International Journal of Recent Trends in Engineering & Research

online ISSN

Content Based Video Classification Using SVM

Publication Date : 28/03/2019


DOI : 10.23883/IJRTER.CONF.20190322.060.IWTAZ


Author(s) :

GOKILA K , JANANIE K R , MADHU BALA C , GOMATHY NAYAGAM M , GOMATHY NAYAGAM M.


Conference Name :
1st International Conference on New Scientific Creations in Engineering and Technology - 2019



Abstract :

Internet users spend an amount of time on videos and their needs have generated tremendous amount of data .However ,too many videos are quite difficult for human beings to categorize and labelling it .As of today ,a significant human effort is needed to categorize these video data file that could substantially help the people to reduce the growing amount of clustering video data on Internet .The main objective of this project is to create a model to categorize and label the videos automatically with the help of SVM methods .As the result of this project we can able to classify the videos without any predefined class labels .We achieved classification accuracy of approximately 90 % on the test set which is a decent result considering the relative simplicity of the model. A proposed system is to identify the video belongs to which category using machine learning model. Our base idea is to collect the common features vectors from various videos dataset. Then we use Support Vector Machine algorithm to train our model to detect the video classification.


No. of Downloads :

4


Indexing

License

Traffic Stats

Total Visits : 5,723