近十幾年來，很多的影像處理前置作業都是要事先定義出影像顯著區域，例如影像切割、影像檢索和調整影響大小等領域等都會利用到顯著區域偵測。顯著區域偵測最後則是會產生一個權重影像。同時，顯著區域偵測也是模擬人眼視覺，截取出人眼第一個會注意的目標，在多媒體應用越來越發達的現在，更可以應用在商業用途中，例如超市擺放位置吸引消費者目光。另外，隨著數位相機的普及，自動對焦系統大幅改善的同時也與顯著區域偵測有相關連性。
顯著區域演算法主要有幾個方向，例如基於頻率域，或是空間域的區域對比檢測法。雖然有許多的方法被提出，但是至今仍沒有一個系統可以針對所有的影像有好的結果。大多的方法都有限制或是特定條件，因此，我們提出一個利用頻率域和空間域合作的系統架構，先分析影像特性再根據影像特性選擇要用哪一個方法來得到顯著圖。
根據實驗結果，依據提出的分析影像特性條件確實能讓影像有更好的顯著區域偵測結果。

The technology of saliency detection has gained remarkable attention for the past decade due to its popularity in the field of image processing, such as image segmentation, image resizing, image retrieval etc. A saliency map is a topographically arranged map that represents visual saliency of a corresponding visual scene. Saliency detection is also applied to commercial applications. For instance, it can be used to simulate consumer reaction to product placement and categorization. Furthermore, as the digital cameras become widely used, the autofocus system has improved significantly based on the saliency detection.
In the last ten years, the development of salient region detection has been addressed in many approaches such as frequency based method, color contrast in spatial domain. However, most of them have limitations or operate under special condition. Therefore, a system applying both the frequency based and spatial domain is proposed. It determines the suitable domain for each different case by analyzing the characteristics of the image. Then, it obtains the salience map by utilizing one of the methods.
According to the experimental results, applying the pre-determination based on the analysis of image characteristics delivers better detection results.

[1]. B. C. Ko and J.Y. Nam, “Object-of-interest image segmentation based on human attention and semantic region clustering”, Journal of Optical Society of America , Vol. 23, No. 10, pp. 2462–2470, 2006.
[2]. A.W.M. Smeulders, M. Worring, S. Santini, A Gupta, and R. Jain, “Content-based image retrieval at the end of the early years”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No. 12, pp. 1349–1380, 2000.
[3]. S. Avidan, and A. Shamir, “Seam carving for content-aware image resizing”, ACM Transactions on Graphics, Vol. 26, No. 3, 2007.
[4]. L. Itti, C. Koch, and E. Niebur, “A model of saliency-based visual attention for rapid scene analysis ”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 11, pp. 1254-1259, Nov. 1998.
[5]. R. Achanta, F. Estrada, P. Wils, and S. Susstrunk, “Salient region detection and segmentation”, International Conference on Computer Vision Systems, 2008.
[6]. X. Hou, and L. Zhang, “Saliency detection: a spectral residual approach”, IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8, 2007.
[7] M. M. Cheng, G. X. Zhang, N. J. Mitra, X. Huang, and S. M. Hu, “Global contrast based salient region detection”, IEEE Conference on Computer Vision and Pattern Recognition, pp. 409-416, 2011.
[8]. F.H. Cheng, and H.W. Mao, “Research on fast image based auto focus technique”, Journal of Information and Applications, Vol. 3 No. 1, pp. 67-76, 2008.
[9]. http://en.wikipedia.org/wiki/Autofocus, July, 2013.
[10]. http://photographylife.com, July, 2013.
[11].http://photographylife.com/how-phase-detection-autofocus-works, July, 2013.
[12]. http://electronics.howstuffworks.com/autofocus3.htm, July, 2013.
[13]. H. Greenspan, S. Belongie, R. Goodman, P. Perona, S. Rakshit, and C.H. Anderson, “Overcomplete Steerable Pyramid Filters and Rotation Invariance”, IEEE Computer Vision and Pattern Recognition, pp. 222-228, 1994.
[14]. V. Gopalakrishnan, Y. Hu, and D. Rajan, “Salient region detection by modeling distributions of color and orientation”, IEEE Transactions on Multimedia, Vol. 11, No. 5, pp. 892–905, Aug. 2009.