140 likes | 155 Views
This project focuses on performing Association Rule Mining on Multi-relational, Multimedia Data, specifically images and text. A corpus of 798 pictures of various types along with descriptions is used for analysis. The goal is to generate association rules on image data (RGBY values) and text data separately, proposing an algorithm to link these domains. The project aims to return descriptive words for unknown images offline, emphasizing multi-arm program processing for association rules on text and image data. Key aspects include the generation of text and image association rules and common key specification for table rebuilding using Apriori method. Further areas for improvement and alternative schemes are discussed.
E N D
Association Rule Mining on Multi-Media Data Auto Annotation on Images Bhavika Patel Hau San Si Tou Juveria Kanodia Muhammad Ahmad
Auto Annotation on Images • This project is on performing Association Rule Mining on Multi-relational, Multimedia Data, particularly pictures and text. • Corpus: a group of 798 picturesof different kinds such as art, landscape … with descriptions • Generate association rules on image data (the RGBY values), and on text data separately. Propose an algorithm to link these two different domains together. • Goal: return words that will describe a given unknown picture
# of text association rules generated from different combination of min supp & conf
# of image association rules generated from different combination of min supp & conf
Single pass rebuild • Specify common key • Rebuild the tables based on the common key • Use Apriori • EXAMPLE: Table 1: purchase(customer,item,amount) item(customer,item_id) Table 2 purchase_total(customer,items) Query: Customers who buy a lot of stuff what do they usually but? purchase_total(X,items) return item(X,item_id)
Conclusion • So we have a partial solution multimedia ARM problem, however there many things that can be done further, to improve upon it. • Need to find a way to restrict the number of keywords that we get. • Need to find an easier method than the present lookup method, as too many files are involved. • Need for an efficient data structure to do the above point. • Alternative Schemes
The End Please visit our project’s website at http://www.cs.rit.edu/~p759-06c to find detailed information.