Learning visual concepts from image instances

Jun-Wei Hsieh*, Cheng Chin Chiang, Yea Shuan Huang, W. E.L. Grimson

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


This paper presents a novel method of retrieving images by learning the commonality of instances from a set of training examples. The proposed scheme uses a coarse-to-fine algorithm to find the desired visual concepts from a set of instances for successful image retrieval. The learner at the coarse stage attempts to partition training data into two smaller compact sets (relevant and irrelevant) to reduce the size of the training examples, thus improving the efficiency of concept learning at the refined stage. At the refined stage, a proposed verification scheme is employed to verify each instance obtained at the coarse stage by examining its indexing and filtering capabilities based on a pool of images. Due to this extra examination step, the desired visual concepts can be learned more accurately, leading to significant improvement in image retrieval. Since no time-consuming optimization process is involved, all the desired visual concepts can be learned online. Experimental results are provided to verify the superiority of the proposed method.

Original languageEnglish
Pages (from-to)1197-1212
Number of pages16
JournalJournal of Information Science and Engineering
Issue number6
StatePublished - Nov 2004


  • Diverse density algorithm
  • Image retrieval
  • Multiple instances
  • Region instances
  • Relevance feedback


Dive into the research topics of 'Learning visual concepts from image instances'. Together they form a unique fingerprint.

Cite this