An efficient algorithm for attention-driven image interpretation from segments |
| |
Authors: | Hong Fu [Author Vitae] Zheru Chi [Author Vitae] [Author Vitae] |
| |
Affiliation: | a Center for Multimedia Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong b School of Information Technologies, The University of Sydney, NSW 2006, Australia |
| |
Abstract: | In the attention-driven image interpretation process, an image is interpreted as containing several perceptually attended objects as well as the background. The process benefits greatly a content-based image retrieval task with attentively important objects identified and emphasized. An important issue to be addressed in an attention-driven image interpretation is to reconstruct several attentive objects iteratively from the segments of an image by maximizing a global attention function. The object reconstruction is a combinational optimization problem with a complexity of 2N which is computationally very expensive when the number of segments N is large. In this paper, we formulate the attention-driven image interpretation process by a matrix representation. An efficient algorithm based on the elementary transformation of matrix is proposed to reduce the computational complexity to 3ωN(N-1)2/2, where ω is the number of runs. Experimental results on both the synthetic and real data show a significantly improved processing speed with an acceptable degradation to the accuracy of object formulation. |
| |
Keywords: | Computer vision Search optimization Region combination Visual attention model Image understanding Content-based image retrieval |
本文献已被 ScienceDirect 等数据库收录! |
|