Volume 18, No. 6, 2021

Segmentation And Feature Extraction Of Content Based Video Retrieval Using Maximum Likelihood Regression Model With Modified-Vgg-16

B. Satheesh Kumar , K. Seetharaman


The recent challenge faced by the users from the multimedia area is to collect the relevant object or unique image from the collection of huge data. During the classification of semantics, the media was allowed to access the text by merging the media with the text or content before the emergence of content based retrieval. The identification of this feature has become major challenges, so to overcome this issue this paper focuses on a deep learning technique with maximum likelihood regression (MLR) model for segmentation and Feature extraction of the input video. Likelihood estimation is to roughly measure the level of pixel, and then regression method determines pixel level to certainly transformblurred and unwanted pixels. The segmentation is done based on the likelihood estimation and the feature of this segmented video is extracted using Modified_ VGG-16 (M_VGG-16) architecture. The result of this technique has been compared with the existing other feature extraction techniques such as conventional Histogram of Oriented Gradients (HOG), LBP (Local Binary Patterns) and CNN (Convolution Neural Network) methods. In this scheme the video frame image retrieval is performed by assigning the indexing to the all video files in the database in order to perform the system more efficiently. Thus the system produces the top result matches for the similar query in comparison with the existing techniques based on precision of 90%, recall of 93% and F1 score of 91% in optimized video frame retrieval.

Pages: 2709-2724

Keywords: content based retrieval, segmentation, Feature extraction, MLR, M_VGG-16

Full Text