Graph cuts based relevance feedback in image retrieval

Lelin Zhang, Sidong Liu, Zhiyong Wang, Weidong Cai, Yang Song, David Dagan Feng

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review


Relevance feedback (RF) allows users to be actively involved in the information retrieval process and has been widely used in various information retrieval tasks. While most existing RF methods in content-based image retrieval (CBIR) focus on visual features of individual images only, in this paper we formulate the relevance feedback process as an energy minimization problem. The energy function takes into account both the feature aspect of each image and the manifold structure among individual images. The solution of labelling images as relevant or irrelevant is obtained with the graph cuts method. As a result, our method enables flexibly partitioning the feature space and labelling of images and is capable of handling challenging scenarios (or queries). Experimental results demonstrate that our proposed method outperforms the popular RF methods.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages5
ISBN (Print)9781479923410
Publication statusPublished - 1 Dec 2013
Externally publishedYes
Event2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, Australia
Duration: 15 Sep 201318 Sep 2013


Conference2013 20th IEEE International Conference on Image Processing, ICIP 2013
CityMelbourne, VIC


  • Content-based image retrieval
  • energy minimization
  • graph cuts
  • interactive retrieval
  • relevance feedback


Dive into the research topics of 'Graph cuts based relevance feedback in image retrieval'. Together they form a unique fingerprint.

Cite this