Title :
Decomposing Bag of Words Histograms
Author :
Gandhi, Anshul ; Alahari, Karteek ; Jawahar, C.V.
Author_Institution :
CVIT, IIIT Hyderabad, Hyderabad, India
Abstract :
We aim to decompose a global histogram representation of an image into histograms of its associated objects and regions. This task is formulated as an optimization problem, given a set of linear classifiers, which can effectively discriminate the object categories present in the image. Our decomposition bypasses harder problems associated with accurately localizing and segmenting objects. We evaluate our method on a wide variety of composite histograms, and also compare it with MRF-based solutions. In addition to merely measuring the accuracy of decomposition, we also show the utility of the estimated object and background histograms for the task of image classification on the PASCAL VOC 2007 dataset.
Keywords :
image classification; image representation; image segmentation; optimisation; MRF-based solution; PASCAL VOC 2007 dataset; composite histogram; global histogram representation; histogram decomposition; image classification; image estimation; image representation; image segmentation; linear classifiers; object categories discrimination; optimization problem; Accuracy; Clutter; Histograms; Image segmentation; Optimization; Support vector machines; Visualization;
Conference_Titel :
Computer Vision (ICCV), 2013 IEEE International Conference on
Conference_Location :
Sydney, NSW
DOI :
10.1109/ICCV.2013.45