Texture recognition and classification is a widely applicable task in computer vision. A key stage in performing this task is feature extraction, which identifies sets of features that describe the visual texture of a...Texture recognition and classification is a widely applicable task in computer vision. A key stage in performing this task is feature extraction, which identifies sets of features that describe the visual texture of an image. Many descriptors can be used to perform texture classification;among the more common of these are the grey level co-occurrence matrix, Gabor wavelets, steerable pyramids and SIFT. We analyse and compare the effectiveness of these methods on the Brodatz, UIUCTex and KTH-TIPS texture image datasets. The efficacy of the descriptors is evaluated both in isolation and by combining several of them by means of machine learning approaches such as Bayesian networks, support vector machines, and nearest-neighbour approaches. We demonstrate that using a combination of features improves reliability over using a single feature type when multiple datasets are to be classified. We determine optimal combinations for each dataset and achieve high classification rates, demonstrating that relatively simple descriptors can be made to perform close to the very best published results. We also demonstrate the importance of selecting the optimal descriptor set and analysis techniques for a given dataset.展开更多
文摘Texture recognition and classification is a widely applicable task in computer vision. A key stage in performing this task is feature extraction, which identifies sets of features that describe the visual texture of an image. Many descriptors can be used to perform texture classification;among the more common of these are the grey level co-occurrence matrix, Gabor wavelets, steerable pyramids and SIFT. We analyse and compare the effectiveness of these methods on the Brodatz, UIUCTex and KTH-TIPS texture image datasets. The efficacy of the descriptors is evaluated both in isolation and by combining several of them by means of machine learning approaches such as Bayesian networks, support vector machines, and nearest-neighbour approaches. We demonstrate that using a combination of features improves reliability over using a single feature type when multiple datasets are to be classified. We determine optimal combinations for each dataset and achieve high classification rates, demonstrating that relatively simple descriptors can be made to perform close to the very best published results. We also demonstrate the importance of selecting the optimal descriptor set and analysis techniques for a given dataset.
