Histopathology Image Classification Using Bag of Features and Kernel Functions

Image representation is all important issue for medical image analysis. classification and retrieval. Recently, the bag of feature,, approach has been proposed to classify natural scenes, using an analogy in which visual features are to images as words are to text documents. This process involves feature detection and description, construction of a visual vocabularly and image representation building through visual-word occurrence analysis. This paper presents an evaluation of different representations obtained from the bag of features approach to classify. histopathology images. The obtained image descriptors are processed using appropriate kernel functions for Support Vector Machines classifiers. This evaluation includes extensive experimentation of different strategies, ami analyses the impact of each configuration in the classification result.