Search

Metallographic image segmentation is a core task towards the automation of metallographic analysis. Currently, the most advanced methods for this task generally employ supervised deep learning segmentation models that require a great number of pixel-level annotated images, while the annotation process is time-consuming and labor-intensive. In order to address this issue, a semi-supervised model called Con2Net is proposed in this work, which leverages unlabeled data to improve performance for metallographic image segmentation. The Con2Net model adopts a multi-decoder architecture, which enforces consistency constraint between each decoder’s output and other decoders’ soft pseudo labels produced by output sharpening. In addition, to mitigate the negative impact caused by sharpening on false predicted pixels, we adopt the sharpening operation only to accurately predicted pixels. For labeled pixels, comparing ground truth to filter out correctly predicted pixels is the simplest and most effective approach. For unlabeled pixels, a contrastive learning module is introduced, which encourages the model to have better intra-class compactness and inter-class dispersion in the feature space. Based on that, pseudo-labels for unlabeled pixels are obtained by calculating the maximum similarity of feature vectors, and then the accurately predicted unlabeled pixels could be filtered out. We conduct experiments on two public datasets for metallographic image segmentation, comparing the proposed Con2Net model with five state-of-the-art semi-supervised segmentation models on three semi-supervised data partition protocols. The results demonstrate that Con2Net not only outperforms the supervised baseline by a significant margin, but also achieves superior segmentation performance compared to other five semi-supervised models. Our source code is available at https://github.com/Siiimon2423/Con2Net.

Automated segmentation of the optic disc (OD) and optic cup (OC) from different datasets plays an important role in the diagnosis of glaucoma and greatly saves human resources in both data annotation and image segmentation. However, the domain shift between different datasets suppresses the generalization ability of the segmentation network, especially damaging the performance of segmentation in the target domain, which is unlabeled. Therefore, using a transfer learning algorithm or domain adaptation method to enhance the migration ability of segmentation models has become an essential step and has attracted the attention of many researchers. In this paper, we propose an unsupervised domain adaptation network, called the Minimizing-entropy and Fourier Domain Adaptation network (MeFDA), to narrow the discrepancy between the source and target domains and prevent the degradation of segmentation performance. First, we perform adversarial optimization on the entropy maps of the predicted segmentation results to alleviate the domain shift. Then, direct entropy-minimization optimization is applied to the unlabeled target domain data to improve the credibility of the prediction segmentation maps. To enhance the prediction consistency of the target domain data, we augment the target domain dataset through the Fourier transform by replacing the low-frequency part in the target images with that of the source images. Then, a semantic consistency constraint is imposed on the raw images and augmented images of the target domain to improve the prediction consistency of the segmentation model, thereby further narrowing the discrepancy between the source and target domains. Experiments on several public retinal fundus image datasets prove the superiority of MeFDA compared with state-of-the-art methods, and the ablation study analyzes the importance of the different proposed components.

Intra-pulse modulation phase calibration is necessary in inverse synthetic aperture radar (ISAR) imaging of high-speed targets. Traditional intra-pulse phase error compensation strategies rarely handle the high-order and slow-time-variant phase components induced during the coherent processing interval. In this paper, a novel intra-pulse modulation phase calibration with a two-dimensional (2-D) parametric phase model is proposed. It models the intra-pulse phase errors as a 2-D time-variant polynomial with accommodation of both fast-time and slow-time modulation. Entropy minimization of high-resolution range profiles (HRRPs) is developed to retrieve the phase error parameters. Improved coordinate descent optimization solver is established by Levenberg-Marquardt (LM) algorithm in order to find the global optimum of entropy efficiently. Comparative experiments using both simulated and real measured data are performed to demonstrate the enhancements of the proposed algorithm.

This paper proposes a new high-velocity motion compensation method for intermediate frequency direct sampling (IFDS) data by adaptive parameter adjustment of a matched filter and entropy minimization. First, the influence of high-velocity motion to IFDS data is analyzed. The high-velocity motion brings in aberration to the range profile and blurring the phase of inverse synthetic aperture radar imaging. Then, adaptive parameter adjustment of a matched filter is designed to accomplish joint high-velocity motion compensation and pulse compression. The iterative search for the velocity utilizing golden section search based on waveform entropy minimization is adopted to improve the efficiency. Experimental results demonstrate the validity of the proposed method.

This paper presents a new entropy minimization criterion for both symbol timing and carrier frequency recovery for wireless receivers. Synchronization is achieved by minimizing the entropy estimated from the eye diagram and the constellation diagram. Key implementation details are addressed toward the realization of entropy-based synchronization algorithms. In addition, the performance is evaluated in controlled conditions. It is shown that, as an alternative to the maximum likelihood criterion, entropy minimization has great potential and offers certain advantages for synchronization in wireless communication, particularly for pulse shaping filters with small excess bandwidth, as well as in multipath fading channels.