Image Retrieval using Bag-of-Features for Lung Cancer Classification

In this paper, Content Based Image Retrieval (CBIR) technique is used to retrieve the images from a large database that are identical to the image provided as a query. The CBIR based Bag-of-Features (BOF) technique is used for extracting features and their classification on the dataset of LIDC/IDRI. Therefore, a lung image retrieval using grid-based feature extraction method and Speeded-Up Robust Features (SURF) algorithm are implemented in this paper. K-Means clustering algorithm is extended to the features extracted by SURF algorithm. MATLAB simulation is performed on selective database, which provides 99% and 98.56% of training and testing accuracy respectively.