With the rapid development of modern medical imaging technology, medical image classification has become more important for medical diagnosis and treatment.
To solve the existence of polysemous words and synonyms problem, this study combines the word bag model with PLSA (Probabilistic Latent Semantic Analysis) and proposes the PLSA-BOW (Probabilistic Latent Semantic Analysis-Bag of Words) model.
In this paper we introduce the bag of words model in text field to image field, and build the model of visual bag of words model.
The method enables the word bag model-based classification method to be further improved in accuracy.
The experimental results show that the PLSA-BOW model for medical image classification can lead to a more accurate classification.
Szummer M., and Picard R.W., Indoor-outdoor image classification, Content-Based Access of Image and Video Database 42 (1998).
Wang S.L., Information-based color feature representation for image classification, Image Processing 6 (2007), 353.
Yang J., Narrowing semantic gap in content-based image retrieval, Computer Distributed Control and Intelligent Environmental Monitoring 433 (2012).
Deng S.Z., , Islam M., and Lu G.J., A review on automatic image annotation techniques, Pattern Recognition 45 (2012), 346.
Zha Z.J., , Tao D.C., and Chua T.-S., Semantic-gap-oriented active learning for multipliable image annotation, IEEE Transaction on Image Processing 21 (2012), 2354.
Li F.F., and Perona P., A Bayesian hierarchical model for learning natural scene categories, Computer Vision and Pattern Recognition 2 (2005), 524.
Hofmann T., Unsupervised learning by probabilistic latent semantic analysis, Machine Learning 42 (2001), 177.
Bentley J.L., Multidimensional binary search trees used for associative searching, Communication of the ACM 18 (1975), 509.
Bishop C.M., Pattern recognition and machine learning, Corr (2007), 424.