Please use this identifier to cite or link to this item:
標題: 基於 8D-RL 描述子的影像擷取系統
Image Retrieval Based on 8D-RL Descriptor
作者: Wen-Jung Tsai
關鍵字: Image retrieval;8D-RL descriptor;HSV color space;Gray-scale image;Quantization;Texture direction extraction;影像擷取;8D-RL 描述子;HSV 色彩空間;灰階影像;量化;紋理方向萃取
引用: [1]Aptoula, E. and Lefevre, S., 'Morphological description of color images for content-based image retrieval,' IEEE Transactions on Image Processing, vol.18, no. 11, pp. 2505-2517, Nov. 2009. [2]Arnold, W. M., Worring, M., Santini, S., Gupta, A., and Jain, R.,'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, Dec. 2000. [3]Bach, J. R., Fuller, C., Gupta, A., Hampapur, A., Horowitz, B., Humphrey, R., Jain, R. C. and Shu, C., 'Virage image search engine: an open framework for image management,' Proceedings of Symposium on Electronic Imaging:Science and Technology - Storage and Retrieval for Image and Video Database IV, IS&T/SPIE, pp.76-87, 1996. [4]Burger, W. and Burge, M. J., 'Digital image processing: an algorithmic introduction using java,' Springer, first edition, 2008. [5]Carson, C., Belongie, S., Greenspan, H. and Malik, J., 'Blobworld: image segmentation using expectation-maximization and its application to image querying,' IEEE Transactions on Pattern Analysis and Machine Intelligence,vol. 24, no. 8, pp. 1026-1038, Aug. 2002. [6]Chen, L., 'Topological structure in visual perception,' Science, vol. 218, no.4573, pp. 91-97, Nov. 1982. [7]Cross, G. and Jain, A., 'Markov random field texture models,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 5, no. 1, pp.25-39, Jan. 1983. [8]ElAlami, M. E., 'Unsupervised image retrieval framework based on rule base system,' Expert Systems with Applications, vol. 38, no. 4, pp. 3539-3549, Apr.2011. [9]Flickner, M., Sawhney, H., Niblack, W., Ashley, J., Huang, Q., Dom, B., Gorkani, M., Hafner, J., Lee, D., Petkovic, D., Steele, D. and Yanker, P., 'Query by image and video content: the QBIC system,' IEEE Computer Society, vol. 28, no. 9, pp. 23-32, Sep. 1995. [10] Gonzalez, R. C. and Woods, R. E., 'Digital image processing,' Prentice Hall, third edition, 2007. [11] Haralick, R. M., Shanmugam, K. and Dinstein, I., 'Textural features for image classification,' IEEE Transactions on Systems, Man and Cybernetics, vol. 3, no. 6, pp. 610-621, Nov. 1973. [12] Huang, J., Kumar, S. R., Mitra, M., Zhu, W. J. and Zabih, R., 'Image indexing using color correlograms,' Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, pp. 762-768, 1997. [13] Huang, P. W. and Dai, S. K., 'Image retrieval by texture similarity,' Pattern Recognition, vol. 36, no. 3, pp. 665-679, Mar. 2003. [14] Huang, P. W. and Dai, S. K., 'Design of a two-stage content-based image retrieval system using texture similarity,' Information Processing and Management, vol. 40, no. 1, pp. 81-96, Jan. 2004. [15] Huang, P. W., Dai, S. K. and Lin, P. L., 'Texture image retrieval and image segmentation using composite sub-band gradient vectors,' Journal of Visual Communication and Image Representation, vol. 17, no. 5, pp. 947-957, Oct. 2006. [16] Huang, P. W and Jean, Y. R., 'Using 2D C+ -strings as spatial knowledge representation for image database system,' Pattern Recognition, vol.27, no. 9,pp. 1249-1257, Sep. 1994. [17] Huang, P. W. and Lee, C. H., 'Image database design based on 9D-SPA representation for spatial relations,' IEEE Transactions on Knowledge and Data Engineering, vol. 16, no. 12, pp. 1486-1496, Dec. 2004. [18] Julesz, B., 'Textons, the elements of texture perception, and their interactions,' Nature, vol. 290, no. 12, pp. 91-97, Mar. 1981. [19] Liu, G. H., Li, Z. Y., Zhang, L., and Xu, Y., 'Image retrieval based on micro-structure descriptor,' Pattern Recognition, vol. 44, no. 9, pp. 2123-2133,Sep. 2011. [20] Liu, G. H., Zhang, L., Hou, Y. K., Li, Z. Y., and Yang, J, Y., 'Image retrieval based on multi-texton histogram,' Pattern Recognition, vol. 43, no. 7, pp.2380-2389, Jul. 2010. [21] Liu, Y., Zhang, D. S., Lu, G. J., and Ma, W. Y., 'A survey of content-based image retrieval with high-level semantics,' Pattern Recognition, vol. 40, no. 1,pp. 262-282, Jan. 2007. [22] Livingstone, M. S. and Hubel, D. H., 'Anatomy and physiology of a color system in the primate visual cortex,' The Journal of Neuroscience, vol. 4, no. 1,pp. 309-356, Oct. 1983. [23] Luo, J. and Crandall, D., 'Color object detection using spatial-color joint probability function,' IEEE Transactions on Image Processing, vol. 15, no. 6,Jun. 2006. [24] Manjunath, B. S., Ohm, J. -R., Vasudevan, V. V. and Yamada, A., 'Color and texture descriptors,' IEEE Transactions on Circuits and Systems for Video Technology, vol. 11, no. 6, Jun. 2001. [25] Manjunath, B. S. and Ma, W. Y., 'Texture features for browsing and retrieval of image data,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 8, pp. 837-842, Aug. 1996. [26] Ma, Y, W. and Manjunath, B. S., 'Netra: a toolbox for navigating large image database,' Proceedings of the IEEE International Conference on Image Processing, Santa Barbara, CA, pp. 26-29, Oct. 1997. [27] Min, R. and Cheng, H. D., 'Effective image retrieval using dominant color descriptor and fuzzy support vector machine,' Pattern Recognition, vol. 42, no. 1, pp. 147-157, Jan. 2009. [28] Ojala, T., Pietikainen, M., Maenpaa, T., 'Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 971-981, Jul. 2002. [29] Palm, C., 'Color texture classification by integrative co-occurrence matrices,' Pattern Recognition, vol. 37, pp. 965-976, May. 2004. [30] Rashedi, E., Nezamabadi-pour, H., and Saryazdi, S., 'A simultaneous feature adaptation and feature selection method for content-based image retrieval systems,' Knowledge-Based Systems, vol. 39, pp. 85-94, Feb. 2013. [31] Pass, G., Zabih, R and Miller, J., 'Comparing images using color coherence vectors,' Proceedings of ACM Multimedia 96, Boston, MA, pp. 65-73, 1996. [32] Pentland, A., Picard, R. W. and Scaroff, S., 'Photobook: content-based manipulation for image databases,' International Journal of Computer Vision,vol. 18, no. 3, pp. 233-254, Jun. 1996. [33] Shrivastava, N. and Tyagi, V., 'Content based image retrieval based on relative locations of multiple regions of interest using selective regions matching,' Information Science, vol.259, no. 20, pp. 212-224, Feb. 2014. [34] Smith, J. R. and Chang, S. F., 'Visualseek: a full automated content-based image query system,' Proceedings of the Fourth ACM International Multimedia Conference, Boston, MA, pp. 87-98, Nov. 1996. [35] Wang, J. Z, Li, J., and Wiederhold, G., 'SIMPLIcity: semantics-sensitive integrated matching for picture libraries,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 9, pp. 947-963, Sep. 2001. [36] Zhang, D. S., Islam, M. M., and Lu, G. J., 'A review on automatic image annotation techniques,' Pattern Recognition, vol. 58, no. 1, pp. 346-362, Jan.2012. [37] 'Color wheel - From Wikipedia, the free encyclopedia,' 11:53, Jun. 2014. Available:
In this thesis, we propose a new image descriptor called 8D-RL which can be used in image retrieval systems for capturing both color and texture features from images.

First, a color image is converted from RGB space to HSV space and into a gray-scale image also. The hue component of the image is quantized by 12 bins and the gray-scale image is quantized by 16 bins. Starting from each pixel of the first row in both quantized images, we count the number of continuous pixels which have the same quantized value along a certain direction. Then we sum up the squared total number of pixels with the same quantized hue value from all continuous intervals as the texture feature of the underlying hue color and direction. Such features are generated based on all directions and all bin values from the hue component image and gray-scale image.

We use Corel-1000 database to exercise our experiments. Corel-1000 database has a total number of 1000 images belonging to 10 categories. In each category, we randomly select fifty images and proceed 500 times experiments. Experimental results show that our 8D-RL feature descriptor can combine color and texture features very effectively and has better performance in terms of precision and recall as compared to the performance of Liu's micro-structure descriptor.

在本篇論文中,我們提出了一種新的影像描述子,作為以色彩及紋理特徵比對標準之影像擷取資訊系統之基礎,此描述子稱為 8D-RL 描述子(8 Directional Run-Length descriptor),用來描述影像的色彩及紋理特徵,此描述子是建構在有方向性的顏色變化所產生的紋理。
將 RGB 色彩空間影像轉換成 HSV 色彩空間影像以及灰階影像後,將 HSV 的色調分量(Hue component)取出,對色調分量影像及灰階影像量化,然後提取色調分量量化影像和灰階量化影像的顏色和紋理資訊。8D-RL 描述子定義八個方向的顏色紋理,從影像最上列的每一個點出發,往八個方向前進,計算鄰居點與該點是否有相同的色調及灰階量化值,若相同則繼續前進,直到與出發點的值不同為止,然後紀錄此區間相同量化值的個數,重複以上動作直到該方向全部的點都計算過為止,將該方向所有區間具有相同某一量化值的個數取平方和後當在該方向對此一量化值的特徵,8D-RL 描述子是對所有色調及灰階強度之量化值在八個方向所整合而成的影像特徵向量。我們使用 Corel-1000 資料庫來進行實驗,此資料庫共有一千張自然影像,分屬十種類別,每一個類別我們隨機選取了五十張影像,用 500 張 query images 進行實驗,實驗結果顯示我們所提出的 8D-RL 影像特徵描述方法很有效率地結合了顏色及紋理的特徵資訊 與 Liu 等人所提出的微結構描述子相比 基於 8D-RL 的 CBIR,具有更高的精確度(Precision)和召回度(Recall)。
其他識別: U0005-2205201509231200
Rights: 同意授權瀏覽/列印電子全文服務,2018-07-15起公開。
Appears in Collections:資訊科學與工程學系所

Files in This Item:
File Description SizeFormat Existing users please Login
nchu-103-7100056014-1.pdf3.21 MBAdobe PDFThis file is only available in the university internal network    Request a copy
Show full item record

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.