CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 1998 vol.20 Issue No.07 - July
Issue No.07 - July (1998 vol.20)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.689300
<p><b>Abstract</b>—Junctions are important features for image analysis and form a critical aspect of image understanding tasks such as object recognition. We present a unified approach to <it>detecting</it> (location of the center of the junction), <it>classifying</it> (by the number of wedges—lines, corners, three-junctions such as <it>T</it> or <it>Y</it> junctions, or four-junctions such as <it>X</it>-junctions), and <it>reconstructing</it> junctions (in terms of radius size, the angles of each wedge and the intensity in each of the wedges) in images. Our main contribution is a modeling of the junction which is complex enough to handle all these issues and yet simple enough to admit an effective dynamic programming solution. Broadly, we use a template deformation framework along with a gradient criterium to detect radial partitions of the template. We use the minimum description length principle to obtain the optimal number of partitions that best describes the junction. Kona [<ref rid="bibi068727" type="bib">27</ref>] is an implementation of this model. We (quantitatively) demonstrate the stability and robustness of the detector by analyzing its behavior in the presence of noise, using synthetic/controlled apparatus. We also present a qualitative study of its behavior on real images.</p>
Junctions, corners, feature detection, low-level vision, minimum description length (MDL) principle, energy minimization.
Laxmi Parida, Davi Geiger, Robert Hummel, "Junctions: Detection, Classification, and Reconstruction", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.20, no. 7, pp. 687-698, July 1998, doi:10.1109/34.689300