Image Applications Research Articles

Validation of morphological ear classification devised by principal component analysis using three-dimensional images for human identification.

This study attempts to classify ear morphology for human identification in forensic investigations by distinguishing between the upper auricle and lobule areas. A three-dimensional homologous model of the ear was created using 414 ear images of males aged 17-93 years reconstructed from computed tomography scans of forensic autopsy cases. Morphological changes were visualized using principal component analysis and areas of significant individual differences within the entire ear were identified. The classification criterion images for the upper auricle (ten images) and lobule (12 images) were developed by combining multiple principal component values: components 1-5 for the upper auricle and 1-6 for the lobule. Three-dimensional ear images of the upper auricle and lobule areas from 414 subjects were categorized using a measurement method based on the minimum distance between 5,507 corresponding points. The results indicate the applicability of the criterion images for the morphological classification of ears in this study.

Robust Carbon‐Dot Optical Disks for Orthogonal Amplitude‐Polarization Encryption Storage

AbstractHigh‐capacity steganography is crucial for the secure exchange of massive information. Exploring orthogonally optical recording can significantly improve encryption levels. However, due to the lack of robust media, the hidden data are easy to be cracked or destructed. Herein, carbon dots have the switchable memory function between optical transmittance and polarization state after receiving excitation power adjustment is discovered. A large‐area carbon‐based disk is further constructed which is measured to resist the high‐temperature damage at 423 K for more than 405 h and is estimated to remain stable at room‐temperature (301 K) beyond 2341 years. With the alternated arrangement of the dual functional carbon dots at one region of the disk, only by using an amplitude‐type holographic diffraction key can the polarized pattern be correctly read out. The ultra‐high secure encryption strategy also puts a bright way to the applications of 3D image hiding, permanent data preservation, and anti‐counterfeiting labels.

Controllable image synthesis methods, applications and challenges: a comprehensive survey

Controllable Image Synthesis (CIS) is a methodology that allows users to generate desired images or manipulate specific attributes of images by providing precise input conditions or modifying latent representations. In recent years, CIS has attracted considerable attention in the field of image processing, with significant advances in consistency, controllability and harmony. However, several challenges still remain, particularly regarding the fine-grained controllability and interpretability of synthesized images. In this paper, we comprehensively and systematically review the CIS from problem definition, taxonomy and evaluation systems to existing challenges and future research directions. First, the definition of CIS is given, and several representative deep generative models are introduced in detail. Second, the existing CIS methods are divided into three categories according to the different control manners used and discuss the typical work in each category critically. Furthermore, we introduce the public datasets and evaluation metrics commonly used in image synthesis and analyze the representative CIS methods. Finally, we present several open issues and discuss the future research direction of CIS.

Application of Sentinel-2 Level-2A images for monitoring water surface in reservoirs in the semiarid region of Pernambuco — Brazil

Remote sensing techniques offer effective and efficient alternatives for observing the spatiotemporal dynamics of surface water in reservoirs. This paper aimed to analyze the applicability of Sentinel-2 Level-2A satellite images from 2016 to 2024 for mapping and monitoring the extent of water surfaces in reservoirs in the Sertão region of Pernambuco state. An automatic, unsupervised, and non-parametric algorithm was employed, combining water indices with reflectance bands of optical images to identify water pixels. The results were compared with two datasets: in situ monitoring and MapBiomas. Issues with optical images affected by clouds over the reservoir and errors in classifying water pixels were noted. Generally, the algorithm tended to underestimate the extent of the water surface due to difficulty detecting water pixels at the edges of the reservoirs. To mitigate this issue, an artificial neural network (ANN) was applied to correct the underestimation bias. The bias correction improved the performance of the metrics when the size and representativeness of the calibration sample were sufficient for training and building the ANN model.

ShiftTransUNet: An Efficient Deep Learning Model for Medical Image Segmentation Using ShiftViT Framework

Deep learning has significantly advanced the field of medical image segmentation. However, the complexity of network structures often leads to high computational demands, limiting their practical efficiency. To enhance the efficiency of image segmentation, this paper introduces an innovative, concise, and lightweight deep learning network. First, to reduce model complexity, we replaced the attention mechanism in the traditional vision transformer (ViT) structure with a shift operation, creating the ShiftViT architecture. This substitution significantly decreased computation and the number of parameters while preserving model performance. Second, to retain and enhance fine-grained features and facilitate more precise information transfer across different layers, we employed a full-scale progressive skip connection strategy. This approach effectively integrates multi-scale feature information, further enhancing model performance. Additionally, to further reduce network complexity, inspired by the independence of probabilities, we opted for depth-wise separable convolution over traditional convolution. This enhances the relative independence between layers. Together, these modifications achieved superior segmentation results on both the Synapse and Automated Cardiac Diagnostic Challenge (ACDC) datasets compared to mainstream models, with substantial advantages in terms of computational efficiency and parameter count. The proposed approach represents an effective solution for medical image applications with limited computational resources and holds great promise for clinical practice.

A graph-guided transformer based on dual-stream perception for hyperspectral image classification

ABSTRACT The excellent capabilities of Transformers and Graph Neural Networks (GNNs) in modelling long-range dependencies and handling irregular data have led to their widespread application in hyperspectral image (HSI) classification tasks. However, the Graph Transformer combining both advantages is rarely used in this field and has some limitations. Current Graph Transformers consider interactions between all nodes within the graph, adding complexity and introducing unnecessary information from noisy nodes. Moreover, the rich spectral information in HSIs is often ignored, and there is a lack of effective fusion of spatial information. In this paper, we propose a dual-stream graph-guided Transformer for HSI classification. In spatial dimension, superpixels are utilized to guide spatial graph generation, capturing global topological dependencies and local details effectively in HSIs. In terms of spectrum, we innovatively construct a spectral graph based on spectral channels and adopt a contribution score-based strategy to adaptively filter out irrelevant edges, achieving sparsity while preserving spectral context relationships. Experimental results demonstrate the significant competitive advantage of our method in HSI classification tasks on three public datasets. The code is available at https://github.com/youngboy03/GTDPNet.

Faceify- Human Face Sketch to Real

The Human Face Sketch to Real Image Application using deep learning presents the development of an innovative application designed to convert human face sketches into realistic image using advanced deep learning techniques. The primary objective of this research is to bridge the gap between manual sketching and digital realism, offering a powerful tool for artists, law enforcement, and digital content creators. The proposed system leverages generative adversarial networks (GANs), particularly a variant known as the Sketch-to-Image GAN (SI-GAN), which is optimizes for translating sparse and abstract sketch lines into high-fidelity facial representations. The architecture consists of a generator network that refines sketches into realistic images, and a discriminator network that distinguishes between generated images and real photographs, continuously enhancing the model’s output. To ensure high accuracy and detail preservation, the model is trained on a diverse dataset comprising thousands of paired sketch and real face images. Advanced techniques such as attention mechanisms and multi-scale feature extraction are incorporated to maintain the integrity of facial features and textures. Additionally, a user friendly interface has been developed, allowing users to input sketches and receive high-quality realistic images in real-time. Evaluation metrics, including structural similarity index (SSIM) and Frechet Inception Distance (FID), Indicate that the proposed model outperforms existing state-of-the-art methods in both quality and realism. Keywords: Image Translation, Conditional Generative Adversarial Networks (CGANs), Deep Learning, Mobile Application Development, Backend Integration, Face Sketch, Photorealistic Image.

Removing thick clouds in landsat 8 OLI images with cloudy time-series auxiliary data

Abstract Thick cloud occlusion severely limits the subsequent application of optical remote-sensing images. Existing mainstream cloud removal methods often use cloud-free homologous temporal images to provide auxiliary information. However, due to the limitation of cloud occlusion and satellite revisit cycle, the time interval between the cloud-free auxiliary image and the target cloudy image is often too large, and the possible land cover changes during the period increase the uncertainty of effective information on the auxiliary images. In this case, more accurate reconstructions may be obtained by using temporally closer and partially cloud-contaminated images. In this paper, a deep network, convLSTM, is developed for cloud removal (i.e., CR-convLSTM), which makes full use of the complementary effective information on partially cloud-contaminated time-series images. Experiments based on simulated clouds indicated that CR-convLSTM can obtain more accurate predictions than the classical cloud removal method MNSPI. CR-convLSTM is an effective cloud removal method with high computational efficiency while ensuring predicting accuracy.

Optical resonant cavities carving pathways in tunable wavelength sensitive visible-NIR organic photodetectors

Enhancing the photodetection capabilities of organic photodetectors (OPDs) is crucial for advancing applications in medical monitoring, optical communications, image sensing, and robotics, where a strong, focused peak response at a specific designed wavelength is essential for improving sensitivity, wavelength selectivity, and resolution in imaging systems. By controlled integration of ZnO layers within PBDBT:BTP-4F-based OPDs to form a Fabry-Pérot optical cavity, we developed a cost-effective approach to fabricating highly sensitive OPDs by utilizing PBDBT:BTP-4F organic bulk heterojunctions, and extended its detection wavelengths into the near-infrared (NIR) range. Our design integrates a single silver (Ag) layer that significantly enhances peak detection at a wavelength of 830 ​nm, resulting in a remarkably narrow full-width at half maximum (FWHM) wavelength of 30 ​nm and yielding a photoresponse ten times greater than that of non-resonant devices. Furthermore, by varying the thickness of the ZnO layer from 77 ​nm to 620 ​nm, we achieve high spectral tunability, allowing fine adjustments of the resonant peak across a spectrum ranging from ultraviolet (UV) and visible to NIR wavelengths. This sensitive photodetector is also well-suited for applications in photoplethysmography (PPG), effectively detecting pulse signals in the NIR spectrum which has significant potential in medical diagnostics. This work advances the integration of cost-effective, wavelength-selective spectroscopic visible-NIR OPDs, paving the way for the next generation of sensitive photodetectors.

Pengaruh Penerapan Nilai-Nilai Islam, Citra Perusahaan Dan Kepuasan Nasabah Terhadap Loyalitas Nasabah Pada Bank Syariah Indonesia Di Kabupaten Bondowoso

This study seeks to evaluate the impact of applying Islamic values, the company's image, and customer satisfaction on customer loyalty in sharia banks located in Bondowoso Regency. The research is explanatory, focusing on the relationship or influence between independent and dependent variables. It employs a quantitative approach, sampling 100 Muslim customers of Indonesian sharia banks. Data collection was conducted via questionnaires distributed through Google Forms. The data were analyzed using multiple linear regression analysis, with the results derived from regression tests. The findings revealed that, firstly, the application of Islamic values does not independently affect customer loyalty. Secondly, the company's image has a partial impact on customer loyalty. Thirdly, customer satisfaction influences customer loyalty. Finally, the combined application of Islamic values, company image, and customer satisfaction has a significant effect on customer loyalty.

Effect of bit-size reduced half-precision floating-point format on image pixel characterization for AI applications

Image processing is an essential first step towards fully utilizing robotics, deep learning, and machine learning techniques. Using techniques like image enhancement, restoration, and segmentation are able to extract pertinent information from images and use it for task execution and decision-making. However, the hardware implementation of these algorithms demands more delay, area, and power. This work proposes a new mantissa bit-size reduced half-precision floating-point format for processing and characterizing image pixels for machine learning algorithms. In the realm of imaging, lowering the mantissa bit-size in floating-point can conserve area and power when utilized for internal calculations. Together with the area-power reduction, there is also a progressive reduction in image quality. For any image application, it becomes necessary to monitor the area and power trade-offs related to the amount of bits used to process the raw data. This work assists in selecting the bit-size for internal computations based on the accuracy requirements of the application by reporting the area, and power for various bit size reductions. The updated pixel values after applying the mantissa bit-size reduction are displayed in this study, along with a theoretical explanation of its inaccuracy. Since multipliers and adders are needed for the majority of mathematical equations in machine learning image algorithms, they are developed later in this work to process the image. The processed image is based on various adjusted pixel values, and the experimental findings demonstrate 75.2% to 21.3% area optimization, and 66.43% to 20.4% power optimization. However, determining the PSNR and MSE values of the processed image allows for quality validation.

Research on on-orbit relative radiometric calibration method based on solar diffuse reflector hyperspectral camera

Abstract In the original image data obtained by optical remote sensing satellite sensors, there is stripe noise caused by inconsistent probe response, which will seriously affect the application effect and accuracy of the image. The importance of relative radiometric calibration is that it can eliminate the stripe noise in the image, thus improving the quality and clarity of the image. In this paper, a relative radiometric calibration method based on the data of a solar diffuse reflector downloaded from the satellite is proposed. The relative radiation calibration coefficient is calculated by using the least square method by obtaining the calibration image of the on-board diffuse reflector covering all the detectors. To verify the method proposed in this paper, the on-board relative radiometric calibration experiment is carried out by using the on-orbit hyperspectral camera of a terrestrial ecological carbon monitoring satellite, and the calibration effect of the calibration coefficient on the original image is tested, and the relative radiometric calibration accuracy is quantitatively analyzed. The experimental results show that the calibration coefficient can effectively eliminate the band noise of the original hyperspectral image. From the quantitative evaluation, the signal-to-noise ratio index of the corrected hyperspectral image is greater than 200, and the generalized noise index is better than 3%, which achieves a good calibration effect and meets the requirements of high-quality remote sensing image application. It provides a reliable guarantee for quantitative remote sensing applications during the satellite’s on-orbit operation.

Retraction Note: Light image enhancement based on embedded image system application in animated character images

Retraction Note: Light image enhancement based on embedded image system application in animated character images

SMALE: Hyperspectral Image Classification via Superpixels and Manifold Learning

As an extremely efficient preprocessing tool, superpixels have become more and more popular in various computer vision tasks. Nevertheless, there are still several drawbacks in the application of hyperspectral image (HSl) processing. Firstly, it is difficult to directly apply superpixels because of the high dimension of HSl information. Secondly, existing superpixel algorithms cannot accurately classify the HSl objects due to multi-scale feature categorization. For the processing of high-dimensional problems, we use the principle of PCA to extract three principal components from numerous bands to form three-channel images. In this paper, a novel superpixel algorithm called Seed Extend by Entropy Density (SEED) is proposed to alleviate the seed point redundancy caused by the diversified content of HSl. It also focuses on breaking the dilemma of manually setting the number of superpixels to overcome the difficulty of classification imprecision caused by multi-scale targets. Next, a space–spectrum constraint model, termed Hyperspectral Image Classification via superpixels and manifold learning (SMALE), is designed, which integrates the proposed SEED to generate a dimensionality reduction framework. By making full use of spatial context information in the process of unsupervised dimension reduction, it could effectively improve the performance of HSl classification. Experimental results show that the proposed SEED could effectively promote the classification accuracy of HSI. Meanwhile, the integrated SMALE model outperforms existing algorithms on public datasets in terms of several quantitative metrics.

Activation function optimization scheme for image classification

Activation function has a significant impact on the dynamics, convergence, and performance of deep neural networks. The search for a consistent and high-performing activation function has always been a pursuit during deep learning model development. Existing state-of-the-art activation functions are manually designed with human expertise except for Swish. Swish was developed using a reinforcement learning-based search strategy. In this study, we propose an evolutionary approach for optimizing activation functions specifically for image classification tasks, aiming to discover functions that outperform current state-of-the-art options. Through this optimization framework, we obtain a series of high-performing activation functions denoted as Exponential Error Linear Unit (EELU). The developed activation functions are evaluated for image classification tasks from two perspectives: (1) five state-of-the-art neural network architectures, such as ResNet50, AlexNet, VGG16, MobileNet, and Compact Convolutional Transformer, which cover computationally heavy to light neural networks, and (2) eight standard datasets, including CIFAR10, Imagenette, MNIST, Fashion MNIST, Beans, Colorectal Histology, CottonWeedID15, and TinyImageNet which cover from typical machine vision benchmark, agricultural image applications to medical image applications. Finally, we statistically investigate the generalization of the resultant activation functions developed through the optimization scheme. With a Friedman test, we conclude that the optimization scheme is able to generate activation functions that outperform the existing standard ones in 92.8% cases among 28 different cases studied, and −x⋅erf(e−x) is found to be the best activation function for image classification generated by the optimization scheme.

A Texture-Considerate Convolutional Neural Network Approach for Color Consistency in Remote Sensing Imagery

Remote sensing allows us to conduct large-scale scientific studies that require extensive mapping and the amalgamation of numerous images. However, owing to variations in radiation, atmospheric conditions, sensor perspectives, and land cover, significant color discrepancies often arise between different images, necessitating color consistency adjustments for effective image mosaicking and applications. Existing methods for color consistency adjustment in remote sensing images struggle with complex one-to-many nonlinear color-mapping relationships, often resulting in texture distortions. To address these challenges, this study proposes a convolutional neural network-based color consistency method for remote sensing cartography that considers both global and local color mapping and texture mapping constrained by the source domain. This method effectively handles complex color-mapping relationships while minimizing texture distortions in the target image. Comparative experiments on remote sensing images from different times, sensors, and resolutions demonstrated that our method achieved superior color consistency, preserved fine texture details, and provided visually appealing outcomes, assisting in generating large-area data products.

Development model based on visual image big data applied to art management

This paper aims to explore the application of visual image big data (BD) in art management, and proposes and develops a new art management model. First of all, this study conducted extensive research on the overview and application of big data, focusing on analyzing the characteristics of big data and its characteristics and application methods in art management. By introducing image processing (IP) technology, this paper expounds on the application of visual image technology in art management in detail and discusses the classification of computer vision images to determine its application direction. On this basis, this paper proposes the application of visual images and big data in art management from three aspects: the accurate acquisition of visual images, the development model of art management, and the development of visual image technology in art resource management and teaching, and strengthens the development model of art management based on IP algorithm. Experiments and surveys show that the art management model development system built by the newly introduced visual image technology, big data technology, and IP algorithm can increase user satisfaction by 24 %. This result shows that the new model has a significant effect in improving the efficiency and quality of art management, providing strong technical support for the field of art management, while also providing designers with a more accurate tool for assessing market trends, helping to adhere to and promote good design concepts.

Discrepancy-based diffusion models for lesion detection in brain MRI

Diffusion probabilistic models (DPMs) have exhibited significant effectiveness in computer vision tasks, particularly in image generation. However, their notable performance heavily relies on labelled datasets, which limits their application in medical images due to the associated high-cost annotations. Current DPM-related methods for lesion detection in medical imaging, which can be categorized into two distinct approaches, primarily rely on image-level annotations. The first approach, based on anomaly detection, involves learning reference healthy brain representations and identifying anomalies based on the difference in inference results. In contrast, the second approach, resembling a segmentation task, employs only the original brain multi-modalities as prior information for generating pixel-level annotations. In this paper, our proposed model – discrepancy distribution medical diffusion (DDMD) – for lesion detection in brain MRI introduces a novel framework by incorporating distinctive discrepancy features, deviating from the conventional direct reliance on image-level annotations or the original brain modalities. In our method, the inconsistency in image-level annotations is translated into distribution discrepancies among heterogeneous samples while preserving information within homogeneous samples. This property retains pixel-wise uncertainty and facilitates an implicit ensemble of segmentation, ultimately enhancing the overall detection performance. Thorough experiments conducted on the BRATS2020 benchmark dataset containing multimodal MRI scans for brain tumour detection demonstrate the great performance of our approach in comparison to state-of-the-art methods.

Robust secret color image sharing anti-cropping and tampering in shares

Secret image sharing (SIS) has excellent properties such as loss tolerance and relatively low computational complexity, providing a brand-new solution for image security protection. However, there has been little research on the robustness of SIS systems, such as how to resist cropping or malicious tampering in shares. Existing related schemes generally focus on grayscale images and suffer from issues such as lossy recovery, weak robustness, and serious pixel expansion, which are challenging to meet the requirements of high-quality sensitive image applications. In this regard, a robust SIS scheme for color images is proposed, which can resist large-scale cropping and malicious tampering in shares. According to the idea of “breaking up the whole cropped area into parts, repairing the shares independently”, the proposed scheme can realize lossless recovery of secret images through organic fusion of secret sharing, error-correcting code, and pixel re-arrangement techniques. Even if all the shares are cropped by 25%, it can still achieve lossless recovery regardless of whether the cropping positions intersect or overlap. It can also resist various malicious tampering (such as marking, defacing, and copy-move forgery) as well as image noise. Moreover, it avoids pixel expansion and requires no auxiliary encryption or preprocessing. Theoretical analysis and experimental results demonstrate that the proposed scheme is superior to existing schemes in terms of robustness and comprehensive performance, and is expected to promote the practical application of SIS.

A transformer-based deep learning model for early prediction of lymph node metastasis in locally advanced gastric cancer after neoadjuvant chemotherapy using pretreatment CT images

Early prediction of lymph node status after neoadjuvant chemotherapy (NAC) facilitates promptly optimization of treatment strategies. This study aimed to develop and validate a deep learning network (DLN) using baseline computed tomography images to predict lymph node metastasis (LNM) after NAC in patients with locally advanced gastric cancer (LAGC). A total of 1205 LAGC patients were retrospectively recruited from three hospitals between January 2013 and March 2023, constituting a training cohort, an internal validation cohort, and two external validation cohorts. A transformer-based DLN was developed using 3D tumor images to predict LNM after NAC. A clinical model was constructed through multivariate logistic regression analysis as a baseline for subsequent comparisons. The performance of the models was evaluated through discrimination, calibration, and clinical applicability. Furthermore, Kaplan-Meier survival analysis was conducted to assess overall survival (OS) of LAGC patients at two follow-up centers. The DLN outperformed the clinical model and demonstrated a robust performance for predicting LNM in the training and validation cohorts, with areas under the curve (AUCs) of 0.804 (95% confidence interval [CI], 0.752-0.849), 0.748 (95% CI, 0.660-0.830), 0.788 (95% CI, 0.735-0.835), and 0.766 (95% CI, 0.717-0.814), respectively. Decision curve analysis exhibited a high net clinical benefit of the DLN. Moreover, the DLN was significantly associated with the OS of LAGC patients [Center 1: hazard ratio (HR), 1.789, P<0.001; Center 2:HR, 1.776, P=0.013]. The transformer-based DLN provides early and effective prediction of LNM and survival outcomes in LAGC patients receiving NAC, with promise to guide individualized therapy. Future prospective multicenter studies are warranted to further validate our model. National Natural Science Foundation of China (NO. 82373432, 82171923, 82202142), Project Funded by China Postdoctoral Science Foundation (NO. 2022M720857), Regional Innovation and Development Joint Fund of National Natural Science Foundation of China (NO. U22A20345), National Science Fund for Distinguished Young Scholars of China (NO. 81925023), Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application (NO. 2022B1212010011), High-level Hospital Construction Project (NO. DFJHBF202105), Natural Science Foundation of Guangdong Province for Distinguished Young Scholars (NO. 2024B1515020091).