Light field microscopy is a high-speed 3D imaging technique that records the light field from multiple angles by the microlens array(MLA), thus allowing us to obtain information about the light source from a single image only. For the fundamental problem of neuron localization, we improve the method of combining depth-dependent dictionary with sparse coding in this paper. In order to obtain higher localization accuracy and good noise immunity, we propose an inertial proximal gradient acceleration algorithm with dry friction, Fast-IPGDF. By preventing falling into a local minimum, our algorithm achieves better convergence and converges quite fast, which improves the speed and accuracy of obtaining the locolization of the light source based on the matching depth of epipolar plane images (EPI). We demonstrate the effectiveness of the algorithm for localizing non-scattered fluorescent beads in both noisy and non-noisy environments. The experimental results show that our method can achieve simultaneous localization of multiple point sources and effective localization in noisy environments. Compared to existing studies, our method shows significant improvements in both localization accuracy and speed.

For pixel-level image fusion, convolutional sparse representation model usually relies on the ADMM in the Fourier domain, generating many iterations and losing the sense of locality, which may result in fused images with blurred texture parts. To extract texture information of images more effectively, a slice-based convolutional sparse representation (SCSR) model is proposed, which is solved by an inertial proximal gradient method with dry friction (IPGM-DF) algorithm in the signal domain. IPGM-DF updates the dictionary and sparse coefficients simultaneously. Experimental results of image fusion show that the proposed method is superior to the convolutional sparse representation-based fusion method in both subjective and objective evaluation, which are comparable to that of SOTA.

Ultrasound tongue imaging is an attractive way for speech production study as it provides an effective visualization for the vocal tract. Automatic classification of phonetic segments (tongue shapes) from raw ultrasound data is vital for further interpretation. Recently, deep learning-based approaches have been adopted in this task, which required a large-scale annotated dataset for the training, and it is not easy to be obtained in practical settings. Moreover, the data may contain many hard examples for the classification task, due to contamination of speckle noise. In this paper, we aim to address these issues: firstly, self-supervised learning is adopted to utilize the unlabeled datasets and extract the features without any human annotations; secondly, hard example mining is applied to imitate the learning path of the clinical linguists. To empirically demonstrate the proposed method’s effectiveness, we evaluate the method on the Ultrax Typically Developing dataset (UXTD) under different scenarios. The results show that the proposed method outperforms the other methods and achieves superior performance. To better promote the study in this field, we release our code publicly at1.