Detection and Extraction of Videos using Decision Trees
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2011, Vol 2, Issue 12
Abstract
This paper addresses a new multimedia data mining framework for the extraction of events in videos by using decision tree logic. The aim of our DEVDT (Detection and Extraction of Videos using Decision Trees) system is for improving the indexing and retrieval of multimedia information. The extracted events can be used to index the videos. In this system we have considered C4.5 Decision tree algorithm [3] which is used for managing both continuous and discrete attributes. In this process, firstly we have adopted an advanced video event detection method to produce event boundaries and some important visual features. This rich multi-modal feature set is filtered by a pre-processing step to clean the noise as well as to reduce the irrelevant data. This will improve the performance of both Precision and Recall. After producing the cleaned data, it will be mined and classified by using a decision tree model. The learning and classification steps of this Decision tree are simple and fast. The Decision Tree has good accuracy. Subsequently, by using our system we will reach maximum Precision and Recall i.e. we will extract pure video events effectively and proficiently.
Authors and Affiliations
: Sk. Abdul Nabi , Shaik Rasool , Dr. P. Premchand
Keywords
Related Articles
- EP ID EP113940
- DOI -
- Views 95
- Downloads 0
Rising Issues in VANET Communication and Security: A State of Art Survey
VANET (Vehicular Adhoc Network) has made an evolution in the transportation hi-tech system in most of the developed countries. VANET plays an important role in an intelligent transportation system (ITS). This paper gives...
Performance Comparison of Collaborative-Filtering Approach with Implicit and Explicit Data
Challenge in developing a collaborative filtering (CF)-based recommendation system is the problem of cold-starting of items that causes the data to sparse and reduces the accuracy of the recommendations. Therefore, to pr...
Enhanced Analytical Hierarchy Process for U-Learning with Near Field Communication (NFC) Technology
Integration of current Virtual Learning Environment (VLE) system with the Near Field Communication (NFC) technology provides Ubiquitous Learning Environment (ULE) in education. The utilization of NFC technology in U-Lear...
An AHP Model towards an Agile Enterprise
Companies are facing different challenges in order to adapt to their environmental context. They should be aware of the changes on the social, political, ecological and economical levels. Moreover, they should act in an...
A Penalized-Likelihood Image Reconstruction Algorithm for Positron Emission Tomography Exploiting Root Image Size
Iterative image reconstruction methods are considered better as compared to the analytical reconstruction methods in terms of their noise characteristics and quantification ability. Penalized-Likelihood Expectation Maxim...