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.

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 Skin lesion segmentation method for dermoscopic images with convolutional neural networks and semantic segmentation

2021 ◽  
Vol 45 (1) ◽  
pp. 122-129
Author(s):  
Dang N.H. Thanh ◽  
Nguyen Hoang Hai ◽  
Le Minh Hieu ◽  
Prayag Tiwari ◽  
V.B. Surya Prasath
Keyword(s):  
Skin Cancer ◽  
Skin Lesion ◽  
Semantic Segmentation ◽  
Segmentation Method ◽  
Lesion Segmentation ◽  
Computing Systems ◽  
Segmentation Methods ◽  
Dermoscopic Image ◽  
Better Than

Melanoma skin cancer is one of the most dangerous forms of skin cancer because it grows fast and causes most of the skin cancer deaths. Hence, early detection is a very important task to treat melanoma. In this article, we propose a skin lesion segmentation method for dermoscopic images based on the U-Net architecture with VGG-16 encoder and the semantic segmentation. Base on the segmented skin lesion, diagnostic imaging systems can evaluate skin lesion features to classify them. The proposed method requires fewer resources for training, and it is suitable for computing systems without powerful GPUs, but the training accuracy is still high enough (above 95 %). In the experiments, we train the model on the ISIC dataset – a common dermoscopic image dataset. To assess the performance of the proposed skin lesion segmentation method, we evaluate the Sorensen-Dice and the Jaccard scores and compare to other deep learning-based skin lesion segmentation methods. Experimental results showed that skin lesion segmentation quality of the proposed method are better than ones of the compared methods.

Identification of Authenticity and Nominal Value of Indonesia Banknotes Using Fuzzy KNearest Neighbor Method

2019 ◽  
Vol 6 (1) ◽  
pp. 32-37
Author(s):  
Ricky Ramadhan ◽  
Jayanti Yusmah Sari ◽  
Ika Purwanti Ningrum
Keyword(s):  
Feature Extraction ◽  
Nearest Neighbor ◽  
Threshold Value ◽  
Segmentation Method ◽  
K Nearest Neighbor ◽  
Real Money ◽  
The Public ◽  
Average Accuracy ◽  
Segmentation Methods ◽  
The Government

The existence of counterfeit money is often troubling the public. The solution given by the government to be careful of counterfeit money is by means of 3D (seen, touched and looked at). However, this step has not been perfectly able to distinguish real money and fake money. So there is a need for a system to help detect the authenticity of money. Therefore, in this study a system was designed that can detect the authenticity of rupiah and its nominal value. For data acquisition, this system uses detection boxes, ultraviolet lights and smartphone cameras. As for feature extraction, this system uses segmentation methods. The segmentation method based on the threshold value is used to obtain an invisible ink pattern which is a characteristic of real money along with the nominal value of the money. The feature is then used in the stage of detection of money authenticity using FKNN (Fuzzy K-Nearest Neighbor) method. From 24 test data, obtained an average accuracy of 96%. This shows that the system built can detect the authenticity and nominal value of the rupiah well.

Learning Subspace Classifiers and Error-Corrective Feature Extraction

1998 ◽  
Vol 12 (04) ◽  
pp. 423-436
Author(s):  
Jorma Laaksonen ◽  
Erkki Oja
Keyword(s):  
Feature Extraction ◽  
Adaptive Learning ◽  
Classification Performance ◽  
Classification Methods ◽  
Subspace Methods ◽  
Statistical Pattern ◽  
Extraction Stage ◽  
Adaptive Feature Extraction ◽  
Modified Formula ◽  
Selection Of

Subspace methods are a powerful class of statistical pattern classification algorithms. The subspaces form semiparametric representations of the pattern classes in the form of principal components. In this sense, subspace classification methods are an application of classical optimal data compression techniques. Additionally, the subspace formalism can be given a neural network interpretation. There are learning versions of the subspace classification methods, in which error-driven learning procedures are applied to the subspaces in order to reduce the number of misclassified vectors. An algorithm for iterative selection of the subspace dimensions is presented in this paper. Likewise, a modified formula for calculating the projection lengths in the subspaces is investigated. The principle of adaptive learning in subspace methods can further be applied to feature extraction. In our work, we have studied two adaptive feature extraction schemes. The adaptation process is directed by errors occurring in the classifier. Unlike most traditional classifier models which take the preceding feature extraction stage as given, this scheme allows for reducing the loss of information in the feature extraction stage. The enhanced overall classification performance resulting from the added adaptivity is demonstrated with experiments in which recognition of handwritten digits has been used as an exemplary application.

scholarly journals An Efficient Convolutional Neural Network Model Combined with Attention Mechanism for Inverse Halftoning

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1574
Author(s):  
Linhao Shao ◽  
Erhu Zhang ◽  
Mei Li
Keyword(s):  
Feature Extraction ◽  
Image Features ◽  
Attention Mechanism ◽  
Discriminative Ability ◽  
Halftone Image ◽  
Multi Stage ◽  
Different Types ◽  
Inverse Halftoning ◽  
Extraction Stage ◽  
Halftone Images

Inverse halftoning acting as a special image restoration problem is an ill-posed problem. Although it has been studied in the last several decades, the existing solutions can’t restore fine details and texture accurately from halftone images. Recently, the attention mechanism has shown its powerful effects in many fields, such as image processing, pattern recognition and computer vision. However, it has not yet been used in inverse halftoning. To better solve the problem of detail restoration of inverse halftoning, this paper proposes a simple yet effective deep learning model combined with the attention mechanism, which can better guide the network to remove noise dot-patterns and restore image details, and improve the network adaptation ability. The whole model is designed in an end-to-end manner, including feature extraction stage and reconstruction stage. In the feature extraction stage, halftone image features are extracted and halftone noises are removed. The reconstruction stage is employed to restore continuous-tone images by fusing the feature information extracted in the first stage and the output of the residual channel attention block. In this stage, the attention block is firstly introduced to the field of inverse halftoning, which can make the network focus on informative features and further enhance the discriminative ability of the network. In addition, a multi-stage loss function is proposed to accelerate the network optimization, which is conducive to better reconstruction of the global image. To demonstrate the generalization performance of the network for different types of halftone images, the experiment results confirm that the network can restore six different types of halftone image well. Furthermore, experimental results show that our method outperforms the state-of-the-art methods, especially in the restoration of details and textures.

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.

scholarly journals Decision Support System Analysis for Malignant Melanoma Detection

2019 ◽  
Vol 8 (4) ◽  
pp. 7365-7369
Keyword(s):  
Skin Cancer ◽  
Malignant Melanoma ◽  
System Analysis ◽  
Human Beings ◽  
Cancer Prediction ◽  
Melanoma Cancer ◽  
Melanoma Detection ◽  
Main Challenge ◽  
Different Types ◽  
Biopsy Method

One of the most deadly dangerous disease is cancer which is among human beings. Skin cancer is of different types that is found recently among humans. Melanoma is one such type of skin cancer which causes majority of death rate. Biopsy method leads to conventional clinical diagnosis for detection of melanoma. The study in this paper presents different benchmarking techniques for melanoma prediction and evaluation. The main challenge is detection of malignant melanoma, which is found to have asymmetrical, irregular borders, notched edges and colour variations. The various stages of skin cancer prediction were analyzed in this paper. A detailed study on various techniques of medical image processing as applied to melanoma images for past years which need the more attention which is discussed here. The techniques and methods that exit are helpful in each of these process are evaluated and summarized. The paper aims at presenting an analysis on to identify on investigation efforts required to group and classify the sub categories available in the literature and to provide a summary of all the available methods for identification of melanoma cancer.

scholarly journals Hyperspectral Image Classification Using Unsupervised Learning Algorithms

2021 ◽  
Author(s):  
Wafa Fatima ◽  
Iqra Ejaz
Keyword(s):  
Feature Extraction ◽  
Hyperspectral Image ◽  
Spectral Feature ◽  
Unsupervised Classification ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Classification Algorithms ◽  
Classification Methods ◽  
Hyperspectral Image Classification ◽  
Different Types

Hyperspectral image (HSI) classification is a mechanism of analyzing differentiated land cover in remotely sensed hyperspectral images. In the last two decades, a number of different types of classification algorithms have been proposed for classifying hyperspectral data. These algorithms include supervised as well as unsupervised methods. Each of these algorithms has its own limitations. In this research, three different types of unsupervised classification methods are used to classify different datasets i-e Pavia Center, Pavia University, Cuprite, Moffett Field. The main objective is to assess the performance of all three classifiers K-Means, Spectral Matching, and Abundance Mapping, and observing their applicability on different datasets. This research also includes spectral feature extraction for hyperspectral datasets.

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.

scholarly journals The Study of Recognition Methods Based on Wavelet Transform for Melanoma Detection

2020 ◽  
pp. 46-61
Author(s):  
Maen Almarei ◽  
Khaled Daqrouq
Keyword(s):  
Feature Extraction ◽  
Wavelet Transform ◽  
Skin Cancer ◽  
Probabilistic Neural Network ◽  
Combination Method ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Cancer Type ◽  
Melanoma Detection ◽  
The World

Skin cancer is one of the most cancers occurring in the world. Malignant melanoma is the most skin cancer type causing death around the world. Melanoma could be treated 100% if they are detected at earlier stages. In this paper, various melanoma detection systems were reviewed according to the year of publishing. All reviewed papers were based on feature extraction methods using wavelet transform (WT) in its two versions: Discrete wavelet transform (DWT), and wavelet packet transform (WPT) for melanoma recognition. Our methodology that was based on the WPT feature extraction and probabilistic neural network (PNN) was used for comparison. The ISIC database was used for differentiating between malignant (1110 images) and benign (1110 image) tumors. A (75% training /25% testing) verification system was applied. Many experiments were conducted using different parameters for each experiment. The support vector machine classifier (SVM) was the most common classifier combined with various types of wavelet features that have appeared in many kinds of literature during the last two decades, which achieved relatively the best accuracy ranged between [76% - 98.29%]. In this paper, our combination method of the WPT and entropy was proposed and evaluated. Several experiments were conducted for testing. A comparison manner was used for discussion of the investigation. The proposed method was an excellent detection method for melanoma regarding the complexity, where no preprocessing stage was conducted.

Sign in / Sign up

Export Citation Format

Share Document