針對巨量影像搜尋中基於區域性線性編碼 之全域影像表示法

Abstract

針對巨量影像搜尋(Large-Scale Image Retrieval)之架構，本論文內容為提出一個基於區域性線性編碼(LLC)的全域影像表示法(Global Image Representation)。由於傳統Fisher vector (FV) 的編碼方式在編碼的過程中需要較為複雜的運算，為了能在編碼效率上有所提升，我們採納了區域性線性編碼，能夠快速決定參數的一種編碼方式。而我們也針對先前所提出的FV以及區域性線性編碼做了一連串的實驗並選擇最適當的全域影像表示法編碼方式，藉此達到更好的編碼效率及搜尋效能。所以本文內容以先前研究為基礎，提出了一個快速的編碼方式，重新的思考如何產生最適當的全域影像表示法，也提出了一些針對原本FV編碼方式的修改，進而對原本的FV作進一步的改善，降低其編碼複雜度及提升搜尋效能。實驗結果顯示，本論文所提出的全域影像表示法的編碼方式相較於一些現有的設計，不但在編碼速度上有相對的優勢，同時在影像搜尋的準確度上也有所提升。

This thesis proposes a global image representation based on Locality-constrained Linear Coding (LLC), with an aim to simplify the encoding process of local descriptors so as to facilitate large-scale image retrieval. Starting from the state-of-the-art Fisher vector (FV) representation, we replace the computation of sophisticated posterior probabilities with simpler LLC. We then conduct several empirical studies to investigate the effects and benefits of this change and to adapt the other terms in FV for a better trade-off between performance and complexity. The result is a simpler global descriptor that combines the merits of both FV and LLC. Experimental results show that when compared with other similar works, our scheme not only brings performance benefits in mean Average Precision, but also offers complexity advantages.