scholarly journals Retinal Blood Vessel Segmentation Using Hybrid Features and Multi-Layer Perceptron Neural Networks

Symmetry ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 894 ◽  
Author(s):  
Nasser Tamim ◽  
M. Elshrkawey ◽  
Gamil Abdel Azim ◽  
Hamed Nassar
Keyword(s):  
Blood Vessel ◽  
Performance Metrics ◽  
Feature Vector ◽  
Disease Diagnosis ◽  
Processing Technique ◽  
Ocular Disease ◽  
Multi Layer Perceptron ◽  
Phase Congruency ◽  
Hybrid Features ◽  
Local Intensity

Segmentation of retinal blood vessels is the first step for several computer aided-diagnosis systems (CAD), not only for ocular disease diagnosis such as diabetic retinopathy (DR) but also of non-ocular disease, such as hypertension, stroke and cardiovascular diseases. In this paper, a supervised learning-based method, using a multi-layer perceptron neural network and carefully selected vector of features, is proposed. In particular, for each pixel of a retinal fundus image, we construct a 24-D feature vector, encoding information on the local intensity, morphology transformation, principal moments of phase congruency, Hessian, and difference of Gaussian values. A post-processing technique depending on mathematical morphological operators is used to optimise the segmentation. Moreover, the selected feature vector succeeded in outfitting the symmetric features that provided the final blood vessel probability as a binary map image. The proposed method is tested on three known datasets: Digital Retinal Image for Extraction (DRIVE), Structure Analysis of the Retina (STARE), and CHASED_DB1 datasets. The experimental results, both visual and quantitative, testify to the robustness of the proposed method. This proposed method achieved 0.9607, 0.7542, and 0.9843 in DRIVE, 0.9632, 0.7806, and 0.9825 on STARE, 0.9577, 0.7585 and 0.9846 in CHASE_DB1, with respectable accuracy, sensitivity, and specificity performance metrics. Furthermore, they testify that the method is superior to seven similar state-of-the-art methods.

NSCT and focus measure optimization based multi-focus image fusion

2021 ◽  
pp. 1-13
Author(s):  
N. Aishwarya ◽  
C. BennilaThangammal ◽  
N.G. Praveena
Keyword(s):  
Simulation Analysis ◽  
Structural Information ◽  
Research Area ◽  
Processing Technique ◽  
The Novel ◽  
Phase Congruency ◽  
Focus Measure ◽  
Fused Image ◽  
Focus Image ◽  
Image Pairs

Getting a complete description of scene with all the relevant objects in focus is a hot research area in surveillance, medicine and machine vision applications. In this work, transform based fusion method called as NSCT-FMO, is introduced to integrate the image pairs having different focus features. The NSCT-FMO approach basically contains four steps. Initially, the NSCT is applied on the input images to acquire the approximation and detailed structural information. Then, the approximation sub band coefficients are merged by employing the novel Focus Measure Optimization (FMO) approach. Next, the detailed sub-images are combined using Phase Congruency (PC). Finally, an inverse NSCT operation is conducted on synthesized sub images to obtain the initial synthesized image. To optimize the initial fused image, an initial decision map is first constructed and morphological post-processing technique is applied to get the final map. With the help of resultant map, the final synthesized output is produced by the selection of focused pixels from input images. Simulation analysis show that the NSCT-FMO approach achieves fair results as compared to traditional MST based methods both in qualitative and quantitative assessments.

scholarly journals An Optimal Feature Parameter Set Based on Gated Recurrent Unit Recurrent Neural Networks for Speech Segment Detection

2020 ◽  
Vol 10 (4) ◽  
pp. 1273 ◽  
Author(s):  
Özlem BATUR DİNLER ◽  
Nizamettin AYDIN
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Feature Vector ◽  
Processing Parameters ◽  
Speech Segmentation ◽  
Hybrid Features ◽  
Speech Segment ◽  
Experimental Findings ◽  
Gated Recurrent Unit ◽  
Optimal Feature

Speech segment detection based on gated recurrent unit (GRU) recurrent neural networks for the Kurdish language was investigated in the present study. The novelties of the current research are the utilization of a GRU in Kurdish speech segment detection, creation of a unique database from the Kurdish language, and optimization of processing parameters for Kurdish speech segmentation. This study is the first attempt to find the optimal feature parameters of the model and to form a large Kurdish vocabulary dataset for a speech segment detection based on consonant, vowel, and silence (C/V/S) discrimination. For this purpose, four window sizes and three window types with three hybrid feature vector techniques were used to describe the phoneme boundaries. Identification of the phoneme boundaries using a GRU recurrent neural network was performed with six different classification algorithms for the C/V/S discrimination. We have demonstrated that the GRU model has achieved outstanding speech segmentation performance for characterizing Kurdish acoustic signals. The experimental findings of the present study show the significance of the segment detection of speech signals by effectively utilizing hybrid features, window sizes, window types, and classification models for Kurdish speech.

scholarly journals Fire-Fly Algorithm Based ANN Classification of Power Transformer Faults

2020 ◽  
Vol 9 (4) ◽  
pp. 1880-1884
Keyword(s):  
Wavelet Transforms ◽  
Performance Metrics ◽  
Feature Vector ◽  
Learning Algorithm ◽  
Power Transformer ◽  
Gas Analysis ◽  
Phase Detection ◽  
Double Line ◽  
Waveform Data

Monitoring and estimating the states of the transformer during faulted phase condition is essential to continuity of supply. Varied techniques are proposed for faulted phase detection to improve condition assessment. In this paper, we propose a novel method to detect and classify power transformer faults using wavelet transform Multi Resolution Analysis (MRA) as feature extracted parameter vector and Fire-Fly Algorithm (FFA) based Artificial Neural network training as classification method. The observed Dissolved Gas Analysis (DGA) waveform data is analyzed with wavelet transforms (WT) to identify abnormalities which is supported by MRA. In MRA, the current, voltage and temperature of winding and oil are decomposed into high and low frequency components. The magnitude of components, signifies the feature vector, gives a detection criteria. After detecting feature vector, dominant coefficients of WT can be used to train the ANN with FFA based learning algorithm. Different types of faults are created on transformer such as Single Line-Ground (SLG), Line-Line (LL), Double Line-Ground LLG, Three phase fault (LLLG) for the analysis using WT and ANN. The detection and classification of the fault signal are executed and examined in different winding location and different fault conditions. Finally, the presented precise model recognizes the faults based on performance metrics with high classification accuracy for various classes.

scholarly journals Multi-Layer Perceptron Neural Network Model Development for Chili Pepper Disease Diagnosis Using Filter and Wrapper Feature Selection Methods

2021 ◽  
Vol 11 (5) ◽  
pp. 7714-7719
Author(s):  
S. Nuanmeesri ◽  
W. Sriurai
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Information Gain ◽  
Disease Diagnosis ◽  
Chili Pepper ◽  
Growth Stages ◽  
Multi Layer Perceptron ◽  
Selection Methods ◽  
Diagnosis Model ◽  
Wrapper Feature Selection

The goal of the current study is to develop a diagnosis model for chili pepper disease diagnosis by applying filter and wrapper feature selection methods as well as a Multi-Layer Perceptron Neural Network (MLPNN). The data used for developing the model include 1) types, 2) causative agents, 3) areas of infection, 4) growth stages of infection, 5) conditions, 6) symptoms, and 7) 14 types of chili pepper diseases. These datasets were applied to the 3 feature selection techniques, including information gain, gain ratio, and wrapper. After selecting the key features, the selected datasets were utilized to develop the diagnosis model towards the application of MLPNN. According to the model’s effectiveness evaluation results, estimated by 10-fold cross-validation, it can be seen that the diagnosis model developed by applying the wrapper method along with MLPNN provided the highest level of effectiveness, with an accuracy of 98.91%, precision of 98.92%, and recall of 98.89%. The findings showed that the developed model is applicable.

scholarly journals Cancer Diagnosis of Microscopic Biopsy Images Using a Social Spider Optimisation-Tuned Neural Network

Diagnostics ◽  
2021 ◽  
Vol 12 (1) ◽  
pp. 11
Author(s):  
Prasanalakshmi Balaji ◽  
Kumarappan Chidambaram
Keyword(s):  
Neural Network ◽  
Performance Metrics ◽  
Disease Diagnosis ◽  
Medical Community ◽  
Diagnostic Tools ◽  
Clinical Cancer Research ◽  
Cancer Disease ◽  
Social Spider ◽  
Life Threatening ◽  
Sensitivity Specificity

One of the most dangerous diseases that threaten people is cancer. If diagnosed in earlier stages, cancer, with its life-threatening consequences, has the possibility of eradication. In addition, accuracy in prediction plays a significant role. Hence, developing a reliable model that contributes much towards the medical community in the early diagnosis of biopsy images with perfect accuracy comes to the forefront. This article aims to develop better predictive models using multivariate data and high-resolution diagnostic tools in clinical cancer research. This paper proposes the social spider optimisation (SSO) algorithm-tuned neural network to classify microscopic biopsy images of cancer. The significance of the proposed model relies on the effective tuning of the weights of the neural network classifier by the SSO algorithm. The performance of the proposed strategy is analysed with performance metrics such as accuracy, sensitivity, specificity, and MCC measures, and the attained results are 95.9181%, 94.2515%, 97.125%, and 97.68%, respectively, which shows the effectiveness of the proposed method for cancer disease diagnosis.

scholarly journals Optical Disc and Blood Vessel Segmentation in Retinal Fundus Images

2019 ◽  
Vol 8 (3) ◽  
pp. 67
Author(s):  
Amira B. Sallow ◽  
Hawkar Kh. Shaikha
Keyword(s):  
Blood Vessel ◽  
Template Matching ◽  
Cross Correlation ◽  
Region Of Interest ◽  
Processing Technique ◽  
Image Processing Technique ◽  
Original Image ◽  
Matching Algorithm ◽  
A New Technique ◽  
Retinal Fundus

Segmentation of optical disk (OD) and blood vessel is one of the significant steps in automatic diabetic retinopathy (DR) detecting. In this paper, a new technique is presented for OD segmentation that depends on the histogram template matching algorithm and OD size. In addition, Kirsch method is used for Blood Vessel (BV) segmentation which is one of the popular methods in the edge detection and image processing technique. The template matching algorithm is used for finding the center of the OD. In this step, the histogram of each RGB (Red, Green, and Blue) planes are founded and then the cross-correlation is founded between the template and the original image, OD location is the point with maximum cross-correlation between them. The OD size varies according to the camera field of sight and the resolution of the original image. The rectangle size of OD is not the same for various databases, the estimated size for DRIVE, STARE, DIARTDB0, and DIARTDB1 are 80×80, 140×140, 190×190, and 190×190 respectively. After finding the OD center and rectangle size of OD, a binary mask is created with Region of Interest (ROI) for segmenting the OD. The DIARTDB0 is used to evaluate the proposed technique, the result is robust and vital with an accuracy of 96%.

scholarly journals A Simple Blood Vessel Detection on Retinal Image Using Image Processing Technique

2021 ◽  
Vol 1874 (1) ◽  
pp. 012035
Author(s):  
Siti Nursyafiqah ◽  
Wan Azani Mustafa ◽  
Syed Zulkarnain Syed Idrus ◽  
Mohd Aminudin Jamlos
Keyword(s):  
Image Processing ◽  
Blood Vessel ◽  
Retinal Image ◽  
Processing Technique ◽  
Image Processing Technique ◽  
Blood Vessel Detection ◽  
Vessel Detection

scholarly journals IRIS IMAGE KEY POINTS DESCRIPTORS BASED ON PHASE CONGRUENCY

2019 ◽  
Vol XLII-2/W12 ◽  
pp. 167-171 ◽  
Author(s):  
M. А. Protsenko ◽  
E. A. Pavelyeva
Keyword(s):  
Feature Vector ◽  
Image Features ◽  
Features Extraction ◽  
New Method ◽  
Phase Congruency ◽  
Hermite Transform ◽  
Iris Image ◽  
Euclidean Metric ◽  
Key Points ◽  
Concentric Circles

<p><strong>Abstract.</strong> In this article the new method for iris image features extraction based on phase congruency is proposed. Iris image key points are calculated using the convolutions with Hermite transform functions. At each key point the feature vector characterizing this key point is obtained based on the phase congruency method. Iris key point descriptor contains phase congruency values at points located on concentric circles around the key point. To compare the key points, Euclidean metric between the key points descriptors is calculated. The distance between the iris images is equal to the number of matched iris key points. The proposed method was tested using the images from CASIA−IrisV4−Interval database and the value of EER&amp;thinsp;=&amp;thinsp;0.226% was obtained.</p>

Sign in / Sign up

Export Citation Format

Share Document