Classification of melanoma based on feature similarity measurement for codebook learning in the bag-of-features model

Publication date: May 2019Source: Biomedical Signal Processing and Control, Volume 51Author(s): Kai Hu, Xiaorui Niu, Si Liu, Yuan Zhang, Chunhong Cao, Fen Xiao, Wanchun Yang, Xieping GaoAbstractBag-of-features (BoF) model based melanoma classification methods can effectively assist dermatologists to diagnose skin diseases. Codebook learning is a key step in the BoF model and the k-means clustering algorithm is often used to learn a codebook. However, the cluster centers generated by k-means algorithm are irresistibly attracted to the denser regions. This produces a suboptimal codebook in which most of the clusters are located in dense regions and a few are in sparse regions. Therefore, this can easily affect the classification accuracy. In this paper, we develop a novel methodology for classifying skin lesions. Firstly, we propose a new codebook learning algorithm based on feature similarity measurement (FSM) to effectively quantify the original features of melanomas. We utilize the combination of the linearly independent and linear prediction (LP) algorithms to measure feature similarity. Especially, the codewords learned by the proposed FSM algorithm are not affected by the density of samples. Therefore, a more discriminating BoF histogram for the melanoma classification is achieved. Secondly, we propose a melanoma classification method based on the FSM codebook learning algorithm. In particular, we adopt the BoF histogram fusion strategy of different feature descriptors, i...
Source: Biomedical Signal Processing and Control - Category: Biomedical Science Source Type: research