IRJET- Skin Disease Detection using Image Processing with Data Mining and Deep Learning
2 likes334 views
This document presents a skin disease detection method using image processing, data mining, and deep learning techniques. The proposed system uses a mobile application where users can upload images of affected skin areas. The images then undergo preprocessing like filtering and segmentation. Features are extracted from the images using techniques like 2D wavelet transform and GLCM. These features are classified using support vector machine (SVM) and convolutional neural network (CNN) models. The results show that CNN achieves higher overall accuracy compared to SVM, with accuracies of 99.1% for CNN vs 90.7% for SVM.
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 4366
classifier proved to be accurate and efficient in detecting
skin disease as compared to SVM Classifier.
FUTURE SCOPE
Future scopesofimprovementinpresentmethodologies are:
1. A common model should be adopted for the identification
of all types of skin diseases
2. Support for multilingualism to develop user-friendliness
3. To expand the multiplatform capability through an
introduction to IOS compatibility
ACKNOWLEDGEMENT
We owe our deep gratitude to our projectguidementor,Mrs.
Jayashree Hajgude (M.E.) Asst. Professor, VESIT, who took a
keen interest in our project work and guided us all along, till
the completion of the project by providing all the necessary
information to us. The success and final outcome of this
project required a lot of guidance and assistance from many
people and we are extremely privileged to have got this
pearls of wisdom shared with us by our mentor during the
course of this research.
REFERENCES
[1] Nisha Yadav, VirenderKumarNarang,Utpal shrivastava,
“Skin Diseases Detection Models using Image
Processing”, International Journal of Computer
Applications (0975 – 8887) Volume 137 – No.12, March
2016.
[2] Er.Shrinidhi Gindhi, Ansari Nausheen, Ansari Zoya,
Shaikh Ruhin, “An Innovative Approach forSkinDisease
Detection Using Image Processing and Data Mining”,
“International Journal of Innovative Research in
Computer and Communication Engineering (IJIRCCE)”,
April 2017.
[3] A.A.L.C.Amarathunga, E.P.W.C. Ellawala, G.N.
Abeysekara, C. R. J. Amalraj, “Expert System For
Diagnosis Of Skin Diseases”, “International Journal Of
Scientific & Technology Research Volume 4, (IJSTR)”,
January 2015.
[4] Amrutha Ravi, Sreejith S, “A Review on Brain Tumour
Detection Using Image Segmentation”, “International
Journal of Emerging Technology and Advanced
Engineering (IJETAE)”, June 2015.
[5] Aswin.R.B, J. Abdul Jaleel, Sibi Salim3, “Implementation
of ANN Classifier using MATLAB for Skin Cancer
Detection”, International Journal of Computer Science
and Mobile Computing (IJCSMC), December 2013.
[6] Rahat Yasir, Md. Ashiqur Rahman, Nova Ahmed,
“Dermatological Disease Detection Using Image
Processing And Artificial Neural Network”, 8th
International Conference On Electrical & Computer
Engineering, December 2014.
[7] Jainesh Rathod, Vishal Waghmode, AniruddhSodha,Dr.
Prasenjit Bhavathankar, “Diagnosis of skin diseases
using Convolutional Neural Networks”,IEEE,November
2018.
[8] [8] Yanhui Guo, Amira S. Ashour, Lei Si, Deep P
Mandalaywala, “Multiple Convolutional Neural Network
for Skin Dermoscopic Image Classification”, Institute of
Electrical and Electronic Engineers(IEEE), 2018.
[9] Aneta Kartali, Miloš Roglić, Marko Barjaktarović, Milica
Đurić-Jovičić, “Real-time Algorithms for Facial Emotion
Recognition: A Comparison of Different Approaches”,
Institute of Electrical and Electronic Engineers(IEEE),
November 2018.
[10] Archana Ajith, Vrinda Goel, Priyanka Vazirani, Dr. M.
Mani Roja, “Digital Dermatology Skin Disease Detection
Model using Image Processing”, Institute of Electrical
and Electronic Engineers(IEEE), 2017.](https://image.slidesharecdn.com/irjet-v6i4954-190718071601/85/IRJET-Skin-Disease-Detection-using-Image-Processing-with-Data-Mining-and-Deep-Learning-4-320.jpg)
IRJET- Skin Disease Detection using Image Processing with Data Mining and Deep Learning
- 1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 4363 Skin Disease Detection Using Image Processing with Data Mining and Deep Learning Mrs. Jayashree Hajgude1, Aishwarya Bhavsar2, Harsha Achara3, Nisha Khubchandani4 1Assistant Professor, Department of Information Technology, VESIT, Mumbai, Maharashtra, India 2,3,4Student, Department of Information Technology, VESIT, Mumbai, Maharashtra, India ---------------------------------------------------------------------***---------------------------------------------------------------------- Abstract - Skin diseases are hazardous and often contagious, especially melanoma, eczema, and impetigo. These skin diseases can be cured if detected early. The fundamental problem with it is, only an expert dermatologist is able to detect and classify such disease. Sometimes, the doctors also fail to correctly classify the disease and hence provide inappropriate medications to the patient. Our paper proposes a skin disease detection method based on Image Processing and Deep Learning Techniques. Our system is mobile based so can be used even in remote areas. The patientneedstoprovide the image of the infected area and it is given as an input to the application. Image Processing and Deep Learning techniques process it and deliver the most accurate output. In this paper, we present a comparison of two different approaches forreal- time skin disease detection algorithm based on accuracy. We have compared Support Vector Machine (SVM) and Convolutional NeuralNetworks(CNN). Theresultsofreal-time testing are presented. Keywords: Convolutional Neural Networks, Support VectorMachine,Eczema,Impetigo,Melanoma,Multilevel Thresholding, GLCM, 2D Wavelet Transform 1. INTRODUCTION Skin diseases have a serious impact on the psychological health of the patient. It can result in the loss of confidence and can even turn the patient into depression. Skin diseases can thus be fatal. It is a serious issue and cannotbeneglected but should be controlled. So it is necessary to identify the skin diseases at an early stage and preventitfromspreading. Human skin is unpredictable and almost a difficult terrain due to its complexity of jaggedness, lesion structures,moles, tone, the presence of dense hairs and other mitigating confusing features. Early detection of skin diseases can prove to be cost effective and can be accessible in remote areas. Identifying the infected area of skin and detecting the type of disease is useful for early awareness. In this paper, a detection system is proposed which enables the users to detect and recognize skin disease. In this system, the user has to provide the image of the affectedarea,theinputimage then undergoes preprocessing which involves filtering to remove the noise, segmentation to extract the lesion and then feature extraction to extract the features of the image and finally classifier to detect the affected area. For classification, Support Vector Machine (SVM) is used. Onthe other hand, deep learning algorithms have a competency to handle large datasets of complex computation hence, Convolutional Neural Network (CNN)isalsoimplementedas a part of research area to detect the affected area of skin. Comparison between SVM and CNN is also representedwith accuracy and confusion matrix. This paper proposed the solution for detecting the skin diseases viz. Melanoma, Impetigo and Eczema. 2. ARCHITECTURE Fig -1: Architecture of System A. User uploads image of the affected area using the mobile application B. Image processing unit receives uploaded image at the backend where following steps will be performed on image. a. Pre-processing of image b. Segmentation to extract skin lesion c. Feature Extraction to extract the features C. Classification model uses extracted features for detection of affected area. D. Result will be shown to the user in mobile application.
- 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 4364 3. IMPLEMENTATION METHODOLOGY Our proposed diagnosis system mainly consists of 2 main components 3.1 Image Processing Unit Image Acquisition: Images are acquired througha camera or locally stored device. Images are obtained from surveys and websites. Image Pre-processing: ForPre-processingofImage,Filtering is performed on image which is a non-linearprocessusedfor enhancing the overall image by preserving the edges of the image. Median filtering is used especially to reduce impulsive, salt-pepper noise. In this, each pixel value in an image is replaced with the median value of its neighboring pixels including itself. Image Segmentation: Image segmentation is performed to separate suspicious lesion from normal skin. This is implemented through MATLAB. For image segmentation, multilevel thresholding using Otsu method is performed where image is segmented into 3 levels using IM Quantize with 2 threshold level. The Segmented image is converted into a color image using label2rgb(). Feature Extraction: Unique features of skin lesion are extracted. Features are extracted using the 2D Wavelet Transform. Features extracted using the wavelet transform are Entropy, Mean, Mean Absolute Deviation, Median Absolute Deviation, Energy, Standard deviation,L1norm, L2 norm, Kurtosis, Skewness. Texture Features extractedusing GLCM are Contrast, Correlation, Energy and Homogeneity. Fig -2: Original Image Fig -3: Filtered Image Fig -4: Segmented Image 3.2 Data Mining Unit Data Mining is often described as the process of discovering patterns in large sets of data. For detection of skin disease, patterns obtained through the data are used. The data in the dataset comprises of visual features(featuresextractedfrom images using image processing). For skin disease classification, Support Vector Machine (SVM) classifier and Convolutional Neural Networks (CNN) classifier is used. Comparison of both the classifiers based on accuracy is shown with the help of confusion matrix. 3.2.1 Support Vector Machine Fig -5: SVM The support vector machine is a supervised learning model used for optimization. It is a unified framework in which different learning machine architecture can be generated through an appropriate choice of kernels.Theprincipal used in SVM is statistical and structural risk minimization. The SVM is already a ready-to-useavailableclassifierinMATLAB. After the feature extraction process, the extracted features are directly fed into the SVM classifier. The process involves two phases: Training Phase: 408 images of eczema,impetigo, melanoma, and others are used for training. Testing Phase: In this phase, test images are given to the classifier and the classifierusesknowledgegainedduring the training phase to classify the test image. 3.2.2 Convolutional Neural Network Fig -6: CNN Architecture
- 3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 4365 A convolutional neural network (CNN) is slightly invariance with the multilayer perceptron. A CNN can have a single convolution layer or it can contain multiple convolution layers. These layers can be interconnected or pooled together. A convolution operation is performed on the input and then the results are passed to the further layers. Thus, due to this, the network can be deep but will contain only a few parameters. Due to this property, a convolutional neural network shows effective results in image and video recognition, natural language processing,andrecommender systems. Convolutional neural networks give accurate results in semantic parsing and paraphrasedetection.Thisis the main reason to use CNN for skin disease detection. After experimenting with SVM classifier, CNN classifier is implemented to train and test skin disease images. Unlike SVM classifier, there is no need to perform processing steps on image. In SVM classifier, an image needs to be processed using image processing unit and then given for the classification toSVMclassifier.CNN classifierisimplemented in such a way where there is no need of image processing module. CNN classifier is a layered architecture where multiple layers perform various operations to train and test the image data. In this proposed solution, 408 images are given to CNN classifier for trainingwhereimagesfortraining are given to Convolution2dLayer. This is the first layer to extract the features from the input image. This layer applies a convolution operation and gives the resulttothenextlayer and applies convolutional filterstotheinput.Itcomputesthe dot product of the input and weights and then adds a bias term. Then ReluLayer is introduced which is Rectified linear Unit Layer for handling nonlinearity in the network. MaxPooling Layer reducesthedimensionalityofimageandis used to divide the input into rectangular regions and computes the maxima of each region. After this operation, FullyConnected Layer multiplies an input with weight matrix, adds bias vector and it is responsible for creating a model for classification layer by applying Softmax Layer. Softmax Layer is a logistic activation function which is used for multiclass classification. Finally Classification Layer will detect the affected area of image and gives the output. 4. RESULTS Disease SVM CNN Eczema 94% 100% Impetigo 100% 98% Melanoma 99% 99.4% No Disease 52% 98.8% Overall Accuracy 90.7% 99.1% Table -1: Accuracy Table It is observed from above table that CNN Algorithm has near perfect accuracy in detecting skin diseases. The confusion matrix shows the percentage of error and accuracy in classification. It also shows corrected and uncorrected results, true positives, false negatives andnumberofclasses. Fig -7: SVM Confusion Matrix Fig -8: CNN Confusion Matrix 5. CONCLUSION This Paper gives the solution for detecting 3 skin diseasesi.e melanoma, eczema, impetigo using Image Processing with SVM classifier and CNN classifier. ComparisonbetweenCNN and SVM Classifier is done with the help of the confusion matrix and the detailed table showing the accuracy of both the classifiers. According to the result obtained, CNN
- 4. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 4366 classifier proved to be accurate and efficient in detecting skin disease as compared to SVM Classifier. FUTURE SCOPE Future scopesofimprovementinpresentmethodologies are: 1. A common model should be adopted for the identification of all types of skin diseases 2. Support for multilingualism to develop user-friendliness 3. To expand the multiplatform capability through an introduction to IOS compatibility ACKNOWLEDGEMENT We owe our deep gratitude to our projectguidementor,Mrs. Jayashree Hajgude (M.E.) Asst. Professor, VESIT, who took a keen interest in our project work and guided us all along, till the completion of the project by providing all the necessary information to us. The success and final outcome of this project required a lot of guidance and assistance from many people and we are extremely privileged to have got this pearls of wisdom shared with us by our mentor during the course of this research. REFERENCES [1] Nisha Yadav, VirenderKumarNarang,Utpal shrivastava, “Skin Diseases Detection Models using Image Processing”, International Journal of Computer Applications (0975 – 8887) Volume 137 – No.12, March 2016. [2] Er.Shrinidhi Gindhi, Ansari Nausheen, Ansari Zoya, Shaikh Ruhin, “An Innovative Approach forSkinDisease Detection Using Image Processing and Data Mining”, “International Journal of Innovative Research in Computer and Communication Engineering (IJIRCCE)”, April 2017. [3] A.A.L.C.Amarathunga, E.P.W.C. Ellawala, G.N. Abeysekara, C. R. J. Amalraj, “Expert System For Diagnosis Of Skin Diseases”, “International Journal Of Scientific & Technology Research Volume 4, (IJSTR)”, January 2015. [4] Amrutha Ravi, Sreejith S, “A Review on Brain Tumour Detection Using Image Segmentation”, “International Journal of Emerging Technology and Advanced Engineering (IJETAE)”, June 2015. [5] Aswin.R.B, J. Abdul Jaleel, Sibi Salim3, “Implementation of ANN Classifier using MATLAB for Skin Cancer Detection”, International Journal of Computer Science and Mobile Computing (IJCSMC), December 2013. [6] Rahat Yasir, Md. Ashiqur Rahman, Nova Ahmed, “Dermatological Disease Detection Using Image Processing And Artificial Neural Network”, 8th International Conference On Electrical & Computer Engineering, December 2014. [7] Jainesh Rathod, Vishal Waghmode, AniruddhSodha,Dr. Prasenjit Bhavathankar, “Diagnosis of skin diseases using Convolutional Neural Networks”,IEEE,November 2018. [8] [8] Yanhui Guo, Amira S. Ashour, Lei Si, Deep P Mandalaywala, “Multiple Convolutional Neural Network for Skin Dermoscopic Image Classification”, Institute of Electrical and Electronic Engineers(IEEE), 2018. [9] Aneta Kartali, Miloš Roglić, Marko Barjaktarović, Milica Đurić-Jovičić, “Real-time Algorithms for Facial Emotion Recognition: A Comparison of Different Approaches”, Institute of Electrical and Electronic Engineers(IEEE), November 2018. [10] Archana Ajith, Vrinda Goel, Priyanka Vazirani, Dr. M. Mani Roja, “Digital Dermatology Skin Disease Detection Model using Image Processing”, Institute of Electrical and Electronic Engineers(IEEE), 2017.