diagram data for having label, random interception 10x10 sizes
Image block as first order convolutional neural networks input.In training second level convolutional neural networks and third level convolutional Neural
When network, the network trained before is done into Face datection in the data for have label respectively and obtains correspondence next stage network
Input data.
Returned for face classification, human face region position, crucial these three the different tasks of point location of face, the present invention adopts
With different loss functions.Face classification uses cross entropy loss function, and its formula is as follows：
Wherein piExpression is the probability of positive sample (face) in the sample,Value be 0 or 1, respectively to should sample
Physical tags be face or non-face.
The European loss function that human face region position is returned and the crucial point location of face is all used, its formula is as follows：
In order to further improve the performance of face classification, present invention employs middle body loss function (center
Loss the distance of face sample and non-face sample in higher dimensional space) is further pulled open, is also demonstrated that in experiment, in every one-level convolution
Added in the face classification task of neutral net after center loss, classification capacity has further raising.Center loss
Formula it is as follows：
To improve the recall rate to face, several losses are defeated by different Weights by more than in training by the present invention
Go out：
Wherein αiRepresent the corresponding weight of different loss, βiCorrespondence sample type.
In the training process of Face datection, difficult face negative sample (hard negative mining) is excavated as instruction
It is always a kind of effective method for improving detectability to practice sample.The present invention is excavated using two kinds of face negative samples simultaneously
Mode, one kind be online mode (online), it is another be offline mode (offline).Online mode realize it is as follows,
The gradient trained in each batch processing (batch) returns the stage, and a counting loss is more than the part face negative sample of given threshold
Gradient, ignore remaining face negative sample.Preferably, face negative sample of the of the invention counting loss than before larger 70%
Gradient, ignore residue 30% easy face negative sample.In the offline stages, the present invention uses a kind of difficult sample
This strategy, i.e., obtain the face negative sample of classification error by the model trained, from the face negative sample of classification error
In select score and a collection of be added to than relatively low that with predetermined probability in training sample.It is threshold value with 0, the present invention is from sorting out
Preferably chosen in wrong face negative sample score 0~0.5 that is a collection of, the people currently trained is added to 40% probability
Continue to train the model in face negative sample.The method can increase substantially network in the training first order convolutional neural networks stage
Classification capacity, makes first order convolutional neural networks filter out most face negative samples, effectively reduces second level convolutional Neural
Network and the number of samples of third level convolutional neural networks processing, improve detectability and the speed of service.It is demonstrated experimentally that more than
Two methods can improve the classification capacity of network.Above probability/numerical value is only preferred mode, the invention is not limited in
This.
After the completion of training, Face datection, detection are carried out to image to be detected using the multistage convolutional neural networks trained
The whole flow process in stage is as follows：
The image of detection is needed for each, image pyramid (resize) is built first, by the every of pyramid diagram picture
One-level as first order convolutional neural networks input.For first order convolutional neural networks, volume is helped into the conversion of full articulamentum
Product network, can correspond to the input of any scale size, and directly output obtains the confidence level figure of human face region position, and thus calculates
Go out correspondence human face region position.
Then Cluster merging is carried out to the human face region that first order convolutional neural networks are exported.The present invention is using a kind of improvement
Non-maxima suppression top K NMS methods carry out Cluster merging, to the same human face region of identification, K before retaining every time
Divide high, be merged into the human face region after the relatively low namely k-th of score, further ensure face recall rate.Will be poly-
Human face region after class merges carries out aligning, then zooms to the input size of second level convolutional neural networks.
Image after scaling will carry out position after the processing of second level convolutional neural networks by the human face region of threshold value
Adjustment, then passes through top K NMS processing.Third level convolutional neural networks except input make 48*48*3 sizes into addition to, other
At the same time process obtains the information of face key point with second level convolutional neural networks.
When being ranked up using non-maxima suppression method to sample score, the present invention not only considers obtaining for current network
Point, go back the score of cumulative calculation previous stage network.Specifically score computing mechanism is：First order convolutional neural networks classification score
It is S1, second level convolutional neural networks classification score S2, third level convolutional neural networks classification score S3, in sequence, sample is passed through
Cross the score T1=S1, score T2=S2 of the sample after the convolutional neural networks of the second level of first order convolutional neural networks use
+ S1*0.5, sample score T3=S3+T2*0.5 after third level convolutional neural networks.Fully take into account three-level convolutional Neural
The weight score of network, experiment proves that this method can improve the accuracy rate of Face datection.
According to another aspect of the present invention, a kind of Face datection based on multitask concatenated convolutional neutral net is additionally provided
Device, the device of the present embodiment refers to above method embodiment, specifically, reference picture 5, and it includes：
Module 400 is set up, the multistage convolutional neural networks for setting up cascade；
Training module 500, for being trained to multistage convolutional neural networks, the use face of training module 500 positive sample,
Face negative sample, part face and face key point sample train multistage convolutional neural networks to carry out face as training sample
Classification, the recurrence of human face region position and the study of face key point location tasks；And training module 500 is in the training stage, together
The face negative sample that Shi Caiyong online modes and offline mode combine to excavate hardly possible is as training sample；
Detection module 600, for carrying out Face datection using the multistage convolutional neural networks trained to image to be detected.
Online mode is realized as follows：The gradient trained in each batch processing returns the stage, and a counting loss is than before larger
The gradient of 70% face negative sample, ignores the easy face negative sample of residue 30%.Offline mode is specially：Pass through training
Good model selects score 0~0.5 to obtain the face negative sample of classification error from the face negative sample of classification error
That is a collection of, be added to 40% probability in the face negative sample currently trained and continue to train the model.
Set up in the multistage convolutional neural networks that module 400 is set up, include what is be sequentially connected per one-level convolutional neural networks
Full connection in multiple convolutional layers, at least one maximum pond layer and full an articulamentum, and rear stage convolutional neural networks
The feature that the feature of layer output is exported with the full articulamentum of upper level convolutional neural networks is combined, then passes through different full connexons
Layer corresponds to the study of different tasks.
The method for detecting human face and device based on multitask concatenated convolutional neutral net of the present invention, with advantages below：
(1) the input size and network structure of first order convolutional neural networks are adjusted, the speed of service greatly improved.
(2) while by the way of online and offline two kinds are excavated difficult face negative sample, increasing first order convolutional Neural
Network is effectively reduced at second level convolutional neural networks and third level convolutional neural networks to the elimination ability of face negative sample
The number of samples of reason, improves detectability and the speed of service.
(3) face classification task in the training process adds center loss constraint, widens face and non-face
Class spacing, be conducive to improve classification capacity.
(4) different scale feature is combined, improves the ability to express of feature.Specifically, second level convolutional neural networks
The feature representation of first order convolutional neural networks is added, third level convolutional neural networks add first order convolutional neural networks
With the feature representation of second level convolutional neural networks, the robustness of different scale is enhanced, second level convolutional neural networks are improved
With the ability of the classification of third level convolutional neural networks.
(5) after by every grade of convolutional neural networks processing, human face region position is used non-maxima suppression top by the present invention
K NMS methods carry out Cluster merging, and adjust human face region position, further increase the accuracy rate of Face datection.In non-pole
When big value suppresses, the strategy weighted using top K NMS and convolutional neural networks score at different levels improves recalling for face
Rate.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.
Claims (13)
1. a kind of method for detecting human face based on multitask concatenated convolutional neutral net, it is characterised in that including：
Set up the multistage convolutional neural networks of cascade；
Train described as training sample using face positive sample, face negative sample, part face and face key point sample
Multistage convolutional neural networks carry out face classification, the recurrence of human face region position and the study of face key point location tasks；
Face datection is carried out to image to be detected using the multistage convolutional neural networks trained；
Wherein, in the training stage, while the face negative sample for combining to excavate hardly possible using online mode and offline mode is as institute
State training sample.
2. the method for detecting human face according to claim 1 based on multitask concatenated convolutional neutral net, it is characterised in that
The online mode is：The gradient trained in each batch processing returns the stage, and a counting loss is more than the groups of people of given threshold
The gradient of face negative sample, ignores remaining face negative sample.
3. the method for detecting human face according to claim 1 based on multitask concatenated convolutional neutral net, it is characterised in that
The offline mode is：The face negative sample of classification error, and the face malfunctioned from classification are obtained by the model trained
Select that score is a collection of in setting range in negative sample, the face negative sample relaying currently trained is added to predetermined probability
The continuous training model.
4. the method for detecting human face according to claim 1 based on multitask concatenated convolutional neutral net, it is characterised in that
Multiple convolutional layers that every one-level in the multistage convolutional neural networks includes being sequentially connected, at least one maximum pond layer and
The feature and upper level convolutional neural networks of full articulamentum output in one full articulamentum, and rear stage convolutional neural networks
The feature of full articulamentum output is combined, then corresponds to by different full connection sublayers the study of different tasks.
5. the method for detecting human face according to claim 4 based on multitask concatenated convolutional neutral net, it is characterised in that
The multistage convolutional neural networks include three-level convolutional neural networks, wherein,
First order convolutional neural networks use the image of 10*10*3 sizes as input, the first order convolutional neural networks bag
Multiple convolutional layers and a maximum pond layer and a full articulamentum are included, after convolution and pondization processing, image is by 10*
10*3 is changed into the feature of 1*1*32 sizes, then corresponds to different tasks by two different full connection sublayers；
Second level convolutional neural networks use the image of 24*24*3 sizes as input, the second level convolutional neural networks bag
Include the full articulamentum that multiple convolutional layers and two maximum pond layers and an output length are 128, the full connection of this grade
The feature of layer output and the 1*1*32 of the first order convolutional neural networks output merging features get up to be formed the spy that length is 160
Levy, then correspond to by two different full connection sublayers the study of different task；
Third level convolutional neural networks use the image of 48*48*3 sizes as input, the third level convolutional neural networks bag
Include the full articulamentum that multiple convolutional layers and three maximum pond layers and an output length are 256, the full connection of this grade
It is 416 that the merging features that the feature of layer output and the length of second layer convolutional neural networks output are 160, which get up to be formed length,
Feature, then correspond to by three different full connection sublayers the study of different task.
6. the method for detecting human face according to claim 1 based on multitask concatenated convolutional neutral net, it is characterised in that
In the training stage, the multistage convolutional neural networks of cascade, multistage convolutional neural networks input sample above is face
Positive sample, face negative sample and part face sample, add face key point sample in afterbody convolutional neural networks, and
Face positive sample and the ratio of face negative sample are improved in convolutional neural networks at different levels later.
7. the method for detecting human face according to claim 1 based on multitask concatenated convolutional neutral net, it is characterised in that
In the training stage, face classification task uses cross entropy loss function, and human face region position is returned and the crucial point location of face is appointed
Business use European loss function, face classification task also use middle body loss function, and by the cross entropy loss function,
The European loss function and the middle body loss function are exported by different Weights.
8. the method for detecting human face according to claim 1 based on multitask concatenated convolutional neutral net, it is characterised in that
In detection-phase, image, to the same human face region of identification, is pressed down after being handled per one-level convolutional neural networks using non-maximum
The individual face region clustering of K is merged into the human face region after k-th before method processed comes sample score, and adjusts face
Regional location.
9. the method for detecting human face according to claim 8 based on multitask concatenated convolutional neutral net, it is characterised in that
When being ranked up using non-maxima suppression method to sample score, using the weight score of the multistage convolutional neural networks
It is used as sample score.
10. the method for detecting human face according to claim 9 based on multitask concatenated convolutional neutral net, its feature exists
In the multistage convolutional neural networks include three-level convolutional neural networks, and the weight score computing mechanism is：First order convolution
Neural network classification score is S1, second level convolutional neural networks classification score S2, third level convolutional neural networks classification score
S3, in sequence, sample passes through the score T1=S1 that first order convolutional neural networks are used, and sample is by second level convolutional Neural
Score T2=S2+S1*0.5 after network, sample score T3=S3+T2*0.5 after third level convolutional neural networks.
11. a kind of human face detection device based on multitask concatenated convolutional neutral net, it is characterised in that including：
Module is set up, the multistage convolutional neural networks for setting up cascade；
Training module, for being trained to the multistage convolutional neural networks, the training module uses face positive sample, people
Face negative sample, part face and face key point sample train the multistage convolutional neural networks to enter pedestrian as training sample
Face classification, the recurrence of human face region position and the study of face key point location tasks；
Detection module, for carrying out Face datection using the multistage convolutional neural networks trained to image to be detected；
The training module is in the training stage, while combining to excavate the face negative sample of hardly possible using online mode and offline mode
It is used as the training sample.
12. the human face detection device according to claim 11 based on multitask concatenated convolutional neutral net, its feature exists
In the online mode is：The gradient trained in each batch processing returns the stage, and a counting loss is more than the part of given threshold
The gradient of face negative sample, ignores remaining face negative sample；The offline mode is：Obtained by the model trained point
Score is selected in the face negative sample of class error, and the face negative sample malfunctioned from classifying a collection of in setting range, with
Predetermined probability, which is added in the face negative sample currently trained, to be continued to train the model.
13. the method for detecting human face according to claim 11 based on multitask concatenated convolutional neutral net, its feature exists
In, it is described to set up in the multistage convolutional neural networks that module is set up, include what is be sequentially connected per one-level convolutional neural networks
Full connection in multiple convolutional layers, at least one maximum pond layer and full an articulamentum, and rear stage convolutional neural networks
The feature that the feature of layer output is exported with the full articulamentum of upper level convolutional neural networks is combined, then passes through different full connexons
Layer corresponds to the study of different tasks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710291289.0A CN107239736A (en) | 2017-04-28 | 2017-04-28 | Method for detecting human face and detection means based on multitask concatenated convolutional neutral net |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710291289.0A CN107239736A (en) | 2017-04-28 | 2017-04-28 | Method for detecting human face and detection means based on multitask concatenated convolutional neutral net |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107239736A true CN107239736A (en) | 2017-10-10 |
Family
ID=59984230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710291289.0A Pending CN107239736A (en) | 2017-04-28 | 2017-04-28 | Method for detecting human face and detection means based on multitask concatenated convolutional neutral net |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107239736A (en) |
Cited By (75)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704848A (en) * | 2017-10-27 | 2018-02-16 | 深圳市唯特视科技有限公司 | A kind of intensive face alignment method based on multi-constraint condition convolutional neural networks |
| CN107909053A (en) * | 2017-11-30 | 2018-04-13 | 济南浪潮高新科技投资发展有限公司 | A kind of method for detecting human face based on grade study concatenated convolutional neutral net |
| CN107944367A (en) * | 2017-11-16 | 2018-04-20 | 北京小米移动软件有限公司 | Face critical point detection method and device |
| CN107967456A (en) * | 2017-11-27 | 2018-04-27 | 电子科技大学 | A kind of multiple neural network cascade identification face method based on face key point |
| CN107992864A (en) * | 2018-01-15 | 2018-05-04 | 武汉神目信息技术有限公司 | A kind of vivo identification method and device based on image texture |
| CN108010078A (en) * | 2017-11-29 | 2018-05-08 | 中国科学技术大学 | A kind of grasping body detection method based on three-level convolutional neural networks |
| CN108062559A (en) * | 2017-11-30 | 2018-05-22 | 华南师范大学 | A kind of image classification method based on multiple receptive field, system and device |
| CN108171196A (en) * | 2018-01-09 | 2018-06-15 | 北京智芯原动科技有限公司 | A kind of method for detecting human face and device |
| CN108229418A (en) * | 2018-01-19 | 2018-06-29 | 北京市商汤科技开发有限公司 | Human body critical point detection method and apparatus, electronic equipment, storage medium and program |
| CN108280455A (en) * | 2018-01-19 | 2018-07-13 | 北京市商汤科技开发有限公司 | Human body critical point detection method and apparatus, electronic equipment, program and medium |
| CN108363948A (en) * | 2017-12-29 | 2018-08-03 | 武汉烽火众智数字技术有限责任公司 | A kind of face information structural method for video investigation |
| CN108491786A (en) * | 2018-03-20 | 2018-09-04 | 南京邮电大学 | A kind of method for detecting human face based on hierarchical network and Cluster merging |
| CN108564029A (en) * | 2018-04-12 | 2018-09-21 | 厦门大学 | Face character recognition methods based on cascade multi-task learning deep neural network |
| CN108664893A (en) * | 2018-04-03 | 2018-10-16 | 福州海景科技开发有限公司 | A kind of method for detecting human face and storage medium |
| CN108830144A (en) * | 2018-05-03 | 2018-11-16 | 华南农业大学 | A kind of milking sow gesture recognition method based on improvement Faster-R-CNN |
| CN108932505A (en) * | 2018-07-25 | 2018-12-04 | 维沃移动通信有限公司 | A kind of image processing method and electronic equipment |
| CN108960314A (en) * | 2018-06-26 | 2018-12-07 | 北京旷视科技有限公司 | Training method, device and electronic equipment based on difficult sample |
| CN109002753A (en) * | 2018-06-01 | 2018-12-14 | 上海大学 | One kind being based on the cascade large scene monitoring image method for detecting human face of convolutional neural networks |
| CN109063826A (en) * | 2018-03-19 | 2018-12-21 | 重庆大学 | A kind of convolutional neural networks implementation method based on memristor |
| CN109117888A (en) * | 2018-08-20 | 2019-01-01 | 北京旷视科技有限公司 | Recongnition of objects method and its neural network generation method and device |
| CN109145987A (en) * | 2018-08-21 | 2019-01-04 | 厦门美图之家科技有限公司 | model generating method and device |
| CN109190442A (en) * | 2018-06-26 | 2019-01-11 | 杭州雄迈集成电路技术有限公司 | A kind of fast face detecting method based on depth cascade convolutional neural networks |
| CN109214175A (en) * | 2018-07-23 | 2019-01-15 | 中国科学院计算机网络信息中心 | Method, apparatus and storage medium based on sample characteristics training classifier |
| CN109359521A (en) * | 2018-09-05 | 2019-02-19 | 浙江工业大学 | The two-way assessment system of Classroom instruction quality based on deep learning |
| CN109376596A (en) * | 2018-09-14 | 2019-02-22 | 广州杰赛科技股份有限公司 | Face matching process, device, equipment and storage medium |
| CN109389105A (en) * | 2018-12-20 | 2019-02-26 | 北京万里红科技股份有限公司 | A kind of iris detection and viewpoint classification method based on multitask |
| CN109446922A (en) * | 2018-10-10 | 2019-03-08 | 中山大学 | A kind of method for detecting human face of real-time robust |
| CN109522872A (en) * | 2018-12-04 | 2019-03-26 | 西安电子科技大学 | A kind of face identification method, device, computer equipment and storage medium |
| CN109657545A (en) * | 2018-11-10 | 2019-04-19 | 天津大学 | A kind of pedestrian detection method based on multi-task learning |
| WO2019091271A1 (en) * | 2017-11-13 | 2019-05-16 | 苏州科达科技股份有限公司 | Human face detection method and human face detection system |
| CN109766919A (en) * | 2018-12-18 | 2019-05-17 | 通号通信信息集团有限公司 | Cascade the gradual change type Classification Loss calculation method and system in object detection system |
| CN109784125A (en) * | 2017-11-10 | 2019-05-21 | 福州瑞芯微电子股份有限公司 | Deep learning network processing device, method and image processing unit |
| CN109800648A (en) * | 2018-12-18 | 2019-05-24 | 北京英索科技发展有限公司 | Face datection recognition methods and device based on the correction of face key point |
| CN109815835A (en) * | 2018-12-29 | 2019-05-28 | 联动优势科技有限公司 | A kind of interactive mode biopsy method |
| CN109886073A (en) * | 2018-12-26 | 2019-06-14 | 深圳云天励飞技术有限公司 | A kind of image detecting method and device |
| CN109919097A (en) * | 2019-03-08 | 2019-06-21 | 中国科学院自动化研究所 | Face and key point combined detection system, method based on multi-task learning |
| CN109948568A (en) * | 2019-03-26 | 2019-06-28 | 东华大学 | Embedded human face identifying system based on ARM microprocessor and deep learning |
| WO2019136894A1 (en) * | 2018-01-10 | 2019-07-18 | Zhejiang Dahua Technology Co., Ltd. | Methods and systems for face alignment |
| CN110037683A (en) * | 2019-04-01 | 2019-07-23 | 上海数创医疗科技有限公司 | The improvement convolutional neural networks and its training method of rhythm of the heart type for identification |
| CN110069989A (en) * | 2019-03-15 | 2019-07-30 | 上海拍拍贷金融信息服务有限公司 | Face image processing process and device, computer readable storage medium |
| CN110084221A (en) * | 2019-05-08 | 2019-08-02 | 南京云智控产业技术研究院有限公司 | A kind of serializing face critical point detection method of the tape relay supervision based on deep learning |
| CN110175504A (en) * | 2019-04-08 | 2019-08-27 | 杭州电子科技大学 | A kind of target detection and alignment schemes based on multitask concatenated convolutional network |
| CN110188780A (en) * | 2019-06-03 | 2019-08-30 | 电子科技大学中山学院 | Method and device for constructing deep learning model for positioning multi-target feature points |
| CN110188615A (en) * | 2019-04-30 | 2019-08-30 | 中国科学院计算技术研究所 | A kind of facial expression recognizing method, device, medium and system |
| CN110188627A (en) * | 2019-05-13 | 2019-08-30 | 睿视智觉（厦门）科技有限公司 | A kind of facial image filter method and device |
| CN110189255A (en) * | 2019-05-29 | 2019-08-30 | 电子科技大学 | Method for detecting human face based on hierarchical detection |
| CN110222565A (en) * | 2019-04-26 | 2019-09-10 | 合肥进毅智能技术有限公司 | A kind of method for detecting human face, device, electronic equipment and storage medium |
| CN110232352A (en) * | 2019-06-12 | 2019-09-13 | 东北大学 | A kind of improved method of the multitask concatenated convolutional neural network model for recognition of face |
| WO2019183758A1 (en) * | 2018-03-26 | 2019-10-03 | Intel Corporation | Methods and apparatus for multi-task recognition using neural networks |
| CN110348358A (en) * | 2019-07-03 | 2019-10-18 | 网易（杭州）网络有限公司 | A kind of Face Detection system, method, medium and calculate equipment |
| CN110390223A (en) * | 2018-04-16 | 2019-10-29 | 北京陌陌信息技术有限公司 | Adjust method, apparatus, equipment and the computer storage medium of facial image |
| CN110458005A (en) * | 2019-07-02 | 2019-11-15 | 重庆邮电大学 | It is a kind of based on the progressive invariable rotary method for detecting human face with pseudo-crystalline lattice of multitask |
| CN110490052A (en) * | 2019-07-05 | 2019-11-22 | 山东大学 | Face datection and face character analysis method and system based on cascade multi-task learning |
| CN110580469A (en) * | 2019-09-10 | 2019-12-17 | 广州麦仑信息科技有限公司 | palm vein recognition system and method based on embedded equipment |
| CN110795975A (en) * | 2018-08-03 | 2020-02-14 | 浙江宇视科技有限公司 | Face false detection optimization method and device |
| CN110826634A (en) * | 2019-11-11 | 2020-02-21 | 北京百度网讯科技有限公司 | Training method and device of target detection model, electronic equipment and storage medium |
| CN110866490A (en) * | 2019-11-13 | 2020-03-06 | 复旦大学 | Face detection method and device based on multitask learning |
| CN110874587A (en) * | 2019-12-26 | 2020-03-10 | 浙江大学 | Face characteristic parameter extraction system |
| CN110889446A (en) * | 2019-11-22 | 2020-03-17 | 高创安邦(北京)技术有限公司 | Face image recognition model training and face image recognition method and device |
| CN110929794A (en) * | 2019-11-28 | 2020-03-27 | 哈尔滨工程大学 | Side-scan sonar image classification method based on multi-task learning |
| CN110956255A (en) * | 2019-11-26 | 2020-04-03 | 中国医学科学院肿瘤医院 | Difficult sample mining method and device, electronic equipment and computer readable storage medium |
| CN111126173A (en) * | 2019-12-04 | 2020-05-08 | 玉林师范学院 | High-precision face detection method |
| CN111327608A (en) * | 2020-02-14 | 2020-06-23 | 中南大学 | Application layer malicious request detection method and system based on cascade deep neural network |
| CN111324776A (en) * | 2018-12-13 | 2020-06-23 | 第四范式（北京）技术有限公司 | Method and device for training graph embedding model, computing equipment and readable medium |
| CN111382624A (en) * | 2018-12-28 | 2020-07-07 | 杭州海康威视数字技术股份有限公司 | Action recognition method, device, equipment and readable storage medium |
| CN111401219A (en) * | 2020-03-10 | 2020-07-10 | 厦门中控智慧信息技术有限公司 | Palm key point detection method and device |
| CN111860055A (en) * | 2019-04-29 | 2020-10-30 | 北京眼神智能科技有限公司 | Face silence living body detection method and device, readable storage medium and equipment |
| CN111898406A (en) * | 2020-06-05 | 2020-11-06 | 东南大学 | Face detection method based on focus loss and multitask cascade |
| CN111931799A (en) * | 2019-05-13 | 2020-11-13 | 百度在线网络技术（北京）有限公司 | Image recognition method and device |
| CN112507862A (en) * | 2020-12-04 | 2021-03-16 | 东风汽车集团有限公司 | Vehicle orientation detection method and system based on multitask convolutional neural network |
| CN112668465A (en) * | 2020-12-25 | 2021-04-16 | 秒影工场(北京)科技有限公司 | Film face extraction method based on multistage CNN |
| CN112836566A (en) * | 2020-12-01 | 2021-05-25 | 北京智云视图科技有限公司 | Multitask neural network face key point detection method for edge equipment |
| CN112883930A (en) * | 2021-03-29 | 2021-06-01 | 动者科技(杭州)有限责任公司 | Real-time true and false motion judgment method based on full-connection network |
| CN112949492A (en) * | 2021-03-03 | 2021-06-11 | 南京视察者智能科技有限公司 | Model series training method and device for face detection and key point detection and terminal equipment |
| CN113496173A (en) * | 2020-04-07 | 2021-10-12 | 北京君正集成电路股份有限公司 | Detection method for last stage of cascaded face detection |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160104058A1 (en) * | 2014-10-09 | 2016-04-14 | Microsoft Technology Licensing, Llc | Generic object detection in images |
| CN105868689A (en) * | 2016-02-16 | 2016-08-17 | 杭州景联文科技有限公司 | Cascaded convolutional neural network based human face occlusion detection method |
-
2017
- 2017-04-28 CN CN201710291289.0A patent/CN107239736A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160104058A1 (en) * | 2014-10-09 | 2016-04-14 | Microsoft Technology Licensing, Llc | Generic object detection in images |
| CN105868689A (en) * | 2016-02-16 | 2016-08-17 | 杭州景联文科技有限公司 | Cascaded convolutional neural network based human face occlusion detection method |
Non-Patent Citations (1)
| Title |
|---|
| KAIPENG ZHANG，ET AL.: "Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks", 《IEEE SIGNAL PROCESSING LETTERS》 * |
Cited By (108)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704848A (en) * | 2017-10-27 | 2018-02-16 | 深圳市唯特视科技有限公司 | A kind of intensive face alignment method based on multi-constraint condition convolutional neural networks |
| CN109784125A (en) * | 2017-11-10 | 2019-05-21 | 福州瑞芯微电子股份有限公司 | Deep learning network processing device, method and image processing unit |
| WO2019091271A1 (en) * | 2017-11-13 | 2019-05-16 | 苏州科达科技股份有限公司 | Human face detection method and human face detection system |
| CN107944367B (en) * | 2017-11-16 | 2021-06-01 | 北京小米移动软件有限公司 | Face key point detection method and device |
| CN107944367A (en) * | 2017-11-16 | 2018-04-20 | 北京小米移动软件有限公司 | Face critical point detection method and device |
| CN107967456A (en) * | 2017-11-27 | 2018-04-27 | 电子科技大学 | A kind of multiple neural network cascade identification face method based on face key point |
| CN108010078A (en) * | 2017-11-29 | 2018-05-08 | 中国科学技术大学 | A kind of grasping body detection method based on three-level convolutional neural networks |
| CN108010078B (en) * | 2017-11-29 | 2020-06-26 | 中国科学技术大学 | Object grabbing detection method based on three-level convolutional neural network |
| CN108062559A (en) * | 2017-11-30 | 2018-05-22 | 华南师范大学 | A kind of image classification method based on multiple receptive field, system and device |
| CN107909053A (en) * | 2017-11-30 | 2018-04-13 | 济南浪潮高新科技投资发展有限公司 | A kind of method for detecting human face based on grade study concatenated convolutional neutral net |
| CN107909053B (en) * | 2017-11-30 | 2020-06-26 | 浪潮集团有限公司 | Face detection method based on hierarchical learning cascade convolution neural network |
| CN108363948A (en) * | 2017-12-29 | 2018-08-03 | 武汉烽火众智数字技术有限责任公司 | A kind of face information structural method for video investigation |
| CN108171196B (en) * | 2018-01-09 | 2021-10-26 | 北京智芯原动科技有限公司 | Face detection method and device |
| CN108171196A (en) * | 2018-01-09 | 2018-06-15 | 北京智芯原动科技有限公司 | A kind of method for detecting human face and device |
| US11741750B2 (en) | 2018-01-10 | 2023-08-29 | Zhejiang Dahua Technology Co., Ltd. | Methods and systems for face alignment |
| US11301668B2 (en) | 2018-01-10 | 2022-04-12 | Zhejiang Dahua Technology Co., Ltd. | Methods and systems for face alignment |
| WO2019136894A1 (en) * | 2018-01-10 | 2019-07-18 | Zhejiang Dahua Technology Co., Ltd. | Methods and systems for face alignment |
| CN107992864A (en) * | 2018-01-15 | 2018-05-04 | 武汉神目信息技术有限公司 | A kind of vivo identification method and device based on image texture |
| CN108280455A (en) * | 2018-01-19 | 2018-07-13 | 北京市商汤科技开发有限公司 | Human body critical point detection method and apparatus, electronic equipment, program and medium |
| CN108280455B (en) * | 2018-01-19 | 2021-04-02 | 北京市商汤科技开发有限公司 | Human body key point detection method and apparatus, electronic device, program, and medium |
| CN108229418A (en) * | 2018-01-19 | 2018-06-29 | 北京市商汤科技开发有限公司 | Human body critical point detection method and apparatus, electronic equipment, storage medium and program |
| CN109063826A (en) * | 2018-03-19 | 2018-12-21 | 重庆大学 | A kind of convolutional neural networks implementation method based on memristor |
| CN108491786A (en) * | 2018-03-20 | 2018-09-04 | 南京邮电大学 | A kind of method for detecting human face based on hierarchical network and Cluster merging |
| US11106896B2 (en) | 2018-03-26 | 2021-08-31 | Intel Corporation | Methods and apparatus for multi-task recognition using neural networks |
| WO2019183758A1 (en) * | 2018-03-26 | 2019-10-03 | Intel Corporation | Methods and apparatus for multi-task recognition using neural networks |
| CN108664893A (en) * | 2018-04-03 | 2018-10-16 | 福州海景科技开发有限公司 | A kind of method for detecting human face and storage medium |
| CN108664893B (en) * | 2018-04-03 | 2022-04-29 | 福建海景科技开发有限公司 | Face detection method and storage medium |
| CN108564029B (en) * | 2018-04-12 | 2020-12-01 | 厦门大学 | Face attribute recognition method based on cascade multitask learning deep neural network |
| CN108564029A (en) * | 2018-04-12 | 2018-09-21 | 厦门大学 | Face character recognition methods based on cascade multi-task learning deep neural network |
| CN110390223A (en) * | 2018-04-16 | 2019-10-29 | 北京陌陌信息技术有限公司 | Adjust method, apparatus, equipment and the computer storage medium of facial image |
| CN108830144B (en) * | 2018-05-03 | 2022-02-22 | 华南农业大学 | Lactating sow posture identification method based on improved Faster-R-CNN |
| CN108830144A (en) * | 2018-05-03 | 2018-11-16 | 华南农业大学 | A kind of milking sow gesture recognition method based on improvement Faster-R-CNN |
| CN109002753B (en) * | 2018-06-01 | 2022-07-08 | 上海大学 | Large-scene monitoring image face detection method based on convolutional neural network cascade |
| CN109002753A (en) * | 2018-06-01 | 2018-12-14 | 上海大学 | One kind being based on the cascade large scene monitoring image method for detecting human face of convolutional neural networks |
| CN109190442B (en) * | 2018-06-26 | 2021-07-06 | 杭州雄迈集成电路技术股份有限公司 | Rapid face detection method based on deep cascade convolution neural network |
| CN108960314A (en) * | 2018-06-26 | 2018-12-07 | 北京旷视科技有限公司 | Training method, device and electronic equipment based on difficult sample |
| CN109190442A (en) * | 2018-06-26 | 2019-01-11 | 杭州雄迈集成电路技术有限公司 | A kind of fast face detecting method based on depth cascade convolutional neural networks |
| CN109214175A (en) * | 2018-07-23 | 2019-01-15 | 中国科学院计算机网络信息中心 | Method, apparatus and storage medium based on sample characteristics training classifier |
| CN109214175B (en) * | 2018-07-23 | 2021-11-16 | 中国科学院计算机网络信息中心 | Method, device and storage medium for training classifier based on sample characteristics |
| CN108932505A (en) * | 2018-07-25 | 2018-12-04 | 维沃移动通信有限公司 | A kind of image processing method and electronic equipment |
| CN110795975B (en) * | 2018-08-03 | 2023-07-21 | 浙江宇视科技有限公司 | Face false detection optimization method and device |
| CN110795975A (en) * | 2018-08-03 | 2020-02-14 | 浙江宇视科技有限公司 | Face false detection optimization method and device |
| CN109117888A (en) * | 2018-08-20 | 2019-01-01 | 北京旷视科技有限公司 | Recongnition of objects method and its neural network generation method and device |
| CN109145987A (en) * | 2018-08-21 | 2019-01-04 | 厦门美图之家科技有限公司 | model generating method and device |
| CN109145987B (en) * | 2018-08-21 | 2020-10-20 | 厦门美图之家科技有限公司 | Model generation method and device |
| CN109359521A (en) * | 2018-09-05 | 2019-02-19 | 浙江工业大学 | The two-way assessment system of Classroom instruction quality based on deep learning |
| CN109376596A (en) * | 2018-09-14 | 2019-02-22 | 广州杰赛科技股份有限公司 | Face matching process, device, equipment and storage medium |
| CN109446922B (en) * | 2018-10-10 | 2021-01-08 | 中山大学 | Real-time robust face detection method |
| CN109446922A (en) * | 2018-10-10 | 2019-03-08 | 中山大学 | A kind of method for detecting human face of real-time robust |
| CN109657545B (en) * | 2018-11-10 | 2022-12-20 | 天津大学 | Pedestrian detection method based on multi-task learning |
| CN109657545A (en) * | 2018-11-10 | 2019-04-19 | 天津大学 | A kind of pedestrian detection method based on multi-task learning |
| CN109522872A (en) * | 2018-12-04 | 2019-03-26 | 西安电子科技大学 | A kind of face identification method, device, computer equipment and storage medium |
| CN111324776A (en) * | 2018-12-13 | 2020-06-23 | 第四范式（北京）技术有限公司 | Method and device for training graph embedding model, computing equipment and readable medium |
| CN109766919B (en) * | 2018-12-18 | 2020-11-10 | 通号通信信息集团有限公司 | Gradual change type classification loss calculation method and system in cascade target detection system |
| CN109800648A (en) * | 2018-12-18 | 2019-05-24 | 北京英索科技发展有限公司 | Face datection recognition methods and device based on the correction of face key point |
| CN109766919A (en) * | 2018-12-18 | 2019-05-17 | 通号通信信息集团有限公司 | Cascade the gradual change type Classification Loss calculation method and system in object detection system |
| CN109389105B (en) * | 2018-12-20 | 2022-02-08 | 北京万里红科技有限公司 | Multitask-based iris detection and visual angle classification method |
| CN109389105A (en) * | 2018-12-20 | 2019-02-26 | 北京万里红科技股份有限公司 | A kind of iris detection and viewpoint classification method based on multitask |
| CN109886073A (en) * | 2018-12-26 | 2019-06-14 | 深圳云天励飞技术有限公司 | A kind of image detecting method and device |
| CN111382624A (en) * | 2018-12-28 | 2020-07-07 | 杭州海康威视数字技术股份有限公司 | Action recognition method, device, equipment and readable storage medium |
| CN111382624B (en) * | 2018-12-28 | 2023-08-11 | 杭州海康威视数字技术股份有限公司 | Action recognition method, device, equipment and readable storage medium |
| CN109815835A (en) * | 2018-12-29 | 2019-05-28 | 联动优势科技有限公司 | A kind of interactive mode biopsy method |
| CN109919097A (en) * | 2019-03-08 | 2019-06-21 | 中国科学院自动化研究所 | Face and key point combined detection system, method based on multi-task learning |
| CN110069989A (en) * | 2019-03-15 | 2019-07-30 | 上海拍拍贷金融信息服务有限公司 | Face image processing process and device, computer readable storage medium |
| CN109948568A (en) * | 2019-03-26 | 2019-06-28 | 东华大学 | Embedded human face identifying system based on ARM microprocessor and deep learning |
| CN110037683A (en) * | 2019-04-01 | 2019-07-23 | 上海数创医疗科技有限公司 | The improvement convolutional neural networks and its training method of rhythm of the heart type for identification |
| CN110175504A (en) * | 2019-04-08 | 2019-08-27 | 杭州电子科技大学 | A kind of target detection and alignment schemes based on multitask concatenated convolutional network |
| CN110222565A (en) * | 2019-04-26 | 2019-09-10 | 合肥进毅智能技术有限公司 | A kind of method for detecting human face, device, electronic equipment and storage medium |
| CN111860055B (en) * | 2019-04-29 | 2023-10-24 | 北京眼神智能科技有限公司 | Face silence living body detection method, device, readable storage medium and equipment |
| CN111860055A (en) * | 2019-04-29 | 2020-10-30 | 北京眼神智能科技有限公司 | Face silence living body detection method and device, readable storage medium and equipment |
| CN110188615B (en) * | 2019-04-30 | 2021-08-06 | 中国科学院计算技术研究所 | Facial expression recognition method, device, medium and system |
| CN110188615A (en) * | 2019-04-30 | 2019-08-30 | 中国科学院计算技术研究所 | A kind of facial expression recognizing method, device, medium and system |
| CN110084221A (en) * | 2019-05-08 | 2019-08-02 | 南京云智控产业技术研究院有限公司 | A kind of serializing face critical point detection method of the tape relay supervision based on deep learning |
| CN110188627A (en) * | 2019-05-13 | 2019-08-30 | 睿视智觉（厦门）科技有限公司 | A kind of facial image filter method and device |
| CN111931799A (en) * | 2019-05-13 | 2020-11-13 | 百度在线网络技术（北京）有限公司 | Image recognition method and device |
| CN110189255A (en) * | 2019-05-29 | 2019-08-30 | 电子科技大学 | Method for detecting human face based on hierarchical detection |
| CN110189255B (en) * | 2019-05-29 | 2023-01-17 | 电子科技大学 | Face detection method based on two-stage detection |
| CN110188780A (en) * | 2019-06-03 | 2019-08-30 | 电子科技大学中山学院 | Method and device for constructing deep learning model for positioning multi-target feature points |
| CN110188780B (en) * | 2019-06-03 | 2021-10-08 | 电子科技大学中山学院 | Method and device for constructing deep learning model for positioning multi-target feature points |
| CN110232352A (en) * | 2019-06-12 | 2019-09-13 | 东北大学 | A kind of improved method of the multitask concatenated convolutional neural network model for recognition of face |
| CN110458005B (en) * | 2019-07-02 | 2022-12-27 | 重庆邮电大学 | Rotation-invariant face detection method based on multitask progressive registration network |
| CN110458005A (en) * | 2019-07-02 | 2019-11-15 | 重庆邮电大学 | It is a kind of based on the progressive invariable rotary method for detecting human face with pseudo-crystalline lattice of multitask |
| CN110348358A (en) * | 2019-07-03 | 2019-10-18 | 网易（杭州）网络有限公司 | A kind of Face Detection system, method, medium and calculate equipment |
| CN110490052A (en) * | 2019-07-05 | 2019-11-22 | 山东大学 | Face datection and face character analysis method and system based on cascade multi-task learning |
| CN110580469A (en) * | 2019-09-10 | 2019-12-17 | 广州麦仑信息科技有限公司 | palm vein recognition system and method based on embedded equipment |
| CN110580469B (en) * | 2019-09-10 | 2022-08-09 | 广州麦仑信息科技有限公司 | Palm vein recognition system and method based on embedded equipment |
| CN110826634A (en) * | 2019-11-11 | 2020-02-21 | 北京百度网讯科技有限公司 | Training method and device of target detection model, electronic equipment and storage medium |
| CN110866490A (en) * | 2019-11-13 | 2020-03-06 | 复旦大学 | Face detection method and device based on multitask learning |
| CN110889446A (en) * | 2019-11-22 | 2020-03-17 | 高创安邦(北京)技术有限公司 | Face image recognition model training and face image recognition method and device |
| CN110956255B (en) * | 2019-11-26 | 2023-04-07 | 中国医学科学院肿瘤医院 | Difficult sample mining method and device, electronic equipment and computer readable storage medium |
| CN110956255A (en) * | 2019-11-26 | 2020-04-03 | 中国医学科学院肿瘤医院 | Difficult sample mining method and device, electronic equipment and computer readable storage medium |
| CN110929794A (en) * | 2019-11-28 | 2020-03-27 | 哈尔滨工程大学 | Side-scan sonar image classification method based on multi-task learning |
| CN111126173B (en) * | 2019-12-04 | 2023-05-26 | 玉林师范学院 | High-precision face detection method |
| CN111126173A (en) * | 2019-12-04 | 2020-05-08 | 玉林师范学院 | High-precision face detection method |
| CN110874587A (en) * | 2019-12-26 | 2020-03-10 | 浙江大学 | Face characteristic parameter extraction system |
| CN110874587B (en) * | 2019-12-26 | 2020-07-28 | 浙江大学 | Face characteristic parameter extraction system |
| CN111327608A (en) * | 2020-02-14 | 2020-06-23 | 中南大学 | Application layer malicious request detection method and system based on cascade deep neural network |
| CN111401219A (en) * | 2020-03-10 | 2020-07-10 | 厦门中控智慧信息技术有限公司 | Palm key point detection method and device |
| CN111401219B (en) * | 2020-03-10 | 2023-04-28 | 厦门熵基科技有限公司 | Palm key point detection method and device |
| CN113496173A (en) * | 2020-04-07 | 2021-10-12 | 北京君正集成电路股份有限公司 | Detection method for last stage of cascaded face detection |
| CN113496173B (en) * | 2020-04-07 | 2023-09-26 | 北京君正集成电路股份有限公司 | Detection method of last stage of cascaded face detection |
| CN111898406B (en) * | 2020-06-05 | 2022-04-29 | 东南大学 | Face detection method based on focus loss and multitask cascade |
| CN111898406A (en) * | 2020-06-05 | 2020-11-06 | 东南大学 | Face detection method based on focus loss and multitask cascade |
| CN112836566A (en) * | 2020-12-01 | 2021-05-25 | 北京智云视图科技有限公司 | Multitask neural network face key point detection method for edge equipment |
| CN112507862A (en) * | 2020-12-04 | 2021-03-16 | 东风汽车集团有限公司 | Vehicle orientation detection method and system based on multitask convolutional neural network |
| CN112668465A (en) * | 2020-12-25 | 2021-04-16 | 秒影工场(北京)科技有限公司 | Film face extraction method based on multistage CNN |
| CN112949492A (en) * | 2021-03-03 | 2021-06-11 | 南京视察者智能科技有限公司 | Model series training method and device for face detection and key point detection and terminal equipment |
| CN112883930A (en) * | 2021-03-29 | 2021-06-01 | 动者科技(杭州)有限责任公司 | Real-time true and false motion judgment method based on full-connection network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107239736A (en) | Method for detecting human face and detection means based on multitask concatenated convolutional neutral net | |
| WO2021244079A1 (en) | Method for detecting image target in smart home environment | |
| CN109741318B (en) | Real-time detection method of single-stage multi-scale specific target based on effective receptive field | |
| CN111291739B (en) | Face detection and image detection neural network training method, device and equipment | |
| CN103093250B (en) | A kind of Adaboost method for detecting human face based on new Haar-like feature | |
| CN108052884A (en) | A kind of gesture identification method based on improvement residual error neutral net | |
| CN104992167A (en) | Convolution neural network based face detection method and apparatus | |
| CN108665481A (en) | Multilayer depth characteristic fusion it is adaptive resist block infrared object tracking method | |
| CN107871100A (en) | The training method and device of faceform, face authentication method and device | |
| CN110782420A (en) | Small target feature representation enhancement method based on deep learning | |
| CN108647741A (en) | A kind of image classification method and system based on transfer learning | |
| CN107403200A (en) | Improve the multiple imperfect picture sorting technique of image segmentation algorithm combination deep learning | |
| CN106709568A (en) | RGB-D image object detection and semantic segmentation method based on deep convolution network | |
| CN109446922B (en) | Real-time robust face detection method | |
| CN109800629A (en) | A kind of Remote Sensing Target detection method based on convolutional neural networks | |
| CN109191455A (en) | A kind of field crop pest and disease disasters detection method based on SSD convolutional network | |
| CN104636732B (en) | A kind of pedestrian recognition method based on the deep belief network of sequence | |
| CN109817276A (en) | A kind of secondary protein structure prediction method based on deep neural network | |
| CN107145889A (en) | Target identification method based on double CNN networks with RoI ponds | |
| CN110569738A (en) | natural scene text detection method, equipment and medium based on dense connection network | |
| CN112150493A (en) | Semantic guidance-based screen area detection method in natural scene | |
| CN106934355A (en) | In-car hand detection method based on depth convolutional neural networks | |
| CN107463881A (en) | A kind of character image searching method based on depth enhancing study | |
| CN111950525B (en) | Fine-grained image classification method based on destructive reconstruction learning and GoogLeNet | |
| CN106372630A (en) | Face direction detection method based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100097 Beijing Haidian District Kunming Hunan Road 51 C block two floor 207. Applicant after: ATHENA EYES SCIENCE & TECHNOLOGY CO., LTD. Address before: 100193 4, 403, block A, 14 building, 10 East North Road, Haidian District, Beijing. Applicant before: ATHENA EYES SCIENCE & TECHNOLOGY CO., LTD. |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 410205 14 Changsha Zhongdian Software Park Phase I, 39 Jianshan Road, Changsha High-tech Development Zone, Yuelu District, Changsha City, Hunan Province Applicant after: Wisdom Eye Technology Co., Ltd. Address before: 100097 2nd Floor 207, Block C, 51 Hunan Road, Kunming, Haidian District, Beijing Applicant before: ATHENA EYES SCIENCE & TECHNOLOGY CO., LTD. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171010 |