利用階層式視覺文字和空間關係驗證提升跨來源影像搜尋之效能

Cross-domain Image Retrieval by Multi-level Feature and Spatial Verification

李哲君(Che-Chun Lee)

指導教授 ： 徐宏民

國立臺灣大學/電機資訊學院/資訊工程學研究所/碩士(2013年)

https://doi.org/10.6342/NTU.2013.01581

摘要

無資料

關鍵字

跨領域 ； 影像搜尋 ； 空間關係驗證 ； 多層次匹配 ； 影像匹配

並列摘要

We proposed a method to solve the general cross-domain image retrieval problem. This method focuses on image content structure but not the detail, so it is particularly useful to matching the images across different visual domains e.g., paintings, hand-drawn sketches and photographs taken in different times.

There is a method trying to solve this problem by classification. Although it gets good performance in the experiment, it is too computationally intensive to do the interactive applications. For finding a fast solution, we analyse the problem causing BoW method fails in the cross-domain setting first. Then, According to the observation, our proposed method releases the strict matched constraint and uses a fast spatial verification to describe the content structure similarity. Finally, our method is very faster than the baseline solution and achieves the same performance.

Key words: Cross-domain, image retrieval, spatial verification, multi-level matching, image matching, sketch

並列關鍵字

Cross-domain ； image retrieval ； spatial verification ； multi-level matching ； image matching ； sketch

參考文獻

[1] Josef Sivic and Andrew Zisserman. Video google: A text retrieval approach to object matching in videos. In ICCV, pages 1470--1477. IEEE Computer Society, 2003.

[2] Bryan C. Russell, Josef Sivic, Jean Ponce, and Helene Dessales. Automatic alignment of paintings and photographs depicting a 3d scene. In ICCV Workshops, pages 545-- 552, 2011.

[4] Abhinav Shrivastava, Tomasz Malisiewicz, Abhinav Gupta, and Alexei A. Efros. Data-driven visual similarity for cross-domain image matching. ACM Trans. Graph., 30(6):154, 2011.

[5] Tomasz Malisiewicz, Abhinav Gupta, and Alexei A. Efros. Ensemble of exemplarsvms for object detection and beyond. In ICCV, pages 89--96, 2011.

[6] Pedro F. Felzenszwalb, Ross B. Girshick, David A. McAllester, and Deva Ramanan. Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell., 32(9):1627--1645, 2010.