ICTACT Journal on Soft Computing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Skin Cancer Detection using Support Vector Machine with Histogram of Oriented Gradients Features


Affiliations
1 Department of Computer Science, Manonmaniam Sundaranar University, India
2 Department of Computer Science, Kamaraj College, India
     

   Subscribe/Renew Journal


This research work proposes an efficient skin cancer detection technique based on Support Vector Machine (SVM) with Histogram of Oriented Gradients (HOG) features. In this, skin cancer images from ISIC 2018 (International Skin Imaging Collaboration 2018) dataset are converted into gray scale and pre-processed using the median filter. The image resampling technique is then applied to rebalance the class distribution. The HOG features are extracted from these preprocessed images. After, the Radial Basis Function (RBF) kernel based SVM classification method is used to classify these extracted HOG features for detecting cancer class labels. These predicted class labels are compared with original labels for performing the evaluation. This proposed method is tested using and achieves 76% accuracy, 85% specificity, 84% precision, 76% recall and 75% F1-score.

Keywords

Skin Cancer, Detection, Machine Learning, Support Vector Machine, Histogram of Oriented Gradients.
Subscription Login to verify subscription
User
Notifications
Font Size

  • U. B. Ansari and T.Sarade, “Skin Cancer Detection using Image Processing”, International Research Journal of Engineering and Technology, Vol. 4, No. 4, pp. 2875-2881,2017.

  • P. Thsper and A. Singh, “A Survey of Lesion Detection using Dermoscopy Image Analysis”, Journal of Gujarat Research Society, Vol. 21, No. 6, pp. 129-143, 2019.

  • M.A. Shukran and N.S. Mariam, “Melanoma Skin Cancer Diagnosis Device using Image Processing Techniques”, International Journal of Recent Technology and Engineering, Vol. 7, No. 4, pp. 490-494, 2019.

  • S. Jaiswar and M. Kadri, “Skin Cancer Detection using Digital Image Processing”, International Journal of Scientific Engineering and Research, Vol. 3, No. 6, pp. 138-140, 2018.

  • A. Murugan and S. Anu, “Detection of Skin Cancer using SVM, Random Forest and kNN Classifiers”, Journal of Medical Systems, Vol. 1, No. 9, pp. 269-275, 2019.

  • C.F. Noel, “Skin Lesion Analysis Toward Melanoma Detection: A Challenge”, Proceedings of International Symposium on Biomedical Imaging, pp. 345-356, 2017.

  • M.M. Vijayalakshmi, “Melanoma Skin Cancer Detection using Image Processing and Machine Learning”, International Journal of Trend in Scientific Research and Development, Vol. 3, No. 4, pp. 1-14, 2019.

  • S.S. Mane and S.V. Shinde, “Different Techniques for Skin Cancer Detection using Dermoscopy Images”, International Journal of Computer Sciences and Engineering, Vol. 5, No. 12, pp. 159-163, 2017.

  • M.Z. Alom, “Skin Cancer Segmentation and Classification with NABLA-N and Inception Recurrent Residual Convolutional Networks”, Proceedings of International Conference on Computer Vision and Pattern Recognition, pp. 1-7, 2019.

  • A. Hecler, “Superior Skin Cancer Classification by the Combination of Human and Artificial Intelligence”, European Journal of Cancer, Vol. 120, pp. 114-121, 2019.

  • Y. Fujisawa and S. Inoue, “The Possibility of Deep Learning-Based, Computer-Aided Skin Cancer Classifiers”, Frontiers in Medicine, Vol. 6, pp. 1-19, 2019.

  • K. Muthukumar and P. Gowthaman, “GTCM Based Skin Lesion Melanoma Disease Detection Approach for Optimal Classification of Medical Images”, International Journal of Recent Technology and Engineering, Vol. 7, No. 3, pp. 1-12, 2019.

  • K. Munir and H. Elahi, “Detection Cancer Diagnosis using Deep Learning: A Bibliographic Review”, Cancers, Vol. 11, pp. 1-36,2019.

  • R. Kaur and Praveen Kumar, “An Enhanced and Automatic Skin Cancer Detection using K-Mean and PSO Technique”, International Journal of Innovative Technology and Exploring Engineering, Vol. 8, No. 9, pp. 634-639, 2019.

  • A. Dascalu and E.O. David, “Skin Cancer Detection by Deep Learning and Sound Analysis Algorithms: A Prospective Clinical Study of an Elementary Dermoscope”, EBioMedicine, Vol. 43, pp. 107-113, 2019.

  • E. Okur and M. Turkan, “A Survey on Automated Melanoma Detection”, Engineering Applications of Artificial Intelligence, Vol. 73, pp. 50-67, 2018.

  • D.A. Gavrilov and N.N. Shchelkunov, “Deep Learning based Skin Lesions Diagnosis”, Remote Sensing and Spatial Information Sciences, Vol. 2, No. 12, pp. 81-85, 2019.

  • I. Patel and S. Patel, “Dermoscopic Image Classification using Image Processing Technique for Melanoma Detection”, International Journal of Research in Advent Technology, Vol. 23, No. 2, pp. 97-103, 2019.

  • A. Masood and A. Al-Jumaily, “Computer Aided Diagnostic Support System for Skin Cancer: A Review of Techniques and Algorithms”, International Journal of Biomedical Imaging, Vol. 2013, pp. 1-22, 2013.

  • M. Hacibeyoglu and M.H. Ibrahim, “The Effect of Over-sampling and Undersampling Techniques in Medical Datasets”, Proceedings of International Conference on Advanced Technologies, Computer Engineering and Science, pp. 429-432, 2018.


Abstract Views: 341

PDF Views: 0




  • Skin Cancer Detection using Support Vector Machine with Histogram of Oriented Gradients Features

Abstract Views: 341  |  PDF Views: 0

Authors

G. Neela Krishna Babu
Department of Computer Science, Manonmaniam Sundaranar University, India
V. Joseph Peter
Department of Computer Science, Kamaraj College, India

Abstract


This research work proposes an efficient skin cancer detection technique based on Support Vector Machine (SVM) with Histogram of Oriented Gradients (HOG) features. In this, skin cancer images from ISIC 2018 (International Skin Imaging Collaboration 2018) dataset are converted into gray scale and pre-processed using the median filter. The image resampling technique is then applied to rebalance the class distribution. The HOG features are extracted from these preprocessed images. After, the Radial Basis Function (RBF) kernel based SVM classification method is used to classify these extracted HOG features for detecting cancer class labels. These predicted class labels are compared with original labels for performing the evaluation. This proposed method is tested using and achieves 76% accuracy, 85% specificity, 84% precision, 76% recall and 75% F1-score.

Keywords


Skin Cancer, Detection, Machine Learning, Support Vector Machine, Histogram of Oriented Gradients.

References