基于目標語義特征的圖像檢索系統(tǒng)
Image Retricval System Based on semantic features of objects
-
摘要: 為克服當前基于內容的圖像檢索技術中低級特征無法準確全面地描述高級語義的問題，該文設計和實現了一個基于目標高級語義特征的檢索系統(tǒng)。該系統(tǒng)利用了一個多級圖像描述模型將語義特征結合到圖像檢索技術中。該圖像描述模型通過在不同層次上對圖像內容進行分析和描述，實現了從低級特征到高級語義的過渡。在此模型的基礎上還研究了相應的檢索機制和反饋技術。該系統(tǒng)的檢索機制定位于圖像中目標的語義內容，與傳統(tǒng)的圖像檢索系統(tǒng)相比更接近人對圖像內容的理解，從而使檢索過程更簡便，檢索效率也得到很大提高。基于目標描述的自適應相關反饋可針對不同用戶的不同需求給出相應的檢索方案，從而使檢索結果得到優(yōu)化。Abstract: Most existing content-based image retrieval systems using low-level features that could not describe high-level semantics thoroughly and accurately. In this paper, a novel system for content-based image retrieval is designed and created, which combines image semantics based on a multi-level model for image description. In this image description model, image contents could be analyzed and represented through different levels and the transition from low-level features to high-level semantics is thus achieved. Corresponding querying mechanism and feedback are also proposed based on this image model. Aiming at object semantics in image, this querying mechanism is much closer to human beings understanding of image contents so that it provides a convenient and effective querying procedure. The feedback used in the system is a self-adaptive relevance feedback based on object descriptions, it permits to propose different querying schemes according to the different demands raised by various users, and thus optimal results could be refined.
-
Y. Rui, T. S. Huang, S. Mehrotra, Relevance feedback techniques in interactive content-based image retrieval, 1998, SPIE 3312: 25-34.[2]D.Z. Hong, J. K. Wu, S. S. Singh, Refining image retrieval based on context-driven method,1999, SPIE 3656: 581-593.[3]A. Jaimes, S. F. Chang, Model-based classification of visual information for content-based retrieval, SPIE 3656: 402-414.[4]E.J. Pauwels, G. Frederix, Finding salient regions in images: Nonparametric clustering for image segmentation and grouping, Computer Vision and Image Understanding, 1999, 75(1): 73-85.[5]Y.Y. Gao, Y. J. Zhang, Object classification using mixed color feature, Proc. ICASSP, Istanbul,2000, 4: 2003-2006.[6]S.G. Mallat, Multifrequency channel decompositions of images and wavelet models, IEEE Trans.on ASSP, 1989, ASSP-37(12): 2091 2110.[7]Y.Y. Gao.[J].Y. J. Zhang, N. S. Merzlyakov, Semantic-based image description model and its implementation in image retrieval, Proc. of ICIG2000, Tianjin.2000,:-[8]高永英,章毓晉,基于多級描述模型的漸近式圖像內容理解,電子學報,2001,29(10):1376-1380.[9]G. Ciocca.[J].R. Schettini, Using a relevance feedback mechanism to improve content-based image retrieval, Proc. of 3rd VISUAL99, Amsterdam.1999,:-[10]梅鎮(zhèn)彤,學習和記憶的神經生物學,上海,上?？茖W技術出版社,1997,51-53. -
計量
- 文章訪問數: 2466
- HTML全文瀏覽量: 141
- PDF下載量: 914
- 被引次數: 0
下載:
