NON INTERACTIVE GRABCUT BASED SEGMENTATION WITH DEEP LEARNING MODEL FOR SKIN LESION DETECTION AND CLASSIFICATION
Journal: International Journal of Advanced Research in Engineering and Technology (IJARET) (Vol.11, No. 10)Publication Date: 2020-10-31
Authors : A. Arulmurugan N. Hema Rajini G.Pradeep;
Page : 1275-1293
Keywords : Deep transfer learning; Dermoscopic images; Skin lesion; Image classification; Segmentation.;
Abstract
Skin lesion segmentation and classification are crucial processes due to the visual resemblance among the benign and melanoma lesions. Robust and effective skin lesion classification is a major task to attain proficient skin lesion diagnosis. Because of the unclear boundaries among the tumor and skin, the segmentation of skin lesion becomes a tedious task. This paper presents a new deep transfer learning (DTL) based segmentation and classification model for diagnosing skin lesions from dermoscopic images. The presented model initially performs bilateral filtering based preprocessing to discard the noise exist in the image. In addition, Noninteractive GrabCut Algorithm is applied to perform the image segmentation process. Afterward, DTL model based on VGGNet-19 Network is utilized to extract a useful set of feature vectors. At last, extreme gradient boosting (XGBoost) and Linear Discriminant Analysis (LDA) models are used to identify the different class labels of skin lesions. For validating the proficient diagnosis outcome of the proposed model, a series of simulations were performed to exhibit the supreme performance of the presented method. From the obtained set of simulations, it is apparent that the VGG19-XGBoost model has outperformed the compared methods with the maximum sensitivity of 95.08%, specificity of 99.17%, and accuracy of 98.65%.
Other Latest Articles
- Determinants of Level of Accessibility to Microfinance among Loan beneficiaries of some Commercial Crop Production Farmers in Niger state, Nigeria
- Investigating Pesticide Use and Management in King Orange (Citrus nobilis) Farming in Vung Liem District, Vinh Long Province, Vietnam
- Assessment of farmers’ vulnerability to climate variability and extreme events: Evidence from dry Kitui, Kenya
- Study of Some Parameters Influencing the post mortem PH of Carcass's muscles of Dromedaries Slaughtered at the Touggourt Slaughterhouse. Algeria
- Why is China's the Belt One Road Initiative successful? — Lessons from the Cooperation with the Five Central Asia Countries
Last modified: 2021-02-22 13:51:11