Image processing method and device and device for image processing
An image processing and image technology, applied in the computer field, can solve the problems of reduced accuracy, face change, influence, etc., to achieve the effect of improving accuracy and accuracy
Pending Publication Date: 2020-08-04
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF6 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, the Haar classifier has a high detection accuracy for face images in constrained environments such as simple background, frontal face, and no occlusion. For face images in harsh and unconstrained environments, the accuracy of detection is greatly reduced, which in turn affects the effect of "face changing"
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 2
[0100] refer to figure 2 , which shows a flow chart of the steps of another image processing method embodiment of the present invention, which may specifically include the following steps:
[0101] Step 201, according to the face detection model, determine the face area in the template image;
[0102] Specifically, input the template image into a face detection model, so as to output the face area in the template image through the face detection model. The face detection model is a neural network model trained according to sample images containing faces and face labeling results corresponding to the sample images.
[0103]Optionally, the face detection model may include a multi-layer convolutional neural network, and a high-level network in the multi-layer convolutional neural network is used to detect macroscopic information in an image, and the macroscopic information includes at least any of the following : Semantic information, motion information, the low-layer network ...
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 embodiment of the invention provides an image processing method and device and a device for image processing. The method specifically comprises the following steps: determining a face changing area in a template image according to a detected face area in the template image, wherein the human face area is obtained by detection according to a human face detection model, and the human face detection model is a neural network model obtained by training according to a sample image containing a human face and a human face labeling result corresponding to the sample image; determining a target face key point in the target image; according to the target face key points, converting the face changing area to obtain a converted template image, wherein the transformed template image comprises features of the target face key points. According to the embodiment of the invention, the accuracy of face detection can be improved, and the accuracy of face change can be further improved.
Description
technical field [0001] The present invention relates to the field of computer technology, in particular to an image processing method, device and device for image processing. Background technique [0002] Along with the development of computer technology, virtual human face (also known as "face changing") technology has also obtained great development. For example, through the "face changing" technology, the face in the template image can be replaced with the face in the photo; or, the face of an actor in a film and television drama can be replaced with the face in the photo, etc. [0003] At present, the AdaBoost (Adaptive Boosting, adaptive enhancement) cascaded face detection classifier (Haar classifier for short) based on Haar (wavelet feature) is usually used to detect the face in the photo or template, and according to the detected face The position cuts out the frontal face image, and then the face in the photo can be replaced with the corresponding face position in ...
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 Applications(China)
IPC IPC(8): G06K9/00
CPCG06V40/161G06V40/168
Inventor 谷枫李斌徐祯
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD