Color Image Research Articles

Bayesian Dictionary Learning on Robust Tubal Transformed Tensor Factorization.

The recent study on tensor singular value decomposition (t-SVD) that performs the Fourier transform on the tubes of a third-order tensor has gained promising performance on multidimensional data recovery problems. However, such a fixed transformation, e.g., discrete Fourier transform and discrete cosine transform, lacks being self-adapted to the change of different datasets, and thus, it is not flexible enough to exploit the low-rank and sparse property of the variety of multidimensional datasets. In this article, we consider a tube as an atom of a third-order tensor and construct a data-driven learning dictionary from the observed noisy data along the tubes of the given tensor. Then, a Bayesian dictionary learning (DL) model with tensor tubal transformed factorization, aiming to identify the underlying low-tubal-rank structure of the tensor effectively via the data-adaptive dictionary, is developed to solve the tensor robust principal component analysis (TRPCA) problem. With the defined pagewise tensor operators, a variational Bayesian DL algorithm is established and updates the posterior distributions instantaneously along the third dimension to solve the TPRCA. Extensive experiments on real-world applications, such as color image and hyperspectral image denoising and background/foreground separation problems, demonstrate both effectiveness and efficiency of the proposed approach in terms of various standard metrics.

Point-of-Care Ultrasound Findings in Occlusive Iliac Vein Thrombus During Pregnancy: A Case Report.

Diagnosing deep venous thromboses and venous thromboemboli (DVT/VTE) in pregnant patients presents a unique challenge for emergency physicians. The risk of DVT/VTE increases during pregnancy, and the potential consequences of misdiagnoses are severe. Point-of-care ultrasonography (POCUS) is frequently a first-line diagnostic imaging modality. However, recent studies have shown a high incidence of thromboses proximal to the common femoral vein during pregnancy, and these would not be visualized using compressive ultrasonography, which traditionally can only visualize thromboses distal to the femoral vein. A 38-year-old female, 25-weeks primiparous, presented to the emergency department with a three-day history of left lower extremity swelling. Point-of-care three-point compression testing was used to evaluate for a DVT; however, no thrombus was visualized. Given high clinical suspicion, color and spectral Doppler testing were performed and demonstrated turbulent flow and reduced respiratory variation in the common femoral vein. This prompted further additional testing for a proximal DVT using magnetic resonance venography, which revealed an occlusive left external iliac thrombus. The patient was subsequently started on daily subcutaneous enoxaparin and discharged home with close follow-up. Emergency physicians play a critical role in evaluations for the presence of DVT/VTE, particularly in pregnant patients. We endorse the use of POCUS with three-point compression testing, as well as color and spectral Doppler imaging, to help identify proximal DVTs in this patient population. This case report can aid physicians in the diagnosis of this pathological condition that if left untreated can have severe consequences.

Non-local feature aggregation quaternion network for single image deraining

The existing deraining methods are based on convolutional neural networks (CNN) learning the mapping relationship between rainy and clean images. However, the real-valued CNN processes the color images as three independent channels separately, which fails to fully leverage color information. Additionally, sliding-window-based neural networks cannot effectively model the non-local characteristics of an image. In this work, we proposed a non-local feature aggregation quaternion network (NLAQNet), which is composed of two concurrent sub-networks: the Quaternion Local Detail Repair Network (QLDRNet) and the Multi-Level Feature Aggregation Network (MLFANet). Furthermore, in the subnetwork of QLDRNet, the Local Detail Repair Block (LDRB) is proposed to repair the backdrop of an image that has not been damaged by rain streaks. Finally, within the MLFANet subnetwork, we have introduced two specialized blocks, namely the Non-Local Feature Aggregation Block (NLAB) and the Feature Aggregation Block (Mix), specifically designed to address the restoration of rain-streak-damaged image backgrounds. Extensive experiments demonstrate that the proposed network delivers strong performance in both qualitative and quantitative evaluations on existing datasets. The code is available at https://github.com/xionggonghe/NLAQNet.

Taming Reversible Halftoning Via Predictive Luminance.

Traditional halftoning usually drops colors when dithering images with binary dots, which makes it difficult to recover the original color information. We proposed a novel halftoning technique that converts a color image into a binary halftone with full restorability to its original version. Our novel base halftoning technique consists of two convolutional neural networks (CNNs) to produce the reversible halftone patterns, and a noise incentive block (NIB) to mitigate the flatness degradation issue of CNNs. Furthermore, to tackle the conflicts between the blue-noise quality and restoration accuracy in our novel base method, we proposed a predictor-embedded approach to offload predictable information from the network, which in our case is the luminance information resembling from the halftone pattern. Such an approach allows the network to gain more flexibility to produce halftones with better blue-noise quality without compromising the restoration quality. Detailed studies on the multiple-stage training method and loss weightings have been conducted. We have compared our predictor-embedded method and our novel method regarding spectrum analysis on halftone, halftone accuracy, restoration accuracy, and the data embedding studies. Our entropy evaluation evidences our halftone contains less encoding information than our novel base method. The experiments show our predictor-embedded method gains more flexibility to improve the blue-noise quality of halftones and maintains a comparable restoration quality with a higher tolerance for disturbances.

Dual image watermarking based on NSST-LWT-DCT for color image

Advanced internet technology allows unauthorized individuals to modify and distribute digital images. Image watermarking is a popular solution for copyright protection and ensuring digital security. This research presents an embedding scheme with a set of conditions using non-subsampled Shearlet transform (NSST), lifting wavelet transform (LWT), and discrete cosine transform (DCT). Red and green channels are employed for the embedding process. The red channel is converted by NSST-LWT. The low-frequency area (LL) frequency is then split into small blocks of 8×8, each partition block is then transformed by DCT. The DCT coefficient of (3,4), (5,2), (5,3), (3,5), called matrix M1, and (2,5), (4,3), (6,2), (4,4), called matrix M2 are selected for singular value decomposition (SVD) process. With a set of conditions, the watermark bits are incorporated into those singular values. The green channel is cropped to get the center image before splitting into 4×4 pixels. The block components are then selected based on the least entropy value for the embedding regions. The selected blocks are then computed using LWT-SVD. A set of conditions for U(1,1) and U(2,1) are used to incorporate the watermark logo. The experimental findings reveal that the suggested scheme achieves high imperceptibility and resilience under various evaluating attacks with an average peak signal-to-noise ratio (PSNR) and correlation value (NC) values are up to 43.89 dB and 0.96, respectively.

A novel colorimetric sensor through peroxymonosulfate activated by CoFe@CN nanozymes for on-site resorcinol detection

The presence of resorcinol (RS) in water contaminated with pollutants may engender environmental and ecosystem risks. In this study, we developed rapid and efficient colorimetric methods for the on-site quantitative determination of RS. Specifically, a synthetic nanozyme composed of nitrogen-doped carbon-coated cobalt-iron (CoFe@CN) was utilized to initiate the oxidation reaction of 3,3′,5,5′-tetramethylbenzidine (TMB) with the activator of peroxymonosulfate (PMS). Compared to the activator of hydrogen peroxide (H2O2), PMS demonstrated a sixfold enhancement in catalytic efficacy, markedly elevating the detection performance. Density Functional Theory calculations indicate that RS can serve as a reducing agent for oxTMB, confirming the theoretical feasibility of this process. A linear relationship between inhibition rate (IR %) of RS concentration and absorbance was established and the colorimetric analysis revealed a linear relationship between RS concentration and gray scale values over the range of 0–45 μM, with a detection limit of 3.39 μM. Furthermore, smartphone-based analysis of color images allows for on-site quantitative analysis of RS concentration, leveraging portability and real-time detection capabilities. This study provides pioneering analytical support for on-site water quality monitoring within the ecological environment.

Temporally enhanced graph convolutional network for hand tracking from an egocentric camera

We propose a robust 3D hand tracking system in various hand action environments, including hand-object interaction, which utilizes a single color image and a previous pose prediction as input. We observe that existing methods deterministically exploit temporal information in motion space, failing to address realistic diverse hand motions. Also, prior methods paid less attention to efficiency as well as robust performance, i.e., the balance issues between time and accuracy. The Temporally Enhanced Graph Convolutional Network (TE-GCN) utilizes a 2-stage framework to encode temporal information adaptively. The system establishes balance by adopting an adaptive GCN, which effectively learns the spatial dependency between hand mesh vertices. Furthermore, the system leverages the previous prediction by estimating the relevance across image features through the attention mechanism. The proposed method achieves state-of-the-art balanced performance on challenging benchmarks and demonstrates robust results on various hand motions in real scenes. Moreover, the hand tracking system is integrated into a recent HMD with an off-loading framework, achieving a real-time framerate while maintaining high performance. Our study improves the usability of a high-performance hand-tracking method, which can be generalized to other algorithms and contributes to the usage of HMD in everyday life. Our code with the HMD project will be available at https://github.com/UVR-WJCHO/TEGCN_on_Hololens2.

Pseudo-ISP: Learning pseudo in-camera signal processing pipeline from a color image denoiser

Existing deep denoisers usually ignore the problem of noise discrepancy between training and test images caused by the different noise modeling of sensor and in-camera signal processing (ISP) pipeline, which inevitably degrades the denoising performance. In this paper, we present an unpaired learning scheme to adapt the color image denoisers for handling test images with noise discrepancy. To this end, we consider a practical training setting equipped with a pre-trained color denoiser, a set of test noisy sRGB images, and an unpaired set of clean sRGB images. Then, we propose to alternate between two modules, i.e., Pseudo-ISP training for learning noise modeling of sensor and in-camera signal processing (ISP) pipeline and denoiser adaption. Instead of modeling the complex noise in sRGB images, we assume the signal-dependent and spatially independent noise in rawRGB space, and specifically design the Pseudo-ISP to learn the pseudo ISP pipeline and pseudo rawRGB noise model jointly. Applying the learned Pseudo-ISP to the unpaired set of clean sRGB images, the corresponding realistic noisy sRGB observations can be easily obtained. Conversely, using the generated paired data for model fine-tuning, the color denoiser can be well adapted for test images. Through iterating between Pseudo-ISP training and denoiser adaption, denoising performance of deep denoisers can be further improved. Experiments show that our Pseudo-ISP not only can boost simple Gaussian blurring-based denoiser to achieve competitive performance against CBDNet, but also is effective in improving state-of-the-art deep denoisers, e.g., CBDNet and RIDNet.

A Lightweight CNN Based on Axial Depthwise Convolution and Hybrid Attention for Remote Sensing Image Dehazing

Hazy weather reduces contrast, narrows the dynamic range, and blurs the details of the remote sensing image. Additionally, color fidelity deteriorates, causing color shifts and image distortion, thereby impairing the utility of remote sensing data. In this paper, we propose a lightweight remote sensing-image-dehazing network, named LRSDN. The network comprises two tailored, lightweight modules arranged in cascade. The first module, the axial depthwise convolution and residual learning block (ADRB), is for feature extraction, efficiently expanding the convolutional receptive field with little computational overhead. The second is a feature-calibration module based on the hybrid attention block (HAB), which integrates a simplified, yet effective channel attention module and a pixel attention module embedded with an observational prior. This joint attention mechanism effectively enhances the representation of haze features. Furthermore, we introduce a novel method for remote sensing hazy image synthesis using Perlin noise, facilitating the creation of a large-scale, fine-grained remote sensing haze image dataset (RSHD). Finally, we conduct both quantitative and qualitative comparison experiments on multiple publicly available datasets. The results demonstrate that the LRSDN algorithm achieves superior dehazing performance with fewer than 0.1M parameters. We also validate the positive effects of the LRSDN in road extraction and land cover classification applications.

Image Enhancement Thanks to Negative Grey Levels in the Logarithmic Image Processing Framework.

The present study deals with image enhancement, which is a very common problem in image processing. This issue has been addressed in multiple works with different methods, most with the sole purpose of improving the perceived quality. Our goal is to propose an approach with a strong physical justification that can model the human visual system. This is why the Logarithmic Image Processing (LIP) framework was chosen. Within this model, initially dedicated to images acquired in transmission, it is possible to introduce the novel concept of negative grey levels, interpreted as light intensifiers. Such an approach permits the extension of the dynamic range of a low-light image to the full grey scale in "real-time", which means at camera speed. In addition, this method is easily generalizable to colour images and is reversible, i.e., bijective in the mathematical sense, and can be applied to images acquired in reflection thanks to the consistency of the LIP framework with human vision. Various application examples are presented, as well as prospects for extending this work.

Implementation of Convolutional Neural Network Algorithms to Detect the Ripeness of Palm Fruits based on Image Colors

The ripeness of oil palm fruit greatly affects the quality of the oil produced. Usually, humans manually detect the maturity of oil palm fruit, a process that can be inconsistent and time-consuming. Therefore, there is a need for automated methods that can improve accuracy and efficiency in determining the maturity of oil palm fruit. The study proposes using the Convolutional Neural Network algorithm to detect oil palm fruit maturity based on digital color images. We expect a convolutional neural network, known for its effectiveness in image analysis, to deliver accurate results in classifying fruit maturity. The aim of this study is to develop and test a model of a convolutional neural network that can classify oil palm fruit into three maturity categories: raw, ripe, and rotten. This study employs a maturity-categorized data set of oil palm images. We built and trained a convolutional neural network model using this data set. We evaluate the model performance using four main metrics: accuracy, precision, recall, and f1-score. We perform an in-depth analysis to assess model performance in each maturity category. The confusion matrix yielded an accuracy of 74.6%. The convolutional neural network model developed showed the highest precision results for the ripe fruit (86.00%), followed by rotten fruit (72.30%), and raw fruit (67.30%). We obtained the highest recalls (85.40%) for the raw fruit category, followed by ripe fruits (75.50%) and rotten fruits (72.30%.

Multiplexing of color images by theta modulation with laser beam in amplitude grating

Multiplexing of color images by theta modulation with laser beam in amplitude grating

Robust tensor recovery via a nonconvex approach with ket augmentation and auto‐weighted strategy

AbstractIn this article, we introduce a nonconvex tensor recovery approach, which employs the powerful ket augmentation technique to expand a low order tensor into a high‐order one so that we can exploit the advantage of tensor train (TT) decomposition tailored for high‐order tensors. Moreover, we define a new nonconvex surrogate function to approximate the tensor rank, and develop an auto‐weighted mechanism to adjust the weights of the resulting high‐order tensor's TT ranks. To make our approach robust, we add two mode‐unfolding regularization terms to enhance the model for the purpose of exploring spatio‐temporal continuity and self‐similarity of the underlying tensors. Also, we propose an implementable algorithm to solve the proposed optimization model in the sense that each subproblem enjoys a closed‐form solution. A series of numerical results demonstrate that our approach works well on recovering color images and videos.

Image privacy protection scheme based on high-quality reconstruction DCT compression and nonlinear dynamics

The protection of digital image privacy in Big Data environment is a hot issue of increasing concern. To address the contradiction between efficiency and security for privacy protection, this paper proposes a high-quality restored image privacy protection scheme based on Discrete Cosine Transform (DCT) frequency domain compression and nonlinear dynamics. First, the RGB space of the color image is converted to YCbCr domain with 4:2:0 sampling. Then, the image is divided into sub-blocks in the spatial domain, followed by block-wise DCT and quantization into frequency domain information. Next, both Alternating Current (AC) and Direct Current (DC) coefficients of all sub-blocks are individually extracted and subjected to compression encoding. Finally, a Rubik’s Cube permutation and filtering diffusion encryption algorithm based on a nonlinear dynamical chaotic system is designed. Moreover, a mechanism for generating dynamic chaotic sequences associated with plaintext is introduced to effectively counter cryptographic attacks. The combined approach of compression and encryption significantly reduces computational complexity while improving encryption efficiency. Through experimental simulation results, the compression encryption scheme demonstrates high compression ratios as well as excellent image recovery quality while providing enhanced security against common cryptographic attacks. The work in this paper provides a preferred joint compression and encryption technical solution for digital image privacy protection in Big Data network.

An Edge-Preserving Regularization Model for the Demosaicing of Noisy Color Images

This paper proposes an edge-preserving regularization technique to solve the color image demosaicing problem in the realistic case of noisy data. We enforce intra-channel local smoothness of the intensity (low-frequency components) and inter-channel local similarity of the depth of object borders and textures (high-frequency components). Discontinuities of both the low-frequency and high-frequency components are accounted for implicitly, i.e., through suitable functions of the proper derivatives. For the treatment of even the finest image details, derivatives of first, second, and third orders are considered. The solution to the demosaicing problem is defined as the minimizer of an energy function, accounting for all these constraints plus a data fidelity term. This non-convex energy is minimized via an iterative deterministic algorithm, applied to a family of approximating functions, each implicitly referring to geometrically consistent image edges. Our method is general because it does not refer to any specific color filter array. However, to allow quantitative comparisons with other published results, we tested it in the case of the Bayer CFA and on the Kodak 24-image dataset, the McMaster (IMAX) 18-image dataset, the Microsoft Demosaicing Canon 57-image dataset, and the Microsoft Demosaicing Panasonic 500-image dataset. The comparisons with some of the most recent demosaicing algorithms show the good performance of our method in both the noiseless and noisy cases.

A two-domain quantum color image watermarking scheme based on LSB algorithm

A two-domain quantum color image watermarking scheme based on LSB algorithm

Optimized Color Image Encryption Using Arnold Transform, URUK Chaotic Map and GWO Algorithm

Optimized Color Image Encryption Using Arnold Transform, URUK Chaotic Map and GWO Algorithm

Non-polypoid Colorectal Lesions Detection and False Positive Detection by Artificial Intelligence under Blue Laser Imaging and Linked Color Imaging.

Artificial intelligence (AI) with white light imaging (WLI) is not enough for detecting non-polypoid colorectal polyps and it still has high false positive rate (FPR). We developed AIs using blue laser imaging (BLI) and linked color imaging (LCI) to detect them with specific learning sets (LS). The contents of LS were as follows, LS (WLI): 1991 WLI images of lesion of 2-10 mm, LS (IEE): 5920 WLI, BLI, and LCI images of non-polypoid and small lesions of 2-20 mm. LS (IEE) was extracted from videos and included both in-focus and out-of-focus images. We designed three AIs as follows: AI (WLI) finetuned by LS (WLI), AI (IEE) finetuned by LS (WLI)+LS (IEE), and AI (HQ) finetuned by LS (WLI)+LS (IEE) only with images in focus. Polyp detection using a test set of WLI, BLI, and LCI videos of 100 non-polypoid or non-reddish lesions of 2-20 mm and FPR using movies of 15 total colonoscopy were analyzed, compared to 2 experts and 2 trainees. The sensitivity for LCI in AI (IEE) (83%) was compared to that for WLI in AI (IEE) (76%: p=0.02), WLI in AI (WLI) (57%: p<0.01), BLI in AI (IEE) (78%: p=0.14), and LCI in trainees (74%: p<0.01). The sensitivity for LCI in AI (IEE) (83%) was significantly higher than that in AI (HQ) (78%: p<0.01). The FPR for LCI (6.5%) in AI (IEE) were significantly lower than that in AI (HQ) (17.3%: p<0.01). AI finetuned by appropriate LS detected non-reddish and non-polypoid polyps under LCI.

A Multi-Plant Height Detection Method Based on Ruler-Free Monocular Computer Vision

Plant height is an important parameter of plant phenotype as one indicator of plant growth. In view of the complexity and scale limitation in current measurement systems, a scaleless method is proposed for the automatic measurement of plant height based on monocular computer vision. In this study, four peppers planted side by side were used as the measurement objects. Two color images of the measurement object were obtained by using a monocular camera at different shooting heights. Binary images were obtained as the images were processed by super-green grayscale and the Otsu method. The binarized images were transformed into horizontal one-dimensional data by the statistical number of vertical pixels, and the boundary points of multiple plants in the image were found and segmented into single-plant binarized images by filtering and searching for valleys. The pixel height was extracted from the segmented single plant image and the pixel displacement of the height was calculated, which was substituted into the calculation together with the reference height displacement to obtain the realistic height of the plant and complete the height measurements of multiple plants. Within the range of 2–3 m, under the light condition of 279 lx and 324 lx, this method can realize the rapid detection of multi-plant phenotypic parameters with a high precision and obtain more accurate plant height measurement results. The absolute error of plant height measurement is not more than ±10 mm, and the absolute proportion error is not more than ± 4%.

Paper-Based Microfluidic Analytical Device Patterned by Label Printer for Point-of-Care Blood Glucose and Hematocrit Detection Using 3D-Printed Smartphone Cassette.

This study presents a portable, low-cost, point-of-care (POC) system for the simultaneous detection of blood glucose and hematocrit. The system consists of a disposable origami microfluidic paper-based analytical device (μPAD) for plasma separation, filtration, and reaction functions and a 3D-printed cassette for hematocrit and blood glucose detection using a smartphone. The origami μPAD is patterned using a cost-effective label printing technique instead of the conventional wax printing method. The 3D-printed cassette incorporates an array of LED lights, which mitigates the effects of intensity variations in the ambient light and hence improves the accuracy of the blood glucose and hematocrit concentration measurements. The hematocrit concentration is determined quantitatively by measuring the distance of plasma wicking along the upper layer of the origami μPAD, which is pretreated with sodium chloride and Tween 20 to induce dehydration and aggregation of the red blood cells. The filtered plasma also penetrates to the lower layer of the origami μPAD, where it reacts with embedded colorimetric assay reagents to produce a yellowish-brown complex. A color image of the reaction complex is captured using a smartphone inserted into the 3D-printed cassette. The image is analyzed using self-written RGB software to quantify the blood glucose concentration. The calibration results indicate that the proposed detection platform provides an accurate assessment of the blood glucose level over the range of 45-630 mg/dL (R2 = 0.9958). The practical feasibility of the proposed platform is demonstrated by measuring the blood glucose and hematocrit concentrations in 13 human whole blood samples. Taking the measurements obtained from commercial glucose and hematocrit meters as a benchmark, the proposed system has a differential of no more than 6.4% for blood glucose detection and 9.1% for hematocrit detection. Overall, the results confirm that the proposed μPAD is a promising solution for cost-effective and reliable POC health monitoring.