Channels Of Color Image Research Articles

Comparison of Preprocessing Method Impact on the Detection of Soldering Splashes Using Different YOLOv8 Versions

Quality inspection of electronic boards during the manufacturing process is a crucial step, especially in the case of specific and expensive power electronic modules. Soldering splash occurrence decreases the reliability and electric properties of final products. This paper aims to compare different YOLOv8 models (small, medium, and large) with the combination of basic image preprocessing techniques to achieve the best possible performance of the designed algorithm. As preprocessing methods, contrast-limited adaptive histogram equalization (CLAHE) and image color channel manipulation are used. The results show that a suitable combination of the YOLOv8 model and preprocessing methods leads to an increase in the recall parameter. In our inspection task, recall can be considered the most important metric. The results are supported by a standard two-way ANOVA test.

Color image encryption algorithm based on Mackey–Glass time-delay chaotic system and quantum random walk

To ensure the confidentiality and integrity of image data and prevent unauthorized data tampering and privacy leaks. This study proposes a new color image encryption scheme based on the Mackey–Glass time-delay chaotic system and quantum random walk. This approach fully leverages the unpredictability of quantum random walks to generate random values. It combines the differences in Hamming distance between the three RGB channels of color images to create a highly complex and random key. The overall image and the three independent RGB channels are arranged in ascending order using Logistic-tent chaotic mapping and the Mackey–Glass time-delay chaotic system to obfuscate the image data. The deformed fractional-order Lorenz chaotic system is introduced, integrated with DNA encoding and decoding technology, and XOR operations are performed to achieve encryption at the spatial and pixel levels, thereby increasing the complexity of decryption. Through extensive experimental research, this solution has demonstrated excellent results in tests such as adjacent pixel correlation, information entropy, and key sensitivity. It has an excellent ability to protect the privacy of images and provides a reliable guarantee for the security of image data.

Inverting Chlorophyll Content in Jujube Leaves Using a Back-Propagation Neural Network–Random Forest–Ridge Regression Algorithm with Combined Hyperspectral Data and Image Color Channels

Chlorophyll content is highly susceptible to environmental changes, and monitoring these changes can be a crucial tool for optimizing crop management and providing a foundation for research in plant physiology and ecology. This is expected to deepen our scientific understanding of plant ecological adaptation mechanisms, offer a basis for improving agricultural production, and contribute to ecosystem management. This study involved the collection of hyperspectral data, image data, and SPAD data from jujube leaves. These data were then processed using SG smoothing and the isolated forest algorithm, following which eigenvalues were extracted using a combination of Pearson’s phase relationship method and the Partial Least Squares Regression–continuous projection method. Subsequently, seven methods were employed to analyze the results, with hyperspectral data and color channel data used as independent variables in separate experiments. The findings indicated that the integrated BPNN-RF-Ridge Regression algorithm provided the best results, with an R2 of 0.8249, MAE of 2.437, and RMSE of 2.9724. The inclusion of color channel data as an independent variable led to a 3.2% improvement in R2, with MAE and RMSE increasing by 1.6% and 3.9%, respectively. These results demonstrate the effectiveness of integrated methods for the determination of chlorophyll content in jujube leaves and underscore the potential of using multi-source data to improve the model fit with a minimal impact on errors. Further research is warranted to explore the application of these findings in precision agriculture for jujube yield optimization and income-related endeavors, as well as to provide insights for similar studies in other plant species.

Genetic Programming to Remove Impulse Noise in Color Images

This paper presents a new filter to remove impulse noise in digital color images. The filter is adaptive in the sense that it uses a detection stage to only correct noisy pixels. Detecting noisy pixels is performed by a binary classification model generated via genetic programming, a paradigm of evolutionary computing based on natural biological selection. The classification model training considers three impulse noise models in color images: salt and pepper, uniform, and correlated. This is the first filter generated by genetic programming exploiting the correlation among the color image channels. The correction stage consists of a vector median filter version that modifies color channel values if some are noisy. An experimental study was performed to compare the proposed filter with others in the state-of-the-art related to color image denoising. Their performance was measured objectively through the image quality metrics PSNR, MAE, SSIM, and FSIM. Experimental findings reveal substantial variability among filters based on noise model and image characteristics. The findings also indicate that, on average, the proposed filter consistently exhibited top-tier performance values for the three impulse noise models, surpassed only by a filter employing a deep learning-based approach. Unlike deep learning filters, which are black boxes with internal workings invisible to the user, the proposed filter has a high interpretability with a performance close to an equilibrium point for all images and noise models used in the experiment.

High dynamic range 3D shape measurement based on crosstalk characteristics of a color camera.

Fringe projection profilometry (FPP) has been widely used in many fields due to its fast speed, high accuracy and full-field characteristics. However, it is still a challenging problem to deal with high dynamic range (HDR) objects for traditional FPP, which utilizes a single exposure time or a single projection intensity. Overexposure will occur in areas with large reflectivity, which exceeds the maximum capturing capacity of camera sensors, resulting in the failure to obtain the accurate intensity, absolute phase and three-dimensional (3D) data. In this paper, a uniform blue image is projected to divide object surface into three areas with different reflectivity by using different intensity responses of RGB channels of color images. Crosstalk coefficient function is applied to obtain intensity of overexposed areas, and then the optimal exposure time of areas is calculated by the linear photometric response of the camera. Finally, three sets of blue fringe patterns with optimal exposure time are synthesized into the fused HDR images to calculate the absolute phase. Experimental results confirm that the proposed method can accurately measure HDR objects with large variation range of reflectivity.

Efficient and secure chaotic PRNG for color image encryption

Random number generation is considered a major problem for any digital color image cipher algorithm and secret communication protocol. Pseudo-random number generators (PRNGs) are used in many security applications because they afford both features, the randomness efficiency and quality of the PRNG. The paper proposes a new PRNG depending on a combination of the Secure Hash Algorithm (SHA-2(256)) with the results of three chaotic maps: the 2D Henon map, the 2D Kaplan-Yorke map, and the 2D Tinkerbell map. In the proposed chaotic generator, 6 initial floating-point numbers with 10−16 precision are inputs to SHA-2(256) for generating the initial values of the three chaotic maps. Then the chaotic maps are iterated to produce a binary sequence that is processed to enhance the sequence complexity based on binary XOR addition operation and 2D shifting scrambling method. The random binary sequences produced by the proposed PRNG algorithm were tested using several number of analyses like the national statistical test suite, correlation analyses, key space analyses, Sum of absolute analyses (SAD), key sensitivity analyses, and histogram analyses. The results proved that scrambling binary sequences have passed successfully the NIST tests where the ratio η of p-value concerns individual sequences between [0.9805, 0.9994], the correlation between the produced sequences is very small where the distributions of Pearson's correlation coefficients belong to [-0.03, 0.03] and the distributions of Hamming distance coefficients belonging to [0.49, 0.52], all the results of the SAD between [0.33237, 0.33451] which are almost close ideal values, and the key space of proposed PRNG is very large which is 2319. The proposed PRNG was applied as a random key generation algorithm on a new color image cipher algorithm, with strong permutation and substitution methods to encrypt and decrypt each image color channel. The practicableness of the algorithm was tested by different statistical and security analyses.

A Cross-Plane Color Image Encryption Algorithm Based on 1D-SLM

With the rapid development of 5G technology, it has become fast and easy for people to transmit information on the Internet. Digital images can express information more intuitively, so transmitting information through images has excellent applications. This paper uses a new chaotic system called 1D-Sin-Logistic-Map (1D-SLM). 1D-SLM has two control parameters, which can provide larger parameter space, and the parameter space in the chaotic state is continuous. Through Lyapunov exponent analysis (LE), bifurcation diagrams analysis, spectral entropy analysis (SE), and 0-1 test, it is verified that 1D-SLM has complex dynamic behavior and is very suitable for cryptography. Compared with other 1D chaotic systems, the 1D-SLM has a larger Lyapunov exponent (LE) and spectral entropy (SE). For color image encryption algorithms, only relying on chaotic mapping is not enough to ensure security. So combined with 1D-SLM, we design a color image encryption algorithm, which is implemented by plane expansion, which reduces the correlation between the three channels of color images. The experimental results show that the proposed cross-plane color image encryption algorithm is safe and resistant to common attack methods.

Color image steganalysis based on quaternion discrete cosine transform

<abstract> <p>With the rapid development and application of Internet technology in recent years, the issue of information security has received more and more attention. Digital steganography is used as a means of secure communication to hide information by modifying the carrier. However, steganography can also be used for illegal acts, so it is of great significance to study steganalysis techniques. The steganalysis technology can be used to solve the illegal steganography problem of computer vision and engineering applications technology. Most of the images in the Internet are color images, and steganalysis for color images is a very critical problem in the field of steganalysis at this stage. Currently proposed algorithms for steganalysis of color images mainly rely on the manual design of steganographic features, and the steganographic features do not fully consider the internal connection between the three channels of color images. In recent years, advanced steganography techniques for color images have been proposed, which brings more serious challenges to color image steganalysis. Quaternions are a good tool to represent color images, and the transformation of quaternions can fully exploit the correlation among color image channels. In this paper, we propose a color image steganalysis algorithm based on quaternion discrete cosine transform, firstly, the image is represented by quaternion, then the quaternion discrete cosine transform is applied to it, and the coefficients obtained from the transformation are extracted to design features of the coeval matrix. The experimental results show that the proposed algorithm works better than the typical color image steganalysis algorithm.</p> </abstract>

2D Sin-Cos-Henon Map for Color Image Encryption with High Security

In this paper, a high security color image encryption algorithm is proposed by 2D Sin-Cos-Hénon (2D-SCH) system. A new two-dimensional chaotic system which is 2D-SCH. This system is hyperchaotic. The use of the 2D-SCH, a color image encryption algorithm based on random scrambling and localization diffusion, is proposed. First, the secret key is generated by SHA512 through plaintext. As the initial value of the 2D-SCH system, the secret key is used to generate chaotic sequences. Then, the random scrambling is designed based on chaotic sequences. Finally, a pair of initial points is generated by the secret key; the image diffuses around this point. The ciphertext is obtained by a double encryption. Different from the traditional encryption algorithm, this paper encrypts three channels of color image simultaneously, which greatly improves the security of the algorithm. Simulation results show that the algorithm can resist various attacks.

Multichannel concat-fusional convolutional neural networks

Because of the advantages of deep learning and information fusion technology, it has drawn much attention for researchers to combine them to achieve target recognition, positioning, and tracking. However, when the existing neural network process multichannel images (e.g., color images), multiple channels as a whole input into neural networks, which makes it hard for networks to fully learn information in R, G, and B channels of images. Therefore, it is not conducive to the final learning effect of the networks. To solve the problem, using different combinations of R, G, and B channels of color images for feature-level fusion, this paper proposes three fusion types as “R/G/B”, “R+G/G+B/B+R”, and “R+G+B/R+G+B/R+G+B” multichannel concat-fusional convolutional neural networks. Experimental results show that multichannel concat-fusional convolutional neural networks with fusional types of “R+G/G+B/B+R” and “R+G+B/R+G+B/R+G+B” achieve better performance than the corresponding non-fusional convolutional neural networks on different datasets. It shows that networks with fusion types of “R+G/G+B/B+R” and “R+G+B/R+G+B/R+G+B” can learn more fully information of R, G, and B channels of color images and improve the learning performance of networks.

Underwater Image Enhancement Method Based on Dynamic Heterogeneous Feature Fusion Neural Network

In recent years, signal and image processing based on fractional calculus has attracted extensive attention. Aiming at the serious problem of gray-scale loss in the existing pseudo color methods in high gray-scale image enhancement, a pseudo color enhancement algorithm suitable for Dynamic heterogeneous feature fusion neural network is proposed, and the traditional jet, HSV and rainbow coding are improved. Firstly, bit depth quantization is performed on the high-level gray image; Secondly, color enhancement is realized by using the constructed high gray-scale enhancement algorithm; Then, combined with the convolution neural network, the compact learning method is used to extract the features of the multi-scale image, and the jump connection is used to prevent the gradient dispersion and overcome the fog blur effect of the underwater image The style cost function is used to learn the correlation between various channels of color image, improve the color correction ability of the model, and overcome the problem of color distortion of underwater image. Experimental results show that compared with traditional image enhancement methods, the proposed method has better comprehensive performance in subjective vision and objective indicators, and has advantages in dealing with underwater image enhancement. While improving the brightness of the image, the problem of color distortion and brightness blocking of the enhanced image is solved. The texture information of the image is effectively restored. The brightness distribution of the enhanced image can well restore the brightness distribution of the real shooting environment, which verifies that the algorithm has higher robustness.

Block-Greedy and CNN Based Underwater Image Dehazing for Novel Depth Estimation and Optimal Ambient Light

A lack of adequate consideration of underwater image enhancement gives room for more research into the field. The global background light has not been adequately addressed amid the presence of backscattering. This paper presents a technique based on pixel differences between global and local patches in scene depth estimation. The pixel variance is based on green and red, green and blue, and red and blue channels besides the absolute mean intensity functions. The global background light is extracted based on a moving average of the impact of suspended light and the brightest pixels within the image color channels. We introduce the block-greedy algorithm in a novel Convolutional Neural Network (CNN) proposed to normalize different color channels’ attenuation ratios and select regions with the lowest variance. We address the discontinuity associated with underwater images by transforming both local and global pixel values. We minimize energy in the proposed CNN via a novel Markov random field to smooth edges and improve the final underwater image features. A comparison of the performance of the proposed technique against existing state-of-the-art algorithms using entropy, Underwater Color Image Quality Evaluation (UCIQE), Underwater Image Quality Measure (UIQM), Underwater Image Colorfulness Measure (UICM), and Underwater Image Sharpness Measure (UISM) indicate better performance of the proposed approach in terms of average and consistency. As it concerns to averagely, UICM has higher values in the technique than the reference methods, which explainsits higher color balance. The μ values of UCIQE, UISM, and UICM of the proposed method supersede those of the existing techniques. The proposed noted a percent improvement of 0.4%, 4.8%, 9.7%, 5.1% and 7.2% in entropy, UCIQE, UIQM, UICM and UISM respectively compared to the best existing techniques. Consequently, dehazed images have sharp, colorful, and clear features in most images when compared to those resulting from the existing state-of-the-art methods. Stable σ values explain the consistency in visual analysis in terms of sharpness of color and clarity of features in most of the proposed image results when compared with reference methods. Our own assessment shows that only weakness of the proposed technique is that it only applies to underwater images. Future research could seek to establish edge strengthening without color saturation enhancement.

A novel color image encryption method based on an evolved dynamic parameter-control chaotic system

The majority of existing image encryption algorithms use single chaotic systems, such as Logistic map or Lorentz system, to be the pseudo-random sequence generator. Actually, neither low nor high dimensional chaotic system can get rid of pseudo-randomness deterioration of chaotic sequence calculated by limited precision computer. Additionally, most of them use only one chaotic pseudo-random sequence throughout the encryption process. These are the more obvious deficiencies. In the current paper, a novel compound chaotic system is applied to color images domain to solve the mentioned problems. Dynamic parameter-control chaotic system can enhance the sequence’s randomness after digitalizing. Corresponding the different sequences generated by the novel chaotic system to each color channel of image is a helpful method to reduce the image’s statistical characteristics in the scrambling process. Finally, the effectiveness and security of the proposed encryption has been illustrated by the experimental, and at the meantime, excellent performance is also demonstrated.

Articular cartilage regeneration in rats using human bone marrow stromal cells

Purpose: Injury to articular cartilage found in knee joints is often disabling and affects both younger and older individuals. Injured cartilage rarely heals, leading to a progressive loss of normal function of the joint in many cases. Current treatments are far from satisfactory. One treatment is surgery (such as drilling through the cartilage to the bone, abrasion to remove diseased cartilage and microfracture). These procedures can result in the formation of a mixture of fibrous tissue and cartilage within the injury, which does not lead to a total recovery of joint function. Autologous human bone marrow stromal cell (hBMSC) transplantation maybe a potential avenue to regenerate articular cartilage. We previously determined that naive (untreated) hBMSC were able to form stable, non-hypertrophic cartilage when transplanted subcutaneously in conjunction with fibrin microbeads covalently coated with hyaluronic acid (FMBs). In our current study, we are investigating the ability of hBMSC/FMB constructs to generate native-like cartilage in an articular defect in immunocompromised rodents. Methods: hBMSCs were obtained from surgical bone waste and grown in culture for 2-3 passages. Approval for this study was given by the institutional Animal Care and Use Committee (ACUC). To create the articular cartilage defects in immunocompromised SRG rats (Hera/Charles River), the patella was laterally displaced and the distal femur was immobilized using a clamp. The defect was made in the trochlear groove of the distal femur using a 1.8mm diameter microdrill. The defect was either left unrepaired (sham), or subsequently filled with either FMBs alone (FMBs Alone), hBMSCs attached to FMBs (FMBs+cells), or with a pellet created by incubating BMSCs with FMBs for 10 days in chondrogenic medium. At the 4-week and 8-week timepoints following surgery, the rats were euthanized and femurs were harvested and fixed in 4% paraformaldehyde for 24 hours and then decalcified using a 10% EDTA solution for 30 days. After decalcification, the femurs were paraffin embedded and sectioned at a thickness of 6 μm. Histological staining was performed using hematoxylin and eosin, toluidine blue, and safranin O methods to assess cartilage formation. Immunohistochemistry for aggrecan within the cartilage was also performed to assess cartilage proteoglycan formation. Image analysis using Image J was performed on sections stained with safranin O. Cartilage thickness was approximated based on the thickness of the intact cartilage surrounding the defect, and a region of interest (ROI) was drawn surrounding the defect with the same depth as the intact cartilage. The image color channels were separated into red, green, and blue, and the blue channel was used to threshold for the stained proteoglycan. The “analyze particles” module of Image J was used to calculate the percentage of the ROI that stained positive for proteoglycan. Second-harmonic generation microscopy was also used to evaluate collagen fibril structure and organization. Results: Toluidine blue staining revealed cartilage formation in defects at the 4-week and 8-week timepoints in both the FMBs+cells and pellet groups. No cartilage was detected in the FMBs alone or sham groups (Figure 1). Percentages of defect area positive for cartilage proteoglycan in the FMBs+cells, pellet, FMBs alone, and sham group defect areas were 8.95%, 3.03%, 0.008%, and 0.094% respectively. A comparable ROI in healthy rat cartilage showed proteoglycan positivity of 58.43% of the area (Figure 2). Second harmonic generation imaging of the defect area showed that from sham to FMB alone to pellet to FMBs+cells groups, the organization of the collagen fibrils begin to more closely approximate healthy rat cartilage (Figure 3). Long-term time points are currently being analyzed. Conclusions: At the early timepoints presented in this abstract, there is evidence of cartilage formation in the drilled articular cartilage defects in both the FMBs+cells and pellet groups. This initial data shows the potential for our method to regenerate articular cartilage in vivo. Analysis of our long-term time points will reveal the extent and quality of healing induced by hBMSCs transplanted in conjunction with FMBs.

Low Rank Pure Quaternion Approximation for Pure Quaternion Matrices

Quaternion matrices are employed successfully in many color image processing applications. In particular, a pure quaternion matrix can be used to represent red, green, and blue channels of color images. A low-rank approximation for a pure quaternion matrix can be obtained by using the quaternion singular value decomposition. However, this approximation is not optimal in the sense that the resulting low-rank approximation matrix may not be pure quaternion, i.e., the low-rank matrix contains a real component which is not useful for the representation of a color image. The main contribution of this paper is to find an optimal rank-$r$ pure quaternion matrix approximation for a pure quaternion matrix (a color image). Our idea is to use a projection on a low-rank quaternion matrix manifold and a projection on a quaternion matrix with zero real component, and develop an alternating projections algorithm to find such optimal low-rank pure quaternion matrix approximation. The convergence of the projection algorithm can be established by showing that the low-rank quaternion matrix manifold and the zero real component quaternion matrix manifold has a nontrivial intersection point. Numerical examples on synthetic pure quaternion matrices and color images are presented to illustrate the projection algorithm can find optimal low-rank pure quaternion approximation for pure quaternion matrices or color images.

A Color Elastica Model for Vector-Valued Image Regularization

Models related to the Euler's elastica energy have proven to be useful for many applications including image processing. Extending elastica models to color images and multichannel data is a challenging task, as stable and consistent numerical solvers for these geometric models often involve high order derivatives. Like the single channel Euler's elastica model and the total variation models, geometric measures that involve high order derivatives could help when considering image formation models that minimize elastic properties. In the past, the Polyakov action from high energy physics has been successfully applied to color image processing. Here, we introduce an addition to the Polyakov action for color images that minimizes the color manifold curvature. The color image curvature is computed by applying the Laplace--Beltrami operator to the color image channels. When reduced to gray-scale images, while selecting appropriate scaling between space and color, the proposed model minimizes Euler's elastica operating on the image level sets. Finding a minimizer for the proposed nonlinear geometric model is a challenge we address in this paper. Specifically, we present an operator-splitting method to minimize the proposed functional. The nonlinearity is decoupled by introducing three vector-valued and matrix-valued variables. The problem is then converted into solving for the steady state of an associated initial-value problem. The initial-value problem is time split into three fractional steps, such that each subproblem has a closed form solution, or can be solved by fast algorithms. The efficiency and robustness of the proposed method are demonstrated by systematic numerical experiments.

Sketch Based Data Retrieval Using Reversible Data Hiding on Images

Sketch Based Image Retrieval as name suggests is a branch of image retrieval that searches the images based on sketches. The sketches bridge the gap between imagination and real images. Sketches act as powerful searching tool in image retrieval. It efficiently uses the data hiding technique, which is a watermarking technique and can be used for embedding messages into images. A message can be embedded into color images without changing its grayscale version. Embedding of messages was thus done using unchanged gray version. It can also extract the messages. This unchanged grayscale version is maintained from message embedding to extraction process. This concept of watermarking generates SBIDR valuable, because many applications or algorithms for color images are based on its corresponding grayscale version. Embedding of data is carried out into in three-color channels of color image and in gray value of Sketch Image. Sketch image is encrypted with key, which will be required at the time of message extraction process after SBIR. In this way grayscale invariance is maintained which made the Sketch Based Retrieval more effective.

An efficient blind color image watermarking algorithm in spatial domain combining discrete Fourier transform

For achieving the purpose of rapid protection of color image copyright better, a novel color image blind watermarking algorithm is proposed in this paper, which integrates discrete Fourier transform (DFT) in spatial domain. According to the unique feature of the direct current (DC) component of DFT, two procedures of embedding and blind extracting watermark are accomplished in spatial domain utilizing the correlation principle between adjacent pixel blocks and different steps in different channels of color image, without real DFT. The experiment results demonstrate that the presented algorithm has strong robustness and high real time under the premise of better watermark invisibility, and solves the puzzles of slow running-speed and weak robustness of large capacity color image digital watermarking algorithm.

VARENN: graphical representation of periodic data and application to climate studies

Analyzing and utilizing spatiotemporal big data are essential for studies concerning climate change. However, such data are not fully integrated into climate models owing to limitations in statistical frameworks. Herein, we employ VARENN (visually augmented representation of environment for neural networks) to efficiently summarize monthly observations of climate data for 1901–2016 into two-dimensional graphical images. Using red, green, and blue channels of color images, three different variables are simultaneously represented in a single image. For global datasets, models were trained via convolutional neural networks. These models successfully classified the rises and falls in temperature and precipitation. Moreover, similarities between the input and target variables were observed to have a significant effect on model accuracy. The input variables had both seasonal and interannual variations, whose importance was quantified for model efficacy. We successfully illustrated the importance of short-term (monthly) fluctuations in the model accuracy, suggesting that our AI-based approach grasped some previously unknown patterns that are indicators of succeeding climate trends. VARENN is thus an effective method to summarize spatiotemporal data objectively and accurately.

A Novel Color Image Encryption Algorithm Based on Hyperchaotic Maps and Mitochondrial DNA Sequences.

Multimedia encryption innovation is one of the primary ways of securely and privately guaranteeing the security of media transmission. There are many advantages when utilizing the attributes of chaos, for example, arbitrariness, consistency, ergodicity, and initial condition affectability, for any covert multimedia transmission. Additionally, many more benefits can be introduced with the exceptional space compliance, unique information, and processing capability of real mitochondrial deoxyribonucleic acid (mtDNA). In this article, color image encryption employs a confusion process based on a hybrid chaotic map, first to split each channel of color images into n-clusters; then to create global shuffling over the whole image; and finally, to apply intrapixel shuffling in each cluster, which results in very disordered pixels in the encrypted image. Then, it utilizes the rationale of human mitochondrial genome mtDNA to diffuse the previously confused pixel values. Hypothetical examination and trial results demonstrate that the anticipated scheme exhibits outstanding encryption, as well as successfully opposes chosen/known plain text, statistical, and differential attacks.