Published in ACM proceedings of The Ninth Indian Conference on Computer Vision, Graphics, Image Processing (ICVGIP), 2014

Nitin Gupta, Sukhendu Das and Sutanu Chakraborti
Visualization and Perception Lab
Department of Computer Science and Engineering, Indian Institute of Technology, Madras, India

Content-based image retrieval (CBIR) techniques retrieve similar digital images from a large database. As the user often does not provide any clue (indication) of the region of interest in a query image, most methods of CBIR rely on a representation of the global content of the image. The desired content in an image is often localized (e.g. car appearing salient in a street) instead of being holistic, demanding the need for an object-centric CBIR. We propose a biologically inspired framework WOW ("What Object is Where") for this purpose. Design of WOW framework is motivated by the cognitive model of human visual perception and feature integration theory (FIT). The key contributions in the proposed approach are: (i) Feedback mechanism between Recognition ("What") and Localization ("Where") modules (both supervised), for a cohesive decision based on mutual consensus; (ii) Hierarchy of visual features (based on FIT) for an effcient recognition task. Integration of information from the two channels ("What and Where") in an iterative feedback mechanism, helps to filter erroneous contents in the outputs of individual modules. Finally, using a similarity criteria based on HOG features (spatially localized by WOW) for matching, our system effectively retrieves a set of rank-ordered samples from the gallery. Experimentation done on various real-life datasets (including PASCAL) exhibits the superior performance of the proposed method.

Framework

Results

* Errorneous retrievals are indicated using red templates and correct ones by green templates.

"Revealing What to Extract from Where for Object-Centric Content Based Image Retrieval (CBIR)", Nitin Gupta, Sukhendu Das and Sutanu Chakraborti; Indian Conference on Computer Vision, Graphics, Image Processing (ICVGIP), 2014.

@inproceedings{frbp, author={Nitin Gupta, Sukhendu Das and Sutanu Chakraborti}, booktitle={{Indian Conference on Computer Vision, Graphics, Image Processing (ICVGIP)}}, title={{Revealing What to Extract from Where for Object-Centric Content Based Image Retrieval (CBIR). }}, year={2014}, }

References

1. G.H. Liu and J.Y. Yang, “Image retrieval based on multi-texton histogram” Pattern Recognition, 2010.

2. G. Dwivedi, S. Das, S. Rakshit, M. Vora, and S. Samanta, “SLAR (Simultaneous Localization And Recognition) framework for smart CBIR,” International Conference on Perception and Machine Intelligence (PerMIn), LNCS, 2012.

3. G.H. Liu, Z.Y. Li, L. Zhang, and Y. Xu, “Image retrieval based on micro-structure descriptor,” Pattern Recognition, 2012.

4. G.H. Liu, L. Zhang, Y.K. Hou, Zuo YongLi, and J.-Y. Yang, “Content-based image retrieval using color difference histogram,” Pattern Recognition, 2013.

5. N. Gupta, S. Das, and G. Dwivedi "Cognitive Inspired WOR Framework to Reveal Image Semantics, for Efficient Content Based Image Retrieval". International Conference on Perception and Machine Intelligence (PerMIn), ACM Proceedings, 2015.