Skin Lesion Detection and Classification Using Transfer Learning
Many people each year die from skin cancer, and this statistic is rising steadily each year. Survival rates are high if detected early. Dermatologists have been trying different methods to aid in the detection skin cancer . Lack of experience and knowledge causes incorrect detection. The purpos
2025-06-28 16:35:03 - Adil Khan
Skin Lesion Detection and Classification Using Transfer Learning
Project Area of Specialization Computer ScienceProject SummaryMany people each year die from skin cancer, and this statistic is rising steadily each year. Survival rates are high if detected early. Dermatologists have been trying different methods to aid in the detection skin cancer . Lack of experience and knowledge causes incorrect detection. The purpose of this project is to present an automatic skin lesions classification system with higher classification rate using the theory of transfer learning and the pre-trained deep neural network.
Project ObjectivesThe main objectives of this research work are
- To study the latest approaches that support skin cancer detection at an early stage.
- To develop the framework that will automatically detect skin cancer detection with help of computer vision technique.
- To improve the accuracy of skin lesion detection.
Experimental setup for proposed research includes the following. PC Core i5. 32/64-bit operating system. Microsoft Windows 7/8. MATLAB 2018 a/b.
Benefits of the ProjectThe proposed method will improves the accuracy of automatic skin lesion detection.
Technical Details of Final DeliverableThis research will assist physician in classifying skin lesion detection.
Final Deliverable of the Project Hardware SystemCore Industry HealthOther Industries Medical Core Technology OthersOther TechnologiesSustainable Development Goals Good Health and Well-Being for PeopleRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 0 | |||
| Nill | Equipment | 0 | 0 | 0 |