Unlock instant, AI-driven research and patent intelligence for your innovation.

Image segmentation method and application and computing equipment

A computing device and image technology, applied in the video field, can solve problems such as hair misclassification, blurred boundaries, and large hair color changes, achieving high-precision segmentation, high robustness, and segmentation accuracy, and improving user experience.

Active Publication Date: 2017-05-31
XIAMEN MEITUZHIJIA TECH
View PDF5 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for some complex application scenarios (such as blurred boundaries between hair and background, large changes in hair color, loss of hair texture details, etc.), hair misclassification is prone to occur.

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
  • Image segmentation method and application and computing equipment
  • Image segmentation method and application and computing equipment
  • Image segmentation method and application and computing equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0021] figure 1 A block diagram of a computing device 100 according to some embodiments of the invention is shown. In the basic configuration 102, the computing device 100 typically includes a system memory 106 and one or more processors 104. The memory bus 108 may be used for communication between the processor 104 and the system memory 106.

[0022] Depending on the desired configuration, the processor 104...

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

No PUM Login to View More

Abstract

The invention discloses an image segmentation method and application and computing equipment. The image segmentation method comprises the steps that an image in each training sample is transmitted forwardly in a convolutional neural network model to be optimized so as to acquire a segmentation mask graph of a target region in the corresponding training sample; a descent gradient algorithm is utilized to perform parameter optimization on the convolutional neural network model to be optimized based on the deviation of the acquired segmentation mask graph of the target region in each training sample from a corresponding annotation mask graph; and the image to be segmented is transmitted forwardly in the convolutional neural network model with optimized parameters to acquire the segmentation mask graph of the target region in the image to be segmented.

Description

Technical field [0001] The present invention relates to the field of video technology, in particular to methods, applications and computing devices for segmenting images. Background technique [0002] Image segmentation is a basic operation in image processing and editing, and accurately segmenting the required area from the image is the key to content-based image processing algorithms. For example, segmenting the hair region from an image is a practical application of image segmentation technology. In some practical tasks such as hair color changing and hair beautification, hair segmentation is a necessary processing step, and it is also the focus and difficulty of the entire task. [0003] Most of the existing solutions are based on general image segmentation processing methods. Commonly used image segmentation methods include threshold segmentation, edge segmentation, region growth segmentation, cluster segmentation and graph cut segmentation methods. Traditional image segmen...

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
no application Login to View More
IPC IPC(8): G06T7/11G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06T2207/20084G06T2207/20081G06T2207/10004G06T2207/10024G06T2207/30201G06V40/162G06N3/045
Inventor 刘挺万鹏飞张伟傅松林
Owner XIAMEN MEITUZHIJIA TECH