u010453586的博客

In this paper, we explore methods for learning local image descriptors from training data. We describe a set of building blocks for constructing descriptors which can be combined together and jointly optimized so as to minimize the error of a nearestneighbor classifier. We consider both linear and nonlinear transforms with dimensionality reduction, and make use of discriminant learning techniques such as Linear Discriminant Analysis (LDA) and Powell minimization to solve for the parameters. Using these techniques, we obtain descriptors that exceed state-of-the-art performance with low dimensionality. In addition to new experiments and recommendations for descriptor learning, we are also making available a new and realistic ground truth data set based on multiview stereo data.

Semantic hashing seeks compact binary codes of data-points so that the Hamming distance between codewords correlates with semantic similarity. In this paper, we show that the problem of finding a best code for a given dataset is closely related to the problem of graph partitioning and can be shown to be NP hard. By relaxing the original problem, we obtain a spectral method whose solutions are simply a subset of thresholded eigen-vectors of the graph Laplacian. By utilizing recent results on convergence of graph Laplacian eigenvectors to the Laplace-Beltrami eigenfunctions of manifolds, we show how to efficiently calculate the code of a novel data-point. Taken together, both learning the code and applying it to a novel point are extremely simple. Our experiments show that our codes outper-form the state-of-the art.

Unsupervised_Segmentation_of_Color-Texture_Regions_in_Images_and_Video

Exploring the Representation Capabilities of the HOG Descriptor