Color Pixels Research Articles

Compact Single-Shot Dual-Wavelength Interferometry for Large Object Measurement with Rough Surfaces

Single-shot dual-wavelength interferometry offers a promising avenue for surface profile measurement of dynamic objects. However, current techniques employing pixel multiplexing or color cameras encounter challenges such as complex optical alignment, limited measurement range, and difficulty in measuring rough surfaces. To address these issues, this study presents a novel approach to single-shot dual-wavelength interferometry. By utilizing separated polarization illumination and detection, along with a monochromatic polarization camera and two slightly different wavelengths, this method enables the simultaneous recording of two frames of separated interferometric patterns. This approach facilitates straightforward optical alignment, expands measurement ranges, accelerates data acquisition, and simplifies data processing for dual-wavelength interferometry. Consequently, it enables online shape measurement of large dynamic samples with rough surfaces.

Enhancing Diabetic Retinopathy Detection Using Pixel Color Amplification and EfficientNetV2: A Novel Approach for Early Disease Identification

Diabetic retinopathy (DR) is a severe complication of diabetes, causing damage to retinal blood vessels due to high blood sugar levels. Early detection is crucial but often requires significant time and expertise from ophthalmologists. While artificial intelligence (AI) and image recognition hold promise for DR detection, inconsistent image quality poses a challenge. Our study presents a novel technique that integrates pixel color amplification and EfficientNetV2 to enhance fundus image attributes, aiming to address issues related to image quality and achieving superior performance in DR detection. Leveraging EfficientNetV2, an advanced convolutional neural network (CNN) architecture, we achieve 84% multiclass accuracy and 99% binary accuracy, surpassing various other CNN models, including VGG16-fc1, VGG16-fc2, NASNet, Xception, Inception ResNetV2, EfficientNet, InceptionV3, MobileNet, and ResNet50. Our research tackles the critical challenge of early detection of DR, essential for preventing vision loss. This advancement holds the potential to enhance the efficiency and accuracy of DR classification, potentially alleviating the burden on medical professionals and ultimately improving the quality of life for individuals at risk of vision loss.

Colour-analyzer: a new dual colour model-based imaging tool to quantify plant disease

BackgroundDespite major efforts over the last decades, the rising demands of the growing global population makes it of paramount importance to increase crop yields and reduce losses caused by plant pathogens. One way to tackle this is to screen novel resistant genotypes and immunity-inducing agents, which must be conducted in a high-throughput manner.ResultsColour-analyzer is a free web-based tool that can be used to rapidly measure the formation of lesions on leaves. Pixel colour values are often used to distinguish infected from healthy tissues. Some programs employ colour models, such as RGB, HSV or L*a*b*. Colour-analyzer uses two colour models, utilizing both HSV (Hue, Saturation, Value) and L*a*b* values. We found that the a* b* values of the L*a*b* colour model provided the clearest distinction between infected and healthy tissue, while the H and S channels were best to distinguish the leaf area from the background.ConclusionBy combining the a* and b* channels to determine the lesion area, while using the H and S channels to determine the leaf area, Colour-analyzer provides highly accurate information on the size of the lesion as well as the percentage of infected tissue in a high throughput manner and can accelerate the plant immunity research field.

Clinical implementation of a fully automated quantitative perfusion cardiovascular magnetic resonance imaging workflow with a simplified dual-bolus contrast administration scheme

This study clinically implemented a ready-to-use quantitative perfusion (QP) cardiovascular magnetic resonance (QP CMR) workflow, encompassing a simplified dual-bolus gadolinium-based contrast agent (GBCA) administration scheme and fully automated QP image post-processing. Twenty-five patients with suspected obstructive coronary artery disease (CAD) underwent both adenosine stress perfusion CMR and an invasive coronary angiography or coronary computed tomography angiography. The dual-bolus protocol consisted of a pre-bolus (0.0075 mmol/kg GBCA at 0.5 mmol/ml concentration + 20 ml saline) and a main bolus (0.075 mmol/kg GBCA at 0.5 mmol/ml concentration + 20 ml saline) at an infusion rate of 3 ml/s. The arterial input function curves showed excellent quality. Stress MBF ≤ 1.84 ml/g/min accurately detected obstructive CAD (area under the curve 0.79; 95% Confidence Interval: 0.66 to 0.89). Combined visual assessment of color pixel QP maps and conventional perfusion images yielded a diagnostic accuracy of 84%, sensitivity of 70% and specificity of 93%. The proposed easy-to-use dual-bolus QP CMR workflow provides good image quality and holds promise for high accuracy in diagnosis of obstructive CAD. Implementation of this approach has the potential to serve as an alternative to current methods thus increasing the accessibility to offer high-quality QP CMR imaging by a wide range of CMR laboratories.

Secure Pixel-Level Data Concealment: A Novel Approach for Securing Black and White Images within Color Images

In the era of rampant digital data transfer, concerns regarding the secure and reliable transmission of information persist, with numerous attempts at concealing and transporting data globally. Despite the plethora of existing techniques, issues persist, ranging from misinterpretation to malicious misuse of data during the transfer process. To address some of these challenges, this research introduces an innovative method centered on the modification of pixel data to embed concealed information. The primary objective is to alter pixel values in a manner that accommodates the storage of data pertaining specifically to black and white image pixel data. The proposed technique is designed to exclusively encode information related to two-pixel values, with careful adjustments made to ensure the masked image remains non-deceptive. Pixel values undergo subtle alterations to mitigate susceptibility issues associated with corner values, particularly at the border values of 254 and 255 for RGB values. The developed method presents a simplified yet robust data hiding technique, allowing the storage of black and white images within color images while achieving a high Peak Signal-to-Noise Ratio (PSNR) compared to standard ".png" images. Crucially, the developed approach addresses the challenge of minimizing drastic changes in pixel color, enhancing the overall fidelity of the stego image. Furthermore, the versatility of the proposed method is showcased by its potential to accommodate more than three images when the stego image size is appropriately large and segmented. A practical and efficient solution has been contributed to the persistent issues associated with secure data transfer, presenting a novel methodology for concealing black and white images within color images.

ProLiF: Progressively-connected Light Field network for efficient view synthesis

This paper presents a simple yet practical network architecture, ProLiF (Progressively-connected Light Field network), for the efficient differentiable view synthesis of complex forward-facing scenes in both the training and inference stages. The progress of view synthesis has advanced significantly due to the recent Neural Radiance Fields (NeRF). However, when training a NeRF, hundreds of network evaluations are required to synthesize a single pixel color, which is highly consuming of device memory and time. This issue prevents the differentiable rendering of a large patch of pixels in the training stage for semantic-level supervision, which is critical for many practical applications such as robust scene fitting, style transferring, and adversarial training. On the contrary, our proposed simple architecture ProLiF, encodes a two-plane light field, which allows rendering a large batch of rays in one training step for image- or patch-level losses. To keep the multi-view 3D consistency of the neural light field, we propose a progressive training strategy with novel regularization losses. We demonstrate that ProLiF has good compatibility with LPIPS loss to achieve robustness to varying light conditions, and NNFM loss as well as CLIP loss to edit the rendering style of the scene.

ALAT PERAGA ELEKTRONIK BERBASIS ARDUINO DENGAN KELUARAN CAHAYA DAN SUARA UNTUK PENGENALAN WARNA BAGI BALITA

Recognizing the color of an object is a basic thing that must be taught to toddlers. This research aims to design and realize a color recognition teaching aids for toddlers, designed using an electronic device based on an Arduino Uno microcontroller with output in the form of audio sound and light. This tool consists of: an object in the form of a colorful plastic ball, an input device in the form of a TCS230 color sensor, a processing and controlling device in the form of an Arduino Uno microcontroller, and output devices in the form of a DC servo motor, RGB LED strip, and loudspeaker. Based on the results of measurements and tests that have been carried out, the Arduino Uno microcontroller can function to control all input and output devices. The TCS230 color sensor successfully detected the color pixel value (RGB) of the object, and issued wavelength information in the form of frequency quantities. The DC servo motor can move to direct the object to the mouth of the slide pipe. The loudspeaker can produce audio sounds according to the name of the object's color. RGB LED strips can emit light according to the color of the object. Overall, the results of the design and realization, measurement and testing of color recognition teaching aids for toddlers are in accordance with what was planned.

DiffRAW: Leveraging Diffusion Model to Generate DSLR-Comparable Perceptual Quality sRGB from Smartphone RAW Images

Deriving DSLR-quality sRGB images from smartphone RAW images has become a compelling challenge due to discernible detail disparity, color mapping instability, and spatial misalignment in RAW-sRGB data pairs. We present DiffRAW, a novel method that incorporates the diffusion model for the first time in learning RAW-to-sRGB mappings. By leveraging the diffusion model, our approach effectively learns the high-quality detail distribution of DSLR images, thereby enhancing the details of output images. Simultaneously, we use the RAW image as a diffusion condition to maintain image structure information such as contours and textures. To mitigate the interference caused by the color and spatial misalignment in training data pairs, we embed a color-position preserving condition within DiffRAW, ensuring that the output images do not exhibit color biases and pixel shift issues. To accelerate the inference process of DiffRAW, we designed the Domain Transform Diffusion Method, an efficient diffusion process with its corresponding reverse process. The Domain Transform Diffusion Method can reduce the required inference steps for diffusion model-based image restoration/enhancement algorithms while enhancing the quality of the generated images. Through evaluations on the ZRR dataset, DiffRAW consistently demonstrates state-of-the-art performance across all perceptual quality metrics (e.g., LPIPS, FID, MUSIQ), while achieving comparable results in PSNR and SSIM.

Structure-aware neural radiance fields without posed camera

The neural radiance fields (NeRF) for realistic novel view synthesis require camera poses to be pre-acquired by a structure-from-motion (SfM) approach. This two-stage strategy is not convenient to use and degrades the performance because the error in the pose extraction can propagate to the view synthesis. We integrate pose extraction and view synthesis into a jointly optimized process so that they can benefit from each other. For network training, only images are given without pre-known camera poses. The camera poses are obtained by the depth-consistent constraint in which the identical feature in different views has the same world coordinates transformed from the local camera coordinates according to the extracted poses. The depth-consistent constraint is jointly optimized with the pixel color constraint. The poses are represented by a CNN-based deep network, whose input is the related frames. This joint optimization enables NeRF to be aware of the scene’s structure, resulting in improved generalization performance. Experiments on three datasets demonstrate the effectiveness of camera pose estimation and novel view synthesis. Code is available at https://github.com/XTU-PR-LAB/SaNerf.

Research on interference compensation methods for color image sensors based on iterative learning

PurposeFixed mode noise and random mode noise always exist in the image sensor, which affects the imaging quality of the image sensor. The charge diffusion and color mixing between pixels in the photoelectric conversion process belong to fixed mode noise. This study aims to improve the image sensor imaging quality by processing the fixed mode noise.Design/methodology/approachThrough an iterative training of an ergoable long- and short-term memory recurrent neural network model, the authors obtain a neural network model able to compensate for image noise crosstalk. To overcome the lack of differences in the same color pixels on each template of the image sensor under flat-field light, the data before and after compensation were used as a new data set to further train the neural network iteratively.FindingsThe comparison of the images compensated by the two sets of neural network models shows that the gray value distribution is more concentrated and uniform. The middle and high frequency components in the spatial spectrum are all increased, indicating that the compensated image edges change faster and are more detailed (Hinton and Salakhutdinov, 2006; LeCun et al., 1998; Mohanty et al., 2016; Zang et al., 2023).Originality/valueIn this paper, the authors use the iterative learning color image pixel crosstalk compensation method to effectively alleviate the incomplete color mixing problem caused by the insufficient filter rate and the electric crosstalk problem caused by the lateral diffusion of the optical charge caused by the adjacent pixel potential trap.

Video saliency-recognition by applying custom spatio temporal fusion technique

<span lang="EN-US">Video saliency detection is a major growing field with quite few contributions to it. The general method available today is to conduct frame wise saliency detection and this leads to several complications, including an incoherent pixel-based saliency map, making it not so useful. This paper provides a novel solution to saliency detection and mapping with its custom spatio-temporal fusion method that uses frame wise overall motion colour saliency along with pixel-based consistent spatio-temporal diffusion for its temporal uniformity. In the proposed method section, it has been discussed how the video is fragmented into groups of frames and each frame undergoes diffusion and integration in a temporary fashion for the colour saliency mapping to be computed. Then the inter group frame are used to format the pixel-based saliency fusion, after which the features, that is, fusion of pixel saliency and colour information, guide the diffusion of the spatio temporal saliency. With this, the result has been tested with 5 publicly available global saliency evaluation metrics and it comes to conclusion that the proposed algorithm performs better than several state-of-the-art saliency detection methods with increase in accuracy with a good value margin. All the results display the robustness, reliability, versatility and accuracy.</span>

Stretchable structural colors with polarization dependence using lithium niobate metasurfaces.

Independently tunable biaxial color pixels, composed of isolated nanosquare dimers, are demonstrated in this study. These pixels are capable of displaying a full range of colors under a linear-polarization dependent reflection mode. The metasurface is constructed by arranging LiNbO3 nanodimers on a PDMS substrate. By exciting a strong magnetic dipole (MD) resonance and effectively suppressing other multipolar resonances using surface lattice resonances, the researchers achieved a single reflection peak with a bandwidth of less than 9 nm and a reflective efficiency of up to 99%. Additionally, the stretchability of the PDMS substrate allows for active and continuous tuning of the metasurface by up to 40% strain, covering almost 150 nm of the visible light spectrum and enabling changes in reflection color. This metasurface holds potential applications in various fields, such as color displays, data storage, and anti-counterfeiting technologies.

Robust face recognition using quaternion interval type II fuzzy logic-based feature extraction on colour images.

In this paper, we propose a new robust and fast learning technique by investigating the effect of integration of quaternion and interval type II fuzzy logic along with non-iterative, parameter free deterministic learning machine (DLM) pertaining to face recognition problem. The traditional learning techniques did not account colour information and degree of pixel wise association of individual pixel of a colour face image in their network. Therefore, this paper presents a new technique named quaternion interval type II based deterministic learning machine (QIntTyII-DLM), which considers the interrelationship between three colour channels viz. red, green, and blue (RGB) by representing each colour pixel of a colour image in quaternion number sequence. Here, quaternion vector representation of a colour face image is fuzzified using interval type II fuzzy logic. This reduces the redundancy between pixels of different colour channels and also transforms colour channels of the image to orthogonal colour space. Thereafter, classification is performed using DLM. Experiments performed (on four standard datasets AR, Georgia Tech, Indian, face (female) and faces 94 (male) face datasets) and comparison done with other existing techniques proves that the proposed technique gives better results in terms of percentage error rate (reduces approximately 10-12%) and computational speed.

Assessment of renal congestion in a rat model with congestive heart failure using superb microvascular imaging.

Renal congestion is a therapeutic target in congestive heart failure. However, its detailed evaluation in a clinical setting is challenging. This study sought to assess renal congestion impairment using superb microvascular imaging (SMI), a simple and accessible method. Dahl salt-sensitive rats, used as a model for congestive heart failure, underwent central venous pressure (CVP) measurements. Renal congestion was evaluated through measurements of renal medullary pressure (RMP) and assessment of renal perfusion using contrast-enhanced ultrasonography at both the early (control group) and heart failure phases (HF group). All rats were assessed with SMI. The region of interest (ROI) was set in interlobular vessels, interlobar vessels, and a combination of these areas. The area ratio was calculated from the color pixel count in the ROI divided by the total pixel count in the ROI. Intrarenal perfusion index (IRPI) was defined as (maximum area ratio-minimum area ratio) / maximum area ratio. There were no significant differences in renal function and left ventricular ejection fraction between the two groups. CVP, time-to-peak (TTP) in the medulla, and RMP were higher in the HF group than in the control group. In the HF group, IRPI, evaluated in the interlobular vessels, was significantly higher than in the control group. IRPI was positively correlated with TTP in the medulla (p = 0.028, R = 0.60) and RMP (p < 0.001, R = 0.84), indicating that IRPI reflected renal congestion. IRPI is a useful tool for assessing renal congestion in rats with congestive heart failure.

Exploration of Agricultural Product Packaging Design Innovation in the Context of Deep Learning

Abstract Utilizing Internet technology and resources to enhance the packaging design of agricultural products is a critical task for promoting their development in the current era. This study proposes an automatic generation design for agricultural product packaging based on deep learning theory, grounded in the principles of packaging design and market value. To represent the spatial relationship and distribution of color pixels, color moments and color correlation maps are used after obtaining color features of agricultural products through the HSV color space. The grayscale covariance matrix method is employed to get the texture features necessary for the packaging design. Proportion, boundary, pairing, white space, and balance calculations are combined to achieve the layout and typography of feature elements in the agricultural packaging design. The impact of deep learning technology-supported packaging design is analyzed. Data show that in the first group, the average values of the sample group (P001, P002, P004) are 2.98, 3.08, and 2.93, respectively, with an overall average of 2.997, while the overall average of the intelligent group (P003) is 2.96. Overall, deep learning technology-assisted image generation has a positive impact on agricultural product packaging design, contributing to a new level of economic development of farming products.

An Efficient VLSI Architecture for Bi-Cubic Interpolation using Carry Skip Adder

In any signal processing system, signal distortion can occur. A compensation scheme would adjust the captured signal to correct for any deviations and ensure accurate signal transmission and preservation. A compensation scheme is used to correct such deviations for mostly linear is used to enhance the quality of reconstructed signal suitable for high-quality super-resolution techniques. This technique is applicable for multidimensional signal processing such as image processing. Except for the resolution of the acquired images, the extracting of colour information is greatly affected by the number of pixels. This scheme enhances the correlation of interpolated pixels and their immediate neighbouring pixels. This research aims to develop a super-resolution demosaicking (SRD) technique to reconstruct high-resolution, full-colour images from samples of the same previously seen (in-painted) image without a sophisticated, time-consuming training process. Hardware-oriented colour demosaicking methods, which give importance to green colour pixels, have thus enhanced the quality of the restored image. A Boundary Mirror and Detector mechanism also considered here for improving the pixel quality up to the boundaries. Three interpolators were economized by using a method called hardware sharing. The present Bi-Cubic interpolation technique has been designed as part of our overall effort to enhance and advance the SRD approach toward better performance and broader acceptance. This had been implemented by VLSI architecture and VHDL, whereas MATLAB had executed the image conversion and de-conversion methods. Comparison in the evaluation of results was done based on PSNR and SSIM values, followed by the analysis of the output results after the synthesis process using a Xilinx Vivado ZYNQ-7-ZC702 FPGA.

Animation line art colorization based on the optical flow method

AbstractColoring an animation sketch sequence is a challenging task in computer vision since the information contained in line sketches is too sparse, and the colors need to be uniform between continuous frames. Many the existing colorization algorithms can only be applied to one image and can be considered color filling algorithms. Such algorithms only provide a color result that fits within a reasonable range and can not be applied to the coloring of frame sequences. This paper proposes an end‐to‐end two‐stage optical flow colorization network to solve the animation frame sequence colorization problem. The first stage of the network finds the direction of the color pixel flow from the detail change between a given reference frame and the next frame of line artwork and then completes the initial coloring process. The second stage of the network performs color correction and clarifies the output of the first stage. Since our algorithm does not directly colorize the image but finds the path of the color change to colorize it, it ensures a consistent color space for the sequence frames after colorization. We conduct experiments on an animation dataset, and the results show that our algorithm is effective. The code is available at https://github.com/silenye/Colorization.

Image Matting using Superpixels Centroid

The orientation and focus of this research piece is the extraction of foreground and compositing this extracted region onto a new background region. This phenomenon is termed as image matting, which is more utilized in film production or digital media world. The proposed method approaches the ill-posed nature of image matting via non-parametric sampling based method along with the clustering technique known as Superpixel. In the proposed method, pixels of entire image(s) are tends to gather in close proximity under one unit (Superpixel) with respect to color, intensity and texture. This gathering in close proximity reduces the search space more than 20 times and helps in efficiently finding association of unknown region with the samples from background and foreground. The use of samples facilitates the pixel color assimilating with local image structure, which is significant to calculate a good resultant alpha matte particularly in the image having complex textured and in natural images. To the best of my knowledge, the matting problem using centroids of Superpixels has not previously been explored. Results are evaluated on different images on online benchmark dataset for image matting. Results are comparable to the different matting algorithms applied independently on images of dataset. Result shows that the proposed approach significantly improves the results.

Morphological features of lung white spots based on the Otsu and Phansalkar thresholding method

&lt;span&gt;COVID-19 is a disease that causes respiratory system disorders, so various tests are needed. One of them uses a chest X-ray or thorax. A chest X-ray will depict the lungs as a whole so that patches like white shadows will be visible. In this study, the number of lung areas and white spots can be observed and detected using segmentation techniques in image processing. But before entering the segmentation stage, the image will go through the preprocessing stage using the tri-threshold fuzzy intensification operators (fuzzy IO) method. It then segmented the lungs using the Otsu method by changing the digital image from grey to black and white based on comparing the threshold value with the pixel colour value of the digital image. Then, further segmentation was carried out using the Phansalkar method to detect and simultaneously count the number of white spots. Referring to the experiments we have carried out, Otsu Phansalkar's segmentation performance promises to be developed further.&lt;/span&gt;

Machine and deep learning-based trophic state classification of national freshwater reservoirs in Taiwan using Sentinel-2 data

Since the beginning of the industrial revolution in the nineteenth century water pollution has grown into a global transboundary problem that negatively impacts aquatic ecosystems a risk linked directly to sustainable economic development, human, aquatic, and wildlife health. However, one major impediment to monitoring lake water quality is a lack of data for the relevant monitoring parameters at the relevant temporal and spatial scales. Therefore, this study investigates sixteen major reservoirs on a national scale based on 2020 in-situ sampling and Sentinel-2 MSI satellite data. Machine and deep learning algorithms were employed to classify and predict various water quality classes using Sentinel-2 MSI pixel color values and spectral indices. Multivariate techniques such as PCA transformation and regularized MANOVA were used as input feature preprocessing for variable reconstruction to deal with collinearity. Consequently, this improved the model classification performances overall. The results highlight deep neural net (DNN) and XGBoost as the outstanding classifying algorithms yielding F1-score of 0.94 and 0.93; Recall of 0.93 and 0.92; ROC-AUC of 0.92 and 0.89 respectively. Nutrient pollution affects all of the investigated reservoirs as they are classified as either meso- or hypereutrophic, and the situation is deteriorating. This study does not only give a feasible solution for effective water quality observation, but also provides a unique data pipeline for basic creation of training data for biogeochemical parameters for studying lake water quality using an integrated Google Earth Engine (GEE) Python Application Programming Interface (API) run in Google Colaboratory notebook.