- 期刊
- OpenAccess
A Performance-Driven Rotational Invariant Image Retrieval System
摘要
The color feature could be well represented in a feature and shape is a distinguishable feature which can make coarse discriminations quickly. Based on those reasons, we present an efficient image retrieval system to consider simultaneously accuracy and performance by combining color moment with shape contexts in this paper. The shape rotation has significant influence on the similarity measure and retrieval performance. Another important contribution of the paper is to present an efficient algorithm for rotation invariance. In the algorithm, the rotated shape contexts together are first clustered and then label each cluster so that the shape contexts in each cluster have the same label. Using the histogram of label frequencies can quickly and efficiently search for similar or rotational shapes. The experimental results have shown that our system is effective and has better retrieval performance than the existing systems.
延伸閱讀
- 郭懿儀（2014）。A Novel Spatial Representation for Image Retrieval〔碩士論文，朝陽科技大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0078-2502201617122929
- 劉信宏（2009）。Rotation Invariant Image Retrieval Using PSO and SVR〔碩士論文，國立虎尾科技大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0028-3007200918212200
- Lee, C. C. (2013). Cross-domain Image Retrieval by Multi-level Feature and Spatial Verification [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU.2013.01581
- 林嘉文（2013）。A Novel Content-Based Image Retrieval System Based on Distance Measure Approach〔碩士論文，國立臺中科技大學〕。華藝線上圖書館。https://doi.org/10.6826/NUTC.2013.00084
- 黃宇濤（2005）。Integrating Semantics and Low Level Features for the Design of Image Retrieval Systems〔碩士論文，淡江大學〕。華藝線上圖書館。https://doi.org/10.6846/TKU.2005.00351