The Study of Recognition Methods Based on Wavelet Transform for Melanoma Detection

Abstract

Skin cancer is one of the most cancers occurring in the world. Malignant melanoma is the most skin cancer type causing death around the world. Melanoma could be treated 100% if they are detected at earlier stages. In this paper, various melanoma detection systems were reviewed according to the year of publishing. All reviewed papers were based on feature extraction methods using wavelet transform (WT) in its two versions: Discrete wavelet transform (DWT), and wavelet packet transform (WPT) for melanoma recognition. Our methodology that was based on the WPT feature extraction and probabilistic neural network (PNN) was used for comparison. The ISIC database was used for differentiating between malignant (1110 images) and benign (1110 image) tumors. A (75% training /25% testing) verification system was applied. Many experiments were conducted using different parameters for each experiment. The support vector machine classifier (SVM) was the most common classifier combined with various types of wavelet features that have appeared in many kinds of literature during the last two decades, which achieved relatively the best accuracy ranged between [76% -98.29%]. In this paper, our combination method of the WPT and entropy was proposed and evaluated. Several experiments were conducted for testing. A Almarei and Daqrouq; JERR, 11(3): 46-61, 2020; Article no.JERR.55316 47 comparison manner was used for discussion of the investigation. The proposed method was an excellent detection method for melanoma regarding the complexity, where no preprocessing stage was conducted. Original Research Article