Search results for: ultrasound images.
2100 DenseNet and Autoencoder Architecture for COVID-19 Chest X-Ray Image Classification and Improved U-Net Lung X-Ray Segmentation
Authors: Jonathan Gong
Abstract:
Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.Keywords: artificial intelligence, convolutional neural networks, deep learning, image processing, machine learning
Procedia PDF Downloads 1212099 Seashore Debris Detection System Using Deep Learning and Histogram of Gradients-Extractor Based Instance Segmentation Model
Authors: Anshika Kankane, Dongshik Kang
Abstract:
Marine debris has a significant influence on coastal environments, damaging biodiversity, and causing loss and damage to marine and ocean sector. A functional cost-effective and automatic approach has been used to look up at this problem. Computer vision combined with a deep learning-based model is being proposed to identify and categorize marine debris of seven kinds on different beach locations of Japan. This research compares state-of-the-art deep learning models with a suggested model architecture that is utilized as a feature extractor for debris categorization. The model is being proposed to detect seven categories of litter using a manually constructed debris dataset, with the help of Mask R-CNN for instance segmentation and a shape matching network called HOGShape, which can then be cleaned on time by clean-up organizations using warning notifications of the system. The manually constructed dataset for this system is created by annotating the images taken by fixed KaKaXi camera using CVAT annotation tool with seven kinds of category labels. A pre-trained HOG feature extractor on LIBSVM is being used along with multiple templates matching on HOG maps of images and HOG maps of templates to improve the predicted masked images obtained via Mask R-CNN training. This system intends to timely alert the cleanup organizations with the warning notifications using live recorded beach debris data. The suggested network results in the improvement of misclassified debris masks of debris objects with different illuminations, shapes, viewpoints and litter with occlusions which have vague visibility.Keywords: computer vision, debris, deep learning, fixed live camera images, histogram of gradients feature extractor, instance segmentation, manually annotated dataset, multiple template matching
Procedia PDF Downloads 952098 Multi-Scaled Non-Local Means Filter for Medical Images Denoising: Empirical Mode Decomposition vs. Wavelet Transform
Authors: Hana Rabbouch
Abstract:
In recent years, there has been considerable growth of denoising techniques mainly devoted to medical imaging. This important evolution is not only due to the progress of computing techniques, but also to the emergence of multi-resolution analysis (MRA) on both mathematical and algorithmic bases. In this paper, a comparative study is conducted between the two best-known MRA-based decomposition techniques: the Empirical Mode Decomposition (EMD) and the Discrete Wavelet Transform (DWT). The comparison is carried out in a framework of multi-scale denoising, where a Non-Local Means (NLM) filter is performed scale-by-scale to a sample of benchmark medical images. The results prove the effectiveness of the multiscaled denoising, especially when the NLM filtering is coupled with the EMD.Keywords: medical imaging, non local means, denoising, multiscaled analysis, empirical mode decomposition, wavelets
Procedia PDF Downloads 1312097 Review on Quaternion Gradient Operator with Marginal and Vector Approaches for Colour Edge Detection
Authors: Nadia Ben Youssef, Aicha Bouzid
Abstract:
Gradient estimation is one of the most fundamental tasks in the field of image processing in general, and more particularly for color images since that the research in color image gradient remains limited. The widely used gradient method is Di Zenzo’s gradient operator, which is based on the measure of squared local contrast of color images. The proposed gradient mechanism, presented in this paper, is based on the principle of the Di Zenzo’s approach using quaternion representation. This edge detector is compared to a marginal approach based on multiscale product of wavelet transform and another vector approach based on quaternion convolution and vector gradient approach. The experimental results indicate that the proposed color gradient operator outperforms marginal approach, however, it is less efficient then the second vector approach.Keywords: gradient, edge detection, color image, quaternion
Procedia PDF Downloads 2242096 Deep Learning-Based Object Detection on Low Quality Images: A Case Study of Real-Time Traffic Monitoring
Authors: Jean-Francois Rajotte, Martin Sotir, Frank Gouineau
Abstract:
The installation and management of traffic monitoring devices can be costly from both a financial and resource point of view. It is therefore important to take advantage of in-place infrastructures to extract the most information. Here we show how low-quality urban road traffic images from cameras already available in many cities (such as Montreal, Vancouver, and Toronto) can be used to estimate traffic flow. To this end, we use a pre-trained neural network, developed for object detection, to count vehicles within images. We then compare the results with human annotations gathered through crowdsourcing campaigns. We use this comparison to assess performance and calibrate the neural network annotations. As a use case, we consider six months of continuous monitoring over hundreds of cameras installed in the city of Montreal. We compare the results with city-provided manual traffic counting performed in similar conditions at the same location. The good performance of our system allows us to consider applications which can monitor the traffic conditions in near real-time, making the counting usable for traffic-related services. Furthermore, the resulting annotations pave the way for building a historical vehicle counting dataset to be used for analysing the impact of road traffic on many city-related issues, such as urban planning, security, and pollution.Keywords: traffic monitoring, deep learning, image annotation, vehicles, roads, artificial intelligence, real-time systems
Procedia PDF Downloads 1852095 Autophagy Suppresses Bladder Tumor Formation in a Mouse Orthotopic Bladder Tumor Formation Model
Authors: Wan-Ting Kuo, Yi-Wen Liu, Hsiao-Sheng Liu
Abstract:
Annual incidence of bladder cancer increases in the world and occurs frequently in the male. Most common type is transitional cell carcinoma (TCC) which is treated by transurethral resection followed by intravesical administration of agents. In clinical treatment of bladder cancer, chemotherapeutic drugs-induced apoptosis is always used in patients. However, cancers usually develop resistance to chemotherapeutic drugs and often lead to aggressive tumors with worse clinical outcomes. Approximate 70% TCC recurs and 30% recurrent tumors progress to high-grade invasive tumors, indicating that new therapeutic agents are urgently needed to improve the successful rate of overall treatment. Nonapoptotic program cell death may assist to overcome worse clinical outcomes. Autophagy which is one of the nonapoptotic pathways provides another option for bladder cancer patients. Autophagy is reported as a potent anticancer therapy in some cancers. First of all, we established a mouse orthotopic bladder tumor formation model in order to create a similar tumor microenvironment. IVIS system and micro-ultrasound were utilized to noninvasively monitor tumor formation. In addition, we carried out intravesical treatment in our animal model to be consistent with human clinical treatment. In our study, we carried out intravesical instillation of the autophagy inducer in mouse orthotopic bladder tumor to observe tumor formation by noninvasive IVIS system and micro-ultrasound. Our results showed that bladder tumor formation is suppressed by the autophagy inducer, and there are no significant side effects in the physiology of mice. Furthermore, the autophagy inducer upregulated autophagy in bladder tissues of the treated mice was confirmed by Western blot, immunohistochemistry, and immunofluorescence. In conclusion, we reveal that a novel autophagy inducer with low side effects suppresses bladder tumor formation in our mouse orthotopic bladder tumor model, and it provides another therapeutic approach in bladder cancer patients.Keywords: bladder cancer, transitional cell carcinoma, orthotopic bladder tumor formation model, autophagy
Procedia PDF Downloads 1682094 Sub-Pixel Mapping Based on New Mixed Interpolation
Authors: Zeyu Zhou, Xiaojun Bi
Abstract:
Due to the limited environmental parameters and the limited resolution of the sensor, the universal existence of the mixed pixels in the process of remote sensing images restricts the spatial resolution of the remote sensing images. Sub-pixel mapping technology can effectively improve the spatial resolution. As the bilinear interpolation algorithm inevitably produces the edge blur effect, which leads to the inaccurate sub-pixel mapping results. In order to avoid the edge blur effect that affects the sub-pixel mapping results in the interpolation process, this paper presents a new edge-directed interpolation algorithm which uses the covariance adaptive interpolation algorithm on the edge of the low-resolution image and uses bilinear interpolation algorithm in the low-resolution image smooth area. By using the edge-directed interpolation algorithm, the super-resolution of the image with low resolution is obtained, and we get the percentage of each sub-pixel under a certain type of high-resolution image. Then we rely on the probability value as a soft attribute estimate and carry out sub-pixel scale under the ‘hard classification’. Finally, we get the result of sub-pixel mapping. Through the experiment, we compare the algorithm and the bilinear algorithm given in this paper to the results of the sub-pixel mapping method. It is found that the sub-pixel mapping method based on the edge-directed interpolation algorithm has better edge effect and higher mapping accuracy. The results of the paper meet our original intention of the question. At the same time, the method does not require iterative computation and training of samples, making it easier to implement.Keywords: remote sensing images, sub-pixel mapping, bilinear interpolation, edge-directed interpolation
Procedia PDF Downloads 2162093 The UAV Feasibility Trajectory Prediction Using Convolution Neural Networks
Authors: Adrien Marque, Daniel Delahaye, Pierre Maréchal, Isabelle Berry
Abstract:
Wind direction and uncertainty are crucial in aircraft or unmanned aerial vehicle trajectories. By computing wind covariance matrices on each spatial grid point, these spatial grids can be defined as images with symmetric positive definite matrix elements. A data pre-processing step, a specific convolution, a specific max-pooling, and a specific flatten layers are implemented to process such images. Then, the neural network is applied to spatial grids, whose elements are wind covariance matrices, to solve classification problems related to the feasibility of unmanned aerial vehicles based on wind direction and wind uncertainty.Keywords: wind direction, uncertainty level, unmanned aerial vehicle, convolution neural network, SPD matrices
Procedia PDF Downloads 182092 Sonication as a Versatile Tool for Photocatalysts’ Synthesis and Intensification of Flow Photocatalytic Processes Within the Lignocellulose Valorization Concept
Authors: J. C. Colmenares, M. Paszkiewicz-Gawron, D. Lomot, S. R. Pradhan, A. Qayyum
Abstract:
This work is a report of recent selected experiments of photocatalysis intensification using flow microphotoreactors (fabricated by an ultrasound-based technique) for photocatalytic selective oxidation of benzyl alcohol (BnOH) to benzaldehyde (PhCHO) (in the frame of the concept of lignin valorization), and the proof of concept of intensifying a flow selective photocatalytic oxidation process by acoustic cavitation. The synthesized photocatalysts were characterized by using different techniques such as UV-Vis diffuse reflectance spectroscopy, X-ray diffraction, nitrogen sorption, thermal gravimetric analysis, and transmission electron microscopy. More specifically, the work will be on: a Design and development of metal-containing TiO₂ coated microflow reactor for photocatalytic partial oxidation of benzyl alcohol: The current work introduces an efficient ultrasound-based metal (Fe, Cu, Co)-containing TiO₂ deposition on the inner walls of a perfluoroalkoxy alkanes (PFA) microtube under mild conditions. The experiments were carried out using commercial TiO₂ and sol-gel synthesized TiO₂. The rough surface formed during sonication is the site for the deposition of these nanoparticles in the inner walls of the microtube. The photocatalytic activities of these semiconductor coated fluoropolymer based microreactors were evaluated for the selective oxidation of BnOH to PhCHO in the liquid flow phase. The analysis of the results showed that various features/parameters are crucial, and by tuning them, it is feasible to improve the conversion of benzyl alcohol and benzaldehyde selectivity. Among all the metal-containing TiO₂ samples, the 0.5 at% Fe/TiO₂ (both, iron and titanium, as cheap, safe, and abundant metals) photocatalyst exhibited the highest BnOH conversion under visible light (515 nm) in a microflow system. This could be explained by the higher crystallite size, high porosity, and flake-like morphology. b. Designing/fabricating photocatalysts by a sonochemical approach and testing them in the appropriate flow sonophotoreactor towards sustainable selective oxidation of key organic model compounds of lignin: Ultrasonication (US)-assitedprecipitaion and US-assitedhydrosolvothermal methods were used for the synthesis of metal-oxide-based and metal-free-carbon-based photocatalysts, respectively. Additionally, we report selected experiments of intensification of a flow photocatalytic selective oxidation through the use of ultrasonic waves. The effort of our research is focused on the utilization of flow sonophotocatalysis for the selective transformation of lignin-based model molecules by nanostructured metal oxides (e.g., TiO₂), and metal-free carbocatalysts. A plethora of parameters that affects the acoustic cavitation phenomena, and as a result the potential of sonication were investigated (e.g. ultrasound frequency and power). Various important photocatalytic parameters such as the wavelength and intensity of the irradiated light, photocatalyst loading, type of solvent, mixture of solvents, and solution pH were also optimized.Keywords: heterogeneous photo-catalysis, metal-free carbonaceous materials, selective redox flow sonophotocatalysis, titanium dioxide
Procedia PDF Downloads 902091 Sonocatalytic Treatment of Baker’s Yeast Wastewater by Using SnO2/TiO2 Composite
Authors: Didem Ildırar, Serap Fındık
Abstract:
Baker’s yeast industry uses molasses as a raw material. Molasses wastewater contains high molecular weight polymers called melanoidins. Melanoidins are obtained after the reactions between the amino acids and carbonyl groups in molasses. The molasses wastewater has high biochemical and chemical oxygen demand and dark brown color. If it is discharged to receiving bodies without any treatment, it prevents light penetration and dissolved oxygen level of the surface water decreases. Melanoidin compounds are toxic effect to the microorganism in water and there is a resistance to microbial degradation. Before discharging molasses wastewater, adequate treatment is necessary. In addition to changing environmental regulations, properties of treated wastewater must be improved. Advanced oxidation processes can be used to improve existing properties of wastewater. Sonochemical oxidation is one of the alternative methods. Sonochemical oxidation employs the use of ultrasound resulting in cavitation phenomena. In this study, decolorization and chemical oxygen demand removal (COD) of baker’s yeast effluent was investigated by using ultrasound. Baker’s yeast effluent was supplied from a factory which is located in the north of Turkey. An ultrasonic homogenizator was used for this study. Its operating frequency is 20kHz. SnO2/TiO2 catalyst has been used as sonocatalyst. The effects of the composite preparation method, mixing time while composite prepared, the molar ratio of SnO2/TiO2, the calcination temperature, and time, the catalyst amount were investigated on the treatment of baker’s yeast effluent. . According to the results, the prepared composite SnO2/TiO2 by using ultrasonic probe gave a better result than prepared composite by using an ultrasonic bath. Prepared composite by using an ultrasonic probe with a 4:1 molar ratio treated at 800°C for 60min gave a better result. By using this composite, optimum catalyst amount was 0.2g/l. At these conditions 26.6% decolorization was obtained. There was no COD removal at the studied conditions.Keywords: baker’s yeast effluent, COD, decolorization, sonocatalyst, ultrasonic irradiation
Procedia PDF Downloads 3152090 Training a Neural Network to Segment, Detect and Recognize Numbers
Authors: Abhisek Dash
Abstract:
This study had three neural networks, one for number segmentation, one for number detection and one for number recognition all of which are coupled to one another. All networks were trained on the MNIST dataset and were convolutional. It was assumed that the images had lighter background and darker foreground. The segmentation network took 28x28 images as input and had sixteen outputs. Segmentation training starts when a dark pixel is encountered. Taking a window(7x7) over that pixel as focus, the eight neighborhood of the focus was checked for further dark pixels. The segmentation network was then trained to move in those directions which had dark pixels. To this end the segmentation network had 16 outputs. They were arranged as “go east”, ”don’t go east ”, “go south east”, “don’t go south east”, “go south”, “don’t go south” and so on w.r.t focus window. The focus window was resized into a 28x28 image and the network was trained to consider those neighborhoods which had dark pixels. The neighborhoods which had dark pixels were pushed into a queue in a particular order. The neighborhoods were then popped one at a time stitched to the existing partial image of the number one at a time and trained on which neighborhoods to consider when the new partial image was presented. The above process was repeated until the image was fully covered by the 7x7 neighborhoods and there were no more uncovered black pixels. During testing the network scans and looks for the first dark pixel. From here on the network predicts which neighborhoods to consider and segments the image. After this step the group of neighborhoods are passed into the detection network. The detection network took 28x28 images as input and had two outputs denoting whether a number was detected or not. Since the ground truth of the bounds of a number was known during training the detection network outputted in favor of number not found until the bounds were not met and vice versa. The recognition network was a standard CNN that also took 28x28 images and had 10 outputs for recognition of numbers from 0 to 9. This network was activated only when the detection network votes in favor of number detected. The above methodology could segment connected and overlapping numbers. Additionally the recognition unit was only invoked when a number was detected which minimized false positives. It also eliminated the need for rules of thumb as segmentation is learned. The strategy can also be extended to other characters as well.Keywords: convolutional neural networks, OCR, text detection, text segmentation
Procedia PDF Downloads 1472089 Color Image Enhancement Using Multiscale Retinex and Image Fusion Techniques
Authors: Chang-Hsing Lee, Cheng-Chang Lien, Chin-Chuan Han
Abstract:
In this paper, an edge-strength guided multiscale retinex (EGMSR) approach will be proposed for color image contrast enhancement. In EGMSR, the pixel-dependent weight associated with each pixel in the single scale retinex output image is computed according to the edge strength around this pixel in order to prevent from over-enhancing the noises contained in the smooth dark/bright regions. Further, by fusing together the enhanced results of EGMSR and adaptive multiscale retinex (AMSR), we can get a natural fused image having high contrast and proper tonal rendition. Experimental results on several low-contrast images have shown that our proposed approach can produce natural and appealing enhanced images.Keywords: image enhancement, multiscale retinex, image fusion, EGMSR
Procedia PDF Downloads 4492088 A Convolutional Neural Network-Based Model for Lassa fever Virus Prediction Using Patient Blood Smear Image
Authors: A. M. John-Otumu, M. M. Rahman, M. C. Onuoha, E. P. Ojonugwa
Abstract:
A Convolutional Neural Network (CNN) model for predicting Lassa fever was built using Python 3.8.0 programming language, alongside Keras 2.2.4 and TensorFlow 2.6.1 libraries as the development environment in order to reduce the current high risk of Lassa fever in West Africa, particularly in Nigeria. The study was prompted by some major flaws in existing conventional laboratory equipment for diagnosing Lassa fever (RT-PCR), as well as flaws in AI-based techniques that have been used for probing and prognosis of Lassa fever based on literature. There were 15,679 blood smear microscopic image datasets collected in total. The proposed model was trained on 70% of the dataset and tested on 30% of the microscopic images in avoid overfitting. A 3x3x3 convolution filter was also used in the proposed system to extract features from microscopic images. The proposed CNN-based model had a recall value of 96%, a precision value of 93%, an F1 score of 95%, and an accuracy of 94% in predicting and accurately classifying the images into clean or infected samples. Based on empirical evidence from the results of the literature consulted, the proposed model outperformed other existing AI-based techniques evaluated. If properly deployed, the model will assist physicians, medical laboratory scientists, and patients in making accurate diagnoses for Lassa fever cases, allowing the mortality rate due to the Lassa fever virus to be reduced through sound decision-making.Keywords: artificial intelligence, ANN, blood smear, CNN, deep learning, Lassa fever
Procedia PDF Downloads 1042087 Assessment of the Performance of the Sonoreactors Operated at Different Ultrasound Frequencies, to Remove Pollutants from Aqueous Media
Authors: Gabriela Rivadeneyra-Romero, Claudia del C. Gutierrez Torres, Sergio A. Martinez-Delgadillo, Victor X. Mendoza-Escamilla, Alejandro Alonzo-Garcia
Abstract:
Ultrasonic degradation is currently being used in sonochemical reactors to degrade pollutant compounds from aqueous media, as emerging contaminants (e.g. pharmaceuticals, drugs and personal care products.) because they can produce possible ecological impacts on the environment. For this reason, it is important to develop appropriate water and wastewater treatments able to reduce pollution and increase reuse. Pollutants such as textile dyes, aromatic and phenolic compounds, cholorobenzene, bisphenol-A and carboxylic acid and other organic pollutants, can be removed from wastewaters by sonochemical oxidation. The effect on the removal of pollutants depends on the type of the ultrasonic frequency used; however, not much studies have been done related to the behavior of the fluid into the sonoreactors operated at different ultrasonic frequencies. Based on the above, it is necessary to study the hydrodynamic behavior of the liquid generated by the ultrasonic irradiation to design efficient sonoreactors to reduce treatment times and costs. In this work, it was studied the hydrodynamic behavior of the fluid in sonochemical reactors at different frequencies (250 kHz, 500 kHz and 1000 kHz). The performances of the sonoreactors at those frequencies were simulated using computational fluid dynamics (CFD). Due to there is great sound speed gradient between piezoelectric and fluid, k-e models were used. Piezoelectric was defined as a vibration surface, to evaluate the different frequencies effect on the fluid into sonochemical reactor. Structured hexahedral cells were used to mesh the computational liquid domain, and fine triangular cells were used to mesh the piezoelectric transducers. Unsteady state conditions were used in the solver. Estimation of the dissipation rate, flow field velocities, Reynolds stress and turbulent quantities were evaluated by CFD and 2D-PIV measurements. Test results show that there is no necessary correlation between an increase of the ultrasonic frequency and the pollutant degradation, moreover, the reactor geometry and power density are important factors that should be considered in the sonochemical reactor design.Keywords: CFD, reactor, ultrasound, wastewater
Procedia PDF Downloads 1832086 Segmentation of Korean Words on Korean Road Signs
Authors: Lae-Jeong Park, Kyusoo Chung, Jungho Moon
Abstract:
This paper introduces an effective method of segmenting Korean text (place names in Korean) from a Korean road sign image. A Korean advanced directional road sign is composed of several types of visual information such as arrows, place names in Korean and English, and route numbers. Automatic classification of the visual information and extraction of Korean place names from the road sign images make it possible to avoid a lot of manual inputs to a database system for management of road signs nationwide. We propose a series of problem-specific heuristics that correctly segments Korean place names, which is the most crucial information, from the other information by leaving out non-text information effectively. The experimental results with a dataset of 368 road sign images show 96% of the detection rate per Korean place name and 84% per road sign image.Keywords: segmentation, road signs, characters, classification
Procedia PDF Downloads 4392085 Tomato-Weed Classification by RetinaNet One-Step Neural Network
Authors: Dionisio Andujar, Juan lópez-Correa, Hugo Moreno, Angela Ri
Abstract:
The increased number of weeds in tomato crops highly lower yields. Weed identification with the aim of machine learning is important to carry out site-specific control. The last advances in computer vision are a powerful tool to face the problem. The analysis of RGB (Red, Green, Blue) images through Artificial Neural Networks had been rapidly developed in the past few years, providing new methods for weed classification. The development of the algorithms for crop and weed species classification looks for a real-time classification system using Object Detection algorithms based on Convolutional Neural Networks. The site study was located in commercial corn fields. The classification system has been tested. The procedure can detect and classify weed seedlings in tomato fields. The input to the Neural Network was a set of 10,000 RGB images with a natural infestation of Cyperus rotundus l., Echinochloa crus galli L., Setaria italica L., Portulaca oeracea L., and Solanum nigrum L. The validation process was done with a random selection of RGB images containing the aforementioned species. The mean average precision (mAP) was established as the metric for object detection. The results showed agreements higher than 95 %. The system will provide the input for an online spraying system. Thus, this work plays an important role in Site Specific Weed Management by reducing herbicide use in a single step.Keywords: deep learning, object detection, cnn, tomato, weeds
Procedia PDF Downloads 952084 Refined Edge Detection Network
Authors: Omar Elharrouss, Youssef Hmamouche, Assia Kamal Idrissi, Btissam El Khamlichi, Amal El Fallah-Seghrouchni
Abstract:
Edge detection is represented as one of the most challenging tasks in computer vision, due to the complexity of detecting the edges or boundaries in real-world images that contains objects of different types and scales like trees, building as well as various backgrounds. Edge detection is represented also as a key task for many computer vision applications. Using a set of backbones as well as attention modules, deep-learning-based methods improved the detection of edges compared with the traditional methods like Sobel and Canny. However, images of complex scenes still represent a challenge for these methods. Also, the detected edges using the existing approaches suffer from non-refined results while the image output contains many erroneous edges. To overcome this, n this paper, by using the mechanism of residual learning, a refined edge detection network is proposed (RED-Net). By maintaining the high resolution of edges during the training process, and conserving the resolution of the edge image during the network stage, we make the pooling outputs at each stage connected with the output of the previous layer. Also, after each layer, we use an affined batch normalization layer as an erosion operation for the homogeneous region in the image. The proposed methods are evaluated using the most challenging datasets including BSDS500, NYUD, and Multicue. The obtained results outperform the designed edge detection networks in terms of performance metrics and quality of output images.Keywords: edge detection, convolutional neural networks, deep learning, scale-representation, backbone
Procedia PDF Downloads 922083 Improvement of Ground Truth Data for Eye Location on Infrared Driver Recordings
Authors: Sorin Valcan, Mihail Gaianu
Abstract:
Labeling is a very costly and time consuming process which aims to generate datasets for training neural networks in several functionalities and projects. For driver monitoring system projects, the need for labeled images has a significant impact on the budget and distribution of effort. This paper presents the modifications done to an algorithm used for the generation of ground truth data for 2D eyes location on infrared images with drivers in order to improve the quality of the data and performance of the trained neural networks. The algorithm restrictions become tougher, which makes it more accurate but also less constant. The resulting dataset becomes smaller and shall not be altered by any kind of manual label adjustment before being used in the neural networks training process. These changes resulted in a much better performance of the trained neural networks.Keywords: labeling automation, infrared camera, driver monitoring, eye detection, convolutional neural networks
Procedia PDF Downloads 1062082 Visualization as a Psychotherapeutic Mind-Body Intervention through Reducing Stress and Depression among Breast Cancer Patients in Kolkata
Authors: Prathama Guha Chaudhuri, Arunima Datta, Ashis Mukhopadhyay
Abstract:
Background: Visualization (guided imagery) is a set of techniques which induce relaxation and help people create positive mental images in order to reduce stress.It is relatively inexpensive and can even be practised by bed bound people. Studies have shown visualization to be an effective tool to improve cancer patients’ anxiety, depression and quality of life. The common images used with cancer patients in the developed world are those involving the individual’s body and its strengths. Since breast cancer patients in India are more family oriented and often their main concerns are the stigma of having cancer and subsequent isolation of their families, including their children, we figured that positive images involving acceptance and integration within family and society would be more effective for them. Method: Data was collected from 119 breast cancer patients on chemotherapy willing to undergo psychotherapy, with no history of past psychiatric illness. Their baseline stress, anxiety, depression and quality of life were assessed using validated tools. The participants were then randomly divided into three groups: a) those who received visualization therapy with standard imageries involving the body and its strengths (sVT), b) those who received visualization therapy using indigenous family oriented imageries (mVT) and c) a control group who received supportive therapy. There were six sessions spread over two months for each group. The psychological outcome variables were measured post intervention. Appropriate statistical analyses were done. Results:Both forms of visualization therapy were more effective than supportive therapy alone in reducing patients’ depression, anxiety and quality of life.Modified VT proved to be significantly more effective in improving patients’ anxiety and quality of life. Conclusion: Visualization is a valuable therapeutic option for reduction of psychological distress and improving quality of life of breast cancer patients.In order to be more effective, the images used need to be modified according to the sociocultural background and individual needs of the patients.Keywords: breast cancer, visualization therapy, quality of life, anxiety, depression
Procedia PDF Downloads 2542081 The Effect of Expanding the Early Pregnancy Assessment Clinic and COVID-19 on Emergency Department and Urgent Care Visits for Early Pregnancy Bleeding
Authors: Harley Bray, Helen Pymar, Michelle Liu, Chau Pham, Tomislav Jelic, Fran Mulhall
Abstract:
Background: Our study assesses the impact of the COVID-19 pandemic on early pregnancy assessment clinic (EPAC) referrals and the use of virtual consultation in Winnipeg, Manitoba. Our clinic expanded to accept referrals from all Winnipeg Emergency Department (ED)/Urgent Care (UC) sites beginning November 2019 to April 2020. By May 2020, the COVID-19 pandemic reached Manitoba and EPAC virtual care was expanded by performing hCG remotely and reviewing blood and ED/UC ultrasound results by phone. Methods: Emergency Department Information Systems (EDIS) and EPAC data reviewed ED/UC visits for pregnancy <20 weeks and vaginal bleeding 1-year pre-COVID (March 12, 2019, to March 11, 2020) and during COVID (March 12, 2020 (first case in Manitoba) to March 11, 2021). Results: There were fewer patient visits for vaginal bleeding or pregnancy of <20 weeks (4264 vs. 5180), diagnoses of threatened abortion (1895 vs. 2283), and ectopic pregnancy (78 vs. 97) during COVID compared with pre-COVID, respectively. ICD 10 codes were missing in 849 (20%) and 1183 (23%) of patients during COVID and pre-COVID, respectively. Wait times for all patient visits improved during COVID-19 compared to pre-COVID (5.1 ± 4.4 hours vs. 5.5 ± 3.8 hours), more patients received obstetrical ultrasounds, 761 (18%) vs. 787 (15%), and fewer patients returned within 30 days (1360 (32%) vs. 1848 (36%); p<0.01). EPAC saw 708 patients (218; 31% new ED/UC) during COVID-19 compared to 552 (37; 7% new ED/UC) pre-COVID. Fewer operative interventions for pregnancy loss (346 vs. 456) and retained products (236 vs. 272) were noted. Surgeries to treat ectopic pregnancy (106 vs 113) remained stable during the study time interval. Conclusion: Accurate identification of pregnancy complications was difficult, with over 20% missing ICD-10 diagnostic codes. There were fewer ED/UC visits and surgical management for threatened abortion during COVID-19, but ectopic pregnancy operative management remained unchanged.Keywords: early pregnancy, ultrasound, COVID-19, obstetrics
Procedia PDF Downloads 122080 Fusion of Shape and Texture for Unconstrained Periocular Authentication
Authors: D. R. Ambika, K. R. Radhika, D. Seshachalam
Abstract:
Unconstrained authentication is an important component for personal automated systems and human-computer interfaces. Existing solutions mostly use face as the primary object of analysis. The performance of face-based systems is largely determined by the extent of deformation caused in the facial region and amount of useful information available in occluded face images. Periocular region is a useful portion of face with discriminative ability coupled with resistance to deformation. A reliable portion of periocular area is available for occluded images. The present work demonstrates that joint representation of periocular texture and periocular structure provides an effective expression and poses invariant representation. The proposed methodology provides an effective and compact description of periocular texture and shape. The method is tested over four benchmark datasets exhibiting varied acquisition conditions.Keywords: periocular authentication, Zernike moments, LBP variance, shape and texture fusion
Procedia PDF Downloads 2692079 HIS Integration Systems Using Modality Worklist and DICOM
Authors: Kulvinder Singh Mann
Abstract:
The usability and simulation of information systems, known as Hospital Information System (HIS), Radiology Information System (RIS), and Picture Archiving, Communication System, for electronic medical records has shown a good impact for actors in the hospital. The objective is to help and make their work easier; such as for a nurse or administration staff to record the medical records of the patient, and for a patient to check their bill transparently. However, several limitations still exists on such area regarding the type of data being stored in the system, ability for data transfer, storage and protocols to support communication between medical devices and digital images. This paper reports the simulation result of integrating several systems to cope with those limitations by using the Modality Worklist and DICOM standard. It succeeds in documenting the reason of that failure so future research will gain better understanding and be able to integrate those systems.Keywords: HIS, RIS, PACS, modality worklist, DICOM, digital images
Procedia PDF Downloads 3062078 Contrast Enhancement of Masses in Mammograms Using Multiscale Morphology
Authors: Amit Kamra, V. K. Jain, Pragya
Abstract:
Mammography is widely used technique for breast cancer screening. There are various other techniques for breast cancer screening but mammography is the most reliable and effective technique. The images obtained through mammography are of low contrast which causes problem for the radiologists to interpret. Hence, a high quality image is mandatory for the processing of the image for extracting any kind of information from it. Many contrast enhancement algorithms have been developed over the years. In the present work, an efficient morphology based technique is proposed for contrast enhancement of masses in mammographic images. The proposed method is based on Multiscale Morphology and it takes into consideration the scale of the structuring element. The proposed method is compared with other state-of-the-art techniques. The experimental results show that the proposed method is better both qualitatively and quantitatively than the other standard contrast enhancement techniques.Keywords: enhancement, mammography, multi-scale, mathematical morphology
Procedia PDF Downloads 4112077 Investigating the Factors Affecting Generalization of Deep Learning Models for Plant Disease Detection
Authors: Praveen S. Muthukumarana, Achala C. Aponso
Abstract:
A large percentage of global crop harvest is lost due to crop diseases. Timely identification and treatment of crop diseases is difficult in many developing nations due to insufficient trained professionals in the field of agriculture. Many crop diseases can be accurately diagnosed by visual symptoms. In the past decade, deep learning has been successfully utilized in domains such as healthcare but adoption in agriculture for plant disease detection is rare. The literature shows that models trained with popular datasets such as PlantVillage does not generalize well on real world images. This paper attempts to find out how to make plant disease identification models that generalize well with real world images.Keywords: agriculture, convolutional neural network, deep learning, plant disease classification, plant disease detection, plant disease diagnosis
Procedia PDF Downloads 1352076 Automatic Classification for the Degree of Disc Narrowing from X-Ray Images Using CNN
Authors: Kwangmin Joo
Abstract:
Automatic detection of lumbar vertebrae and classification method is proposed for evaluating the degree of disc narrowing. Prior to classification, deep learning based segmentation is applied to detect individual lumbar vertebra. M-net is applied to segment five lumbar vertebrae and fine-tuning segmentation is employed to improve the accuracy of segmentation. Using the features extracted from previous step, clustering technique, k-means clustering, is applied to estimate the degree of disc space narrowing under four grade scoring system. As preliminary study, techniques proposed in this research could help building an automatic scoring system to diagnose the severity of disc narrowing from X-ray images.Keywords: Disc space narrowing, Degenerative disc disorders, Deep learning based segmentation, Clustering technique
Procedia PDF Downloads 1172075 A Custom Convolutional Neural Network with Hue, Saturation, Value Color for Malaria Classification
Authors: Ghazala Hcini, Imen Jdey, Hela Ltifi
Abstract:
Malaria disease should be considered and handled as a potential restorative catastrophe. One of the most challenging tasks in the field of microscopy image processing is due to differences in test design and vulnerability of cell classifications. In this article, we focused on applying deep learning to classify patients by identifying images of infected and uninfected cells. We performed multiple forms, counting a classification approach using the Hue, Saturation, Value (HSV) color space. HSV is used since of its superior ability to speak to image brightness; at long last, for classification, a convolutional neural network (CNN) architecture is created. Clusters of focus were used to deliver the classification. The highlights got to be forbidden, and a few more clamor sorts are included in the information. The suggested method has a precision of 99.79%, a recall value of 99.55%, and provides 99.96% accuracy.Keywords: deep learning, convolutional neural network, image classification, color transformation, HSV color, malaria diagnosis, malaria cells images
Procedia PDF Downloads 812074 Heavy Metals Estimation in Coastal Areas Using Remote Sensing, Field Sampling and Classical and Robust Statistic
Authors: Elena Castillo-López, Raúl Pereda, Julio Manuel de Luis, Rubén Pérez, Felipe Piña
Abstract:
Sediments are an important source of accumulation of toxic contaminants within the aquatic environment. Bioassays are a powerful tool for the study of sediments in relation to their toxicity, but they can be expensive. This article presents a methodology to estimate the main physical property of intertidal sediments in coastal zones: heavy metals concentration. This study, which was developed in the Bay of Santander (Spain), applies classical and robust statistic to CASI-2 hyperspectral images to estimate heavy metals presence and ecotoxicity (TOC). Simultaneous fieldwork (radiometric and chemical sampling) allowed an appropriate atmospheric correction to CASI-2 images.Keywords: remote sensing, intertidal sediment, airborne sensors, heavy metals, eTOCoxicity, robust statistic, estimation
Procedia PDF Downloads 4082073 A Versatile Data Processing Package for Ground-Based Synthetic Aperture Radar Deformation Monitoring
Authors: Zheng Wang, Zhenhong Li, Jon Mills
Abstract:
Ground-based synthetic aperture radar (GBSAR) represents a powerful remote sensing tool for deformation monitoring towards various geohazards, e.g. landslides, mudflows, avalanches, infrastructure failures, and the subsidence of residential areas. Unlike spaceborne SAR with a fixed revisit period, GBSAR data can be acquired with an adjustable temporal resolution through either continuous or discontinuous operation. However, challenges arise from processing high temporal-resolution continuous GBSAR data, including the extreme cost of computational random-access-memory (RAM), the delay of displacement maps, and the loss of temporal evolution. Moreover, repositioning errors between discontinuous campaigns impede the accurate measurement of surface displacements. Therefore, a versatile package with two complete chains is developed in this study in order to process both continuous and discontinuous GBSAR data and address the aforementioned issues. The first chain is based on a small-baseline subset concept and it processes continuous GBSAR images unit by unit. Images within a window form a basic unit. By taking this strategy, the RAM requirement is reduced to only one unit of images and the chain can theoretically process an infinite number of images. The evolution of surface displacements can be detected as it keeps temporarily-coherent pixels which are present only in some certain units but not in the whole observation period. The chain supports real-time processing of the continuous data and the delay of creating displacement maps can be shortened without waiting for the entire dataset. The other chain aims to measure deformation between discontinuous campaigns. Temporal averaging is carried out on a stack of images in a single campaign in order to improve the signal-to-noise ratio of discontinuous data and minimise the loss of coherence. The temporal-averaged images are then processed by a particular interferometry procedure integrated with advanced interferometric SAR algorithms such as robust coherence estimation, non-local filtering, and selection of partially-coherent pixels. Experiments are conducted using both synthetic and real-world GBSAR data. Displacement time series at the level of a few sub-millimetres are achieved in several applications (e.g. a coastal cliff, a sand dune, a bridge, and a residential area), indicating the feasibility of the developed GBSAR data processing package for deformation monitoring of a wide range of scientific and practical applications.Keywords: ground-based synthetic aperture radar, interferometry, small baseline subset algorithm, deformation monitoring
Procedia PDF Downloads 1512072 Seawater Changes' Estimation at Tidal Flat in Korean Peninsula Using Drone Stereo Images
Authors: Hyoseong Lee, Duk-jin Kim, Jaehong Oh, Jungil Shin
Abstract:
Tidal flat in Korean peninsula is one of the largest biodiversity tidal flats in the world. Therefore, digital elevation models (DEM) is continuously demanded to monitor of the tidal flat. In this study, DEM of tidal flat, according to different times, was produced by means of the Drone and commercial software in order to measure seawater change during high tide at water-channel in tidal flat. To correct the produced DEMs of the tidal flat where is inaccessible to collect control points, the DEM matching method was applied by using the reference DEM instead of the survey. After the ortho-image was made from the corrected DEM, the land cover classified image was produced. The changes of seawater amount according to the times were analyzed by using the classified images and DEMs. As a result, it was confirmed that the amount of water rapidly increased as the time passed during high tide.Keywords: tidal flat, drone, DEM, seawater change
Procedia PDF Downloads 1932071 Imaginations of the Silk Road in Sven Hedin’s Travel Writings: 1900-1936
Authors: Kexin Tan
Abstract:
The Silk Road is a concept idiosyncratic in nature. Western scholars co-created and conceptualized in its early days, transliterated into the countries along the Silk Road, redefined, reimagined, and reconfigured by the public in the second half of the twentieth century. Therefore, the image is not only a mirror of the discursive interactions between East and West but Self and Other. The travel narrative of Sven Hedin, through which the Silk Road was enriched in meanings and popularized, is the focus of this study. This article examines how the Silk Road was imagined in three key texts of Sven Hedin: The Silk Road, The Wandering Lake, and The Flight of “Big Horse”. Three recurring themes are extracted and analyzed: the Silk Road, the land of enigmas, the virgin land, and the reconnecting road. Ideas about ethnotypes and images drawn from theorists such as Joep Leerssen have been deployed in the analysis. This research tracks how the images were configured, concentrating on China’s ethnotypes, travel writing tropes, and the Silk Road discourse that preceded Sven Hedin. Hedin’s role in his expedition, his geopolitical viewpoints, and the commercial considerations of his books are also discussed in relation to the intellectual construct of the Silk Road. It is discovered that the images of the Silk Road and the discursive traditions behind it are mobile rather than static, inclusive than antithetical. The paradoxical characters of the Silk Road reveal the complexity of the socio-historical background of Hedin’s time, as well as the collision of discursive traditions and practical issues. While it is true that Hedin’s discursive construction of the Silk Road image embodies the bias of Self-West against Other-East, its characteristics such as fluidity and openness could probably offer a hint at its resurgence in the postcolonial era.Keywords: the silk road, Sven Hedin, imagology, ethnotype, travelogue
Procedia PDF Downloads 184