Can keypoint descriptors be used in outdoor image classification?

In this paper, we approach a Content Based Image Retrieval problem using keypoints and texture. We employ an algorithm that allows computing a fixed number of keypoints for all the images in the dataset, by adapting a certain parameter of the keypoints computation method. The SIFT (Scale Invariant Feature Transform) and SURF (Speeded Up Robust Features) algorithms yield the required keypoints. We also used texture features to improve the retrieval results. The texture features are computed using Local Binary Patterns (LBP), Gray Level Co-occurrence Matrices (GLCM), Dual Tree Complex Wavelet Transform (DTCWT), and Gabor filters. The methods were tested on our own dataset, ODIDS which contains outdoor images, mainly acquired in the city of Iaşi, Romania. We performed location identification with good results. [ABSTRACT FROM AUTHOR]