Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Interactive matting method based on recurrent neural network

A cyclic neural network and interactive mapping technology, applied in the computer field, can solve the problems of large workload requirements and high dependence on user input quality

Active Publication Date: 2019-02-22
DALIAN UNIV OF TECH
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0017] The present invention aims at the problem that the existing digital matting algorithm has a large workload and is highly dependent on user input quality, and designs an interactive matting method based on a cyclic neural network

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
  • Interactive matting method based on recurrent neural network
  • Interactive matting method based on recurrent neural network
  • Interactive matting method based on recurrent neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The present invention will be described in further detail below in conjunction with specific embodiments, but the present invention is not limited to specific embodiments.

[0061] The specific implementation process of the interactive matting method based on the cyclic neural network is mainly divided into two aspects. That is, the generation of the data set required for training the model and the selection and training method of the hyperparameters of the model itself.

[0062] (1) Training network model

[0063] When training this interactive matting method, we need a dataset with a large amount of data. The data set should include a colorful two-dimensional picture, which should contain an obvious foreground object to be extracted. In addition, corresponding to each color picture, the data set should also contain an accurate matting result (Alpha Matte), which is the real value (Ground Truth) during the training process. Existing related datasets include a mattin...

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 provides an interactive matting method based on a recurrent neural network, and belongs to the computer technical field. The invention designs an interactive matting method based on a circulating neural network for solving the problem that the workload of the existing digital matting algorithm is large and the input quality of the user is highly dependent. The designed framework reduces the non-value judgement result by artificially detecting the information area in the cycle process, and can obtain the matting result of the mainstream matting method while reducing the workload.The invention has the following beneficial effects: (1) an interactive model, (2) a long-term and short-term memory network, (3) a reinforcement learning method and (4) a three-dimensional scene rendering.

Description

technical field [0001] The invention relates to an interactive map-cutting method based on a cyclic neural network, which belongs to the technical field of computers. Background technique [0002] Image matting is a technology that separates the foreground in the image from the background. This technology can extract the area that people need, so as to facilitate subsequent operations on the key information of the image. Image matting is a hot problem in the direction of computer vision. Existing high-performance digital matting methods usually require prior knowledge, that is, the trimap of the entire image. However, the acquisition of the three-part map greatly increases the workload. For a small number of matting methods based on interactive input. The present invention aims at exploring a digital matting method based on interaction but limiting the user interaction mode by using a deep recurrent neural network, so as to achieve a satisfactory matting effect while redu...

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): G06T7/11G06T7/194
CPCG06T2207/20081G06T2207/20084G06T2207/20092G06T7/11G06T7/194
Inventor 陈少喆杨鑫尹宝才张强魏小鹏
Owner DALIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com