Neural network model establishing method for image key point detection
A technology of neural network model and establishment method, which is applied in the direction of biological neural network model, image enhancement, neural architecture, etc., can solve the problem of insufficient robustness, achieve good accuracy and robustness, and reduce the effect of error
Pending Publication Date: 2020-05-08
深圳市图郅创新科技有限公司
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The traditional image processing method obtains the outline of the dressed human body through image segmentation, and requires subsequent processing to obtain the contour features of the net body for anthropometric measurement, which is not robust enough
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
[0026] Such as Figure 1-Figure 4 As shown, the present invention takes the key points of the human body contour as an example, and the steps of the neural network model establishment method for the detection of the key points of the image are as follows:
[0027] S10 prepares a human body contour key point data set. The data set is divided into the human body image data and the position coordinates of the corresponding key points of the body contour of the human body on the image. Human body image data is divided into image data in specific poses of the front and side of the human body. The contour key points are located on the human body contour, and the number can be specified as required.
[0028] Preprocessing of the S12 dataset. The image is uniformly scaled to the specified size, and the position coordinates of the contour key points on the image are mapped to the scaled image. Calculate the mean M and variance N of each RGB channel of all images in the image data se...
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
A neural network model establishing method for image key point detection is characterized by comprising the following steps of the step of acquiring an image key point data set wherein the data set iscomposed of a plurality of images and original position coordinates of image key points; preprocessing the data set, scaling the images in the data set to a specified size in a unified manner, and normalizing pixel values on the images; a data set classification step of dividing the preprocessed data set into a test set, a verification set and a test set; a data training step of inputting the data in the test set into a neural network model for training to obtain a plurality of error values; and a neural network model parameter correction step: reversely inputting each error value obtained inthe data training step into the neural network model to correct parameters of the neural network model, and verifying and testing the corrected model by using the test set and verification set data to obtain a final neural network model.
Description
technical field [0001] The invention relates to the field of computers, in particular to a neural network model establishment method for image key point detection. Background technique [0002] At present, the measurement of human body size mainly relies on manual work. With the popularization of smart phones, the collection of images has become more and more convenient. Image processing technology can use computers and other equipment to automatically process images and extract useful data from images. Using image processing technology, features can be extracted from the outline of the human body in the image, and then the feature data can be processed to obtain the size information of the human body for subsequent processing. The traditional image processing method obtains the silhouette of the dressed human body through image segmentation, and requires subsequent processing to obtain the contour features of the clean body for anthropometric measurement, which is not rob...
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 IPC IPC(8): G06T7/13G06N3/04
CPCG06T7/13G06T2207/20081G06T2207/30196G06N3/045
Inventor 朱帅印丁雪峰
Owner 深圳市图郅创新科技有限公司