A real-time fast face detection method
A detection method and face technology, applied in the direction of neural learning methods, instruments, biological neural network models, etc., can solve problems such as changes and uncertain face patterns, and achieve speed, high practical value, development prospects, and accuracy Improved effect
Active Publication Date: 2019-10-29
NANJING NANYOU INST OF INFORMATION TECHNOVATION CO LTD
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Other appendages on the face such as: beards, glasses, etc. will cause uncertainty in the face pattern; (3) The impact of the uncertainty in the image acquisition process: light intensity, number and direction of light sources, shooting angles, different Imaging methods and image resolution can cause changes in image quality
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0029] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:
[0030] Faces can appear in images from different perspectives. In order to achieve the robustness of the detection method, we need to consider different appearances in different directions, angles, scales, etc. Based on this, the present invention provides a real-time high-precision human face fast detection algorithm.
[0031] figure 1 It is the overall flowchart of the method of the present invention, a real-time high-precision face detection algorithm, including three major steps of neural network training and design, feature description operator design, algorithm and weak classifier fusion.
[0032] The detailed process is as follows:
[0033] Step A, design a convolutional neural network model BFCNN based on face classification;
[0034] Step B, using the cross ratio (IOU), from the image I in the public face database raw , get the positiv...
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 real-time high-precision human face rapid detection method, which belongs to the technical field of image processing target detection. Based on the combination of Boosting algorithm and convolutional neural network, the ability of convolutional neural network to extract face features while filtering out environmental noise is used, so that the noise area in the image can be quickly cleared and the useful information in the image can be retained. , which greatly speeds up the speed of the face detection algorithm. At the same time, the high-precision classifier constructed by combining the Boosing algorithm and the designed feature algorithm processes the feature map obtained by the convolutional neural network, which can quickly and accurately obtain the face in the image. specific location. The present invention provides a novel, robust and high-precision fast face detection method, provides a brand-new idea in the field of face detection, and has very high practical value and development prospect.
Description
technical field [0001] The invention relates to the technical field of image target detection, in particular to a real-time high-precision human face rapid detection method. Background technique [0002] With the development of applications such as e-commerce, face detection, as an important prerequisite for many biometric authentication technologies, has always received a lot of attention. Face is a collection of patterns containing rich information, and it is one of the main signs of mutual dialectics and recognition of human beings. Today, the application background of face detection has gone far beyond the scope of face recognition systems. In content-based retrieval , digital video processing, video detection and other aspects have important application value. [0003] In recent years, due to the needs of anti-terrorism, homeland security, and social security, various countries in the world have increased investment in the field of security. At present, many research g...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
Inventor 李晓飞刘佳雯韩光
Owner NANJING NANYOU INST OF INFORMATION TECHNOVATION CO LTD