A Comparative analysis of stroke diagnosis from retinal images using hand-crafted features and CNN

2021 ◽  
pp. 1-9
Author(s):  
R. S Jeena ◽  
G. Shiny ◽  
A. Sukesh Kumar ◽  
K. Mahadevan
Keyword(s):  
Neural Network ◽  
Comparative Analysis ◽  
Early Detection ◽  
Comparative Study ◽  
Texture Features ◽  
Detection Algorithm ◽  
Developing Nations ◽  
Retinal Images ◽  
Fundus Images ◽  
Stroke Diagnosis

Stroke is a major reason for disability and mortality in most of the developing nations. Early detection of stroke is highly significant in bio-medical research. Research illustrates that signs of stroke are reflected in the eye and may be analyzed from fundus images. A custom dataset of fundus images has been compiled for formulating an automated stroke detection algorithm. In this paper, a comparative study of hand-crafted texture features and convolutional neural network (CNN) has been recommended for stroke diagnosis. The custom CNN model has also been compared with five pre-trained models from ImageNet. Experimental results reveal that the recommended custom CNN model gives the best performance by achieving an accuracy of 95.8 %.

scholarly journals Automated Detection of Microaneurysmsusing Probabilistic Cascaded Neural Network

2018 ◽  
Vol 11 (3) ◽  
pp. 1083
Author(s):  
Jeyapriya J ◽  
K S Umadevi ◽  
R Jagadeesh Kannan
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Blood Vessel ◽  
Automated Detection ◽  
Convolution Neural Network ◽  
Retinal Images ◽  
Fundus Images ◽  
Catching Up

The diagnosing features for Diabetic Retinopathy (DR) comprises of features occurring in and around the regions of blood vessel zone which will result into exudes, hemorrhages, microaneurysms and generation of textures on the albumen region of eye balls. In this study we presenta probabilistic convolution neural network based algorithms, utilized for the extraction of such features from the retinal images of patient’s eyeballs. The classifications proficiency of various DR systems is tabulated and examined. The majority of the reported systems are profoundly advanced regarding the analyzed fundus images is catching up to the human ophthalmologist’s characterization capacities.

scholarly journals Klasifikasi Fase Retinopati Diabetes Menggunakan Backpropagation Neural Network

2013 ◽  
Vol 7 (1) ◽  
pp. 23
Author(s):  
Rocky Yefrenes Dillak ◽  
Agus Harjoko
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Macular Edema ◽  
Proliferative Diabetic Retinopathy ◽  
Texture Features ◽  
Fundus Images ◽  
Gray Level ◽  
Backpropagation Neural Network ◽  
Maximum Probability ◽  
Keywords Diabetic Retinopathy

AbstrakRetinopati diabetes (DR) merupakan salah satu komplikasi pada retina yang disebabkan oleh penyakit diabetes. Tingkat keparahan DR dibagi atas empat kelas yakni: normal, non-proliferative diabetic retinopathy (NPDR), proliferative diabetic retinopathy (PDR), dan macular edema (ME). Penelitian ini bertujuan mengembangkan suatu metode yang dapat digunakan untuk melakukan klasifikasi terhadap fase DR. Data yang digunakan sebanyak 97 citra yang fitur – fiturnya  diekstrak menggunakan gray level cooccurence matrix (GLCM). Fitur ciri tersebut adalah maximum probability, correlation, contrast, energy, homogeneity, dan entropy. Fitur – fitur ini dilatih menggunakan jaringan syaraf tiruan backpropagation untuk dilakukan klasifikasi. Kinerja  yang dihasilkan dari pendekatan ini adalah sensitivity 100%, specificity 100% dan accuracy  97.73%  Kata kunci— fase retinopati diabetes, GLCM, backpropagation neural network  Abstract Diabetic retinopathy (DR) is one of the complications on retina caused by diabetes. The aim of this studyis to develop a system that can be used for automatic mass screenings of diabetic retinopathy. Four classes are identified: normal retina, non-proliferative diabetic retinopathy (NPDR), proliferative diabetic retinopathy (PDR), and macular edema (ME). Ninenty-seven retinal fundus images in used in this study. Six different texture features such as maximum probability, correlation, contrast, energy, homogeneity, and entropy were extracted from the digital fundus images using gray level cooccurence matrix (GLCM). These features were fed into a backpropagation neural network classifier for automatic classification. The  proposed approach is able to classify with sensitivity 100%, specificity 100% and accuracy  97.73%  Keywords— diabetic retinopathy stages, GLCM,  backpropagation neural network

scholarly journals Accident vehicle types classification: a comparative study between different deep learning models

2021 ◽  
Vol 21 (3) ◽  
pp. 1474
Author(s):  
Mardin A. Anwer ◽  
Shareef M. Shareef ◽  
Abbas M. Ali
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Comparative Analysis ◽  
Comparative Study ◽  
Evaluation Process ◽  
Convolution Neural Network ◽  
Learning Models ◽  
Vehicle Accidents ◽  
Network Topologies ◽  
Base Network

<span>Classifying and finding type of individual vehicles within an accident image are considered difficult problems. This research concentrates on accurately classifying and recognizing vehicle accidents in question. The aim to provide a comparative analysis of vehicle accidents. A number of network topologies are tested to arrive at convincing results and a variety of matrices are used in the evaluation process to identify the best networks. The best two networks are used with faster recurrent convolution neural network (Faster RCNN) and you only look once (YOLO) to determine which network will identifiably detect the location and type of the vehicle. In addition, two datasets are used in this research. In consequence, experiment results show that MobileNetV2 and ResNet50 have accomplished higher accuracy compared to the rest of the models, with 89.11% and 88.45% for the GAI dataset as well as 88.72% and 89.69% for KAI dataset, respectively. The findings reveal that the ResNet50 base network for YOLO achieved higher accuracy than MobileNetV2 for YOLO, ResNet50 for Faster RCNN with 83%, 81%, and 79% for GAI dataset and 79%, 78% and 74% for KAI dataset.</span>

scholarly journals ANÁLISE DE MÉTODOS DE DETECÇÃO E RECONHECIMENTO DE FACES UTILIZANDO VISÃO COMPUTACIONAL E ALGORITMOS DE APRENDIZADO DE MÁQUINA

2021 ◽  
Vol 13 (2) ◽  
pp. 01-11
Author(s):  
Lucas José da Costa ◽  
Thiago Luz de Sousa ◽  
Francisco Assis da Silva ◽  
Leandro Luiz de Almeida ◽  
Danillo Roberto Pereira ◽  
...  
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Comparative Analysis ◽  
Execution Time ◽  
Digital Images ◽  
Facial Recognition ◽  
Detection Algorithm ◽  
Ambient Lighting ◽  
The Face ◽  
Haar Cascade

The advancement in technology in recent decades has provided many facilities for humanity in various applications, and facial recognition technology is one of them. There are several problemsto be solved to perform face recognition from digital images, such as varying ambient lighting, changing the face physical characteristics and resolution of the images used. This work aimed to perform a comparative analysis between some of thedetection and facial recognition methods, as well as their execution time. We use the Eigenface, Fisherface and LBPH facial recognition algorithms in conjunction with the Haar Cascade facedetection algorithm, all from the OpenCV library. We also explored the use of CNN neural network for facial recognition in conjunction with the HOG facial detection algorithm, these from the Dlib library. The work aimed, besides analyzing the algorithms in relation to hit rates, factors such as reliability and execution time were also considered

Automatic Exudates Detection in Diabetic Retinopathy Images

2016 ◽  
Vol 5 (2) ◽  
pp. 45
Author(s):  
H. Faouzi ◽  
Mohamed Fakir
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Early Detection ◽  
Edge Detection ◽  
Detection Algorithm ◽  
Vascular Lesions ◽  
Edge Detection Algorithm ◽  
Invariant Moments ◽  
Recognition Phase ◽  
Prompt Diagnosis

Diabetic Retinopathy (DR) refers to the presence of typical retinal micro vascular lesions in persons with diabetics. When the disease is at the early state, a prompt diagnosis may help in preventing irreversible damages to the diabetic eye. If the exudates are closer to macula, then the situation is critical. Early detection can potentially reduce the risk of blind.  This paper proposes tool for the early detection of Diabetic Retinopathy using edge detection, algorithm kmeans in segmentation phase, invariant moments (Hu and Affine) and descriptor GIST in extraction phase. In the recognition phase, neural network is adopted. All tests are applied on database DIARETDB1.

scholarly journals Ship Target Detection Algorithm Based on Improved Faster R-CNN

Electronics ◽  
2019 ◽  
Vol 8 (9) ◽  
pp. 959 ◽  
Author(s):  
Qi ◽  
Li ◽  
Chen ◽  
Wang ◽  
Dong ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Target Detection ◽  
Texture Features ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Marine Transportation ◽  
Computational Speed ◽  
Neural Network Algorithm ◽  
Detection Search

Ship target detection has urgent needs and broad application prospects in military and marine transportation. In order to improve the accuracy and efficiency of the ship target detection, an improved Faster R-CNN (Faster Region-based Convolutional Neural Network) algorithm of ship target detection is proposed. In the proposed method, the image downscaling method is used to enhance the useful information of the ship image. The scene narrowing technique is used to construct the target regional positioning network and the Faster R-CNN convolutional neural network into a hierarchical narrowing network, aiming at reducing the target detection search scale and improving the computational speed of Faster R-CNN. Furthermore, deep cooperation between main network and subnet is realized to optimize network parameters after researching Faster R-CNN with subject narrowing function and selecting texture features and spatial difference features as narrowed sub-networks. The experimental results show that the proposed method can significantly shorten the detection time of the algorithm while improving the detection accuracy of Faster R-CNN algorithm.

A Comparative Study of Different Blood Vessel Detection on Retinal Images

2019 ◽  
Vol 11 (4) ◽  
Author(s):  
Wan Azani Mustafa ◽  
◽  
Ahmad Syauqi Mahmud ◽  
Muhammad Zaid Aihsan ◽  
M. Saifizi ◽  
...  
Keyword(s):  
Blood Vessel ◽  
Comparative Study ◽  
Retinal Images ◽  
Blood Vessel Detection ◽  
Vessel Detection

Impact of Globalisation on Pandemics: A comparative study on SARS and Covid-19 (Preprint)

2020 ◽  
Author(s):  
Johann Johann And Devika
Keyword(s):  
Comparative Analysis ◽  
Comparative Study ◽  
Descriptive Analysis ◽  
Qualitative Comparative Analysis ◽  
Global Scale ◽  
Global Level ◽  
Economic Stability ◽  
The Past ◽  
The World ◽  
Close Relationship

BACKGROUND Since November 2019, Covid - 19 has spread across the globe costing people their lives and countries their economic stability. The world has become more interconnected over the past few decades owing to globalisation and such pandemics as the Covid -19 are cons of that. This paper attempts to gain deeper understanding into the correlation between globalisation and pandemics. It is a descriptive analysis on how one of the factors that was responsible for the spread of this virus on a global scale is globalisation. OBJECTIVE - To understand the close relationship that globalisation and pandemics share. - To understand the scale of the spread of viruses on a global scale though a comparison between SARS and Covid -19. - To understand the sale of globalisation present during SARS and Covid - 19. METHODS A descriptive qualitative comparative analysis was used throughout this research. RESULTS Globalisation does play a significant role in the spread of pandemics on a global level. CONCLUSIONS - SARS and Covid - 19 were varied in terms of severity and spread. - The scale of globalisation was different during the time of SARS and Covid - 19. - Globalisation can be the reason for the faster spread in Pandemics.

Sign in / Sign up

Export Citation Format

Share Document