An Effective Face Anti-Spoofing Method via Stereo Matching

Li, Zhishan; Yuan, Jiayan; Jia, Baozhi; He, Yifan; Xie, Lei

doi:10.1109/lsp.2021.3072284

Cited by 14 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the disparity information between matching points, the three-dimensional (3D) structure information of the corresponding scene can be recovered (Li, 2018). Therefore, stereo-matching is widely used in many fields, such as 3D reconstruction (Ye & Wu, 2018), face recognition (Li et al, 2021), target tracking (Lu & Lin, 2016) and smart city (Zhang et al, 2019). Stereo-matching methods can be separated into traditional (Scharstein & Szeliski, 2002) and deep-learning methods (Park & Lee, 2017).…”

Section: Introductionmentioning

confidence: 99%

Minimum spanning tree dynamic programming stereo‐matching method based on superpixels

Wang

2023

The Photogrammetric Record

View full text Add to dashboard Cite

The minimum spanning tree (MST) stereo-matching method is an information-infiltration process. The difference in edge attributes of an MST can cause the edge-expansion phenomenon, which affects the matching accuracy. To accurately recover image-depth information, a dynamicprogramming stereo-matching method based on the MST was proposed. First, the colour Birchfield Tomasi costcalculation method based on image adaptive colour information was proposed to obtain stable initial cost values.Second, the image was segmented into superpixel regions using the simple linear iterative clustering algorithm. The pixel-and region-level MSTs were then constructed. Next, combined with the idea of dynamic programming, the MST cost-aggregation process was re-deduced. On this basis, the aggregate cost values of the two MSTs were obtained. Finally, the aggregate cost values were combined adaptively to acquire the high-precision smooth disparity map. The Middlebury 2014 dataset was used for the experiments. The experimental results indicate that the proposed method can effectively improve the accuracy of stereo-matching.

show abstract

Section: Introductionmentioning

confidence: 99%

Minimum spanning tree dynamic programming stereo‐matching method based on superpixels

Wang

2023

The Photogrammetric Record

View full text Add to dashboard Cite

show abstract

“…Particularly, although dense correspondence estimation is a fundamental task in computer vision, which has been investigated widely on other signal formats (e.g. 2D image [9], [10]), it remains a challenging problem for point cloud data due to the inherent characteristics of the point cloud (e.g. irregularity, orderless), the serious deformation of object shape, and so on.…”

Section: Introductionmentioning

confidence: 99%

Searching Dense Point Correspondences via Permutation Matrix Learning

Zhang

Sun

Dai

et al. 2022

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Although 3D point cloud data has received widespread attentions as a general form of 3D signal expression, applying point clouds to the task of dense correspondence estimation between 3D shapes has not been investigated widely. Furthermore, even in the few existing 3D point cloud-based methods, an important and widely acknowledged principle, i.e. one-toone matching, is usually ignored. In response, this paper presents a novel end-to-end learning-based method to estimate the dense correspondence of 3D point clouds, in which the problem of point matching is formulated as a zero-one assignment problem to achieve a permutation matching matrix to implement the oneto-one principle fundamentally. Note that the classical solutions of this assignment problem are always non-differentiable, which is fatal for deep learning frameworks. Thus we design a special matching module, which solves a doubly stochastic matrix at first and then projects this obtained approximate solution to the desired permutation matrix. Moreover, to guarantee end-to-end learning and the accuracy of the calculated loss, we calculate the loss from the learned permutation matrix but propagate the gradient to the doubly stochastic matrix directly which bypasses the permutation matrix during the backward propagation. Our method can be applied to both non-rigid and rigid 3D point cloud data and extensive experiments show that our method achieves state-of-the-art performance for dense correspondence learning.

show abstract

“…e corresponding points obtained from the binocular imaging model can be used to recover the depth of the scene or its 3D coordinate information. erefore, stereo matching has a wide application space in 3D reconstruction [2], medicine [3], face recognition [4], automatic driving [5], and many other elds. As for stereo matching, it can be divided into two main categories.…”

Section: Introductionmentioning

confidence: 99%

Binocular Images Dense Matching considering Image Adaptive Color Weights and Feature Points

Wang

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

When the matching cost function in Semiglobal Matching is unstable, the inaccurate matching cost values will be propagated in the cost aggregation process. It will lead to a serious mismatching phenomenon. To address the problem, a binocular images dense matching method considering image adaptive color weights and feature points was proposed. Firstly, The Color Birchfield Tomasi (CBT) matching cost calculation method was proposed to obtain a stable initial cost volume, which combined image adaptive color weights and gradient information. Secondly, the Scale-invariant Feature Transform matching algorithm was used to extract the a priori feature points from binocular images. Then, the feature points were filtrated. The cost volume was optimized by using their coordinate information and disparity information. Finally, an aggregation path segmentation rectification method was adopted to optimize the SGM aggregation paths and reduce the propagation of incorrect paths. Experimental results demonstrate that the proposed method can effectively improve the stability and accuracy of dense matching, reduce the mismatching phenomenon, and finally produce high-quality disparity maps.

show abstract

An Effective Face Anti-Spoofing Method via Stereo Matching

Cited by 14 publications

References 20 publications

Minimum spanning tree dynamic programming stereo‐matching method based on superpixels

Minimum spanning tree dynamic programming stereo‐matching method based on superpixels

Searching Dense Point Correspondences via Permutation Matrix Learning

Binocular Images Dense Matching considering Image Adaptive Color Weights and Feature Points

Contact Info

Product

Resources

About