Search results for: Deep learning based segmentation

Authors: Bitewulign Mekonnen

Abstract:

Context: This scientific paper focuses on the use of near-infrared (NIR) spectroscopy to determine glucose concentration in aqueous solutions accurately and rapidly. The study compares six different machine learning methods for predicting glucose concentration and also explores the development of a deep learning model for classifying NIR spectra. The objective is to optimize the detection model and improve the accuracy of glucose prediction. This research is important because it provides a comprehensive analysis of various machine-learning techniques for estimating aqueous glucose concentrations. Research Aim: The aim of this study is to compare and evaluate different machine-learning methods for predicting glucose concentration from NIR spectra. Additionally, the study aims to develop and assess a deep-learning model for classifying NIR spectra. Methodology: The research methodology involves the use of machine learning and deep learning techniques. Six machine learning regression models, including support vector machine regression, partial least squares regression, extra tree regression, random forest regression, extreme gradient boosting, and principal component analysis-neural network, are employed to predict glucose concentration. The NIR spectra data is randomly divided into train and test sets, and the process is repeated ten times to increase generalization ability. In addition, a convolutional neural network is developed for classifying NIR spectra. Findings: The study reveals that the SVMR, ETR, and PCA-NN models exhibit excellent performance in predicting glucose concentration, with correlation coefficients (R) > 0.99 and determination coefficients (R²)> 0.985. The deep learning model achieves high macro-averaging scores for precision, recall, and F1-measure. These findings demonstrate the effectiveness of machine learning and deep learning methods in optimizing the detection model and improving glucose prediction accuracy. Theoretical Importance: This research contributes to the field by providing a comprehensive analysis of various machine-learning techniques for estimating glucose concentrations from NIR spectra. It also explores the use of deep learning for the classification of indistinguishable NIR spectra. The findings highlight the potential of machine learning and deep learning in enhancing the prediction accuracy of glucose-relevant features. Data Collection and Analysis Procedures: The NIR spectra and corresponding references for glucose concentration are measured in increments of 20 mg/dl. The data is randomly divided into train and test sets, and the models are evaluated using regression analysis and classification metrics. The performance of each model is assessed based on correlation coefficients, determination coefficients, precision, recall, and F1-measure. Question Addressed: The study addresses the question of whether machine learning and deep learning methods can optimize the detection model and improve the accuracy of glucose prediction from NIR spectra. Conclusion: The research demonstrates that machine learning and deep learning methods can effectively predict glucose concentration from NIR spectra. The SVMR, ETR, and PCA-NN models exhibit superior performance, while the deep learning model achieves high classification scores. These findings suggest that machine learning and deep learning techniques can be used to improve the prediction accuracy of glucose-relevant features. Further research is needed to explore their clinical utility in analyzing complex matrices, such as blood glucose levels.

Keywords: machine learning, signal processing, near-infrared spectroscopy, support vector machine, neural network

Procedia PDF Downloads 95

Authors: Simeon Mayala, Ida Herdlevær, Jonas Bull Haugsøen, Shamundeeswari Anandan, Sonia Gavasso, Morten Brun

Abstract:

In this paper, we propose a minimum spanning tree-based method for segmenting brain tumors. The proposed method performs interactive segmentation based on the minimum spanning tree without tuning parameters. The steps involve preprocessing, making a graph, constructing a minimum spanning tree, and a newly implemented way of interactively segmenting the region of interest. In the preprocessing step, a Gaussian filter is applied to 2D images to remove the noise. Then, the pixel neighbor graph is weighted by intensity differences and the corresponding minimum spanning tree is constructed. The image is loaded in an interactive window for segmenting the tumor. The region of interest and the background are selected by clicking to split the minimum spanning tree into two trees. One of these trees represents the region of interest and the other represents the background. Finally, the segmentation given by the two trees is visualized. The proposed method was tested by segmenting two different 2D brain T1-weighted magnetic resonance image data sets. The comparison between our results and the standard gold segmentation confirmed the validity of the minimum spanning tree approach. The proposed method is simple to implement and the results indicate that it is accurate and efficient.

Keywords: brain tumor, brain tumor segmentation, minimum spanning tree, segmentation, image processing

Procedia PDF Downloads 122

Authors: Afaq Ahmad, Yifei Wang, Muhammad Kashif

Abstract:

This paper addresses the rising safety accidents in China's construction industry by focusing on detecting safety helmet usage among workers using deep learning techniques. It enhances existing datasets through the collection of construction site images and merges them with public datasets to create a diverse sample library. An improved Cascade R-CNN algorithm is developed, incorporating a Swin Transformer for better feature extraction, ROI Align for detecting small and occluded targets, and Gaussian weighted Soft-NMS to reduce redundant detections. The model, trained on the "My-SHWD" dataset, achieved a mean Average Precision of 92.66%, showcasing strong performance. Additionally, a helmet detection system was designed for testing images, videos, and live feeds, demonstrating reliability and stability in practical applications.

Keywords: deep learning, safety helmet-wearing detection, cascade R-CNN, swin transformer

Procedia PDF Downloads 5

Authors: David Jurado, Carlos Ávila

Abstract:

Detection of early signs of breast cancer development is crucial to quickly diagnose the disease and to define adequate treatment to increase the survival probability of the patient. Computer Aided Detection systems (CADs), along with modern data techniques such as Machine Learning (ML) and Neural Networks (NN), have shown an overall improvement in digital mammography cancer diagnosis, reducing the false positive and false negative rates becoming important tools for the diagnostic evaluations performed by specialized radiologists. However, ML and NN-based algorithms rely on datasets that might bring issues to the segmentation tasks. In the present work, an automatic segmentation and detection algorithm is described. This algorithm uses image processing techniques along with the Hough transform to automatically identify microcalcifications that are highly correlated with breast cancer development in the early stages. Along with image processing, automatic segmentation of high-contrast objects is done using edge extraction and circle Hough transform. This provides the geometrical features needed for an automatic mask design which extracts statistical features of the regions of interest. The results shown in this study prove the potential of this tool for further diagnostics and classification of mammographic images due to the low sensitivity to noisy images and low contrast mammographies.

Keywords: breast cancer, segmentation, X-ray imaging, hough transform, image analysis

Procedia PDF Downloads 84

Authors: Ian Omung'a

Abstract:

Breast cancer remains to be one of the deadliest cancers for women worldwide, with the risk of developing tumors being as high as 50 percent in Sub-Saharan African countries like Kenya. With as many as 42 percent of these cases set to be diagnosed late when cancer has metastasized and or the prognosis has become terminal, Full Field Digital [FFD] Mammography remains an effective screening technique that leads to early detection where in most cases, successful interventions can be made to control or eliminate the tumors altogether. FFD Mammograms have been proven to multiply more effective when used together with Computer-Aided Detection and Diagnosis [CADe] systems, relying on algorithmic implementations of Deep Learning techniques in Computer Vision to carry out deep pattern recognition that is comparable to the level of a human radiologist and decipher whether specific areas of interest in the mammogram scan image portray abnormalities if any and whether these abnormalities are indicative of a benign or malignant tumor. Within this paper, we review emergent Deep Learning techniques that will prove relevant to the development of State-of-The-Art FFD Mammogram CADe systems. These techniques will span self-supervised learning for context-encoded occlusion, self-supervised learning for pre-processing and labeling automation, as well as the creation of a standardized large-scale mammography dataset as a benchmark for CADe systems' evaluation. Finally, comparisons are drawn between existing practices that pre-date these techniques and how the development of CADe systems that incorporate them will be different.

Keywords: breast cancer diagnosis, computer aided detection and diagnosis, deep learning, whole mammogram classfication, ultrasound classification, computer vision

Procedia PDF Downloads 93

Authors: Lei Qin

Abstract:

As shared accommodation has become one of the most important market developments in the tourism industry, numerous contributions have emerged on travelers’ motivations to choose shared accommodation. A debated question, however, resides in the heterogeneity of travelers based on motivations. This paper aims to reconcile opposing perspectives by comparing motivation segmentation at two distinct phases of innovation adoption of this new hospitality option: (i) before the first travel – potential users showing interest (n=420) and (ii) after the first travel – users (n=420). Interestingly, we find that travelers (including pre-and-post adopters) have a stronger agreement in experiential motivations than practical motivations. However, the heterogeneity of motivations among travelers is significantly higher in users, increasing from two to six clusters, which means travelers cluster into more and distinct motivation groups after adoption. Rather than invalidating specific assumptions used in the literature in terms of motivation heterogeneity, this paper reconciles opposing findings by putting them along with one another in the process of innovation adoption. A subsequent tourists’ segmentation based on motivations were conducted according to their innovation adoption stages.

Keywords: motivation, pre-and-post adoption, shared accommodation, segmentation

Procedia PDF Downloads 143

Authors: Hy Dang, Bo Mei

Abstract:

The development of machine learning methods and techniques has opened doors for investigation in many areas such as medicines, economics, finance, etc. One active research area involving machine learning is stock market prediction. This research paper tries to consider multiple techniques and methods for stock movement prediction using historical price or price factors. The paper explores the effectiveness of some deep learning frameworks for forecasting stock. Moreover, an architecture (TimeStock) is proposed which takes the representation of time into account apart from the price information itself. Our model achieves a promising result that shows a potential approach for the stock movement prediction problem.

Keywords: classification, machine learning, time representation, stock prediction

Procedia PDF Downloads 147

Authors: Jimeng Shi, Mahek Jain, Giri Narasimhan

Abstract:

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed-length window in the past as an explicit input. In this paper, we study how the performance of predictive models changes as a function of different look-back window sizes and different amounts of time to predict the future. We also consider the performance of the recent attention-based Transformer models, which have had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (RNN, LSTM, GRU, and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the UCI website, which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean Average Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.

Keywords: air quality prediction, deep learning algorithms, time series forecasting, look-back window

Procedia PDF Downloads 156

Authors: Vaibhav Dalmia, Manoj Phirke, Renith G

Abstract:

With the wide adoption of UAVs (unmanned aerial vehicles) in various industries by the government as well as private corporations for solving computer vision tasks it’s necessary that their potential is analyzed completely. Recent advances in Deep Learning have also left us with a plethora of algorithms to solve different computer vision tasks. This study provides a comprehensive survey on solving the Visual Object Tracking problem and explains the tradeoffs involved in building a real-time yet reasonably accurate object tracking system for UAVs by looking at existing methods and evaluating them on the aerial datasets. Finally, the best trackers suitable for UAV-based applications are provided.

Keywords: deep learning, drones, single object tracking, visual object tracking, UAVs

Procedia PDF Downloads 159

Authors: Khalil Bachiri, Ali Yahyaouy, Nicoleta Rogovschi

Abstract:

Improved user experience is a goal of contemporary recommender systems. Recommender systems are starting to incorporate reinforcement learning since it easily satisfies this goal of increasing a user’s reward every session. In this paper, we examine the most effective Reinforcement Learning agent tactics on the Movielens (1M) dataset, balancing precision and a variety of recommendations. The absence of variability in final predictions makes simplistic techniques, although able to optimize ranking quality criteria, worthless for consumers of the recommendation system. Utilizing the stochasticity of Leonard-Ornstein processes, our suggested strategy encourages the agent to investigate its surroundings. Research demonstrates that raising the NDCG (Discounted Cumulative Gain) and HR (HitRate) criterion without lowering the Ornstein-Uhlenbeck process drift coefficient enhances the diversity of suggestions.

Keywords: recommender systems, reinforcement learning, deep learning, DDPG, Leonard-Ornstein process

Procedia PDF Downloads 145

Authors: Rohit Semwal, Shivam Arora, Saurav, Sangita Roy

Abstract:

This work proposes a supervised framework with deep convolutional neural networks (CNNs) for vision-based sign language recognition of static gestures. Our approach addresses the acquisition and segmentation of correct inputs for the CNN-based classifier. Microsoft Kinect™ sensor, despite complex environmental conditions, can track hands efficiently. Skin Colour based segmentation is applied on cropped images of hands in different poses, used to depict different sign language gestures. The segmented hand images are used as an input for our classifier. The CNN classifier proposed in the paper is able to classify the input images with a high degree of accuracy. The system was trained and tested on 39 static sign language gestures, including 26 letters of the alphabet and 13 commonly used words. This paper includes a problem definition for building the proposed system, which acts as a sign language translator between deaf/mute and the rest of the society. It is then followed by a focus on reviewing existing knowledge in the area and work done by other researchers. It also describes the working principles behind different components of CNNs in brief. The architecture and system design specifications of the proposed system are discussed in the subsequent sections of the paper to give the reader a clear picture of the system in terms of the capability required. The design then gives the top-level details of how the proposed system meets the requirements.

Keywords: sign language, CNN, HCI, segmentation

Procedia PDF Downloads 159

Authors: Supriya H. S., Chandrakala B. M.

Abstract:

Deep learning based models have been recently successful adoption for network traffic prediction. However, training a deep learning model for various prediction tasks is considered one of the critical tasks due to various reasons. This research work develops Multi-Layer Hybrid Network (MLHN) for network traffic prediction and analysis; MLHN comprises the three distinctive networks for handling the different inputs for custom feature extraction. Furthermore, an optimized and efficient parameter-tuning algorithm is introduced to enhance parameter learning. MLHN is evaluated considering the “Big Data Challenge” dataset considering the Mean Absolute Error, Root Mean Square Error and R^2as metrics; furthermore, MLHN efficiency is proved through comparison with a state-of-art approach.

Keywords: MLHN, network traffic prediction

Procedia PDF Downloads 90

Authors: Martin K. Steiger, Lukas Heisler, Hans-Georg Brachtendorf

Abstract:

Deep neural networks and their variants form the backbone of many AI applications. Based on the so-called residual networks, a continuous formulation of such models as ordinary differential equations (ODEs) has proven advantageous since different techniques may be applied that significantly increase the learning speed and enable controlled trade-offs with the resulting error at the same time. For the evaluation of such models, high-performance numerical differential equation solvers are used, which also provide the gradients required for training. However, whether classical gradient-based methods are even applicable or which one yields the best results has not been discussed yet. This paper aims to redeem this situation by providing empirical results for different applications.

Keywords: deep neural networks, gradient-based learning, image processing, ordinary differential equation networks

Procedia PDF Downloads 170

Authors: Shu-Yu Hsu, Chen-Chien Hsu, Wei-Yen Wang

Abstract:

Color segmentation is a basic and simple way for recognizing the visual markers in a robotic tracking system. In this paper, we propose a new method for color segmentation by incorporating differential evolution algorithm and connected component labeling to autonomously preset the HSV threshold of visual markers. To evaluate the effectiveness of the proposed algorithm, a ROBOTIS OP2 humanoid robot is used to conduct the experiment, where five most commonly used color including red, purple, blue, yellow, and green in visual markers are given for comparisons.

Keywords: color segmentation, differential evolution, connected component labeling, humanoid robot

Procedia PDF Downloads 605

Authors: Shaik Ayesha Fathima, Shaik Noor Jahan, Duvvada Rajeswara Rao

Abstract:

Earth's environment and its evolution can be seen through satellite images in near real-time. Through satellite imagery, remote sensing data provide crucial information that can be used for a variety of applications, including image fusion, change detection, land cover classification, agriculture, mining, disaster mitigation, and monitoring climate change. The objective of this project is to propose a method for classifying satellite images according to multiple predefined land cover classes. The proposed approach involves collecting data in image format. The data is then pre-processed using data pre-processing techniques. The processed data is fed into the proposed algorithm and the obtained result is analyzed. Some of the algorithms used in satellite imagery classification are U-Net, Random Forest, Deep Labv3, CNN, ANN, Resnet etc. In this project, we are using the DeepLabv3 (Atrous convolution) algorithm for land cover classification. The dataset used is the deep globe land cover classification dataset. DeepLabv3 is a semantic segmentation system that uses atrous convolution to capture multi-scale context by adopting multiple atrous rates in cascade or in parallel to determine the scale of segments.

Keywords: area calculation, atrous convolution, deep globe land cover classification, deepLabv3, land cover classification, resnet 50

Procedia PDF Downloads 140

Authors: Peifei Zhu, Zisheng Li, Yasuki Kakishita, Mayumi Suzuki, Tomoaki Chono

Abstract:

Segmentation of left ventricle (LV) from cardiac ultrasound images provides a quantitative functional analysis of the heart to diagnose disease. Active Shape Model (ASM) is a widely used approach for LV segmentation but suffers from the drawback that initialization of the shape model is not sufficiently close to the target, especially when dealing with abnormal shapes in disease. In this work, a two-step framework is proposed to improve the accuracy and speed of the model-based segmentation. Firstly, a robust and efficient detector based on Hough forest is proposed to localize cardiac feature points, and such points are used to predict the initial fitting of the LV shape model. Secondly, to achieve more accurate and detailed segmentation, ASM is applied to further fit the LV shape model to the cardiac ultrasound image. The performance of the proposed method is evaluated on a dataset of 800 cardiac ultrasound images that are mostly of abnormal shapes. The proposed method is compared to several combinations of ASM and existing initialization methods. The experiment results demonstrate that the accuracy of feature point detection for initialization was improved by 40% compared to the existing methods. Moreover, the proposed method significantly reduces the number of necessary ASM fitting loops, thus speeding up the whole segmentation process. Therefore, the proposed method is able to achieve more accurate and efficient segmentation results and is applicable to unusual shapes of heart with cardiac diseases, such as left atrial enlargement.

Keywords: hough forest, active shape model, segmentation, cardiac left ventricle

Procedia PDF Downloads 341

Authors: Gajendra Kumar Mourya, Dinesh Bhatia, Akash Handique, Sunita Warjri, Syed Achaab Amir

Abstract:

Nowadays, Medical imaging has become an integral part of modern healthcare. Abdominal CT images are an invaluable mean for abdominal organ investigation and have been widely studied in the recent years. Diagnosis of liver pathologies is one of the major areas of current interests in the field of medical image processing and is still an open problem. To deeply study and diagnose the liver, segmentation of liver is done to identify which part of the liver is mostly affected. Manual segmentation of the liver in CT images is time-consuming and suffers from inter- and intra-observer differences. However, automatic or semi-automatic computer aided segmentation of the Liver is a challenging task due to inter-patient Liver shape and size variability. In this paper, we present a technique for automatic segmenting the liver from CT images using Random Forest Classifier. Random forests or random decision forests are an ensemble learning method for classification that operate by constructing a multitude of decision trees at training time and outputting the class that is the mode of the classes of the individual trees. After comparing with various other techniques, it was found that Random Forest Classifier provide a better segmentation results with respect to accuracy and speed. We have done the validation of our results using various techniques and it shows above 89% accuracy in all the cases.

Keywords: CT images, image validation, random forest, segmentation

Procedia PDF Downloads 313

Authors: Leah Lee

Abstract:

This paper examines the correlation between deep learning models and emotions with noises to see whether or not noises mask emotions. The deep learning models used are plain convolutional neural networks (CNN), auto-encoder, long short-term memory (LSTM), and Visual Geometry Group-16 (VGG-16). Emotion datasets used are Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Toronto Emotional Speech Set (TESS), and Surrey Audio-Visual Expressed Emotion (SAVEE). To make it four times bigger, audio set files, stretch, and pitch augmentations are utilized. From the augmented datasets, five different features are extracted for inputs of the models. There are eight different emotions to be classified. Noise variations are white noise, dog barking, and cough sounds. The variation in the signal-to-noise ratio (SNR) is 0, 20, and 40. In summation, per a deep learning model, nine different sets with noise and SNR variations and just augmented audio files without any noises will be used in the experiment. To compare the results of the deep learning models, the accuracy and receiver operating characteristic (ROC) are checked.

Keywords: auto-encoder, convolutional neural networks, long short-term memory, speech emotion recognition, visual geometry group-16

Procedia PDF Downloads 78

Authors: Wei Li, Tuo Yang

Abstract:

In order to satisfy the real-time and accurate requirements of cigarette smoke detection in complex scenes, a cigarette smoke detection technology based on the combination of deep learning and color features was proposed. Firstly, based on the color features of cigarette smoke, the suspicious cigarette smoke area in the image is extracted. Secondly, combined with the efficiency of cigarette smoke detection and the problem of network overfitting, a network model for cigarette smoke detection was designed according to YOLOV3 algorithm to reduce the false detection rate. The experimental results show that the method is feasible and effective, and the accuracy of cigarette smoke detection is up to 99.13%, which satisfies the requirements of real-time cigarette smoke detection in complex scenes.

Keywords: deep learning, computer vision, cigarette smoke detection, YOLOV3, color feature extraction

Procedia PDF Downloads 87

Authors: Dingyang Hu, Dan Liu

Abstract:

DNN (Deep Neural Network) deep learning models are widely used in classification, prediction, and other task scenarios. To address the difficulties of generic adversarial perturbation generation for deep learning models under black-box conditions, a generic adversarial ingestion generation method based on a saliency map (CJsp) is proposed to obtain salient image regions by counting the factors that influence the input features of an image on the output results. This method can be understood as a saliency map attack algorithm to obtain false classification results by reducing the weights of salient feature points. Experiments also demonstrate that this method can obtain a high success rate of migration attacks and is a batch adversarial sample generation method.

Keywords: adversarial sample, gradient, probability, black box

Procedia PDF Downloads 105

Authors: Ananya Gangavarapu

Abstract:

Convolutional Neural Networks (CNN) based models are providing diagnostic capabilities on par with the medical specialists in many specialty areas. However, collecting the medical data for training purposes is very challenging because of the increased regulations around data collections and privacy concerns around personal health data. The gathering of the data becomes even more difficult if the capture devices are edge-based mobile devices (like smartphones) with feeble wireless connectivity in rural/remote areas. In this paper, I would like to highlight Federated Learning approach to mitigate data privacy and security issues.

Keywords: deep learning in healthcare, data privacy, federated learning, training in distributed environment

Procedia PDF Downloads 142

Authors: Xiaodong Li, Peng Gao, Chao-Jung Huang, Shiying Hao, Xuefeng B. Ling, Yongxia Han, Yaqi Zhang, Le Zheng, Chengyin Ye, Modi Liu, Minjie Xia, Changlin Fu, Bo Jin, Karl G. Sylvester, Eric Widen

Abstract:

Predicting the risk of Pancreatic Adenocarcinoma (PA) in advance can benefit the quality of care and potentially reduce population mortality and morbidity. The aim of this study was to develop and prospectively validate a risk prediction model to identify patients at risk of new incident PA as early as 3 months before the onset of PA in a statewide, general population in Maine. The PA prediction model was developed using Deep Neural Networks, a deep learning algorithm, with a 2-year electronic-health-record (EHR) cohort. Prospective results showed that our model identified 54.35% of all inpatient episodes of PA, and 91.20% of all PA that required subsequent chemoradiotherapy, with a lead-time of up to 3 months and a true alert of 67.62%. The risk assessment tool has attained an improved discriminative ability. It can be immediately deployed to the health system to provide automatic early warnings to adults at risk of PA. It has potential to identify personalized risk factors to facilitate customized PA interventions.

Keywords: cancer prediction, deep learning, electronic health records, pancreatic adenocarcinoma

Procedia PDF Downloads 157

Authors: Xiaoyan Dai, Hsieh Yisan

Abstract:

Barcode processing of captured images is a huge challenge, as different shooting conditions can result in different barcode appearances. This paper proposes a deep learning-based barcode detection using synthetic-to-real data augmentation. We first augment barcodes themselves; we then augment images containing the barcodes to generate a large variety of data that is close to the actual shooting environments. Comparisons with previous works and evaluations with our original data show that this approach achieves state-of-the-art performance in various real images. In addition, the system uses hybrid resolution for barcode “scan” and is applicable to real-time applications.

Keywords: barcode detection, data augmentation, deep learning, image-based processing

Procedia PDF Downloads 174

Authors: Rita Magdalena, N. K. Caecar Pratiwi, Yunendah Nur Fuadah, Sofia Saidah, Bima Sakti

Abstract:

Vessel segmentation of retinal fundus is important for biomedical sciences in diagnosing ailments related to the eye. Segmentation can simplify medical experts in diagnosing retinal fundus image state. Therefore, in this study, we designed a software using MATLAB which enables the segmentation of the retinal blood vessels on retinal fundus images. There are two main steps in the process of segmentation. The first step is image preprocessing that aims to improve the quality of the image to be optimum segmented. The second step is the image segmentation in order to perform the extraction process to retrieve the retina’s blood vessel from the eye fundus image. The image segmentation methods that will be analyzed in this study are Morphology Operation, Discrete Wavelet Transform and combination of both. The amount of data that used in this project is 40 for the retinal image and 40 for manually segmentation image. After doing some testing scenarios, the average accuracy for Morphology Operation method is 88.46 % while for Discrete Wavelet Transform is 89.28 %. By combining the two methods mentioned in later, the average accuracy was increased to 89.53 %. The result of this study is an image processing system that can segment the blood vessels in retinal fundus with high accuracy and low computation time.

Keywords: discrete wavelet transform, fundus retina, morphology operation, segmentation, vessel

Procedia PDF Downloads 197

Authors: Sasidhar B., Bhaskar Rao N., Ramesh Babu D. R., Ravi Shankar M.

Abstract:

Segmentation of lung pleura is a preprocessing step in Computer-Aided Diagnosis (CAD) which helps in reducing false positives in detection of lung cancer. The existing methods fail in extraction of lung regions with the nodules at the pleura of the lungs. In this paper, a new method is proposed which segments lung regions with nodules at the pleura of the lungs based on curvature analysis and morphological operators. The proposed algorithm is tested on 06 patient’s dataset which consists of 60 images of Lung Image Database Consortium (LIDC) and the results are found to be satisfactory with 98.3% average overlap measure (AΩ).

Keywords: curvature analysis, image segmentation, morphological operators, thresholding

Procedia PDF Downloads 596

Authors: Fidel Lòpez Saca, Carlos Avilés-Cruz, Miguel Magos-Rivera, José Antonio Lara-Chávez

Abstract:

Automated object recognition and identification systems are widely used throughout the world, particularly in assembly lines, where they perform quality control and automatic part selection tasks. This article presents the design and implementation of an object recognition system in an assembly line. The proposed shapes-color recognition system is based on deep learning theory in a specially designed convolutional network architecture. The used methodology involve stages such as: image capturing, color filtering, location of object mass centers, horizontal and vertical object boundaries, and object clipping. Once the objects are cut out, they are sent to a convolutional neural network, which automatically identifies the type of figure. The identification system works in real-time. The implementation was done on a Raspberry Pi 3 system and on a Jetson-Nano device. The proposal is used in an assembly course of bachelor’s degree in industrial engineering. The results presented include studying the efficiency of the recognition and processing time.

Keywords: deep-learning, image classification, image identification, industrial engineering.

Procedia PDF Downloads 162

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, with the development of large-scale pre-trained lan-guage models, building vector representations of text through deep neural network models has become a standard practice for natural language processing tasks. From the performance on downstream tasks, we can know that the text representation constructed by these models contains linguistic information, but its encoding mode and extent are unclear. In this work, a structural probe is proposed to detect whether the vector representation produced by a deep neural network is embedded with a syntax tree. The probe is trained with the deep metric learning method, so that the distance between word vectors in the metric space it defines encodes the distance of words on the syntax tree, and the norm of word vectors encodes the depth of words on the syntax tree. The experiment results on ELMo and BERT show that the syntax tree is encoded in their parameters and the word representations they produce.

Keywords: deep metric learning, syntax tree probing, natural language processing, word representations

Procedia PDF Downloads 68

Authors: Edgardo V. Gubatanga Jr., Mark Joshua Salvacion

Abstract:

Most aerial LiDAR systems have accompanying aerial cameras in order to capture not only the terrain of the surveyed area but also its true-color appearance. However, the presence of atmospheric clouds, poor lighting conditions, and aerial camera problems during an aerial survey may cause absence of aerial photographs. These leave areas having terrain information but lacking aerial photographs. Intensity images can be derived from LiDAR data but they are only grayscale images. A deep learning model is developed to create a complex function in a form of a deep neural network relating the pixel values of LiDAR-derived intensity images and true-color images. This complex function can then be used to predict the true-color images of a certain area using intensity images from LiDAR data. The predicted true-color images do not necessarily need to be accurate compared to the real world. They are only intended to look realistic so that they can be used as base maps.

Keywords: aerial LiDAR, colorization, deep learning, intensity images

Procedia PDF Downloads 168

Authors: Chad Goldsworthy, B. Rajeswari Matam

Abstract:

The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.

Keywords: convolutional neural networks, data imbalance, deep learning, focal loss, species classification, wildlife conservation

Procedia PDF Downloads 193

Authors: Gaokai Liu

Abstract:

The distribution of material grain sizes reflects the strength, fracture, corrosion and other properties, and the grain size can be acquired via the grain boundary. In recent years, the automatic grain boundary detection is widely required instead of complex experimental operations. In this paper, an effective solution is applied to acquire the grain boundary of material images. First, the initial superpixel segmentation result is obtained via a superpixel approach. Then, a region merging method is employed to merge adjacent regions based on certain similarity criterions, the experimental results show that the merging strategy improves the superpixel segmentation result on material datasets.

Keywords: grain boundary detection, image segmentation, material images, region merging

Procedia PDF Downloads 170