A review: Which is the best way to organize/classify images by content? Export

@article{bosch06, abstract = {Thousands of images are generated every day, which implies the necessity to classify, organise and access them using an easy, faster and efficient way. Scene classification, the classification of images into semantic categories (e.g. coast, mountains and streets), is a challenging and important problem nowadays. Many different approaches concerning scene classification have been proposed in the last few years. This article presents a detailed review of some of the most commonly used scene classification approaches. Furthermore, the surveyed techniques have been tested and their accuracy evaluated. Comparative results are shown and discussed giving the advantages and disadvantages of each methodology.}, author = {Bosch, Anna and Noz, Xavier M. and Mart\'{\i}, Robert}, citeulike-article-id = {3545240}, citeulike-linkout-0 = {http://dx.doi.org/http://dx.doi.org/10.1016/j.imavis.2006.07.015}, citeulike-linkout-1 = {http://dx.doi.org/10.1016/j.imavis.2006.07.015}, comment = {This paper presents some image categorization methods and classify them according to the used visual features. The author classify visual methods in low-level scene modeling and intermediate semantic modeling. In the low-level modeling, two main approaches are discussed: global features, such as histograms, and sub-block features. The intermediate modeling is divided in three categories: semantic objects (coarse segmentation), a visual bag-of-words approach and semantic properties. This paper includes the experimental evaluation of those methods in a natural scene classification task. One of the main conclusions in this paper is that the bag-of-words approach is the most effective technique for image classification tasks. The classification algorithms are generally based on bayesian frameworks, SMVs, and KNN, but it is not the main paper discussion.}, doi = {http://dx.doi.org/10.1016/j.imavis.2006.07.015}, journal = {Image and Vision Computing}, keywords = {bosch06}, number = {6}, pages = {778--791}, posted-at = {2008-11-17 04:13:18}, priority = {0}, title = {A review: Which is the best way to organize/classify images by content?}, url = {http://dx.doi.org/http://dx.doi.org/10.1016/j.imavis.2006.07.015}, volume = {25}, year = {2007} }

TY - JOUR ID - bosch06 L3 - citeulike-article-id:3545240 N2 - Thousands of images are generated every day, which implies the necessity to classify, organise and access them using an easy, faster and efficient way. Scene classification, the classification of images into semantic categories (e.g. coast, mountains and streets), is a challenging and important problem nowadays. Many different approaches concerning scene classification have been proposed in the last few years. This article presents a detailed review of some of the most commonly used scene classification approaches. Furthermore, the surveyed techniques have been tested and their accuracy evaluated. Comparative results are shown and discussed giving the advantages and disadvantages of each methodology. IS - 6 JF - Image and Vision Computing EP - 791 TI - A review: Which is the best way to organize/classify images by content? VL - 25 SP - 778 KW - bosch06 N1 - This paper presents some image categorization methods and classify them according to the used visual features. The author classify visual methods in low-level scene modeling and intermediate semantic modeling. In the low-level modeling, two main approaches are discussed: global features, such as histograms, and sub-block features. The intermediate modeling is divided in three categories: semantic objects (coarse segmentation), a visual bag-of-words approach and semantic properties. This paper includes the experimental evaluation of those methods in a natural scene classification task. One of the main conclusions in this paper is that the bag-of-words approach is the most effective technique for image classification tasks. The classification algorithms are generally based on bayesian frameworks, SMVs, and KNN, but it is not the main paper discussion. AU - Bosch, Anna AU - Noz, Xavier AU - Martí, Robert PY - 2007/// UR - http://dx.doi.org/http://dx.doi.org/10.1016/j.imavis.2006.07.015 ER -