Search results for: image retrieval

Authors: Sheldon Liu, Gordon Wang, Lei Liu, Xuefeng Liu

Abstract:

Anomaly detection, also referred to as one-class classification, plays a crucial role in identifying product images that deviate from the expected distribution. This study introduces Data-centric Anomaly Detection with Diffusion Models (DCADDM), presenting a systematic strategy for data collection and further diversifying the data with image generation via diffusion models. The algorithm addresses data collection challenges in real-world scenarios and points toward data augmentation with the integration of generative AI capabilities. The paper explores the generation of normal images using diffusion models. The experiments demonstrate that with 30% of the original normal image size, modeling in an unsupervised setting with state-of-the-art approaches can achieve equivalent performances. With the addition of generated images via diffusion models (10% equivalence of the original dataset size), the proposed algorithm achieves better or equivalent anomaly localization performance.

Keywords: diffusion models, anomaly detection, data-centric, generative AI

Procedia PDF Downloads 67

Authors: Y. S. Zhou, C. R. Li, L. L. Tang, C. X. Gao, D. J. Wang, Y. Y. Guo

Abstract:

Triangular trihedral corner reflector (CR) has been widely used as point target for synthetic aperture radar (SAR) calibration and image quality assessment. The additional “tip” of the triangular plate does not contribute to the reflector’s theoretical RCS and if it interacts with a perfectly reflecting ground plane, it will yield an increase of RCS at the radar bore-sight and decrease the accuracy of SAR calibration and image quality assessment. Regarding this problem, two types of CRs were manufactured. One was the hexagonal trihedral CR. It is a self-illuminating CR with relatively small plate edge length, while large edge length usually introduces unexpected edge diffraction error. The other was the triangular trihedral CR with extended bottom plate which considers the effect of ‘tip’ into the total RCS. In order to assess the performance of the two types of new CRs, flight campaign over the National Calibration and Validation Site for High Resolution Remote Sensors was carried out. Six hexagonal trihedral CRs and two bottom-extended trihedral CRs, as well as several traditional triangular trihedral CRs, were deployed. KOMPSAT-5 X-band SAR image was acquired for the performance analysis of the hexagonal trihedral CRs. C-band airborne SAR images were acquired for the performance analysis of the bottom-extended trihedral CRs. The analysis results showed that the impulse response function of both the hexagonal trihedral CRs and bottom-extended trihedral CRs were much closer to the ideal sinc-function than the traditional triangular trihedral CRs. The flight campaign results validated the advantages of new types of CRs and they might be useful in the future SAR calibration mission.

Keywords: synthetic aperture radar, calibration, corner reflector, KOMPSAT-5

Procedia PDF Downloads 258

Authors: Mi Ju Choi

Abstract:

This study investigated the perception of gaming tourists toward Macau and developed a typology of gaming tourists. The 1,497 responses from tourists in Macau were collected through convenience sampling method. The dimensions of multi-culture, convenience, economy, gaming, and unsafety, were subsequently extracted as the factors of perception of gaming tourists in Macau. Cluster analysis was performed using the delineated factors (perception of tourists on Macau). Four heterogonous groups were generated, namely, gaming lovers (n = 467, 31.2%), exotic lovers (n = 509, 34.0%), reasonable budget seekers (n = 269, 18.0%), and convenience seekers (n = 252, 16.8%). Further analysis was performed to investigate any difference in gaming behavior and tourist activities. The findings are expected to contribute to the efforts of destination marketing organizations (DMOs) in establishing effective business strategies, provide a profile of gaming tourists in certain market segments, and assist DMOs and casino managers in establishing more effective marketing strategies for target markets.

Keywords: destination image, gaming tourists, Macau, segmentation

Procedia PDF Downloads 284

Authors: Harold Mauricio Díaz-Vargas, Cristian Alfonso Jimenez-Castaño, David Augusto Cárdenas-Peña, Guillermo Alberto Ortiz-Gómez, Alvaro Angel Orozco-Gutierrez

Abstract:

Precise identification of the nerves is a crucial task performed by anesthesiologists for an effective Peripheral Nerve Blocking (PNB). Now, anesthesiologists use ultrasound imaging equipment to guide the PNB and detect nervous structures. However, visual identification of the nerves from ultrasound images is difficult, even for trained specialists, due to artifacts and low contrast. The recent advances in deep learning make neural networks a potential tool for accurate nerve segmentation systems, so addressing the above issues from raw data. The most widely spread U-Net network yields pixel-by-pixel segmentation by encoding the input image and decoding the attained feature vector into a semantic image. This work proposes a conditioning approach and encoder pre-training to enhance the nerve segmentation of traditional U-Nets. Conditioning is achieved by the one-hot encoding of the kind of target nerve a the network input, while the pre-training considers five well-known deep networks for image classification. The proposed approach is tested in a collection of 619 US images, where the best C-UNet architecture yields an 81% Dice coefficient, outperforming the 74% of the best traditional U-Net. Results prove that pre-trained models with the conditional approach outperform their equivalent baseline by supporting learning new features and enriching the discriminant capability of the tested networks.

Keywords: nerve segmentation, U-Net, deep learning, ultrasound imaging, peripheral nerve blocking

Procedia PDF Downloads 85

Authors: M. A. Alqahtani, D. P. Coleman, N. D. Pugh, L. D. M. Nokes

Abstract:

In diagnostic ultrasound, the echo graphic B-scan texture is an important area of investigation since it can be analyzed to characterize the histological state of internal tissues. An important factor requiring consideration when evaluating ultrasonic tissue texture is the depth. The effect of attenuation with depth of ultrasound, the size of the region of interest, gain, and dynamic range are important variables to consider as they can influence the analysis of texture features. These sources of variability have to be considered carefully when evaluating image texture as different settings might influence the resultant image. The aim of this study is to investigate the effect of depth on the texture features in-vivo using a 3D ultrasound probe. The left leg medial head of the gastrocnemius muscle of 10 healthy subjects were scanned. Two regions A and B were defined at different depth within the gastrocnemius muscle boundary. The size of both ROI’s was 280*20 pixels and the distance between region A and B was kept constant at 5 mm. Texture parameters include gray level, variance, skewness, kurtosis, co-occurrence matrix; run length matrix, gradient, autoregressive (AR) model and wavelet transform were extracted from the images. The paired t –test was used to test the depth effect for the normally distributed data and the Wilcoxon–Mann-Whitney test was used for the non-normally distributed data. The gray level, variance, and run length matrix were significantly lowered when the depth increased. The other texture parameters showed similar values at different depth. All the texture parameters showed no significant difference between depths A and B (p > 0.05) except for gray level, variance and run length matrix (p < 0.05). This indicates that gray level, variance, and run length matrix are depth dependent.

Keywords: ultrasound image, texture parameters, computational biology, biomedical engineering

Procedia PDF Downloads 275

Authors: Youcef Faci, Ahmed Mebtouche, Badredine Maalem

Abstract:

n the present work, an experimental study is carried out using acoustic emission and DIC techniques to analyze the damage of open hole woven composite carbon/epoxy under solicitations. Damage mechanisms were identified based on acoustic emission parameters such as amplitude, energy, and cumulative account. The findings of the AE measurement were successfully identified by digital image correlation (DIC) measurements. The evolution value of bolt angle inclination during tensile tests was studied and analyzed. Consequently, the relationship between the bolt inclination angles during tensile tests associated with failure modes of fastened joints of composite materials is determined. Moreover, there is an interaction between laminate pattern, laminate thickness, fastener size and type, surface strain concentrations, and out-of-plane displacement. Conclusions are supported by microscopic visualizations of the composite specimen.

Keywords: tensile test, damage, acoustic emission, digital image correlation

Procedia PDF Downloads 53

Authors: Ming-Hsiang Shih, Wen-Pei Sung, Shih-Heng Tung

Abstract:

The purposes of hydraulic gate are to maintain the functions of storing and draining water. It bears long-term hydraulic pressure and earthquake force and is very important for reservoir and waterpower plant. The high tensile strength of steel plate is used as constructional material of hydraulic gate. The cracks and rusts, induced by the defects of material, bad construction and seismic excitation and under water respectively, thus, the mechanics phenomena of gate with crack are probing into the cause of stress concentration, induced high crack increase rate, affect the safety and usage of hydroelectric power plant. Stress distribution analysis is a very important and essential surveying technique to analyze bi-material and singular point problems. The finite difference infinitely small element method has been demonstrated, suitable for analyzing the buckling phenomena of welding seam and steel plate with crack. Especially, this method can easily analyze the singularity of kink crack. Nevertheless, the construction form and deformation shape of some gates are three-dimensional system. Therefore, the three-dimensional Digital Image Correlation (DIC) has been developed and applied to analyze the strain variation of steel plate with crack at weld joint. The proposed Digital image correlation (DIC) technique is an only non-contact method for measuring the variation of test object. According to rapid development of digital camera, the cost of this digital image correlation technique has been reduced. Otherwise, this DIC method provides with the advantages of widely practical application of indoor test and field test without the restriction on the size of test object. Thus, the research purpose of this research is to develop and apply this technique to monitor mechanics crack variations of weld steel hydraulic gate and its conformation under action of loading. The imagines can be picked from real time monitoring process to analyze the strain change of each loading stage. The proposed 3-Dimensional digital image correlation method, developed in the study, is applied to analyze the post-buckling phenomenon and buckling tendency of welded steel plate with crack. Then, the stress intensity of 3-dimensional analysis of different materials and enhanced materials in steel plate has been analyzed in this paper. The test results show that this proposed three-dimensional DIC method can precisely detect the crack variation of welded steel plate under different loading stages. Especially, this proposed DIC method can detect and identify the crack position and the other flaws of the welded steel plate that the traditional test methods hardly detect these kind phenomena. Therefore, this proposed three-dimensional DIC method can apply to observe the mechanics phenomena of composite materials subjected to loading and operating.

Keywords: welded steel plate, crack variation, three-dimensional digital image correlation (DIC), crack stel plate

Procedia PDF Downloads 505

Authors: Shubham Gogri, Lucia Florescu

Abstract:

Medical diagnosis and radiotherapy treatment planning using Computed Tomography (CT) rely on the quantitative accuracy and quality of the CT images. At the same time, requirements for CT imaging include reducing the radiation dose exposure to patients and minimizing scanning time. A solution to this is the sparse-view CT technique, based on a reduced number of projection views. This, however, introduces a new problem— the incomplete projection data results in lower quality of the reconstructed images. To tackle this issue, deep learning methods have been applied to enhance the quality of the sparse-view CT images. A first approach involved employing Mir-Net, a dedicated deep neural network designed for image enhancement. This showed promise, utilizing an intricate architecture comprising encoder and decoder networks, along with the incorporation of the Charbonnier Loss. However, this approach was computationally demanding. Subsequently, a specialized Generative Adversarial Network (GAN) architecture, rooted in the Pix2Pix framework, was implemented. This GAN framework involves a U-Net-based Generator and a Discriminator based on Convolutional Neural Networks. To bolster the GAN's performance, both Charbonnier and Wasserstein loss functions were introduced, collectively focusing on capturing minute details while ensuring training stability. The integration of the perceptual loss, calculated based on feature vectors extracted from the VGG16 network pretrained on the ImageNet dataset, further enhanced the network's ability to synthesize relevant images. A series of comprehensive experiments with clinical CT data were conducted, exploring various GAN loss functions, including Wasserstein, Charbonnier, and perceptual loss. The outcomes demonstrated significant image quality improvements, confirmed through pertinent metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) between the corrected images and the ground truth. Furthermore, learning curves and qualitative comparisons added evidence of the enhanced image quality and the network's increased stability, while preserving pixel value intensity. The experiments underscored the potential of deep learning frameworks in enhancing the visual interpretation of CT scans, achieving outcomes with SSIM values close to one and PSNR values reaching up to 76.

Keywords: generative adversarial networks, sparse view computed tomography, CT image correction, Mir-Net

Procedia PDF Downloads 132

Authors: Hu Ding, Kai Liu, Guoan Tang

Abstract:

The Chinese Loess Plateau suffers from serious gully erosion induced by natural and human causes. Gully features detection including gully-affected area and its two dimension parameters (length, width, area et al.), is a significant task not only for researchers but also for policy-makers. This study aims at gully-affected area detection in three catchments of Chinese Loess Plateau, which were selected in Changwu, Ansai, and Suide by using unmanned aerial vehicle (UAV). The methodology includes a sequence of UAV data generation, image segmentation, feature calculation and selection, and random forest classification. Two experiments were conducted to investigate the influences of segmentation strategy and feature selection. Results showed that vertical and horizontal root-mean-square errors were below 0.5 and 0.2 m, respectively, which were ideal for the Loess Plateau region. The segmentation strategy adopted in this paper, which considers the topographic information, and optimal parameter combination can improve the segmentation results. Besides, the overall extraction accuracy in Changwu, Ansai, and Suide achieved was 84.62%, 86.46%, and 93.06%, respectively, which indicated that the proposed method for detecting gully-affected area is more objective and effective than traditional methods. This study demonstrated that UAV can bridge the gap between field measurement and satellite-based remote sensing, obtaining a balance in resolution and efficiency for catchment-scale gully erosion research.

Keywords: unmanned aerial vehicle (UAV), object-analysis image analysis, gully erosion, gully-affected area, Loess Plateau, random forest

Procedia PDF Downloads 201

Authors: Won Young Choi, Kwan Kyu Park

Abstract:

Recently, the road depression happening in the urban area is different from the cause of the sink hole and the generation mechanism occurring in the limestone area. The main cause of sinkholes occurring in the city center is the loss of soil due to the damage of old underground buried materials and groundwater discharge due to large underground excavation works. The method of detecting the sinkhole in the urban area is mostly using the Ground Penetration Radar (GPR). However, it is challenging to implement compact system and detecting watery state since it is based on electromagnetic waves. Although many ultrasonic underground detection studies have been conducted, near-ground detection (several tens of cm to several meters) has been developed for bulk systems using geophones as a receiver. The goal of this work is to fabricate a miniaturized sinkhole detecting system based on low-cost ultrasonic transducers of 40 kHz resonant frequency with high transmission pressure and receiving sensitivity. Motived by biomedical ultrasonic imaging methods, we detect air layers below the ground such as asphalt through the pulse-echo method. To improve image quality using multi-channel, linear array system is implemented, and image is acquired by classical synthetic aperture imaging method. We present the successful feasibility test of multi-channel sinkhole detector based on ultrasonic transducer. In this work, we presented and analyzed image results which are imaged by single channel pulse-echo imaging, synthetic aperture imaging.

Keywords: road depression, sinkhole, synthetic aperture imaging, ultrasonic transducer

Procedia PDF Downloads 131

Authors: Farina Riaz, Shahab Abdulla, Srinjoy Ganguly, Hajime Suzuki, Ravinesh C. Deo, Susan Hopkins

Abstract:

Recently, quantum machine learning has received significant attention. For various types of data, including text and images, numerous quantum machine learning (QML) models have been created and are being tested. Images are exceedingly complex data components that demand more processing power. Despite being mature, classical machine learning still has difficulties with big data applications. Furthermore, quantum technology has revolutionized how machine learning is thought of, by employing quantum features to address optimization issues. Since quantum hardware is currently extremely noisy, it is not practicable to run machine learning algorithms on it without risking the production of inaccurate results. To discover the advantages of quantum versus classical approaches, this research has concentrated on colored image data. Deep learning classification models are currently being created on Quantum platforms, but they are still in a very early stage. Black and white benchmark image datasets like MNIST and Fashion MINIST have been used in recent research. MNIST and CIFAR-10 were compared for binary classification, but the comparison showed that MNIST performed more accurately than colored CIFAR-10. This research will evaluate the performance of the QML algorithm on the colored benchmark dataset CIFAR-10 to advance QML's real-time applicability. However, deep learning classification models have not been developed to compare colored images like Quantum Convolutional Neural Network (QCNN) to determine how much it is better to classical. Only a few models, such as quantum variational circuits, take colored images. The methodology adopted in this research is a hybrid approach by using penny lane as a simulator. To process the 10 classes of CIFAR-10, the image data has been translated into grey scale and the 28 × 28-pixel image containing 10,000 test and 50,000 training images were used. The objective of this work is to determine how much the quantum approach can outperform a classical approach for a comprehensive dataset of color images. After pre-processing 50,000 images from a classical computer, the QCNN model adopted a hybrid method and encoded the images into a quantum simulator for feature extraction using quantum gate rotations. The measurements were carried out on the classical computer after the rotations were applied. According to the results, we note that the QCNN approach is ~12% more effective than the traditional classical CNN approaches and it is possible that applying data augmentation may increase the accuracy. This study has demonstrated that quantum machine and deep learning models can be relatively superior to the classical machine learning approaches in terms of their processing speed and accuracy when used to perform classification on colored classes.

Keywords: CIFAR-10, quantum convolutional neural networks, quantum deep learning, quantum machine learning

Procedia PDF Downloads 105

Authors: Saad Alkentar, Abdulkareem Assalem

Abstract:

Recognizing small targets has always posed a significant challenge in image analysis. Over long distances, the image signal-to-noise ratio tends to be low, limiting the amount of useful information available to detection systems. Consequently, visual target recognition becomes an intricate task to tackle. In this study, we introduce a Track Before Detect (TBD) approach that leverages target trajectory information (coordinates) to effectively distinguish between noise and potential targets. By reframing the problem as a multivariate time series classification, we have achieved remarkable results. Specifically, our TBD method achieves an impressive 97% accuracy in separating target signals from noise within a mere half-second time span (consisting of 10 data points). Furthermore, when classifying the identified targets into our predefined categories—airplane, drone, and bird—we achieve an outstanding classification accuracy of 96% over a more extended period of 1.5 seconds (comprising 30 data points).

Keywords: small targets, drones, trajectory information, TBD, multivariate time series

Procedia PDF Downloads 28

Authors: Malihe Aliasgari, Yousef Nejatbakhsh

Abstract:

The era of Big Data and the immensity of real-life datasets compels computation tasks to be performed in a distributed fashion, where the data is dispersed among many servers that operate in parallel. However, massive parallelization leads to computational bottlenecks due to faulty servers and stragglers. Stragglers refer to a few slow or delay-prone processors that can bottleneck the entire computation because one has to wait for all the parallel nodes to finish. The problem of straggling processors, has been well studied in the context of distributed computing. Recently, it has been pointed out that, for the important case of linear functions, it is possible to improve over repetition strategies in terms of the tradeoff between performance and latency by carrying out linear precoding of the data prior to processing. The key idea is that, by employing suitable linear codes operating over fractions of the original data, a function may be completed as soon as enough number of processors, depending on the minimum distance of the code, have completed their operations. The problem of matrix-matrix multiplication in the presence of practically big sized of data sets faced with computational and memory related difficulties, which makes such operations are carried out using distributed computing platforms. In this work, we study the problem of distributed matrix-matrix multiplication W = XY under storage constraints, i.e., when each server is allowed to store a fixed fraction of each of the matrices X and Y, which is a fundamental building of many science and engineering fields such as machine learning, image and signal processing, wireless communication, optimization. Non-secure and secure matrix multiplication are studied. We want to study the setup, in which the identity of the matrix of interest should be kept private from the workers and then obtain the recovery threshold of the colluding model, that is, the number of workers that need to complete their task before the master server can recover the product W. The problem of secure and private distributed matrix multiplication W = XY which the matrix X is confidential, while matrix Y is selected in a private manner from a library of public matrices. We present the best currently known trade-off between communication load and recovery threshold. On the other words, we design an achievable PSGPD scheme for any arbitrary privacy level by trivially concatenating a robust PIR scheme for arbitrary colluding workers and private databases and the proposed SGPD code that provides a smaller computational complexity at the workers.

Keywords: coded distributed computation, private information retrieval, secret sharing, stragglers

Procedia PDF Downloads 102

Authors: Kien Vu, Jien Min Soh, Mohamed Jahangir Abubacker, Piyawut Pattamanon, Soojin Lee, Suvro Banerjee

Abstract:

Recent advances in Generative Artificial Intelligence (GenAI), in particular Large Language Models (LLMs) have shown promise to disrupt multiple industries at scale. However, LLMs also present unique challenges, notably, these so-called "hallucination" which is the generation of outputs that are not grounded in the input data that hinders its adoption into production. Common practice to mitigate hallucination problem is utilizing Retrieval Agmented Generation (RAG) system to ground LLMs'response to ground truth. RAG converts the grounding documents into embeddings, retrieve the relevant parts with vector similarity between user's query and documents, then generates a response that is not only based on its pre-trained knowledge but also on the specific information from the retrieved documents. However, the RAG system is not suitable for tabular data and subsequent data analysis tasks due to multiple reasons such as information loss, data format, and retrieval mechanism. In this study, we have explored a novel methodology that combines planning-and-execution and code generation agents to enhance LLMs' data analysis capabilities. The approach enables LLMs to autonomously dissect a complex analytical task into simpler sub-tasks and requirements, then convert them into executable segments of code. In the final step, it generates the complete response from output of the executed code. When deployed beta version on DataSense, the property insight tool of PropertyGuru, the approach yielded promising results, as it was able to provide market insights and data visualization needs with high accuracy and extensive coverage by abstracting the complexities for real-estate agents and developers from non-programming background. In essence, the methodology not only refines the analytical process but also serves as a strategic tool for real estate professionals, aiding in market understanding and enhancement without the need for programming skills. The implication extends beyond immediate analytics, paving the way for a new era in the real estate industry characterized by efficiency and advanced data utilization.

Keywords: large language model, reasoning, planning and execution, code generation, natural language processing, prompt engineering, data analysis, real estate, data sense, PropertyGuru

Procedia PDF Downloads 56

Authors: Toufic Abd El-Latif Sadek

Abstract:

The asphalt object represents the asphalted areas like roads, and the concrete object represents the concrete areas like concrete buildings. The efficient extraction of asphalt and concrete objects from one satellite thermal image occurred at a specific time, by preventing the gaps in times which give the close and same brightness values between asphalt and concrete, and among other objects. So that to achieve efficient extraction and then better analysis. Seven sample objects were used un this study, asphalt, concrete, metal, rock, dry soil, vegetation, and water. It has been found that, the best timing for capturing satellite thermal images to extract the two objects asphalt and concrete from one satellite thermal image, saving time and money, occurred at a specific time in different months. A table is deduced shows the optimal timing for capturing satellite thermal images to extract effectively these two objects.

Keywords: asphalt, concrete, satellite thermal images, timing

Procedia PDF Downloads 301

Authors: Lise Paule Labéjof, Raíza Sales Pereira Bizerra, Galileu Barbosa Costa, Thaísa Barros dos Santos

Abstract:

Since the beginning of the microscopy, improving the image quality has always been a concern of its users. Especially for transmission electron microscopy (TEM), the problem is even more important due to the complexity of the sample preparation technique and the many variables that can affect the conservation of structures, proper operation of the equipment used and then the quality of the images obtained. Animal tissues being transparent it is necessary to apply a contrast agent in order to identify the elements of their ultrastructural morphology. Several methods of contrastation of tissues for TEM imaging have already been developed. The most used are the “in block” contrastation and “in situ” contrastation. This report presents an alternative technique of application of contrast agent in vivo, i.e. before sampling. By this new method the electromicrographies of the tissue sections have better contrast compared to that in situ and present no artefact of precipitation of contrast agent. Another advantage is that a small amount of contrast is needed to get a good result given that most of them are expensive and extremely toxic.

Keywords: image quality, microscopy research, staining technique, ultra thin section

Procedia PDF Downloads 415

Authors: Haji Ali Haji, Hussein Suleman, Ulrike Rivett

Abstract:

This paper presents the design, development and evaluation of an application prototype developed to support tuberculosis (TB) patients’ treatment adherence. The system makes use of graphics and voice reminders as opposed to text messaging to encourage patients to follow their medication routine. To evaluate the effect of the prototype applications, participants were given mobile phones on which the reminder system was installed. Thirty-eight people, including TB health workers and patients from Zanzibar, Tanzania, participated in the evaluation exercises. The results indicate that the participants found the mobile graphic-based application is useful to support TB treatment. All participants understood and interpreted the intended meaning of every image correctly. The study findings revealed that the use of a mobile visual-based application may have potential benefit to support TB patients (both literate and illiterate) in their treatment processes.

Keywords: ICT4D, mobile technology, tuberculosis, visual-based reminder

Procedia PDF Downloads 417

Authors: Ahmedou Moulaye Idriss, Tfeil Yahya, Tamas Ungi, Gabor Fichtinger

Abstract:

Image-guided therapy (IGT) plays a crucial role in minimally invasive procedures for liver interventions. Accurate segmentation of the liver and precise needle placement is essential for successful interventions such as needle aspiration. In this study, we propose a deep learning-based liver 3D slicer designed to enhance segmentation accuracy and facilitate needle aspiration procedures. The developed 3D slicer leverages state-of-the-art convolutional neural networks (CNNs) for automatic liver segmentation in medical images. The CNN model is trained on a diverse dataset of liver images obtained from various imaging modalities, including computed tomography (CT) and magnetic resonance imaging (MRI). The trained model demonstrates robust performance in accurately delineating liver boundaries, even in cases with anatomical variations and pathological conditions. Furthermore, the 3D slicer integrates advanced image registration techniques to ensure accurate alignment of preoperative images with real-time interventional imaging. This alignment enhances the precision of needle placement during aspiration procedures, minimizing the risk of complications and improving overall intervention outcomes. To validate the efficacy of the proposed deep learning-based 3D slicer, a comprehensive evaluation is conducted using a dataset of clinical cases. Quantitative metrics, including the Dice similarity coefficient and Hausdorff distance, are employed to assess the accuracy of liver segmentation. Additionally, the performance of the 3D slicer in guiding needle aspiration procedures is evaluated through simulated and clinical interventions. Preliminary results demonstrate the effectiveness of the developed 3D slicer in achieving accurate liver segmentation and guiding needle aspiration procedures with high precision. The integration of deep learning techniques into the IGT workflow shows great promise for enhancing the efficiency and safety of liver interventions, ultimately contributing to improved patient outcomes.

Keywords: deep learning, liver segmentation, 3D slicer, image guided therapy, needle aspiration

Procedia PDF Downloads 27

Authors: Francis Zerd, Brian E. Moore, Atuganile E. Malango, Patrick W. Hosokawa, Kevin O. Lillehei, Laurence Lemery Mchome, D. Ryan Ormond

Abstract:

Introduction: Since neuropathologic diagnosis in the developing world is hampered by limitations in technical infrastructure, trained laboratory personnel, and subspecialty-trained pathologists, the use of telepathology for diagnostic support, second-opinion consultations, and ongoing training holds promise as a means of addressing these challenges. This research aims to assess the utility of static teleneuropathology in improving neuropathologic diagnoses in low- and middle-income countries. Methods: Consecutive neurosurgical biopsy and resection specimens obtained at Muhimbili National Hospital in Tanzania between July 1, 2018, and June 30, 2019, were selected for retrospective, blinded static-image neuropathologic review followed by on-site review by an expert neuropathologist. Results: A total of 75 neuropathologic cases were reviewed. The agreement of static images and on-site glass diagnosis was 71% with strict criteria and 88% with less stringent criteria. This represents an overall improvement in diagnostic accuracy from 36% by general pathologists to 71% by a neuropathologist using static telepathology (or 76% to 88% with less stringent criteria). Conclusions: Telepathology offers a suitable means of providing diagnostic support, second-opinion consultations, and ongoing training to pathologists practicing in resource-limited countries. Moreover, static digital teleneuropathology is an uncomplicated, cost-effective, and reliable way to achieve these goals.

Keywords: neuropathology, resource-limited settings, static image, Tanzania, teleneuropathology

Procedia PDF Downloads 90

Authors: Angela Bargenda, Erhard Lick, Dhoha Trabelsi

Abstract:

Research in retailing has identified the importance of atmospherics as an essential element in enhancing store image, store patronage intentions, and the overall shopping experience in a retail environment. However, in the area of atmospherics, store window design, which represents an essential component of external store atmospherics, remains a vastly underrepresented phenomenon in extant scholarship. This paper seeks to fill this gap by exploring the relevance of store window design as an atmospheric tool. In particular, empirical evidence of theme-based theatrical store front windows, which put emphasis on the use of verbo-visual design elements, was found in Paris and New York. The purpose of this study was to identify to what extent such multimodal window designs of high-end department stores in metropolitan cities have an impact on store entry decisions and attitudes towards the retailer’s image. As theoretical construct, the linguistic concept of multimodality and Mehrabian’s and Russell’s model in environmental psychology were applied. To answer the research question, two studies were conducted. For Study 1 a case study approach was selected to define three different types of store window designs based on different types of visual-verbal relations. Each of these types of store window design represented a different level of cognitive elaboration required for the decoding process. Study 2 consisted of an on-line survey carried out among more than 300 respondents to examine the influence of these three types of store window design on the consumer behavioral variables mentioned above. The results of this study show that the higher the cognitive elaboration needed to decode the message of the store window, the lower the store entry propensity. In contrast, the higher the cognitive elaboration, the higher the perceived image of the retailer’s image. One important conclusion is that in order to increase consumers’ propensity to enter stores with theme-based theatrical store front windows, retailers need to limit the cognitive elaboration required to decode their verbo-visual window design.

Keywords: consumer behavior, multimodality, store atmospherics, store window design

Procedia PDF Downloads 176

Authors: Sergey Ermolin, Olga Ermolin

Abstract:

A Deep Convolution Neural Network with Triplet Loss is used to identify duplicate images in real-estate advertisements in the presence of image artifacts such as watermarking, cropping, hue/brightness adjustment, and others. The effects of batch normalization, spatial dropout, and various convergence methodologies on the resulting detection accuracy are discussed. For comparative Return-on-Investment study (per industry request), end-2-end performance is benchmarked on both Nvidia Titan GPUs and Intel’s Xeon CPUs. A new real-estate dataset from San Francisco Bay Area is used for this work. Sufficient duplicate detection accuracy is achieved to supplement other database-grounded methods of duplicate removal. The implemented method is used in a Proof-of-Concept project in the real-estate industry.

Keywords: visual recognition, convolutional neural networks, triplet loss, spatial batch normalization with dropout, duplicate removal, advertisement technologies, performance benchmarking

Procedia PDF Downloads 320

Authors: Hamza A. A. Al-Sewadi, Adnan H. M. Al-Helali, Samaa A. K. Khamis

Abstract:

Ownership proofs of multimedia such as text, image, audio or video files can be achieved by the burial of watermark is them. It is achieved by introducing modifications into these files that are imperceptible to the human senses but easily recoverable by a computer program. These modifications would be in the time domain or frequency domain or both. This paper presents a procedure for watermarking by mixing amplitude modulation with frequency transformation histogram; namely a specific value is used to modulate the intensity component Y of the YIQ components of the carrier image. This scheme is referred to as histogram embedding technique (HET). Results comparison with those of other techniques such as discrete wavelet transform (DWT), discrete cosine transform (DCT) and singular value decomposition (SVD) have shown an enhance efficiency in terms of ease and performance. It has manifested a good degree of robustness against various environment effects such as resizing, rotation and different kinds of noise. This method would prove very useful technique for copyright protection and ownership judgment.

Keywords: authentication, copyright protection, information hiding, ownership, watermarking

Procedia PDF Downloads 546

Authors: Iman Iraei, Mina Sharifi

Abstract:

A method for object tracking in motion blurred images is proposed in this article. This paper shows that object tracking could be improved with this approach. We use mean shift algorithm to track different objects as a main tracker. But, the problem is that mean shift could not track the selected object accurately in blurred scenes. So, for better tracking result, and increasing the accuracy of tracking, wavelet transform is used. We use a feature named as blur extent, which could help us to get better results in tracking. For calculating of this feature, we should use Harr wavelet. We can look at this matter from two different angles which lead to determine whether an image is blurred or not and to what extent an image is blur. In fact, this feature left an impact on the covariance matrix of mean shift algorithm and cause to better performance of tracking. This method has been concentrated mostly on motion blur parameter. transform. The results reveal the ability of our method in order to reach more accurately tracking.

Keywords: mean shift, object tracking, blur extent, wavelet transform, motion blur

Procedia PDF Downloads 195

Authors: Marcos Bosques-Perez, Walter Izquierdo, Harold Martin, Liangdon Deng, Josue Rodriguez, Thony Yan, Mercedes Cabrerizo, Armando Barreto, Naphtali Rishe, Malek Adjouadi

Abstract:

Aerial imagery is a powerful tool when it comes to analyzing temporal changes in ecosystems and extracting valuable information from the observed scene. It allows us to identify and assess various elements such as objects, structures, textures, waterways, and shadows. To extract meaningful information, multispectral cameras capture data across different wavelength bands of the electromagnetic spectrum. In this study, the collected multispectral aerial images were subjected to principal component analysis (PCA) to identify independent and uncorrelated components or features that extend beyond the visible spectrum captured in standard RGB images. The results demonstrate that these principal components contain unique characteristics specific to certain wavebands, enabling effective object identification and image segmentation.

Keywords: big data, image processing, multispectral, principal component analysis

Procedia PDF Downloads 149

Authors: Mahdi Bazarganigilani

Abstract:

Aortic enlargement, also known as an aortic aneurysm, can occur when the walls of the aorta become weak. This disease can become deadly if overlooked and undiagnosed. In this paper, a computer-aided diagnosis (CAD) system was introduced to accurately diagnose aortic enlargement from chest x-ray images. An enhanced convolutional neural network (CNN) was employed and then trained by transfer learning by using three different main areas from the original images. The areas included the left lung, heart, and right lung. The accuracy of the system was then evaluated on 1001 samples by using 4-fold cross-validation. A promising accuracy of 90% was achieved in terms of the F-measure indicator. The results showed using different areas from the original image in the training phase of CNN could increase the accuracy of predictions. This encouraged the author to evaluate this method on a larger dataset and even on different CAD systems for further enhancement of this methodology.

Keywords: computer-aided diagnosis systems, aortic enlargement, chest X-ray, image processing, convolutional neural networks

Procedia PDF Downloads 139

Authors: Jeff Colwell, Benjamin Knox

Abstract:

While fire and explosion incidents are often observed by eyewitnesses, the weight that fire investigators should place on those observations in their investigations is a complex issue. There is no doubt that eyewitness statements can be an important component to an investigation, particularly when other evidence is sparse, as is often the case when damage to the scene is severe. However, it is well known that eyewitness statements can be incorrect for a variety of reasons, including deception. In this paper, we reviewed factors that can have an effect on the complex processes associated with the perception, retention, and retrieval of an event. We then review the accuracy of eyewitness statements from unique criminal and civil incidents, including fire and explosion incidents, in which the accuracy of the statements could be independently evaluated. Finally, the motives for deceptive eyewitness statements are described, along with techniques that fire and explosion investigators can employ, to increase the accuracy of the eyewitness statements that they solicit.

Keywords: fire, explosion, eyewitness, reliability

Procedia PDF Downloads 359

Authors: Daianne Fernandes Diogenes

Abstract:

Railway ballast aggregates’ shape properties and size distribution can be directly affected by several factors, such as traffic, fouling, and maintenance processes, which cause breakage and wearing, leading to the fine particles’ accumulation through the ballast layer. This research aims to analyze the influence of traffic, tamping process, and sleepers’ stiffness on aggregates' shape and mechanical properties, by using traditional and digital image processing (DIP) techniques and cyclic tests, like resilient modulus (RM) and permanent deformation (PD). Aggregates were collected in different phases of the railway service life: (i) right after the crushing process; (ii) after construction, for the aggregates positioned below the sleepers and (iii) after 5 years of operation. An increase in the percentage of cubic particles was observed for the materials (ii) and (iii), providing a better interlocking, increasing stiffness and reducing axial deformation after 5 years of service, when compared to the initial conditions.

Keywords: digital image processing, mechanical behavior, railway ballast, shape properties

Procedia PDF Downloads 107

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on HSI dataset Indian Pines. The results confirm the capability of the proposed method.

Keywords: continual learning, data reconstruction, remote sensing, hyperspectral image segmentation

Procedia PDF Downloads 230

Authors: Maria Kountouridou, Dino Domic

Abstract:

Within an increasingly competitive and dynamic environment, the higher education sector is becoming more commodified, with the concept of branding to become exceedingly imperative and an inextricable ingredient for the university’s success. Branding in higher education has proven to be an effective strategy that managed to receive considerable attention in the recent few years, and a growing number of articles have begun to appear in the literature. However, a clear void in the literature confirms that the concept of students’ perceptions towards the university’s brand image has not been researched extensively. An investigation on this central concept is of paramount importance since it will facilitate the development of an inductively generated theoretical model concerning branding in higher education. This research focuses on examining the impact of the ‘positive-visualization-course in brand identity’ upon the perception of freshmen students towards a university’s brand image. A grounded theory methodology has been selected, consisting of semi-structured interviews. Forty-two students have participated in the research, among which twenty-five women and seventeen men. The identification of the sample emerged through the use of the snowball sampling technique. The participants were divided into two groups (experimental and control group) after the researcher had taken into consideration the factor ‘program of study’, to eliminate any possible interaction between the participants of each group. An experiment was carried out where a ‘positive-visualization-course in brand identity’ was conducted among the participants of the experimental group, while the participants of the control group have not been exposed to the course. For the purpose of this research, the term ‘positive-visualization-course in brand identity’ refers to a course where brand history, past achievements/recognitions/awards, its values, and its mission are presented. Prior to the course implementation, face-to-face semi-structured interviews were carried out among the participants of both groups, with the aim of examining the freshmen students’ perceptions towards the university’s brand image. One week after the course implementation, the researcher carried out semi-structured interviews with the participants of the experimental group only in order to identify whether students’ perceptions had been affected after the course completion. Four months after the course completion, semi-structured interviews were carried out among the participants of both groups. Eight months after the course completion, semi-structured interviews were conducted with the aim of identifying the freshmen students’ updated perceptions. Data has been analyzed using substantive coding (open and selective coding), theoretical coding, field memos, and constant comparative analysis. The findings strongly suggest that the ‘positive-visualization-course in brand identity’ can positively affect freshmen students’ perceptions towards a university’s brand image. Additionally, other factors conduce to the formation of perception throughout the months. This study contributes and expands upon the existing literature by presenting an inductively generated theoretical model to guide future research in the links between ‘positive-visualization-course in brand identity’ and the perception of freshmen students towards a university’s brand image.

Keywords: brand image, brand name, branding, higher education marketing, perception

Procedia PDF Downloads 162

Authors: Hamza A. Ali, Adnan H. M. Al-Helali

Abstract:

Generally, a watermark is information that identifies the ownership of multimedia (text, image, audio or video files). It is achieved by introducing modifications into these files that are imperceptible to the human senses but easily recoverable by a computer program. These modifications are done according to a secret key in a descriptive model that would be either in the time domain or frequency domain or both. This paper presents a procedure for watermarking by mixing amplitude modulation with frequency transformation histogram; namely a specific value is used to modulate the intensity component Y of the YIQ components of the carrier image. This scheme is referred to as histogram embedding technique (HET). Results comparison with those of other techniques such as discrete wavelet transform (DWT), discrete cosine transform (DCT) and singular value decomposition (SVD) have shown an enhance efficiency in terms of ease and performance. It has manifested a good degree of robustness against various environment effects such as resizing, rotation and different kinds of noise. This method would prove very useful technique for copyright protection and ownership judgment.

Keywords: watermarking, ownership, copyright protection, steganography, information hiding, authentication

Procedia PDF Downloads 355