Semi-supervised Large-scale Fiber Detection in Material Images with Synthetic Data
This addresses a domain-specific challenge in material science by enabling accurate fiber detection without extensive manual labeling, though it appears incremental as it builds on existing detection methods.
The paper tackles the problem of detecting large-scale elliptical fibers in degraded microscopic material images by proposing a semi-supervised deep learning method with synthetic data, which reduces the need for heavy annotations and shows robustness to image degradations.
Accurate detection of large-scale, elliptical-shape fibers, including their parameters of center, orientation and major/minor axes, on the 2D cross-sectioned image slices is very important for characterizing the underlying cylinder 3D structures in microscopic material images. Detecting fibers in a degraded image poses a challenge to both current fiber detection and ellipse detection methods. This paper proposes a new semi-supervised deep learning method for large-scale elliptical fiber detection with synthetic data, which frees people from heavy data annotations and is robust to various kinds of image degradations. A domain adaptation strategy is utilized to reduce the domain distribution discrepancy between the synthetic data and the real data, and a new Region of Interest (RoI)-ellipse learning and a novel RoI ranking with the symmetry constraint are embedded in the proposed method. Experiments on real microscopic material images demonstrate the effectiveness of the proposed approach in large-scale fiber detection.