Description

ABSTRACT

Human Cancer is one of the most dangerous disease which is mainly caused by genetic instability of multiple molecular alterations. Among many forms of human cancer, skin cancer is the most common one. To identify skin cancer at an early stage we will study and analyze them through various techniques named as segmentation and feature extraction. Here, we focus malignant melanoma skin cancer, (due to the high concentration of Melanoma- Hier we offer our skin, in the dermis layer of the skin) detection. In this, We used our ABCD rule dermoscopy technology for malignant melanoma skin cancer detection. In this system different step for melanoma skin lesion characterization i.e, first the Image Acquisition Technique, pre-processing, segmentation, define feature for skin Feature Selection determines lesion characterization, classification methods. In the Feature extraction by digital image processing method includes, symmetry detection, Border Detection, color, and diameter detection and also we used LBP for extract the texture based features. Here we proposed the Back Propagation Neural Network to classify the benign or malignant stage.

Demo Video

EXISTING METHOD

• Principal Component Analysis
• Local binary pattern and shape features
• KNN and FNN classifier

DRAW BACKS OF EXISTING METHOD

• High Computational load and poor discriminatory power.
• LBP doesn’t differentiate the local texture region.
• FNN is slow training for large feature set.
• Less accuracy in classification

PROPOSED METHOD

Skin lesion classification for Computer Aided Diagnosis (CAD) system based on,

• Hybrid features involves color features and texture descriptors
• ANN-Back Propagation Neural Network classifier 

BLOCK DIAGRAM

METHODOLOGIES

• Color Space Conversion
• GLCM Features Extraction and ABCD Parameters
• BPN Training and Classification
• Adaptive thresholding

ADVANTAGES

• PNN is fast and better compatible in classification.
• Low computational complexity

APPLICATION

• Skin cancer diagnosis support system in Health care fields

SOFTWARE REQUIREMENT

• Matlab7.5 and above versions

RESULTS

 

             

For more Image Processing projects ,Click here

https://www.pantechsolutions.net/image-processing-projects