Support vector machine active learning for image retrieval

Simon Tong, Edward Yi Chang

Proceedings of the ninth ACM international conference on Multimedia - MULTIMEDIA '01 · 2001 · 487 citations · 0 references

Concepts

TL;DR

Relevance feedback is essential for image databases but is challenging because users cannot directly specify queries, requiring interactive selection of a few images to accurately capture the desired concept. The authors propose using a support vector machine active learning algorithm to perform relevance feedback in image retrieval. The algorithm selects the most informative images for user labeling and rapidly learns a decision boundary separating relevant from irrelevant images. Experiments demonstrate that the algorithm attains significantly higher search accuracy than traditional query refinement schemes after only three to four rounds of relevance feedback.

Abstract

Relevance feedback is often a critical component when designing image databases. With these databases it is difficult to specify queries directly and explicitly. Relevance feedback interactively determinines a user's desired output or query concept by asking the user whether certain proposed images are relevant or not. For a relevance feedback algorithm to be effective, it must grasp a user's query concept accurately and quickly, while also only asking the user to label a small number of images. We propose the use of a support vector machine active learning algorithm for conducting effective relevance feedback for image retrieval. The algorithm selects the most informative images to query a user and quickly learns a boundary that separates the images that satisfy the user's query concept from the rest of the dataset. Experimental results show that our algorithm achieves significantly higher search accuracy than traditional query refinement schemes after just three to four rounds of relevance feedback.