Edge, junction, and corner detection using color distributions Export

@article{citeulike:1595558, abstract = {For over 30 years (1970-2000) researchers in computer vision have been proposing new methods for performing low-level vision tasks such as detecting edges and corners. One key element shared by most methods is that they represent local image neighborhoods as constant in color or intensity with deviations modeled as noise. Due to computational considerations that encourage the use of small neighborhoods where this assumption holds, these methods remain popular. The research presented models a neighborhood as a distribution of colors. The goal is to show that the increase in accuracy of this representation translates into higher-quality results for low-level vision tasks on difficult, natural images, especially as neighborhood size increases. We emphasize large neighborhoods because small ones often do not contain enough information. We emphasize color because it subsumes gray scale as an image range and because it is the dominant form of human perception. We discuss distributions in the context of detecting edges, corners, and junctions, and we show results for each}, author = {Ruzon, M. A. and Tomasi, C.}, booktitle = {Pattern Analysis and Machine Intelligence, IEEE Transactions on}, citeulike-article-id = {1595558}, citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=969118}, journal = {Pattern Analysis and Machine Intelligence, IEEE Transactions on}, keywords = {-operator, compass}, number = {11}, pages = {1281--1295}, posted-at = {2007-08-27 05:19:10}, priority = {0}, title = {Edge, junction, and corner detection using color distributions}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=969118}, volume = {23}, year = {2001} }

TY - JOUR ID - citeulike:1595558 L3 - citeulike-article-id:1595558 N2 - For over 30 years (1970-2000) researchers in computer vision have been proposing new methods for performing low-level vision tasks such as detecting edges and corners. One key element shared by most methods is that they represent local image neighborhoods as constant in color or intensity with deviations modeled as noise. Due to computational considerations that encourage the use of small neighborhoods where this assumption holds, these methods remain popular. The research presented models a neighborhood as a distribution of colors. The goal is to show that the increase in accuracy of this representation translates into higher-quality results for low-level vision tasks on difficult, natural images, especially as neighborhood size increases. We emphasize large neighborhoods because small ones often do not contain enough information. We emphasize color because it subsumes gray scale as an image range and because it is the dominant form of human perception. We discuss distributions in the context of detecting edges, corners, and junctions, and we show results for each IS - 11 JF - Pattern Analysis and Machine Intelligence, IEEE Transactions on EP - 1295 TI - Edge, junction, and corner detection using color distributions VL - 23 T2 - Pattern Analysis and Machine Intelligence, IEEE Transactions on SP - 1281 KW - -operator KW - compass AU - Ruzon, MA AU - Tomasi, C PY - 2001/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=969118 ER -