Method and system for carrying out face fatigue state recognition by relative coverage element reduction
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A fatigue state and face technology, which is applied in the system field of face fatigue state recognition, can solve the problems of face fatigue expression recognition, too many rules and a large amount of calculation, etc., and achieve excellent generalization performance, fast classification speed, and calculation Small amount of effect
Inactive Publication Date: 2017-06-13
NORTHEAST AGRICULTURAL UNIVERSITY
View PDF1 Cites 2 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0006] The present invention aims to solve the problem of large amount of calculation or many rules in face fatigue expression recognition using the prior art and the problem that face fatigue expression recognition cannot be carried out by covering element reduction at present
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0046] Specific implementation mode one: combine figure 1 To describe this embodiment,
[0047] The method for identifying the fatigue state of a human face by using relative coverage element reduction described in this embodiment includes the following steps:
[0048] 1. Train a relative coverage meta-classifier:
[0049] Step 1, obtain the human face video frame of the video image in the video recording device;
[0050] Step 2, detect the face core area in each face video frame;
[0051] Step 3, extracting the features of the core area of the face;
[0052] Step 4, based on the state of the face in each face video frame, classify each frame of image;
[0053] Step 5, combine the features of the core area of the face with the corresponding annotations to form labeled training samples, and form a training sample set;
[0054] Step 6, generating a neighborhood covering element for each sample in the training sample set, and counting the samples covered by the neighborhoo...
specific Embodiment approach 2
[0067] The neighborhood covering element described in step 6 of this embodiment is as follows:
[0068]
[0069] where x i ,x j Represents two arbitrary samples without category labels (only feature attributes and no category attributes); U represents the sample set; Δ(x i ,x j ) is a distance function, and δ is a function that depends on x i The parameter that represents the distance threshold.
[0070] Other steps and parameters are the same as those in the first embodiment.
specific Embodiment approach 3
[0072] Δ(x) described in step 6 described in this embodiment i ,x j ) is calculated using the Euclidean distance.
[0073] Other steps and parameters are the same as in the second embodiment.
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses a method and a system for carrying out face fatigue state recognition by relative coverage element reduction, and relates to the technical field of image recognition, in particular to a system and a method for the face fatigue state recognition. In order to solve the problems in the prior art that a calculated amount is large or more rules are in the presence when the face fatigue state recognition is carried out and face fatigue expression recognition can not be carried out through coverage element reduction at present, the method comprises the following steps that: firstly, obtaining the face video frame of a video image, detecting a face core area, and extracting the feature of the face core area; then, on the basis of a face state, carrying out category annotation on each frame of image, and combining with the feature of the face core area to form a training sample set; then, generating a neighbourhood coverage element for each sample in the training sample set, and counting and training the sample covered by the neighbourhood coverage element to form a relative coverage element classifier; and finally, utilizing the relative coverage element classifier to carry out the face fatigue state recognition on the new video image. The method is suitable for the face fatigue state recognition.
Description
technical field [0001] The invention relates to the technical field of image recognition, in particular to a system and method for recognizing a fatigue state of a human face. Background technique [0002] In many practical application problems, it is often necessary to make a correct judgment on a thing (usually called a sample) based on past experience. When the real distribution characteristics of samples in this problem space cannot be fully understood, or the number of samples owned When it is not sufficient, or the problem faced is a classification problem in a high-dimensional sparse sample space, etc., in the above cases, two problems generally need to be solved, one is to extract and represent the features of the sample , the second is to classify new samples according to certain principles. The nearest neighbor classifier and k-nearest neighbor classifier are effective ways to solve such problems, but the disadvantage of these two methods is that the decision-maki...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more