A novel melanoma detection model: adapted K-means clustering-based segmentation process

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
S. T. Sukanya ◽  
Jerine
Keyword(s):  
Feature Extraction ◽  
Clustering Algorithm ◽  
Normal Skin ◽  
Detection Model ◽  
Melanoma Detection ◽  
Proposed Model ◽  
Deep Convolution Neural Network ◽  
Local Vector ◽  
Conventional Models ◽  
Occurrence Matrix

AbstractObjectivesThe main intention of this paper is to propose a new Improved K-means clustering algorithm, by optimally tuning the centroids.MethodsThis paper introduces a new melanoma detection model that includes three major phase’s viz. segmentation, feature extraction and detection. For segmentation, this paper introduces a new Improved K-means clustering algorithm, where the initial centroids are optimally tuned by a new algorithm termed Lion Algorithm with New Mating Process (LANM), which is an improved version of standard LA. Moreover, the optimal selection is based on the consideration of multi-objective including intensity diverse centroid, spatial map, and frequency of occurrence, respectively. The subsequent phase is feature extraction, where the proposed Local Vector Pattern (LVP) and Grey-Level Co-Occurrence Matrix (GLCM)-based features are extracted. Further, these extracted features are fed as input to Deep Convolution Neural Network (DCNN) for melanoma detection.ResultsFinally, the performance of the proposed model is evaluated over other conventional models by determining both the positive as well as negative measures. From the analysis, it is observed that for the normal skin image, the accuracy of the presented work is 0.86379, which is 47.83% and 0.245% better than the traditional works like Conventional K-means and PA-MSA, respectively.ConclusionsFrom the overall analysis it can be observed that the proposed model is more robust in melanoma prediction, when compared over the state-of-art models.

A robust grey wolf-based deep learning for brain tumour detection in MR images

2020 ◽  
Vol 65 (2) ◽  
pp. 191-207
Author(s):  
A. Geetha ◽  
N. Gomathi
Keyword(s):  
Feature Extraction ◽  
Brain Tumour ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Grey Wolf ◽  
Detection Model ◽  
Proposed Model ◽  
Skull Stripping ◽  
Occurrence Matrix

AbstractIn recent times, the detection of brain tumours has become more common. Generally, a brain tumour is an abnormal mass of tissue where the cells grow uncontrollably and are apparently unregulated by the mechanisms that control cells. A number of techniques have been developed thus far; however, the time needed in a detecting brain tumour is still a challenge in the field of image processing. This article proposes a new accurate detection model. The model includes certain processes such as preprocessing, segmentation, feature extraction and classification. Particularly, two extreme processes such as contrast enhancement and skull stripping are processed under the initial phase. In the segmentation process, we used the fuzzy means clustering (FCM) algorithm. Both the grey co-occurrence matrix (GLCM) as well as the grey-level run-length matrix (GRLM) features were extracted in the feature extraction phase. Moreover, this paper uses a deep belief network (DBN) for classification. The optimized DBN concept is used here, for which grey wolf optimisation (GWO) is used. The proposed model is termed the GW-DBN model. The proposed model compares its performance over other conventional methods in terms of accuracy, specificity, sensitivity, precision, negative predictive value (NPV), the F1Score and Matthews correlation coefficient (MCC), false negative rate (FNR), false positive rate (FPR) and false discovery rate (FDR), and proves the superiority of the proposed work.

scholarly journals An Improved YOLOv2 for Vehicle Detection

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4272 ◽  
Author(s):  
Jun Sang ◽  
Zhongyuan Wu ◽  
Pei Guo ◽  
Haibo Hu ◽  
Hong Xiang ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Vehicle Detection ◽  
Training Dataset ◽  
Validation Dataset ◽  
Detection Accuracy ◽  
Extraction Ability ◽  
Detection Model ◽  
Vehicle Type ◽  
Proposed Model ◽  
Bounding Boxes

Vehicle detection is one of the important applications of object detection in intelligent transportation systems. It aims to extract specific vehicle-type information from pictures or videos containing vehicles. To solve the problems of existing vehicle detection, such as the lack of vehicle-type recognition, low detection accuracy, and slow speed, a new vehicle detection model YOLOv2_Vehicle based on YOLOv2 is proposed in this paper. The k-means++ clustering algorithm was used to cluster the vehicle bounding boxes on the training dataset, and six anchor boxes with different sizes were selected. Considering that the different scales of the vehicles may influence the vehicle detection model, normalization was applied to improve the loss calculation method for length and width of bounding boxes. To improve the feature extraction ability of the network, the multi-layer feature fusion strategy was adopted, and the repeated convolution layers in high layers were removed. The experimental results on the Beijing Institute of Technology (BIT)-Vehicle validation dataset demonstrated that the mean Average Precision (mAP) could reach 94.78%. The proposed model also showed excellent generalization ability on the CompCars test dataset, where the “vehicle face” is quite different from the training dataset. With the comparison experiments, it was proven that the proposed method is effective for vehicle detection. In addition, with network visualization, the proposed model showed excellent feature extraction ability.

scholarly journals A New Approach of Iris Detection and Recognition

2017 ◽  
Vol 7 (5) ◽  
pp. 2530
Author(s):  
Rubel Biswas ◽  
Jia Uddin ◽  
Md. Junayed Hasan
Keyword(s):  
Feature Extraction ◽  
Iris Recognition ◽  
Gabor Filter ◽  
Histogram Equalization ◽  
Support Vector ◽  
Second Phase ◽  
Neighborhood Structure ◽  
Feature Extraction Method ◽  
Detection Model ◽  
Proposed Model

This paper proposes an IRIS recognition and detection model for measuring the e-security. This proposed model consists of the following blocks: segmentation and normalization, feature encoding and feature extraction, and classification. In first phase, histogram equalization and canny edge detection is used for object detection. And then, Hough Transformation is utilized for detecting the center of the pupil of an IRIS. In second phase, Daugmen’s Rubber Sheet model and Log Gabor filter is used for normalization and encoding and as a feature extraction method GNS (Global Neighborhood Structure) map is used, finally extracted feature of GNS is feed to the SVM (Support Vector Machine) for training and testing. For our tested dataset, experimental results demonstrate 92% accuracy in real portion and 86% accuracy in imaginary portion for both eyes. In addition, our proposed model outperforms than other two conventional methods exhibiting higher accuracy.

scholarly journals Melanoma Detection in Dermoscopic Images Using a Cellular Automata Classifier

Computers ◽  
2022 ◽  
Vol 11 (1) ◽  
pp. 8
Author(s):  
Benjamín Luna-Benoso ◽  
José Cruz Martínez-Perales ◽  
Jorge Cortés-Galicia ◽  
Rolando Flores-Carapia ◽  
Víctor Manuel Silva-García
Keyword(s):  
Feature Extraction ◽  
Skin Cancer ◽  
Cellular Automata ◽  
Sensitivity And Specificity ◽  
Computer Aided Design ◽  
Cancer Type ◽  
Cad System ◽  
Melanoma Detection ◽  
Proposed Model ◽  
Global Patterns

Any cancer type is one of the leading death causes around the world. Skin cancer is a condition where malignant cells are formed in the tissues of the skin, such as melanoma, known as the most aggressive and deadly skin cancer type. The mortality rates of melanoma are associated with its high potential for metastasis in later stages, spreading to other body sites such as the lungs, bones, or the brain. Thus, early detection and diagnosis are closely related to survival rates. Computer Aided Design (CAD) systems carry out a pre-diagnosis of a skin lesion based on clinical criteria or global patterns associated with its structure. A CAD system is essentially composed by three modules: (i) lesion segmentation, (ii) feature extraction, and (iii) classification. In this work, a methodology is proposed for a CAD system development that detects global patterns using texture descriptors based on statistical measurements that allow melanoma detection from dermoscopic images. Image analysis was carried out using spatial domain methods, statistical measurements were used for feature extraction, and a classifier based on cellular automata (ACA) was used for classification. The proposed model was applied to dermoscopic images obtained from the PH2 database, and it was compared with other models using accuracy, sensitivity, and specificity as metrics. With the proposed model, values of 0.978, 0.944, and 0.987 of accuracy, sensitivity and specificity, respectively, were obtained. The results of the evaluated metrics show that the proposed method is more effective than other state-of-the-art methods for melanoma detection in dermoscopic images.

A Comparative Study of Various Techniques used for Melanoma Detection

2017 ◽  
Vol 7 (11) ◽  
pp. 44
Author(s):  
RAINA RAJU K ◽  
S. Swapna Kumar
Keyword(s):  
Feature Extraction ◽  
Skin Cancer ◽  
Normal Skin ◽  
Classification Methods ◽  
Segmentation Method ◽  
Fatal Disease ◽  
Melanoma Detection ◽  
Segmentation Methods ◽  
Different Types ◽  
Extraction Stage

Skin cancer is one of the most fatal disease. It is easily curable, when it is detected in its beginning stage. Early detection of melanoma through accurate techniques and innovative technologies has the greatest potential for decreasing mortality associated with this disease. Mainly there are four steps for detecting melanoma which includes preprocessing, segmentation, feature extraction and classification. The preprocessing stage will remove all the artifacts associated with the lesion. The exact boundaries of lesion are identified from normal skin through segmentation method. Feature extraction stage is used for calculating and obtaining different parameters of the lesion region. The final stage is to classify the lesion as benign or malignant.  In this paper different types of segmentation methods and classification methods are described. Both of these stages are accurately implemented to reach the final detection of the lesion.

Malware Detection Using Optimized Activation-Based Deep Belief Network: An Application on Internet of Things

2019 ◽  
Vol 18 (04) ◽  
pp. 1950042
Author(s):  
G. V. R. Sagar
Keyword(s):  
Feature Extraction ◽  
Feature Selection ◽  
Information Gain ◽  
Malware Detection ◽  
Activation Function ◽  
Deep Belief Network ◽  
Belief Network ◽  
Detection Model ◽  
Conventional Models ◽  
Extraction Phase

Number of malware detection models has been proposed recently, which still poses major limitations in terms of detection rate. Hence, to overcome this, this paper introduces a new malware detection model with three stages: Feature Extraction, Feature selection and Classification. In feature extraction phase, the Term Frequency-Inverse Document Frequency (TF-IDF) and Information gain (IG) features are extracted. More importantly, the IG feature is subjected with the Holoentropy evaluation. Following the feature extraction phase feature selection is performed using Principle Component Analysis (PCA). Finally, to do the classification process, Deep Belief Network (DBN) is used with optimized activation function. To work out this optimization scenario, this paper intends to propose a new hybrid algorithm that combines the concept of Lion Algorithm (LA) and Glowworm Swarm Algorithm (GSO). The performance of proposed Lion Updated GSO (LU-GSO) is compared over other conventional models with respect to various evaluation measures and proves the betterments over others. Through the performance analysis, it was observed that the proposed model attains high accuracy, which is 10.21%, 10.04%, 9.18% and 6.42% better than LA, GSO, GWO and PSO, respectively.

scholarly journals Kumaşlarda Hatayı Yerel Olarak Arayan Denetimsiz Bir Sistem

2020 ◽  
Vol 27 (120) ◽  
pp. 252-259
Author(s):  
Fatma Günseli YAŞAR ÇIKLAÇANDIR ◽  
Semih UTKU ◽  
Hakan ÖZDEMİR
Keyword(s):  
Feature Extraction ◽  
Success Rate ◽  
Clustering Algorithm ◽  
Computer Control ◽  
Control Unit ◽  
Gray Level ◽  
Success Rates ◽  
Feature Extraction Method ◽  
Weft Direction ◽  
Occurrence Matrix

Defects in the fabrics during or after weaving reduce the quality of them. With the development of technology, the frequency of the defects seen in fabrics has decreased, but still occurs. In the process of detecting fabric defects, the quality control unit tries to detect fabric defects. This process is both personal and time consuming, leading to costly and personal Errors. For this reason, solutions have been proposed in studies to carry out and automate the process under computer control. In this study, fabric images are divided into blocks of equal sizes to find out whether there are any defects in the fabrics. The features, which are Extracted by applying feature extraction method to each block of the image, are inserted into the K-means clustering algorithm. Two different methods are applied for feature extraction (gray level co-formation matrix and median difference) and their performances have been compared. The success rate of detecting the defect increases up to 97.99% when the gray level co-occurrence matrix is used. The success rate of detecting the defect increases up to 86.91% when the median differences are used. In addition, In addition, when the success rates are calculated separately for the defects in the weft direction and the defects in the warp direction, it is concluded that the defects in the weft direction are easier to find than the defects in the warp direction.

Automatic Lung Tuberculosis Detection Model Using Thorax Radiography Image

2021 ◽  
pp. 223-242
Author(s):  
Sudhir Kumar Mohapatra
Keyword(s):  
Textural Features ◽  
Lung Region ◽  
Statistical Features ◽  
Detection Model ◽  
Lung Tuberculosis ◽  
Disease Rates ◽  
Proposed Model ◽  
High Death ◽  
Occurrence Matrix ◽  
Public Datasets

Tuberculosis (TB) is a communal disease with high death and disease rates worldwide. The chest radiograph (CXR) is commonly used in diagnostic solutions for lung TB. Automatic computer-aided solutions to identify TB using CXRs and can advance the efficiency of the diagnostic of TB. In this chapter, an automatic TB detection model using CXR image is proposed. By identifying open issues include how detect the lung region automatically and what are the features, one can identify if a given CXR image is infected or normal using three public datasets such as Schengen, Montgomery Country (MC), and JSRT. The possible textural features of a lung object are obtained from the first-order and second-order gray level co-occurrence matrix (GLCM) statistical features. The performance of the proposed model was evaluated using accuracy, sensitivity, and specificity, and the model achieved AUC 91%, 62%, 71%, and 81% on Schengen, JSRT, MC, and combined datasets.

A Comparative Study of Various Techniques used for Melanoma Detection

2017 ◽  
Vol 7 (9) ◽  
pp. 52
Author(s):  
Raina Raju K ◽  
S. Swapna Kumar
Keyword(s):  
Feature Extraction ◽  
Skin Cancer ◽  
Normal Skin ◽  
Classification Methods ◽  
Segmentation Method ◽  
Fatal Disease ◽  
Melanoma Detection ◽  
Segmentation Methods ◽  
Different Types ◽  
Extraction Stage

Skin cancer is one of the most fatal disease. It is easily curable, when it is detected in its beginning stage. Early detection of melanoma through accurate techniques and innovative technologies has the greatest potential for decreasing mortality associated with this disease. Mainly there are four steps for detecting melanoma which includes preprocessing, segmentation, feature extraction and classification. The preprocessing stage will remove all the artifacts associated with the lesion. The exact boundaries of lesion are identified from normal skin through segmentation method. Feature extraction stage is used for calculating and obtaining different parameters of the lesion region. The final stage is to classify the lesion as benign or malignant.  In this paper different types of segmentation methods and classification methods are described. Both of these stages are accurately implemented to reach the final detection of the lesion.

scholarly journals RAPID TARGET DETECTION IN HIGH RESOLUTION REMOTE SENSING IMAGES USING YOLO MODEL

2018 ◽  
Vol XLII-3 ◽  
pp. 1915-1920 ◽  
Author(s):  
Z. Wu ◽  
X. Chen ◽  
Y. Gao ◽  
Y. Li
Keyword(s):  
Remote Sensing ◽  
Feature Extraction ◽  
High Resolution ◽  
Object Detection ◽  
Remote Sensing Images ◽  
Regression Problem ◽  
Extraction Region ◽  
Proposed Model ◽  
Deep Convolution Neural Network ◽  
Bounding Boxes

Object detection in high resolution remote sensing images is a fundamental and challenging problem in the field of remote sensing imagery analysis for civil and military application due to the complex neighboring environments, which can cause the recognition algorithms to mistake irrelevant ground objects for target objects. Deep Convolution Neural Network(DCNN) is the hotspot in object detection for its powerful ability of feature extraction and has achieved state-of-the-art results in Computer Vision. Common pipeline of object detection based on DCNN consists of region proposal, CNN feature extraction, region classification and post processing. YOLO model frames object detection as a regression problem, using a single CNN predicts bounding boxes and class probabilities in an end-to-end way and make the predict faster. In this paper, a YOLO based model is used for object detection in high resolution sensing images. The experiments on NWPU VHR-10 dataset and our airport/airplane dataset gain from GoogleEarth show that, compare with the common pipeline, the proposed model speeds up the detection process and have good accuracy.

Sign in / Sign up

Export Citation Format

Share Document