Graph convolutional network‐based image matting algorithm for computer vision applications

Abstract

Image matting plays a vital role in a variety of computer vision tasks including video editing and image fusion. Previously presented image matting algorithms might fail in producing favorable results since most of them concentrate on the similarity between the neighboring pixels while neglecting the corresponding spatial relationship. To address this issue, an end-to-end image matting framework through leveraging deep learning mechanism and graph theory is proposed. The proposed pipeline is a concatenation of one deep feature extraction component and a Graph Convolutional Network (GCN). The former part takes an image and its corresponding trimap as inputs and can generate the pixel-wise features, which are then exploited as the input of the GCN locating at the latter part of the proposed framework. The GCN would refine the features for every pixel and predict the alpha matte outcome of the image. The approach outperforms a group of state-of-the-art matting techniques as shown by the theoretical analysis and experimental results in terms of both accuracy and visual effects.

Design of an Intelligent Laboratory Facial Recognition System Based on Expression Keypoint Extraction

“…The study's findings supported the model's predictions. The outcomes confirmed the model's accuracy in image processing, which is extremely beneficial in boosting the visual impression [7]. A transformer fault diagnosis model based on a graph convolutional network was created by W. Liao.…”

“…According to the uniform division strategy, a consistent weight vector 1 w exists for each node and neighbouring point of the face expression key point, at which point the graph convolution is implemented as shown in equation (7).…”

“…In equation (7), A denotes the adjacency matrix, Λ denotes the degree matrix of the adjacency matrix A , and 1 w denotes the weight vector. Information on facial images needs to be propagated, requiring connections to be made between keypoints of adjacent frames.…”

Application of 2D Images in Visual and Tactile Dimensions of Fiber Art Design

“…Li et al found that previously presented image matting algorithms might fail to produce favorable results since most of them concentrate on the similarity between the neighboring pixels while neglecting the corresponding spatial relationship. To address this issue, an end-to-end image matting framework through leveraging deep learning mechanism and graph theory is proposed [5]. Wang analyzed the development of traditional hand-woven craftsmanship into modern three-dimensional works, which had a positive impact on people's lives, for example, the application of fber art in specifc products [6].…”

Research on image features extraction based on graph convolutional network (Withdrawal Notice)

“…Graph convolutional networks can be utilized to learn representations of nodes and edges in a graph, and can be used for tasks such as node classification, link prediction and graph classification. Graph convolutional networks have been utilized in a variety of applications including drug discovery, recommendation systems and natural language processing [8] .…”