Object Recognition with Discriminately Trained Part-Based Model on HOG (Histogram of Oriented Gradients)
The object recognization techniques which are available at present cannot process the partial visible objects and cannot classify them depending on the shape. This is the main objective of my proposed system which is to recognize the object from the image if any parts of the object are visible using discriminative part-based model .The main objectives of this work was to apply the coarse root filter method and get the high-resolution parts that are converted into deformable models and are stored in training dataset. An object can be identified by matching with deformable cost of the object model present in the training dataset.
KeywordsObject detection Coarse root filter Deformable model HOG (Histogram of oriented Gradients)
- 1.Felzenszwalb, P., McAllester, D., Ramanan, D.: A Discriminatively Trained, Multiscale, Deformable Part Model. 978-1-4244-2243-2/08/$25.00 ©2008 IEEEGoogle Scholar
- 2.Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Google Scholar
- 3.Felzenszwalb, P., McAllester, D., Ramanan, D.: Visual object detection with deformable part models. Commun. ACM 56(9), 97 (2013)Google Scholar
- 4.McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)Google Scholar
- 5.Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. 0-7695-1272-0/01 $10.00 0 2001 EEEGoogle Scholar