High-entropy layouts for content-based browsing and retrieval

Multimedia browsing and retrieval systems can use dimensionality reduction methods to map from high-dimensional content-based feature distributions to low-dimensional layout spaces for visualization. However, this often results in displays in which many items are occluded whilst large regions are empty or only sparsely populated with items. Furthermore, such methods do not take into account the shape of the region of layout space to be populated. This paper proposes a layout method that addresses these limitations. Layout distributions with low Renyi quadratic entropy are penalized since these result in displays in which some regions are over-populated (i.e. many images are occluded), sparsely populated or empty. Experiments using two image datasets and a comparison with two related methods show the effectiveness of the proposed method.

• Type: Conference
• Year: 2009
• Where: CIVR
• Authors: Ruixuan Wang, Stephen J. McKenna, Junwei Han
• Keywords: CIVR 2009, Dimensionality Reduction Methods, Layout Space, Low-dimensional Layout Spaces, Multimedia