A human contour extraction method based on depth learning
A human body contour and deep learning technology, which is applied to instruments, character and pattern recognition, and computer components, etc., can solve problems such as poor human body contour extraction and slow model training speed
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0163] The source of the data set is Baidu's human body image segmentation database. The data in this database are images containing human bodies taken from various angles. There are 5387 training images and labeled samples in the database. The present invention selects 1,000 images as the training set, and selects 500 images as the test set in the remaining part. In the experiment, the network input image size is fixed at 224×224. In order to accurately and objectively evaluate the effect of the method in this paper, and to facilitate comparison with existing methods, the overlap rate is used to measure the performance of the improved human contour extraction model. The overlap rate is defined as follows:
[0164]
[0165] Among them, S is the degree of overlap, A P Extract the body area predicted by the network for the body contour, A GT Is the actual human body area. The higher the S, the higher the degree of overlap and the better the effect of human contour extraction.
...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


