The object recognition problem has challenged the computer vision community for long time due to the huge change in the scale, occlusion and lighting conditions which have a great effect on the appearance of the objects. The problem of generic object recognition (GOR) has the previously mentioned difficulties in addition to the intra-class and inter-class variability problems. Despite the difficulties of the generic object recognition problem many approaches appeared trying to provide a solution to this problem. We present our model for 2D generic object recognition which achieves good performance on difficult object category datasets. Moreover, we present a model for generic 3D object recognition from range images.
@InProceedings{hegazy_et_al:DagSemProc.08422.8, author = {Hegazy, Doaa and Denzler, Joachim}, title = {{Generic Object Recognition}}, booktitle = {Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes}, series = {Dagstuhl Seminar Proceedings (DagSemProc)}, ISSN = {1862-4405}, year = {2009}, volume = {8422}, editor = {Joachim Denzler and Michael Koch}, publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik}, address = {Dagstuhl, Germany}, URL = {https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.8}, URN = {urn:nbn:de:0030-drops-18668}, doi = {10.4230/DagSemProc.08422.8}, annote = {Keywords: Generic object recognition, Boosting, Range images} }
Feedback for Dagstuhl Publishing