Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues Export

@article{citeulike:883988, abstract = {The goal of this work is to accurately detect and localize boundaries in natural scenes using local image measurements. We formulate features that respond to characteristic changes in brightness, color, and texture associated with natural boundaries. In order to combine the information from these features in an optimal way, we train a classifier using human labeled images as ground truth. The output of this classifier provides the posterior probability of a boundary at each image location and orientation. We present precision-recall curves showing that the resulting detector significantly outperforms existing approaches. Our two main results are 1) that cue combination can be performed adequately with a simple linear model and 2) that a proper, explicit treatment of texture is required to detect boundaries in natural images.}, address = {Los Alamitos, CA, USA}, author = {Martin, David R. and Fowlkes, Charless C. and Malik, Jitendra}, citeulike-article-id = {883988}, citeulike-linkout-0 = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2004.1273918}, citeulike-linkout-1 = {http://dx.doi.org/10.1109/TPAMI.2004.1273918}, citeulike-linkout-2 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1273918}, doi = {10.1109/TPAMI.2004.1273918}, issn = {0162-8828}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, keywords = {clutter, cocish, color, learning, perception, saliency, segmentation, texture\_analysis, visual\_search}, number = {5}, pages = {530--549}, posted-at = {2009-09-18 01:40:24}, priority = {2}, publisher = {IEEE Computer Society}, title = {Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues}, url = {http://dx.doi.org/10.1109/TPAMI.2004.1273918}, volume = {26}, year = {2004} }

TY - JOUR ID - citeulike:883988 L3 - citeulike-article-id:883988 N2 - The goal of this work is to accurately detect and localize boundaries in natural scenes using local image measurements. We formulate features that respond to characteristic changes in brightness, color, and texture associated with natural boundaries. In order to combine the information from these features in an optimal way, we train a classifier using human labeled images as ground truth. The output of this classifier provides the posterior probability of a boundary at each image location and orientation. We present precision-recall curves showing that the resulting detector significantly outperforms existing approaches. Our two main results are 1) that cue combination can be performed adequately with a simple linear model and 2) that a proper, explicit treatment of texture is required to detect boundaries in natural images. IS - 5 JF - IEEE Transactions on Pattern Analysis and Machine Intelligence SN - 0162-8828 AD - Los Alamitos, CA, USA EP - 549 TI - Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues PB - IEEE Computer Society VL - 26 SP - 530 KW - clutter KW - cocish KW - color KW - learning KW - perception KW - saliency KW - segmentation KW - texture_analysis KW - visual_search AU - Martin, David AU - Fowlkes, Charless AU - Malik, Jitendra PY - 2004/// UR - http://dx.doi.org/10.1109/TPAMI.2004.1273918 ER -