Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Lahore, Pakistan.
Department of Computer Science, COMSATS University Islamabad, Abbottabad Campus, Abbottabad, Pakistan.
Curr Med Imaging. 2020;16(6):711-719. doi: 10.2174/1573405615666190422152926.
In this study, a novel and fully automatic skin disease classification approach is proposed using statistical feature extraction and Artificial Neural Network (ANN) based classification using first and second order statistical moments, the entropy of different color channels and texture-based features.
The basic aim of our study is to develop an automated system for skin disease classification that can help a general physician to automatically detect the lesion and classify it to disease types.
The performance of the proposed approach is corroborated by extensive experiments performed on a dataset of 588 images containing 6907 lesion regions.
The results show that the proposed methodology can be effectively used to construct a skin disease classification system.
Our proposed method is designed for a specific skin tone. Future investigation is needed to analyze the impact of different skin tones on the performance of lesions detection and classification system.
本研究提出了一种新颖的、全自动的皮肤病分类方法，该方法使用基于一阶和二阶统计矩、不同颜色通道的熵以及基于纹理的特征的统计特征提取和人工神经网络（ANN）进行分类。
我们研究的基本目的是开发一种用于皮肤病分类的自动化系统，帮助普通医生自动检测病变并将其分类为疾病类型。
通过对包含 6907 个病变区域的 588 张图像数据集进行广泛的实验，验证了所提出方法的性能。
结果表明，所提出的方法可有效地用于构建皮肤病分类系统。
我们提出的方法是针对特定肤色设计的。未来需要研究不同肤色对病变检测和分类系统性能的影响。
