Computer Image Research Articles

Low Computational Complexity SAR Imaging Algorithm for Ship Monitoring via 2-D Band-Limited Sparse Fourier Transform

Low Computational Complexity SAR Imaging Algorithm for Ship Monitoring via 2-D Band-Limited Sparse Fourier Transform

A framework for identification of brain tumors from MR images using progressive segmentation

Abstract Purpose This study addresses the critical health issue of brain tumors, focusing on enhancing the accuracy of tumor segmentation from Magnetic Resonance Imaging (MRI) images. The primary research question investigates the effectiveness of a novel Hybrid Watershed–Clustering framework and its underlying Progressive Segmentation of the MR Images using the Radius and Intensity Measure (PS-RIM) algorithm. The aim is to improve the detection and segmentation of brain tumors within MR images, surpassing the efficacy of current methodologies. Methods The methodology involves a three-stage process. In the preprocessing stage, noise reduction and intensity normalization techniques are applied to clarify the images. The next stage is region-based segmentation, which includes morphological processing, edge detection, and thresholding to delineate tumor areas accurately. The final post-processing stage enhances segmentation accuracy and reduces false positives by integrating clustering machine learning techniques, specifically the K-Means cluster algorithm, to refine tumor identification. Results The framework's comprehensive evaluation across various MR images shows a significant improvement in accuracy over existing segmentation methods. The PS-RIM algorithm within the framework effectively captures the diverse presentations of tumor appearances in MR images. The research recorded an impressive accuracy rate of 98.11% in tumor detection, demonstrating enhanced identification and segmentation quality. Conclusions The study concludes that the proposed Hybrid Watershed–Clustering framework, powered by the PS-RIM algorithm, markedly improves the detection and differentiation of brain tumors in MR images. It exhibits exceptional accuracy, resilience, and computational efficiency. These findings hold substantial potential for advancing computer vision and image analysis in medical diagnostics, which could improve patient outcomes in managing brain tumors. Graphical abstract

Improving the reliability of deep learning computational ghost imaging with prediction uncertainty based on neighborhood feature maps

Improving the reliability of deep learning computational ghost imaging with prediction uncertainty based on neighborhood feature maps

Digital Image Forensics Using Deep Learning and Person Identification

In the realm of computer vision and image processing, the task of digital image identification holds significant importance across various domains. This paper presents a comparative study of two distinct methodologies for digital image identification: deep learning and the Haar cascade algorithm. Deep learning, specifically Convolutional Neural Networks (CNNs), has emerged as a powerful tool for automatically learning hierarchical representations from data and has achieved remarkable success in image-related tasks. In contrast, the Haar cascade algorithm, a classic machine learning technique, offers real-time object detection capabilities with its efficient feature-based approach. Through a series of experiments and evaluations on benchmark datasets, we analyze the performance, strengths, and limitations of these methodologies. Factors such as dataset size, computational resources, and application requirements are considered in the comparison. Our findings provide insights into the suitability of deep learning and the Haar cascade algorithm for various image identification tasks, aiding practitioners and researchers in selecting the most appropriate approach based on specific project needs. This research contributes to advancing the field of image processing and computer vision by offering a comprehensive analysis of these two prominent methodologies in digital image identification. Key Words: Deep Learning, Convolutional Neural Network (CNN), Haar cascade algorithm, image, forgery, detection

Neurophotonics beyond the surface: unmasking the brain's complexity exploiting optical scattering.

The intricate nature of the brain necessitates the application of advanced probing techniques to comprehensively study and understand its working mechanisms. Neurophotonics offers minimally invasive methods to probe the brain using optics at cellular and even molecular levels. However, multiple challenges persist, especially concerning imaging depth, field of view, speed, and biocompatibility. A major hindrance to solving these challenges in optics is the scattering nature of the brain. This perspective highlights the potential of complex media optics, a specialized area of study focused on light propagation in materials with intricate heterogeneous optical properties, in advancing and improving neuronal readouts for structural imaging and optical recordings of neuronal activity. Key strategies include wavefront shaping techniques and computational imaging and sensing techniques that exploit scattering properties for enhanced performance. We discuss the potential merger of the two fields as well as potential challenges and perspectives toward longer term in vivo applications.

Adaptive Ghost Imaging Based on 2D-Haar Wavelets

To improve the imaging speed of ghost imaging and ensure the accuracy of the images, an adaptive ghost imaging scheme based on 2D-Haar wavelets has been proposed. This scheme is capable of significantly retaining image information even under under-sampling conditions. By comparing the differences in light intensity distribution and sampling characteristics between Hadamard and 2D-Haar wavelet illumination patterns, we discovered that the lateral and longitudinal information detected by the high-frequency 2D-Haar wavelet measurement basis could be used to predictively adjust the diagonal measurement basis, thereby reducing the number of measurements required. Simulation and experimental results indicate that this scheme can still achieve high-quality imaging results with about a 25% reduction in the number of measurements. This approach provides a new perspective for enhancing the efficiency of computational ghost imaging.

Spatial wavefront shaping with a multipolar-resonant metasurface for structured illumination microscopy [Invited]

Structured illumination microscopy (SIM) achieves superresolution in fluorescence imaging through patterned illumination and computational image reconstruction, yet current methods require bulky, costly modulation optics and high-precision optical alignment, thus hindering the widespread implementation of SIM. To address this challenge, this work demonstrates how nano-optical metasurfaces, rationally designed to tailor the far-field optical wavefront at sub-wavelength dimensions, hold great potential as ultrathin, single-surface, all-optical wavefront modulators for SIM. We computationally demonstrate this principle with a multipolar-resonant metasurface composed of silicon nanostructures that generate versatile optical wavefronts in the far field upon variation of the polarization or angle of incident light. Algorithmic optimization is performed to identify the seven most suitable illumination patterns for SIM generated by the metasurface based on three key criteria. We quantitatively demonstrate that multipolar-resonant metasurface SIM (mrm-SIM) achieves resolution gain that is comparable to conventional methods by applying the seven optimal metasurface-generated wavefronts to simulated fluorescent objects and reconstructing the objects using proximal gradient descent. Notably, we show that mrm-SIM achieves these resolution gains with a far-field illumination pattern that circumvents complex equipment and alignment requirements of comparable methodologies. The work presented here paves the way for a metasurface-enabled experimental simplification of structured illumination microscopy.

Neural‐Optic Co‐Designed Polarization‐Multiplexed Metalens for Compact Computational Spectral Imaging

AbstractIn the expanding fields of mobile technology and augmented reality, there is a growing demand for compact, high‐fidelity spectral imaging systems. Traditional spectral imaging techniques face limitations due to their size and complexity. Diffractive optical elements (DOEs), although helpful in reducing size, primarily modulate the phase of light. Here, an end‐to‐end computational spectral imaging framework based on polarization‐multiplexed metalens is introduced. A distinguishing feature of this approach lies in its capacity to simultaneously modulate orthogonal polarization channels. When harnessed in conjunction with a neural network, it facilitates the attainment of high‐fidelity spectral reconstruction. Importantly, the framework is intrinsically fully differentiable, a feature that permits the joint optimization of both the metalens structure and the parameters governing the neural network. The experimental results presented herein validate the exceptional spatial‐spectral reconstruction performance, underscoring the efficacy of this system in practical, real‐world scenarios. This innovative approach transcends the traditional boundaries separating hardware and software in the realm of computational imaging and holds the promise of substantially propelling the miniaturization of spectral imaging systems.

An easy to use tool for the analysis of subcellular mRNA transcript colocalisation in smFISH data

Single molecule fluorescence in situ hybridisation (smFISH) has become a valuable tool to investigate the mRNA expression of single cells. However, it requires a considerable amount of programming expertise to use currently available open-source analytical software packages to extract and analyse quantitative data about transcript expression. Here, we present FISHtoFigure, a new software tool developed specifically for the analysis of mRNA abundance and co-expression in QuPath-quantified, multi-labelled smFISH data. FISHtoFigure facilitates the automated spatial analysis of transcripts of interest, allowing users to analyse populations of cells positive for specific combinations of mRNA targets without the need for computational image analysis expertise. As a proof of concept and to demonstrate the capabilities of this new research tool, we have validated FISHtoFigure in multiple biological systems. We used FISHtoFigure to identify an upregulation in the expression of Cd4 by T-cells in the spleens of mice infected with influenza A virus, before analysing more complex data showing crosstalk between microglia and regulatory B-cells in the brains of mice infected with Trypanosoma brucei brucei. These analyses demonstrate the ease of analysing cell expression profiles using FISHtoFigure and the value of this new tool in the field of smFISH data analysis.

Multi-camera Vehicle Tracking and Recognition with Multimodal Contrastive Domain Sharing GAN and Topological Embeddings

Tracking vehicles across a city using a network of multiple cameras are pivotal for enhancing urban and traffic management systems. However, this task is riddled with challenges such as wide geographical coverage, frequent view obstructions, and the diverse appearances of vehicles from various angles.
 To address these complexities, the proposed solution, dubbed Overlapped Vehicle Detection and Tracking using Multimodal Contrastive Domain Sharing Generative Adversarial Network optimized with Efficient Multi-camera system (MCDS-GAN), leverages cutting-edge techniques from computer vision, image processing, machine learning, and sensor fusion. This advanced system detects and tracks vehicles even in scenarios where multiple camera views overlap, making it applicable across domains like traffic management, surveillance, and autonomous vehicles.
 The methodology involves utilizing datasets like Common Objects in Context and ImageNet for training. Detection and tracking are performed using the Multimodal Contrastive Domain Sharing Generative Adversarial Network, followed by vehicle re-identification facilitated by the Topological Information Embedded Convolution Neural Network (TIE-CNN).
 Moreover, optimization techniques are employed to ensure synchronization and efficiency within the system. Implemented in Python, the effectiveness of MCDS-GAN is rigorously evaluated using metrics such as Accuracy, Precision, Recall, Latency, Response Time, and Scalability. Simulation results showcase its superiority, achieving significantly higher accuracy rates compared to existing methods such as OC-MCT-OFOV, MT-MCT-VM-CLM, and TI-VRI.

Quantification of cell shape, intracellular flows and transport based on DIC object detection and tracking.

Computational image analysis combined with label-free imaging has helped maintain its relevance for cell biology, despite the rapid technical improvements in fluorescence microscopy with the molecular specificity of tags. Here, we discuss some computational tools developed in our lab and their application to quantify cell shape, intracellular organelle movement and bead transport in vitro, using differential interference contrast (DIC) microscopy data as inputs. The focus of these methods is image filtering to enhance image gradients, and combining them with segmentation and single particle tracking (SPT). We demonstrate the application of these methods to Escherichia coli cell length estimation and tracking of densely packed lipid granules in Caenorhabditis elegans one-celled embryos, diffusing beads in solutions of different viscosities and kinesin-driven transport on microtubules. These approaches demonstrate how improvements to low-level image analysis methods can help obtain insights through quantitative cellular and subcellularmicroscopy.

Fast high quality computational ghost imaging based on saliency variable sampling detection

Fast computational ghost imaging with high quality and ultra-high-definition resolution reconstructed images has important application potential in target tracking, biological imaging and other fields. However, as far as we know, the resolution (pixels) of the reconstructed image is related to the number of measurements. And the limited resolution of reconstructed images at low measurement times hinders the application of computational ghost imaging. Therefore, in this work, a new computational ghost imaging method based on saliency variable sampling detection is proposed to achieve high-quality imaging at low measurement times. This method physically variable samples the salient features and realizes compressed detection of computational ghost imaging based on the salient periodic features of the bucket detection signal. Numerical simulation and experimental results show that the reconstructed image quality of our method is similar to the compressed sensing method at low measurement times. Even at 500 (sampling rate 0.76%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0.76\\%$$\\end{document}) measurement times, the reconstructed image of the method still has the target features. Moreover, the 2160×4096\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$2160\ imes 4096$$\\end{document} (4K) pixels ultra-high-definition resolution reconstructed images can be obtained at only a sampling rate of 0.11%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0.11\\%$$\\end{document}. This method has great potential value in real-time detection and tracking, biological imaging and other fields.

Multi-user visible light communication based on computational temporal ghost imaging and code division multiple access with wide field of view and encryption

In this paper, we propose a wide field of view optical encrypted communication based on computational temporal ghost imaging (CTGI) and code division multiple access (CDMA) with a violet series-biased micro-light-emitting diode (micro-LED) in visible light communication (VLC) system. Using CDMA to achieve multi-user communication, and CTGI to achieve secure transmission and improve signal quality, it is demonstrated that the algorithm ensures the transmission of LED under large field of view (FOV), with error-free communication at a wide angle of 120°. In terms of anti-interference encryption, correct demodulation can be achieved under 45% occlusion attack or 80% Gaussian noise attack, with a total of 6.16×10216 possibilities to ensure the security of user’s information, providing an approach for the practical application of VLC system.

CasFormer: Cascaded transformers for fusion-aware computational hyperspectral imaging

Computational hyperspectral imaging (CHI) is a cutting-edge technique, which plays a pivotal role in breaking through the quality bottleneck of hyperspectral images (HSI). Among the techniques employed in this domain, the coded aperture snapshot spectral imaging (CASSI) system holds widespread recognition. Nevertheless, the imaging capability of CASSI remains limited due to the hardware conditions and the fragility of outcomes associated with the ill-posed blind reconstruction process. To this end, we propose a novel cascaded transformer architecture, termed CasFormer, specifically crafted for fusion-aware CHI by means of a dual-imaging mechanism. CasFormer facilitates the effective enhancement of hyperspectral imaging quality by fusing RGB images, with a focus on spatial and spectral domains. As the name suggests, CasFormer is primarily composed of a series of cascade-attention blocks, enabling the fusion of high-spatial-resolution RGB images through spatial coherence alignment and the recovery of spectrally sequential information more compactly and accurately. Furthermore, CasFormer incorporates physical constraints through a decoupling-based loss function, ensuring spatial consistency and spectral fidelity in the fusion-aware CHI process. Extensive experiments conducted across multiple datasets demonstrate the superiority of CasFormer in achieving high-quality imaging results compared to SOTA CHI algorithms. Our code and benchmark datasets will be openly accessible at https://github.com/danfenghong/Information_Fusion_CasFormer.

Review of Machine Learning Techniques based Skin Microstructure Segmentation and Aging Classification

Abstract: Advancements in computer vision and image processing have fueled a growing interest in understanding the intricate details of skin microstructure for various applications, particularly in the context of aging. This review systematically examines recent developments in skin microstructure segmentation and aging classification methodologies, shedding light on the evolving landscape of research in this domain. Skin aging is a complex process characterized by various morphological and topological changes in the skin microstructure. Analyzing these changes can provide valuable insights into skin health and aging progression. This paper focuses on recent research advancements in skin microstructure segmentation and aging classification using convolutional neural network (CNN)-based models.

Compressed Sensing Image Reconstruction with Fast Convolution Filtering

Image reconstruction is a crucial aspect of computational imaging. The compressed sensing reconstruction (CS) method has been developed to obtain high-quality images. However, the CS method is commonly time-consuming in image reconstruction. To overcome this drawback, we propose a compressed sensing reconstruction method with fast convolution filtering (F-CS method), which significantly increases reconstruction speed by reducing the number of convolution operations without image fill. The experimental results show that by using the F-CS method, the reconstruction speed can be increased by a factor of 7 compared to the conventional CS method. Moreover, the F-CS method proposed in this paper is compared with the back-propagation reconstruction (BP) method and super-resolution reconstruction (SR) method, and it is validated that the proposed method has a lower computational resource cost for high-quality image reconstruction and exhibits a much more balanced capability.

Schwartz Symmetry Condition for Coherent Diffraction Imaging Patterns

We demonstrate a symmetry condition for the mixed partial derivatives of measured data when performing a coherent diffraction imaging (CDI) experiment for differentiable samples under scientific investigation. The proposed condition can be used as a physical restriction to improve real data measurements and has been used within the most celebrated phase-retrieval inversion algorithms as an ad hoc constraint without proof. The symmetry relies on John’s ultrahyperbolic equation for the X-ray transform, which is also demonstrated to be valid in the imaging regime for CDI. The obtained conditions are easy to implement and can be used as a constraint by computational imaging methods.

Application of sensor recognition based on artificial intelligence image algorithms in sports and human health

With the rapid development of artificial intelligence technology, the application of image algorithm in multimedia vision technology has made remarkable progress. In the field of sports, human health is an important concern, so it is of great significance to apply artificial intelligence image algorithm to the research of human health in sports. This paper uses computer vision and image processing technology, combined with artificial intelligence algorithm, to analyze and process the multimedia image of the movement. Through the acquisition and preprocessing of moving images, the key information and features of the movement are extracted. Then, deep learning algorithms and pattern recognition technology are used to analyze and evaluate the posture, movement and body state of the exercisers. Finally, according to the analysis results, personalized health advice and guidance are provided. The results show that the method can accurately identify and analyze the posture, movement and body state of the athletes, provide personalized health advice and guidance, help the athletes to improve the training effect, avoid sports injuries, and improve the level and quality of sports.

High-resolution X-Ray imaging of small animal samples based on Commercial-Off-The-Shelf CMOS image sensors.

An automated system for acquiring microscopic-resolution radiographic images of biological samples was developed. Mass-produced, low-cost, and easily automated components were used, such as Commercial-Off-The-Self CMOS image sensors (CIS), stepper motors, and control boards based on Arduino and RaspberryPi. System configuration, imaging protocols, and Image processing (filtering and stitching) were defined to obtain high-resolution images and for successful computational image reconstruction. Radiographic images were obtained for animal samples including the widely used animal models zebrafish (Danio rerio) and the fruit-fly (Drosophila melanogaster), as well as other small animal samples. The use of phosphotungstic acid (PTA) as a contrast agent was also studied. Radiographic images with resolutions of up to (7±0.6)μm were obtained, making this system comparable to commercial ones. This work constitutes a starting point for the development of more complex systems such as X-ray attenuation micro-tomography systems based on low-cost off-the-shelf technology. It will also bring the possibility to expand the studies that can be carried out with small animal models at many institutions (mostly those working on tight budgets), particularly those on the effects of ionizing radiation and absorption of heavy metal contaminants in animal tissues.

Multi-input mutual supervision network for single-pixel computational imaging

In this study, we propose a single-pixel computational imaging method based on a multi-input mutual supervision network (MIMSN). We input one-dimensional (1D) light intensity signals and two-dimensional (2D) random image signal into MIMSN, enabling the network to learn the correlation between the two signals and achieve information complementarity. The 2D signal provides spatial information to the reconstruction process, reducing the uncertainty of the reconstructed image. The mutual supervision of the reconstruction results for these two signals brings the reconstruction objective closer to the ground truth image. The 2D images generated by the MIMSN can be used as inputs for subsequent iterations, continuously merging prior information to ensure high-quality imaging at low sampling rates. The reconstruction network does not require pretraining, and 1D signals collected by a single-pixel detector serve as labels for the network, enabling high-quality image reconstruction in unfamiliar environments. Especially in scattering environments, it holds significant potential for applications.