Extracting ocean


Published on

  • Be the first to comment

  • Be the first to like this

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Extracting ocean

  1. 1. Extracting Spatial Semantics in Association Rules for Ocean Image RetrievalAuthor:Li-Jen Kao,Yo-Ping Huang, Frode Eika Sandnes Source:Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics San Antonio, TX, USA - October 2009Advisor:Yin-Fu HuangStudent:YU-HSIEN CHO
  2. 2. OUTLINEI. IntroductionII. Related Works 1. CBIR 2. Inter-transaction Association Rules AlgorithmIII. Ocean Image RetrievalIV. Experimental Results And DiscussionV. Conclusion
  3. 3. I. Introduction Database:Argo is a global research organization that deploys over 3,000 freedrifting profiling floats that measure the temperature and salinity of the upper 2000 meters of the ocean. This facilitates continuous monitoring of the temperature and salinity of the upper ocean. In order to get effective retrieval results, the image retrieval technology is critical to image database systems. The inter-transaction association rules algorithm is applied to get salinity or temperature variation patterns. And use Euclidean distance to measure the distance between these two objects
  4. 4. II. Related Works1. CBIR-Content-based Image Retrieval Modern multimedia technologies have led to huge and growing archives of images in diverse applications such as medicine, remote-sensing, entertainment, education and online information services. In recent years, automatic indexing and retrieval based on image content has become more desirable for developing large volume image retrieval applications. (Fig. 1) *Color, shape, texture and Spatial Semantic are the main features both humans and computers used to recognize images.
  5. 5. Fig.1 New Generation CBIR System
  6. 6.  QBIC:Query By Image Content IBM QBIC (Query by Image Content) system is the first capture system, can be retrieved, the conditions include keywords and images in color, texture, shape and other characteristics. Provides three ways to search: First, the user can specify the main color of the query image. Second, query the probability of relative pixel from the image. Third, drawn by the users’ expectations of image which needed the color of object box, and set the shape of their representatives.
  7. 7.  VisualSEEK: VisualSEEKis a allows users to search image and video on the World Wide Web, developed by Columbia Universitys New Media Technology Center. The retrieval feature contains color, shape, texture and spatial information, spatial relationships (Fig. 2)between objects is also taken into consideration in order to improve the ability of search.
  8. 8. Fig.2 The reference model with concentric model Fig. 3 Salinity variations occurred in sub-zone K1, K2, L1 and L2.Table. 1The radius and angle to x-axis for each sub-zone in the concentric circles.
  9. 9. 2. Inter-transaction Association Rules AlgorithmIn order to minimize the effort involved in mining uninterestingrules, a sliding window denoted by w is introduced.
  10. 10. Example: Fig. 4 shows a transaction database T with five transactions located at intervals 1, 4, 6, 9, and 10. And w=4 . Assuming that w has a value of 4, we will have five sliding windows W1, W2, W3, W4, and W5, with addresses of 1, 4, 6, 9, and 10, respectively. From the figure, it can be seen that subwindow W1[0] contains items a, b, e, g, and j while subwindow W1[3] contains c, f, and j. W1 will be {a(0),b(0),e(0),g(0),j(0),c(3),f(3),j(3)}Fig.4 Transaction database and sliding widows.
  11. 11. Example:Let minsup and minconf be 40 percent and 60 percentrespectively. Then, an example of an intertransactionassociation rule which will be mined from the database inFig. 4 will be: This rule has a support of 40 percent and a confidence of 66 percent.
  12. 12. III. Ocean Image RetrievalIn this section, the process of how to retrieve the ocean imageis introduced.Before retrieving images in the database, the objects are cutfrom query image according to their color in ocean image anda set of concentric circles is also applied to the query image tohelp annotate location information to objects cut from queryimage.The following method is used to identify the location of anobject.The object location is denoted by its coordinate
  13. 13. |qo,to|color =|cq - ct||qo,to|location =|xq - xt| + |yq - yt|
  14. 14. The following example explains how to get additional images topredict future variation trends.Example: Assume there are total n objects {O1,O2,…….,On} cut fro the query image.
  15. 15. IV. Experimental Results And DiscussionThis study utilized ocean salinity and temperature image atdepth of 100 meters from January 2001 to December 2006.A database was built comprising these images.Table 2 shows the market-basket type transaction set ofsalinity and temperature variations. Each transaction isrecorded with spatial and temporal information.Table 3 shows the intervals that the salinity andtemperature variations are mapped to. NOR events areused to classify situations where no variations occur in aspecific sub-area.Table 4 shows the results of the quantitative attributes inTable 2 mapped to several intervals.
  16. 16. Table. 2 A database with quantitative attributes“Salinity variation” and “Temperature variation” Table. 3 The mapping intervals for salinity and temperature quantitative values.
  17. 17. Table. 4 The “Salinity variation” and “Temperature variation” Mapping results from Table. 2.Table 5 shows part of the discovered inter-transaction associationrules. For example, the rule, H1SRL(0) -> A2SRL(3), means that ifsalinity rose from 0.05 psu to 0.15 psu in the area that is in the west-south sector near Taiwan, then salinity will rise from 0.05 psu to 0.15psu in the east sector far away from Taiwan the next 3 months. Table. 5 Partial discovered inter-transaction association rules.
  18. 18. Fig.5 Result of the images.
  19. 19. V. Conclusion This study proposes a strategy where concentric circles are used as a reference model to annotate location information to the objects in image. This allows the spatial semantics to be maintained for either the images in database or the query image. The proposed intelligent image retrieval system can get more images to help user predict future salinity or temperature variation trends.