現行的貨櫃檢驗作業方式為使用人力於貨櫃集散站交換各項單據，以及人工進行檢查的方式相對耗時，檢查過程中也容易產生疏忽之情況，本研究希望透過影像處理特徵比對之技術，研究貨櫃背面影像建立特徵並進行比對，利用電腦判斷貨櫃在運輸的過程中有無被掉包或破壞，取代人工執行檢驗的作業。本研究的概念以人類的視覺為出發點來開發貨櫃特徵建立與比對。我們將貨櫃車出關與入關時的背面彩色影像進行取像動作，利用影像前處理(如透過邊緣影像的垂直投影與傾斜投影)的方式去除畫面之背景取出前景貨櫃，再由此前景畫面以貨櫃本身比例進行區塊(block)分割，由各個區塊找出具有特徵的區塊,首先藉由貨櫃本身的顏色資訊以色調(hue)分析並分類這些顏色資訊取得彩色部分的影像特徵，再利用邊緣偵測(edge detection)累積邊緣的像素(pixel)數目資訊作為另一種特徵，最後結合這兩種特徵進行區塊之比對動作，確認出關與入關之貨櫃是否有明顯差異，確保貨櫃在運輸途中的安全性與抵達後的完整度。

In this study, we proposed our method for preventing the current disadvantages (e.g., time wasting and human-made mistakes) by using computer image processing instead of manually done by manpower in the problem of container’s transport processing. Our research focus on defining features for containers and makes matching for checking whether the containers have been destroyed or exchanged. Features matching here is similar to human’s approach by examining the colors and edge amounts of the given containers. Base on the container images, we can preprocess (e.g., vertical projection and oblique projection) those images to extract the container from the whole image. The container image will be segmented into several blocks by considering the proportion of an ordinary container. Then, our proposed method will try to find out the possible features for each block. First of all, the hue feature is considered to deal with the color of a container. Secondly, the pixels number of possible edges after applying edge detection is accumulated. Our approach is to combine and compare these two features to check if there is any significant difference between two designated containers. Base on the experiments we did using our proposed method, the security aspect during shipping and the integrity aspect after arriving of the containers can be ensured.

[1] 財政部關稅總局(Directorate General of Customs, Ministry of Finance), http://web.customs.gov.tw/
[2] 行政院經濟建設委員會,“優質經貿網絡計畫綱要”, 行政院院臺經字第0970057810號核定, 編號(98)008.902, 2009.
[3] David G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints”, International Journal of Computer Vision, Vol.60, No.2, pp.91-110, 2004.
[4] 呂進發，「使用影像處理技術辨認貨櫃號碼」，碩士論文，國立高雄第一科技大學電腦與通訊工程系，2004.
[5] W. Pan, Y.S. Wang and H. Yang, “Robust container code recognition system”, The Fifth World Congress on Intelligent Control and Automation, pp. 4061-4065, June 2004.
[6] J. Yin, A. Cao and J. Li, “A New Method for Container Code Location”, IEEE International Conference on Automation and Logistics, pp. 2482-2485, 2007.
[7] S. Gu, X. Luo, “An Efficient Algorithm of Container Code Characters Location”, 2nd International Conference on Computer Engineering and Technology (ICCET), pp. v6-180-v6-183, 2010.
[8] R.C. Gonzales, R.E. Woods, Digital Image Processing 3/e, Pearson Education, 2008.
[9] R.C. Gonzales, R.E. Woods, Digital Image Processing Using MATLAB 2/e, McGraw-Hill Education, 2010.
[10] G. Bradski, A. Kaehler, Learning OpenCV, O’Reilly Media, 2008.
[11] W.S. Gao, L. Yang, X.G. Zhang, H.Z. Liu, “An Improved Sobel Edge Detection”, 3rd IEEE International Conference on Computer Science and Information Technology (ICCSIT), pp.67-71, 2010.
[12] B. Wang, S.S. Fan, “An improved CANNY edge detection algorithm”, WCSE '09. Second International Workshop on Computer Science and Engineering, pp. 497 - 500 ,2009.
[13] 鍾國亮, “影像處理與電腦視覺”, 臺灣東華書局股份有限公司, 台北, 2006.
[14] N. Otsu, “A threshold selection method from gray level histogram,” IEEE Trans. on Systems, Man, and Cybernetics, SMC-8, 1978, pp. 62-66.
[15] H.Z. Wang, Ying Dong, “An Improved Image Segmentation Algorithm Based on Otsu Method”, International Symposium on Photoelectronic Detection and Imaging 2007: Related Technologies and Applications, L. Zhou, Ed., vol. 6625 of Proceedings of SPIE, pp. 66250I-1-66250I-8, 2008.
[16] 郭士銘，「以DSP實現遠端同步教學傳播系統」，碩士論文，國立臺灣科技大學電機工程系，2010.
[17] S.Y. Chien, S. Y. Ma and L. G. Chen, “Efficient Moving Object Segmentation Algorithm Using Background Registration Technique,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 12, No. 7, pp. 577-586, 2002.
[18] C. Zhang, Wang, P., “A new method of color image segmentation based on intensity and hue clustering” 15th International Conference on Pattern Recognition, 2000. Proceedings, pp. 613-616, 2000.
[19] K.J. Kim, S.M. Park, Y.J. Choi, “Deciding the Number of Color Histogram Bins for Vehicle Color Recognition”, Asia-Pacific Services Computing Conference, 2008. APSCC '08. IEEE, pp. 134-138, 2008.
[20] 維基百科全書 (Wikipedia), “Intermodal container”, http://en.wikipedia.org/wiki/Intermodal_container
[21] 長榮海運股份有限公司 (Evergreen Marine Crop.), http://www.evergreen-marine.com/tw/tei1/jsp/TEI1_Containers.jsp