Image Processing Features Research Articles

An optimized support vector machine for lung cancer classification system

IntroductionLung cancer is one of the main causes of the rising death rate among the expanding population. For patients with lung cancer to have a higher chance of survival and fewer deaths, early categorization is essential. The goal of thisresearch is to enhance machine learning to increase the precision and quality of lung cancer classification.MethodsThe dataset was obtained from an open-source database and was utilized for testing and training. The suggested system used a CT scan picture as its input image, and it underwent a variety of image processing operations, including segmentation, contrast enhancement, and feature extraction.ResultsThe training process produces a chameleon swarm-based supportvector machine that can identify between benign, malignant, and normal nodules.ConclusionThe performance of the system is evaluated in terms of false-positive rate (FPR), sensitivity, specificity, recognition time and recognition accuracy.

An Automated Histopathological Colorectal Cancer Multi‐Class Classification System Based on Optimal Image Processing and Prominent Features

ABSTRACTColorectal cancer (CRC) is characterized by the uncontrollable growth of cancerous cells within the rectal mucosa. In contrast, colon polyps, precancerous growths, can develop into colon cancer, causing symptoms like rectal bleeding, abdominal pain, diarrhea, weight loss, and constipation. It is the leading cause of death worldwide, and this potentially fatal cancer severely afflicts the elderly. Furthermore, early diagnosis is crucial for effective treatment, as it is often more time‐consuming and laborious for experts. This study improved the accuracy of CRC multi‐class classification compared to previous research utilizing diverse datasets, such as NCT‐CRC‐HE‐100 K (100,000 images) and CRC‐VAL‐HE‐7 K (7,180 images). Initially, we utilized various image processing techniques on the NCT‐CRC‐HE‐100 K dataset to improve image quality and noise‐freeness, followed by multiple feature extraction and selection methods to identify prominent features from a large data hub and experimenting with different approaches to select the best classifiers for these critical features. The third ensemble model (XGB‐LightGBM‐RF) achieved an optimum accuracy of 99.63% with 40 prominent features using univariate feature selection methods. Moreover, the third ensemble model also achieved 99.73% accuracy from the CRC‐VAL‐HE‐7 K dataset. After combining two datasets, the third ensemble model achieved 99.27% accuracy. In addition, we trained and tested our model with two different datasets. We used 80% data from NCT‐CRC‐HE‐100 K and 20% data from CRC‐VAL‐HE‐7 K, respectively, for training and testing purposes, while the third ensemble model obtained 98.43% accuracy in multi‐class classification. The results show that this new framework, which was created using the third ensemble model, can help experts figure out what kinds of CRC diseases people are dealing with at the very beginning of an investigation.

Klasifikasi Tingkat Kemanisan Buah Kersen Berdasarkan Fitur Warna NTSC Menggunakan Jaringan Syaraf Tiruan Berbasis Pengolahan Citra Digital

<em><span lang="EN-US">The fruit of the calabura tree (Muntingia calabura) is a small red fruit originating from the Prunus genus, often found along roadsides. This fruit contains numerous nutrients beneficial for bodily health, serving as a highly potential source of nutrition. Presently, a challenge exists in determining the sweetness level of calabura fruit, relying heavily on manual human assessment. The development of classification utilizing technology is considered a crucial step. Previous research has concentrated on classifying various objects using RGB, HSV, YCbCr color feature extraction. However, it was observed that RGB, HSV, YCbCr color features are not universally suitable, particularly for calabura fruits. Hence, this study employs a method of classifying the sweetness level of calabura fruit based on NTSC color features using a Digital Image Processing-based Artificial Neural Network (ANN). This approach leverages color-based image processing features. The research involves several stages, starting from acquiring 300 calabura fruit images with 3 levels of classification to the classification process utilizing Backpropagation in the ANN. Multiple training and testing scenarios were conducted to select feature combinations with the highest accuracy and fastest computational time. Results revealed that the most effective feature used was the NTSC color feature as a skin characteristic parameter. Based on training outcomes using 210 training images, the accuracy reached 100% with a computational time of 1.66 seconds per image. Meanwhile, testing with 90 sample images showed an accuracy of 94% with a computational time of 4.23 seconds per image. Thus, it can be concluded that the employed method successfully classifies the quality of calabura fruit images based on color features and skin characteristics.</span></em>

An automated system for 2D building detection from UAV-based geospatial datasets

The focus of this manuscript is on integrating optical images and laser point clouds carried on low-cost UAVs to create an automated system capable of generating urban city models. After pre-processing both datasets, we co-registered both datasets using the DLT transformation model. We estimated structure heights from the LiDAR dataset through a progressive morphological filter followed by removing bare ground. Unsupervised and supervised image classification techniques were applied to a six-band image created from the optical and LiDAR datasets. After finding building footprints, we traced their edges, outlined their borderlines, and identified their geometric boundaries through several image processing and rule-based feature identification algorithms. Comparison between manually digitized and automatically extracted buildings showed a detection rate of about 92.3 % with an average of 7.4 % falsely identified areas with the six-band image in contrast to classifying only the RGB image that detected about 63.2 % of the building pixels with 25.3 % pixels incorrectly identified. Moreover, our building detection rate with the 6-band image was superior to that attained by performing traditional image segmentation for only the LiDAR DEM. Shifts in the horizontal coordinates between corner points identified by a human operator and those detected by the proposed system were in the range of 10–15 cm. This is an improvement over traditional satellite and manned-aerial large mapping systems that have lower accuracies due to sensor limitations and platform altitude. These findings demonstrate the benefits of fusing multiple UAV remote sensing datasets over utilizing a single dataset for urban area mapping and 3D city modeling.

Implementing artificial intelligence models for automatic vocal tract image segmentation

Modeling articulatory representations is critical to the scientific study of speech production and has been addressed by quantifying dynamical movements of the vocal tract. However, modeling dynamic articulatory data has proven time-consuming and computationally taxing. For example, real-time imaging data of the vocal tract has been assessed using contour-tracking methods for image segmentation that require manually creating vocal tract templates and human supervision to correct image segmentation (e.g., Bresch & Narayanan 2009). Recently, new work has introduced multimodal approaches to model articulatory data (Jain et al., 2024), but these approaches still require manual initiation/correction. We combine previous segmentation methods such as the Chan-Vese Segmentation algorithm (Getreuer 2012) with AI models like the Segment Anything Model (SAM) (Kirillov et al. 2023) to test means for optimizing image segmentation of vocal tract articulators in real-time magnetic resonance imaging (rtMRI) data. We deploy non-linear filtering and parameter optimization so as to prioritize desirable image processing features, such as smoothing the image while sharpening the edges. Processing these optimized images into SAM allows for segmentation of critical vocal tract articulators and the airway. In sum, the goal of this work is to automatically segment without manual intervention moving articulators in rtMRI speech production data. [Work supported by NSF.]

Automated crack localization for road safety using contextual u-net with spatial-channel feature integration

Accurate and timely crack localization is crucial for road safety and maintenance, but image processing and hand-crafted feature engineering methods, often fail to distinguish cracks from background noise under diverse lighting and surface conditions. This paper proposes a framework utilizing contextual U-Net deep learning model to automatically localize cracks in road images. The framework design considers crack localization as a task of pixel-level segmenting, and analyzing each pixel in a road image to determine if it belongs to a crack or not. The proposed U-Net model uses a robust EfficientNet encoder to capture crucial details (spatial features) and overall patterns (channel-wise features) within the road image. This balanced approach helps the model learn effectively from both individual elements and the context of the images, leading to improved crack detection. A customized hierarchical attention mechanism is designed to make U-Net model contextually adaptive to focus on relevant features at different scales and resolutions for accurately localizing road cracks that can vary widely in size and shape. The model's effectiveness is demonstrated through extensive evaluations on the benchmarked and custom-made datasets.

Identification of Milling Cutter Wear State under Variable Working Conditions Based on Optimized SDP

Traditional data-driven tool wear state recognition methods rely on complete data under targeted working conditions. However, in actual cutting operations, working conditions vary, and data for many conditions lack labels, with data distribution characteristics differing between conditions. To address these issues, this article proposes a method for recognizing the wear state of milling cutters under varying working conditions based on an optimized symmetrized dot pattern (SDP). This method utilizes complete data from source working conditions for representation learning, transferring a generalized milling cutter wear state recognition model to varying working condition scenarios. By leveraging computer image processing features, the vibration signals produced by milling are converted into desymmetrization dot pattern images. Clustering analysis is used to extract template images of different wear states, and differential evolution algorithms are employed to adaptively optimize parameters using the maximization of Euclidean distance as an indicator. Transfer learning with a residual network incorporating an attention mechanism is used to recognize the wear state of milling cutters under varying working conditions. The experimental results indicate that the method proposed in this paper reduces the impact of working condition changes on the mapping relationship of milling cutter wear states. In the wear state identification experiment under varying conditions, the accuracy reached 97.39%, demonstrating good recognition precision and generalization ability.

Enhanced Diagnostics Based on Deep Learning for Varicose Vein Detection

Varicose veins, a prevalent vascular condition affecting a significant portion of the population, necessitate early detection for optimal intervention and improved patient outcomes. This study introduces a novel diagnostic approach for varicose vein detection, leveraging the capabilities of deep learning. Varicose veins represent a prevalent vascular condition that can lead to discomfort and complications if not identified and treated promptly. This research introduces an advanced diagnostic methodology for varicose vein detection, utilizing deep learning techniques. Our approach harnesses the capabilities of deep neural networks, specifically employing a convolution neural network (CNN) architecture. Trained on a diverse dataset of vascular images, the model demonstrates a high proficiency in identifying varicose veins by capturing nuanced patterns and subtle features. Fine-tuning through transfer learning ensures adaptability to variations in patient demographics and imaging conditions. To enhance diagnostic precision, our system incorporates advanced image processing techniques and feature extraction methods. The integration of image segmentation algorithms and anatomical feature analysis provides detailed insights into the extent and severity of varicose veins. Furthermore, the model is designed to accommodate multi-modal imaging data, incorporating information from various imaging modalities to enhance diagnostic accuracy. Validation of our approach is conducted on a comprehensive dataset encompassing a spectrum of varicose vein cases, including varying degrees of severity. The results underscore the superior performance of our deep learning-based diagnostic system, achieving notable sensitivity and specificity in varicose vein detection. This proposed enhanced diagnostic tool holds promise for healthcare professionals, streamlining the diagnostic process and facilitating early and accurate identification of varicose veins. The potential implications include improved patient outcomes through timely intervention and the development of personalized treatment strategies. As we continue refining and expanding our model, its integration into clinical practice could contribute to a more efficient and effective management of varicose vein disorders.

Integration of Machine Learning and Iot based Multi-Layer Wireless Sensor Networks for Seamless Smart Home Automation

The integration of machine learning algorithms with Internet of Things -based multi-layer wireless sensor networks offers a transformative solution to modern smart home automation and security. This paper seeks to explore both the Sensor Data Processing and Machine Learning Components used. In essence, the machine learning model leverages aggregate sensor data to improve the efficiency and safety of modern living environments. Through attention to detail during the preprocessing and feature engineering of sensor data, the system analyzed learned patterns of household activity, including motion intensity, door/window interactions, and normal occupancy. Subsequently, the features were utilized as input variables in a number of models, including Convolutional Neural Networks , Support Vector Machines, Recurrent Neural Networks, and K-Nearest Neighbors. By simulating both vacation and occupant mode, the models processed the available data using to detect potential threats or other deficiencies in the patterns. Overall the results led by the model suggest that the Convolutional Neural Network model is the best amongst all of the aforementioned algorithms. It demonstrated the best accuracy out of all the other models due to the advanced image processing and facial recognition features, solidified by its 98.56% accuracy rate in recognizing a potential intruder. Other models were also effective or reasonably accurate, with the following results: SVMs – 95.45%; RNNs – 93.4%; and KNNs – 91.23%. The evaluation process also involves the calculation of precision, recall, and F1 score, which also indicates the overall strength of the model. The aggregation of these results implies a considerable potential for internet-of-things systems in combination with machine learning methods to cultivate smarter and safer living environments.

Broken Strand Detection of Overhead Ground Wire by Image Processing and Morphological Feature Analysis

Broken Strand Detection of Overhead Ground Wire by Image Processing and Morphological Feature Analysis

Evaluating ChatGPT's Capabilities on Orthopedic Training Examinations: An Analysis of New Image Processing Features.

Introduction The efficacy of integrating artificial intelligence (AI) models like ChatGPT into the medical field, specifically orthopedic surgery, has yet to be fully determined. The most recent adaptation of ChatGPT that has yet to be explored is its image analysis capabilities. This study assesses ChatGPT's performance in answering Orthopedic In-Training Examination (OITE) questions, including those that require image analysis. Methods Questions from the 2014, 2015, 2021, and 2022 AAOS OITE were screened for inclusion. All questions without images were entered into ChatGPT 3.5 and 4.0 twice. Questions that necessitated the use of images were only entered into ChatGPT 4.0 twice, as this is the only version of the system that can analyze images. The responses were recorded and compared to AAOS's correct answers, evaluating the AI's accuracy and precision. Results A total of 940 questions were included in the final analysis (457 questions with images and 483 questions without images). ChatGPT 4.0 performed significantly better on questions that did not require image analysis (67.81% vs 47.59%, p<0.001). Discussion While the use of AI in orthopedics is an intriguing possibility, this evaluation demonstrates how, even with the addition of image processing capabilities, ChatGPT still falls short in terms of its accuracy. As AI technology evolves, ongoing research is vital to harness AI's potential effectively, ensuring it complements rather than attempts to replace the nuanced skills of orthopedic surgeons.

Effect of material properties on emotion: a virtual reality study.

Designers know that part of the appreciation of a product comes from the properties of its materials. These materials define the object's appearance and produce emotional reactions that can influence the act of purchase. Although known and observed as important, the affective level of a material remains difficult to assess. While many studies have been conducted regarding material colors, here we focus on two material properties that drive how light is reflected by the object: its metalness and smoothness. In this context, this work aims to study the influence of these properties on the induced emotional response. We conducted a perceptual user study in virtual reality, allowing participants to visualize and manipulate a neutral object - a mug. We generated 16 material effects by varying it metalness and smoothness characteristics. The emotional reactions produced by the 16 mugs were evaluated on a panel of 29 people using James Russel's circumplex model, for an emotional measurement through two dimensions: arousal (from low to high) and valence (from negative to positive). This scale, used here through VR users' declarative statements allowed us to order their emotional preferences between all the virtual mugs. Statistical results show significant positive effects of both metalness and smoothness on arousal and valence. Using image processing features, we show that this positive effect is linked to the increasing strength (i.e., sharpness and contrast) of the specular reflections induced by these material properties. The present work is the first to establish this strong relationship between specular reflections induced by material properties and aroused emotions.

Wood Quality Analyzing System

This paper presents a comprehensive approach to optimizing furniture design processes and facilitating wood identification through the development of a mobile application. The application is designed to provide users with intuitive tools and resources for informed decisionmaking in furniture design and wood selection. The first component of the mobile application focuses on optimizing furniture design through furniture size and quality consideration. This encompasses the creation of an intuitive user interface that enables users to specify their furniture design preferences, including material selection criteria. A comprehensive wood database is meticulously curated, furnishing users with comprehensive details on wood sizes, qualities, and thicknesses, thereby aiding in material selection and waste reduction initiatives. Algorithms are employed to recommend optimal wood sizes, considering factors such as material selection, waste reduction, and cost analysis. Visual representation tools are included, allowing users to preview furniture designs with different wood options, facilitating informed decisionmaking. Furthermore, feedback mechanisms have been integrated to enable users to provide feedback on recommended wood sizes and qualities, thereby facilitating continuous enhancement and refinement of recommendations. The second component aims to identify the type of wood by its appearance. Image processing features have been developed to precisely extract visual characteristics from wood sample images, thereby aiding in the identification of wood species. Machine learning models are trained to classify wood species based on visual characteristics obtained from images, thereby enhancing the precision of identification. User interaction tools have been designed to ensure ease of use and accessibility for users in capturing and submitting wood sample images. Within the application, educational resources and materials are provided to help users learn about different wood species, aiding their understanding and selection process.

Application research of interior space design elements based on image processing

In order to quantitatively analyze the application performance of elements in interior space design, a detection method of texture visual features of elements distribution images in interior space design based on image processing and texture edge contour features detection is proposed. A multi-resolution visual information collection model for detecting the texture visual characteristics of element distribution images in indoor space design is constructed, and a visual characteristic identification model for element application configuration in indoor space design is established. Multi-texture grid block area combination design method is adopted to realize the fusion of element application configuration visual images in indoor space design. Through the edge feature detection method of texture grid area, Establish a visual parameter identification model of element application configuration in interior space design, extract the visual information feature quantity of element application configuration in interior space design, adopt Harris corner feature matching method, realize distributed detection of texture edge contour features of element application configuration visual features in interior space design, and fuse detection of high-resolution texture information through combined filtering and collaborative filtering. The collection and optimization of visual features of element application configuration in interior space design are realized, and the distributed detection algorithm of texture edge contour features is adopted to improve the convergence level of detection of texture visual features of element distribution images in interior space design, and the application of elements in interior space design based on image processing is realized. The simulation results show that this method has good resolution and strong visual expression ability in extracting the texture visual features of element distribution images in interior space design, which improves the quantitative analysis ability of elements in interior space design.

Stand-Alone Melanoma Diagnostic System Using the Raspberry PI 4

Skin cancer, in general, is a growing threat to human health. Melanoma skin cancer is one of the most severe types of skin cancer in humans. In the initial stages, melanoma affects the skin in general, and it may develop and spread to other parts of the human body in its advanced stages. Early detection can reduce its severity and improve treatment outcomes. In this study, the proposed system includes image processing techniques and feature extraction by combining Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM), in addition to enhancing the extracted features with the diameter feature. A Support Vector Machine (SVM) model with a radial basis function (RBF) kernel was employed to train and predict the results of the test data on the Raspberry Pi 4 platform. The available International Skin Imaging Collaboration (ISIC) dataset of skin images was used in the training and testing of this system. The test results showed that the proposed system achieves high specificity (99.35%), medium sensitivity (75.35%), and comprehensive accuracy (93.71%).

A surrogate modeling method for distributed land surface hydrological models based on deep learning

Surrogate modelling methods have been used to estimate spatially distributed parameters of land surface hydrological models due to their computational efficiency. However, traditional surrogate techniques have trouble in modelling high-dimensional input–output maps. In addition, their applications to a distributed model over large spatial and temporal domains are very unlikely to produce consistent spatial pattern and dynamic relationship of model input and output, leading to unbalanced model performance across different spatiotemporal domains. To address these issues, we employ a deep autoregressive neural network to construct an accurate and reliable surrogate system of distributed dynamic model outputs. The network uses a deep convolutional encoder-decoder architecture to take full advantage of the deep convolutional layers in high-dimensional image processing and spatial feature extraction. Moreover, the autoregressive strategy makes the network good at handling dynamic relationship between the time-varying model input and output. We apply this deep learning (DL) network to building a surrogate model of the Variable Infiltration Capacity (VIC) model simulated soil moisture over the Huaihe river basin of China. The results show that the adopted deep autoregressive neural network can provide an accurate surrogate model of the high-dimensional dynamic relationship between 15 input fields and 1 output field, each covering 408 grids, over multiple years. This surrogate model significantly outperforms the popular long short-term memory (LSTM) model, achieving an average mean squared error (MSE) of 0.26 and an average R2 of 0.76 using the test datasets. The surrogate's MSE and R2 performance represents an average improvement of 43% and 33%, respectively, compared to the LSTM model. In addition, it shows better spatial performance than the LSTM model, demonstrating its superior performance in approximating spatial patterns of VIC simulated soil moisture. The accuracy of this surrogate method and its ability to handle high-dimensional data is promising for advancing parameter uncertainty quantification of distributed land surface hydrological models, which usually have high dimensionality due to the large number of variables involved, including distributed parameters, input forcing variables, and output variables.

RWD122 The Application of Artificial Intelligence for Enhanced Diagnosis of Prostate Cancer Using Biopsy Evidence That Are Substantiated By Genetic Markers

Although the most prevalent approach for the detection and diagnosis of prostate cancer is by examining the biopsy images, the presence of substantial variability in biopsy analysis often leads to delays in optimized treatment. The recent advancements in the genomic domain, with coding and non-coding genes as biomarkers along with sequencing data using artificial intelligence (AI), have led to improved decision making and better clinical management. In this study, we propose a hybrid approach that combines the state-of-the-art technologies for image processing and genomic features for an effective detection of Gleason score in the field of prostate carcinogenesis.

Fruit Disease Identification using Image Processing Techniques and Feature Extraction

The detection and classification of fruit diseases using image processing is an important field of research in agriculture. This technology can help farmers quickly and accurately identify diseased fruits and take appropriate measures to control the spread of the disease. The proposed system involves capturing images of fruits using a camera, followed by processing and analysis of these images to detect and classify the type of disease present. The images are first pre-processed to remove noise and enhance their quality, after which they are segmented to identify regions of interest. Various features such as color, texture, and shape are extracted from these regions, which are then used to classify the disease. Machine learning algorithms such as support vector machines (SVM), artificial neural networks (ANN), and decision trees are commonly used to classify diseases. The performance of these algorithms is evaluated based on metrics such as accuracy, precision, and recall. The proposed system has the potential to significantly reduce the time and effort required for disease detection and classification. This can help farmers to take timely and informed decisions to prevent the spread of the disease, ultimately resulting in increased crop yield and profitability.

FEATURES OF HANDWRITING IMAGE PROCESSING AND ANALYSIS

FEATURES OF HANDWRITING IMAGE PROCESSING AND ANALYSIS

Superpixel segmentation based on image density

Superpixel segmentation can get the middle features in image processing, effectively reduce the dimensionality of the image, and is widely used in image processing fields. To get the regular and compact superpixels in real-time, a superpixel segmentation algorithm based on image density is proposed in this paper. Firstly, the image is uniformly divided according to the number of superpixels to be obtained. Secondly, to get the clustering ability of the pixels, the density image is produced. Thirdly, the seed is chosen in each sub-region block according to the density and then the superpixels are obtained by clustering. During the clustering process, the pixel around the seed should be added into the superpixel if it meets the conditions, and the small supeipixels are merged into the big superpixels around them. Finally, the result shows that the proposed algorithm has the best segmentation effect, and a good balance in accuracy, regularity, and time cost.