Image Processing Model Research Articles

Predicting oil accumulation by fruit image processing and linear models in traditional and super high-density olive cultivars

The paper focuses on the seasonal oil accumulation in traditional and super-high density (SHD) olive plantations and its modelling employing image-based linear models. For these purposes, at 7-10-day intervals, fruit samples (cultivar Arbequina, Fasola, Frantoio, Koroneiki, Leccino, Maiatica) were pictured and images segmented to extract the Red (R), Green (G), and Blue (B) mean pixel values which were re-arranged in 35 RGB-derived colorimetric indexes (CIs). After imaging, the samples were crushed and oil concentration was determined (NIR). The analysis of the correlation between oil and CIs revealed a differential hysteretic behavior depending on the covariates (CI and cultivar). The hysteresis area (Hyst) was then quantified and used to rank the CIs under the hypothesis that CIs with the maximum or minimum Hyst had the highest correlation coefficient and were the most suitable predictors within a general linear model. The results show that the predictors selected according to Hyst-based criteria had high accuracy as determined using a Global Performance Indicator (GPI) accounting for various performance metrics (R2, RSME, MAE). The use of a general linear model here presented is a new computational option integrating current methods mostly based on artificial neural networks. RGB-based image phenotyping can effectively predict key quality traits in olive fruit supporting the transition of the olive sector towards a digital agriculture domain.

Automated denoising software for calcium imaging signals using deep learning

Dynamic Ca2+ signaling is crucial for cell survival and death, and Ca2+ imaging approaches are commonly used to study and measure cellular Ca2+ patterns within cells. However, the presence of image noise from instrumentation and experimentation protocols can impede the accurate extraction of Ca2+ signals. Removing noise from Ca2+ Spatio-Temporal Maps (STMaps) is essential for precisely analyzing Ca2+ datasets. Current methods for denoising STMaps can be time-consuming and subjective and rely mainly on image processing protocols. To address this, we developed CalDenoise, an automated software that employs robust image processing and deep learning models to remove noise and enhance Ca2+ signals in STMaps effectively. CalDenoise integrates four pipelines capable of efficiently removing salt-and-pepper, impulsive, and periodic noise and detecting and removing background noise. Comprising both an image-processing-based pipeline and three generative-adversarial-network-based (GAN) deep learning models, CalDenoise proficiently removes complex noise patterns. The software features adjustable parameters to enhance accuracy and is integrated into a user-friendly graphical interface for easy access and streamlined usage.CalDenoise can serve as a robust platform for denoising complex dynamic fluorescence signal images across diverse cell types, including Ca2+, voltage, ions, and pH signals.

The collapse of modern exposures in the recording of X-RAY images in medicine

This article reviewed the methods and algorithms for processing and diagnosing X-ray images that are widely used in medicine today. In order to improve the implementation of deep learning in modern medicine and further improve the widespread use of HMLs, the method, algorithm and model of X-ray image processing using the Raspberry Pi device were analyzed.

Deep Learning with Crested Porcupine Optimizer for Detection and Classification of Paddy Leaf Diseases for Sustainable Agriculture

India has a vast number of inhabitants and the main food source distribution is from agriculture. Agricultural lands are being demolished generally owing to plant and crop illnesses. The detection of plant diseases by using image processing models can aid agriculturalists in defending the farming area from damaging or affecting it. Paddy is the main harvest worldwide. Early recognition of the paddy diseases at dissimilar phases of development is very vital in paddy production. However, the present manual technique in identifying and classifying paddy diseases needs a very educated farmer and is time-consuming. Deep learning (DL) is an effectual research area in the classification of agriculture patterns where it can efficiently solve the problems of diseases identification. Therefore, the articles focus on the design and expansion of Deep Learning based Crested Porcupine Optimizer for the Detection and Classification of Paddy Leaf Diseases (DLCPO-DCPLD) method for Sustainable Agriculture. The main aim of the DLCPO-DCPLD method use DL method for the recognition and identification of rice plant leaf diseases. To accomplish this, the DLCPO-DCPLD technique performs the image pre-processing using Median Filtering (MF) to recover the excellence of the input frames. Next, the ConvNeXt-L method is applied for extraction of feature vectors from the pre-processed images. Also, the Conditional Variational Autoencoder (CVAE) model is utilized for the automated classification of Paddy Leaf diseases. Eventually, the hyperparameter tuning of the CVAE technique is accomplished by implementing the Crested Porcupine Optimizer (CPO) technique. To safeguard the enhanced predictive results of the DLCPO-DCPLD method, a sequence of experimentations is implemented on the benchmark dataset. The experimental validation of the DLCPO-DCPLD method portrayed a superior accuracy value of 99.12% over existing approaches.

Truncated M13 phage for smart detection of E. coli under dark field

BackgroundThe urgent need for affordable and rapid detection methodologies for foodborne pathogens, particularly Escherichia coli (E. coli), highlights the importance of developing efficient and widely accessible diagnostic systems. Dark field microscopy, although effective, requires specific isolation of the target bacteria which can be hindered by the high cost of producing specialized antibodies. Alternatively, M13 bacteriophage, which naturally targets E. coli, offers a cost-efficient option with well-established techniques for its display and modification. Nevertheless, its filamentous structure with a large length-diameter ratio contributes to nonspecific binding and low separation efficiency, posing significant challenges. Consequently, refining M13 phage methodologies and their integration with advanced microscopy techniques stands as a critical pathway to improve detection specificity and efficiency in food safety diagnostics.MethodsWe employed a dual-plasmid strategy to generate a truncated M13 phage (tM13). This engineered tM13 incorporates two key genetic modifications: a partial mutation at the N-terminus of pIII and biotinylation at the hydrophobic end of pVIII. These alterations enable efficient attachment of tM13 to diverse E. coli strains, facilitating rapid magnetic separation. For detection, we additionally implemented a convolutional neural network (CNN)-based algorithm for precise identification and quantification of bacterial cells using dark field microscopy.ResultsThe results obtained from spike-in and clinical sample analyses demonstrated the accuracy, high sensitivity (with a detection limit of 10 CFU/μL), and time-saving nature (30 min) of our tM13-based immunomagnetic enrichment approach combined with AI-enabled analytics, thereby supporting its potential to facilitate the identification of diverse E. coli strains in complex samples.ConclusionThe study established a rapid and accurate detection strategy for E. coli utilizing truncated M13 phages as capture probes, along with a dark field microscopy detection platform that integrates an image processing model and convolutional neural network.Graphical

Robust Model Watermarking for Image Processing Networks via Structure Consistency.

The intellectual property of deep networks can be easily "stolen" by surrogate model attack. There has been significant progress in protecting the model IP in classification tasks. However, little attention has been devoted to the protection of image processing models. By utilizing consistent invisible spatial watermarks, the work (Zhang et al. 2020) first considered model watermarking for deep image processing networks and demonstrated its efficacy in many downstream tasks. Its success depends on the hypothesis that if a consistent watermark exists in all prediction outputs, that watermark will be learned into the attacker's surrogate model. However, when the attacker uses common data augmentation attacks (e.g., rotate, crop, and resize) during surrogate model training, it will fail because the underlying watermark consistency is destroyed. To mitigate this issue, we propose a new watermarking methodology, "structure consistency", based on which a new deep structure-aligned model watermarking algorithm is designed. Specifically, the embedded watermarks are designed to be aligned with physically consistent image structures, such as edges or semantic regions. Experiments demonstrate that our method is more robust than the baseline in resisting data augmentation attacks. Besides that, we test the generalization ability and robustness of our method to a broader range of adaptive attacks.

SEAIS: Secure and Efficient Agricultural Image Storage Combining Blockchain and Satellite Networks

The image integrity of real-time monitoring is crucial for monitoring crop growth, helping farmers and researchers improve production efficiency and crop yields. Unfortunately, existing schemes just focus on ground equipment and drone imaging, neglecting satellite networks in remote or extreme environments. Given that satellite internet features wide area coverage, we propose SEAIS, a secure and efficient agricultural image storage scheme combining blockchain and satellite networks. SEAIS presents the mathematical model of image processing and transmission based on satellite networks. Moreover, to ensure the integrity and authenticity of image data during pre-processing such as denoising and enhancement, SEAIS includes a secure agricultural image storage and verification method based on blockchain, homomorphic encryption, and zero-knowledge proof. Specifically, images are stored via IPFS, with hash values and metadata recorded on the blockchain, ensuring immutability and transparency. The simulation results show that SEAIS exhibits more stable and efficient processing times in extreme environments. Also, it maintains low on-chain storage overhead, enhancing scalability.

Optimal quantum circuit generation for pixel segmentation in multiband images

A novel approach is proposed for multiband image processing via quantum models in real situations. Quantum circuits are automatically generated ad-hoc for each use case via multiobjective genetic algorithms. Using this universal method, image processing tasks such as segmentation can be carried out by considering the properties that constitute each pixel. The generated circuits present a low level of correlation between qubits, and thus can be considered quantum-inspired machine learning models. The effectiveness of this methodology has been validated by applying it to different segmentation use cases. Comparisons are made between optimized classical kernel methods and the generated quantum-inspired models to understand their behaviors. The results show that quantum models for multiband image processing achieve accuracies similar to those of classical methods.

In-line semantic segmentation of kimchi cabbage deterioration using YOLOv8n and DeepLabv3+

To ensure the safety of kimchi cabbage (KC), the effective identification of deterioration is required. In this study, we aimed to develop and validate a semantic segmentation pipeline to detect and segment the mild and severe deterioration of KC on moving industrial conveyor belts. The pipeline integrates the YOLOv8n and DeepLabv3+ models, image processing and semantic labelling models, respectively. The YOLOv8n model was employed for initial detection, achieving an F1 score (a measure of precision and recall) of 0.988 and an AP50 (average precision at 50 % intersection over union (IoU) with the ground truth) of 0.994. For detailed segmentation, the DeepLabv3+ model with Resnet101 and Mobilenetv3 backbones was used, and the performance of these models was evaluated based on F1 scores. The YOLOv8n model demonstrated high accuracy in detection. Further, the DeepLabv3+ model with the Resnet101 backbone achieved F1 scores of 0.772 and 0.851, and IoUs of 0.628 and 0.741 for mild and severe deterioration, respectively. Notably, the DeepLabv3+ model with Mobilenetv3 backbone excelled in identifying severe deterioration, indicating its potential for generating rapid alerts in edge devices. Crucially, the developed methodology enables the real-time, in-line monitoring of KC deterioration and is adaptable for future edge device applications. The results of this study highlight the potential of accessible technologies in advancing agricultural quality control, setting a benchmark for future research to expand data sources and enhance detection capabilities.

Automatic recognition system for concrete cracks with support vector machine based on crack features

Cracks are a common problem in concrete surfaces. With the continuous optimization of machine vision-based inspection systems, effective crack detection and recognition is the core of the entire system. In this study, support vector machine (SVM) was used to distinguish cracks from other regions. To complete the recognition system of the SVM, a framework consisting of an image processing and recognition model was proposed. An algorithm combining the Prewitt operator with the Otsu threshold was proposed for image segmentation. The binary image processed by the new algorithm combined with mathematical morphology can result in a more complete crack zone and fewer interference regions. After the initial parameter extraction, most of the impurity areas were screened by preliminary discrimination, removing 99% of the impurities. This processing step ensured the balance and effectiveness of the samples. To establish an automatic identification model based on SVM with a radial basis function, compactness, occupancy rate, and length–width ratio were selected as input parameters after comparing these three features with all six features of the crack. The recognition accuracy of this system reaches 97.14%, demonstrating that the proposed method is effective and satisfies practical requirements.

Implementation and Efficient Analysis of Preprocessing Techniques in Deep Learning for Image Classification

Deep learning models have recently been preferred to perform certain image-processing tasks. Recently, with the increasing radiation, heat, and poor lighting conditions, the raw image samples may contain noisy and ambiguous information. To process these images, the deep learning model requires a large number of data samples to learn the missing information from other clear data samples. This necessitates training the neural network with a huge dataset. The researchers are now attempting to filter and improve such noisy images via preprocessing in order to provide valid and accurate feature information to the neural network layers. However, certain research studies claim that some useful information may be lost when the image is not preprocessed with an appropriate filter or enhancement technique. The MSA (meta-synthesis and analysis) approach is utilized in this work to present the impact of the image processing applications done with and without preprocessing steps. Also, this work summarizes the existing deep learning-based image processing models utilizing or not preprocessing steps in their implementation. This work has also found that 85% of the existing techniques involve a preprocessing step while developing a deep learning model. However, a maximum accuracy of 96.89% is observed on Sine-Net when it is implemented without a preprocessing and the same model gave 96.85% when implemented with preprocessing. This research provides various research insights on the requirement and non-requirement of preprocessing steps in a deep learning-based implementation.

NetraDeep: An Integrated Deep Learning and Image Processing System for Precise Detection of Hard Exudates

Hard Exudate (HE) is a common manifestation of various eye diseases, such as diabetic retinopathy (DR), and a prominent cause of vision loss and blindness. Researchers aim to visualize and quantify these exudates using deep learning (DL) and image processing (IP) models from retinal images. However, the requirement for a large number of labelled image datasets for DL models to work on diverse and poor-quality images makes this task challenging. To address this challenge, we introduce NetraDeep, a system that integrates data-driven DL and rule-based IP techniques for exudate segmentation. Our system uses IP models to detect and extract some features and assists DL models in detecting more advanced features and vice versa. The IP models are rule-based and use predefined rules to process images, while the DL models are data-driven and learn from the input data. NetraDeep provides visual and quantitative assessments while mitigating noise and other confounding factors such as artifacts and noise. The training of DL models of this system requires only a limited number of labelled fundus images from publicly available datasets. It provides accurate pixel-wise segmentation results on the public and private image datasets collected from local eye hospitals. Through extensive evaluation, our system achieved remarkable performance, with a dice coefficient of \(0.84\) for the public dataset and a rating of \(9.78\) and \(9.43\) out of 10, as corroborated by two medical experts with experience of more than 20 and 5 years, respectively, for the private image dataset.

Landscape Architecture Carbon Emission Lifecycle Management Tool Based on Artificial Intelligence

In the contemporary discourse, carbon emissions have emerged as a focal point of global concern due to their role in inducing climate warming and precipitating ecological collapse. The establishment of a comprehensive carbon emission management system, coupled with effective measures, holds the potential to mitigate climate change, safeguard ecological integrity, improve health conditions, and promote global sustainable development. The Carbon Lifecycle AI Project Management Tool (CLA) proposed in this paper makes use of Large Language Model (LLM) and image processing model to intelligently analyze and manage the carbon emission of landscape architecture throughout its life cycle, and focuses on solving the carbon emission problem in landscape architecture. By gathering, integrating, and analyzing data related to landscape architecture, including information on material selection, plant configuration, and energy utilization, comprehensive monitoring and management of carbon emissions from landscape architecture are achieved. CLA not only offers real-time monitoring and analytical capabilities for carbon emissions but also identifies emission reduction opportunities and provides corresponding optimization recommendations, thus offering crucial support for the sustainable development of the landscape architecture industry.

The artistic image processing for visual healing in smart city

This study investigates the processing methods of artistic images within the context of Smart city (SC) initiatives, focusing on the visual healing effects of artistic image processing to enhance urban residents’ mental health and quality of life. Firstly, it examines the role of artistic image processing techniques in visual healing. Secondly, deep learning technology is introduced and improved, proposing the overlapping segmentation vision transformer (OSViT) for image blocks, and further integrating the bidirectional long short-term memory (BiLSTM) algorithm. An innovative artistic image processing and classification recognition model based on OSViT-BiLSTM is then constructed. Finally, the visual healing effect of the processed art images in different scenes is analyzed. The results demonstrate that the proposed model achieves a classification recognition accuracy of 92.9% for art images, which is at least 6.9% higher than that of other existing model algorithms. Additionally, over 90% of users report satisfaction with the visual healing effects of the artistic images. Therefore, it is found that the proposed model can accurately identify artistic images, enhance their beauty and artistry, and improve the visual healing effect. This study provides an experimental reference for incorporating visual healing into SC initiatives.

Deep Learning‐Enabled Vasculometry Depicts Phased Lesion Patterns in High Myopia Progression

PurposeTo investigate the potential phases in myopic retinal vascular alterations for further elucidating the mechanisms underlying the progression of high myopia (HM). MethodsFor this retrospective study, participants diagnosed with high myopia at Beijing Tongren Hospital were recruited. Based on bionic mechanisms of human vision, an intelligent image processing model was developed and utilized to extract and quantify the morphological characteristics of retinal vasculatures in different regions measured by papilla-diameter (PD), including vascular caliber, arteriole-to-venule ratio (AVR), tortuosity, the angle of the vascular arch (AVA), the distance of the vascular arch (DVA), density, fractal dimension, and venular length. In addition, the optic disc and the area of peripapillary atrophy (PPA) were also quantified. The characteristics of the overall population, as well as patients aged less than 25 years old, were compared by different genders. Univariate and multiple linear regression analyses were conducted to investigate the correlation of retinal vasculature parameters with PPA width, and detailed trends of the vascular indicators were analyzed to explore the potential existence of staged morphological changes. FindingsThe study included 14,066 fundus photographs of 5775 patients (aged 41.2 ± 18.6 years), of whom 7379 (61.2 %) were female. The study included 12,067 fundus photographs of 5320 patients (aged 41.2 ± 18.6 years). Significant variations in the morphological parameters of retinal vessels were observed between males and females. After adjusting for age and sex, multiple linear regression analysis showed that an increased PPA width ratio was associated with lower AVA (1PD), DVA (1PD), vascular caliber (0.5–1.0 PD), tortuosity (0.5–1.0 PD), density and fractal dimension (all P < 0.001, Spearman’s ρ < 0). Overall, the changes in retinal vascular morphology showed two phases: tortuosity (0.5–1.0PD) and AVA (1PD) decreased rapidly in the first stage but significantly more slowly in the second stage, while vascular density and fractal dimension showed a completely opposite trend with an initial slow decline followed by a rapid decrease. ConclusionsThis study identified two distinct phases of retinal vascular morphological changes during the progression of HM. Traction lesions were predominant in the initial stage, while atrophic lesions were predominant in the later stage. These findings provide further insight into the development mechanism of HM from the perspective of retinal vasculature.

High-Frequency Matters: Attack and Defense for Image-Processing Model Watermarking

High-Frequency Matters: Attack and Defense for Image-Processing Model Watermarking

Visual Communication Design of Weak and Small Target Images Based on Image Processing Model and Data Fusion

Visual Communication Design of Weak and Small Target Images Based on Image Processing Model and Data Fusion

L1RR: Model Pruning Using Dynamic and Self-Adaptive Sparsity for Remote-Sensing Target Detection to Prevent Target Feature Loss

Limited resources for edge computing platforms in airborne and spaceborne imaging payloads prevent using complex image processing models. Model pruning can eliminate redundant parameters and reduce the computational load, enhancing processing efficiency on edge computing platforms. Current challenges in model pruning for remote-sensing object detection include the risk of losing target features, particularly during sparse training and pruning, and difficulties in maintaining channel correspondence for residual structures, often resulting in retaining redundant features that compromise the balance between model size and accuracy. To address these challenges, we propose the L1 reweighted regularization (L1RR) pruning method. Leveraging dynamic and self-adaptive sparse modules, we optimize L1 sparsity regularization, preserving the model’s target feature information using a feature attention loss mechanism to determine appropriate pruning ratios. Additionally, we propose a residual reconstruction procedure, which removes redundant feature channels from residual structures while maintaining the residual inference structure through output channel recombination and input channel recombination, achieving a balance between model size and accuracy. Validation on two remote-sensing datasets demonstrates significant reductions in parameters and floating point operations (FLOPs) of 77.54% and 65%, respectively, and a 48.5% increase in the inference speed on the Jetson TX2 platform. This framework optimally maintains target features and effectively distinguishes feature channel importance compared to other methods, significantly enhancing feature channel robustness for difficult targets and expanding pruning applicability to less difficult targets.

Анализ тенденций развития традиционных промыслов коренных народов в условиях климатических изменений (на примере Новосибирских островов и прибрежных арк­тических районов Якутии)

The article considers the possible positive impact of climate change in the Arctic zone of Russia on the traditional trades of indigenous peoples. The authors have carried out an analysis of trends in the development of fossil mammoth bone and wild reindeer extraction against the background of climatic changes occurring in the region. They have revealed that climate changes in the area of the Novosibirsk Islands archipelago and coastal Arctic regions contribute to an increase in vegetation productivity, thus creating new conditions for the development of reindeer husbandry and an increase in the number of wild reindeer. Based on the MODIS satellite image-processing model, the researchers have estimated the changes in the food supply of wild reindeer on the Novosibirsk Islands for the period 2000-2021. The results show that the degradation of permafrost rocks under conditions of climate change contributes to the development of traditional activity of indigenous peoples in the field of collecting fossil animal derivatives. The authors have confirmed the hypothesis about the positive impact of climate change on these areas of traditional activity by data on the dynamics of allocated quotas for the production of wild reindeer in 2010-2023, as well as data on issued and current licenses for the collection of fossil mammoth bones in the Republic of Sakha (Yakutia) for 2016-2024. Basing on the results, the authors suggest developing traditional trades of indigenous peoples in the Arctic zone of the country and elaborating adaptation measures for the local population to the climate change processes.

HealthSquare: A Survey of Deep Learning Based Healthcare Platform

The multi-health diagnosis web application HealthSquare represents a pioneering endeavor in healthcare technology by integrating advanced AI models for comprehensive health analysis. The system comprises multiple components, including two image processing models for fracture detection from X-ray reports and brain tumor identification from MRI scans. Additionally, GCP’s Vertex AI is leveraged for blood &amp; thyroid report analysis to predict &amp; provide descriptive diagnosis. Moreover, the platform enables users to create accounts for secure storage of medical reports, akin to a specialized digital locker tailored specifically for healthcare documents. Furthermore, an AI-driven chat bot offers real-time health- related guidance and recommendations to users based on their queries. The integration of these components aims to redefine healthcare diagnostics by providing users with accessible, accurate, and personalized health analysis tools. Utilizing advanced image processing techniques, AI-driven analyses, and secure user accounts, the project strives to revolutionize healthcare by offering a comprehensive and user-centric approach to medical diagnosis and health management. Keywords: AI Integration, Fracture Detection, Brain Tumor Identification, Thyroid Detection, Blood Analysis, Secure Medical Report Storage, AI Chat Bot.