Trajectory-based writing system refers to writing a linguistic character or word in free space by moving a finger, marker, or handheld device. It is widely applicable where traditional pen-up and pen-down writing systems are troublesome. Due to the simple writing style, it has a great advantage over the gesture-based system. However, it is a challenging task because of the non-uniform characters and different writing styles. In this research, we developed an air-writing recognition system using three-dimensional (3D) trajectories collected by a depth camera that tracks the fingertip. For better feature selection, the nearest neighbor and root point translation was used to normalize the trajectory. We employed the long short-term memory (LSTM) and a convolutional neural network (CNN) as a recognizer. The model was tested and verified by the self-collected dataset. To evaluate the robustness of our model, we also employed the 6D motion gesture (6DMG) alphanumeric character dataset and achieved 99.32% accuracy which is the highest to date. Hence, it verifies that the proposed model is invariant for digits and characters. Moreover, we publish a dataset containing 21,000 digits; which solves the lack of dataset in the current research.

Deep learning (DL) in magnetic resonance imaging (MRI) shows excellent performance in image reconstruction from undersampled k-space data. Artifact-free and high-quality MRI reconstruction is essential for ensuring accurate diagnosis, supporting clinical decision-making, enhancing patient safety, facilitating efficient workflows, and contributing to the validity of research studies and clinical trials. Recently, deep learning has demonstrated several advantages over conventional MRI reconstruction methods. Conventional methods rely on manual feature engineering to capture complex patterns and are usually computationally demanding due to their iterative nature. Conversely, DL methods use neural networks with hundreds of thousands of parameters and automatically learn relevant features and representations directly from the data. Nevertheless, there are some limitations to DL-based techniques concerning MRI reconstruction tasks, such as the need for large, labeled datasets, the possibility of overfitting, and the complexity of model training. Researchers are striving to develop DL models that are more efficient, adaptable, and capable of providing valuable information for medical practitioners. We provide a comprehensive overview of the current developments and clinical uses by focusing on state-of-the-art DL architectures and tools used in MRI reconstruction. This study has three objectives. Our main objective is to describe how various DL designs have changed over time and talk about cutting-edge tactics, including their advantages and disadvantages. Hence, data pre- and post-processing approaches are assessed using publicly available MRI datasets and source codes. Secondly, this work aims to provide an extensive overview of the ongoing research on transformers and deep convolutional neural networks for rapid MRI reconstruction. Thirdly, we discuss several network training strategies, like supervised, unsupervised, transfer learning, and federated learning for rapid and efficient MRI reconstruction. Consequently, this article provides significant resources for future improvement of MRI data pre-processing and fast image reconstruction.

We propose a time-sequential switching light-field (LF) camera for alternative image capture of high-resolution two-dimensional (2D) images and three-dimensional (3D) LF elemental images as additional functionalities. For image data acquisitions of both the 2D and 3D LF imaging of moving objects at a video-frame rate (or even higher frame rate up to approximately 1000 fps), a polarization-dependent-switching micro-lens array (PMLA) is implemented in the LF camera system instead of a conventional passive-type MLA. By controlling the incident polarization conditions using an electrically fast-switching liquid crystal layer, the imaging mode can be time-sequentially switched quite rapidly (switching times of approximately 220 μs and 290 μs for the mode conversions from the 3D LF to the 2D mode, and the reversal mode change, respectively). Using the elemental image sets sampled from the alternating time-sequential imaging results, either directional-view images or depth-refocused images can be reconstructed and provided at a moving picture frame-rate. The depth-refocused images are possible for a wide depth range from 25 cm to 350 cm. Directional views of 22 x 22 and 9 x 9 in portions can be reconstructed for the single shot image capture and the time-sequential video-rate image capture, respectively.

The joint tracking-based writing system refers to writing characters by changing the position of the finger joint. It is a new research field in interaction-based input systems. However, joint tracking is a very challenging task. In this article, we present a new method for a finger-joint tracking-based character recognition system using a 3-D camera. The proposed method tracks the finger-joint from 3-D information to identify a numerical digit, alphabet, character, special key, or symbol using the distance between the thumb tip and another finger-joint. The recognition is based on Euclidean distance thresholding and geometric slope techniques. Joint data are stored in a 3-D matrix to assign the 3-D coordinate values. The exact character is identified according to the specified definitions. First, a single hand-based digit recognition method is introduced, in which the left or right hand is used. Second, a double hand-based writing system is presented in which both hands are used simultaneously; this system features a full keyboard with 124 different characters. Our results show an overall accuracy of 91.95% and 91.85% for single-hand and double-hand recognition, respectively; with a recognition time of less than 60 ms for each character. An important contribution of this article is that the proposed system can work in both light and dark environments, requires only a small computation area and has a large number of character sets (124 characters). In addition, a region-based user study has been conducted to verify the approach.