Video Classification Using Normalized Information Distance

Abstract

There has been a vast collection of multimedia resources on the net. This has opened an opening for researchers to explore and advance the science in the field of research in storing, handling, and retrieving digital videos. Video classification and segmentation are fundamental steps for efficient accessing; retrieving, browsing and compressing large amount of video data. The basic operation video analysis is to design a system that can accurately and automatically segments video material into shots and scenes. This paper presents a detailed video segmentation technique based on pervious researches which lacks performance and since some of the videos is stored in a compressed form using the Normalized Information Distance (NID) which approximates the value of a theoretical distance between objects using the Kolmogrov Complexity Theory. This technique produced a better result in reference to performance, high recall of 95.5% and a precision of 89.7%.

Audio-Video based Classification using SVM and AANN

“…For each audio signal we arrived at 39 features. This number, 39, is computed from the length of the parameterized static vector (13), plus the delta coefficients (13) plus the acceleration coefficients (13). The classification results for the different features are shown in Fig.…”

“…In many existing video data base management systems contentbased queries uses low-level features. At the highest level of hierarchy, video database can be categorized into different genres such as cartoon, sports, commercials, news and music and are discussed in [13], [14], and [15]. Video data stream can be classified into various sub categories cartoon, sports, commercial, news and serial are analysis in [2], [3], [7] and [16].…”

Audio-video based Segmentation and Classification using SVM and AANN

“…The preceptual approach is used for automatic music genre classification based on spectral and cepstral features in [15].A hierarchy based approach for video classification using a tree-based RBF network is in [8]. In [11] a method is proposed for video classification using normalized information distance. Visual database can be preceptual and categorized into different genres in [7].…”

Video Classification and Shot Detection for Video Retrieval Applications

“…The literature reports many approaches for video classification viz., broad genre classification 2,3,4 that categorizes video database into cartoon, sports, commercials, news, music; limited domain classification which organize 5,6,7,8 a video into different sub categories and at the final level, the semantic content 9,10 classification that identifies the specific events like highlights and crowd in a video sequence.…”

“…Normally, the classification methods cannot be applied for digital media in compressed form. Normalized Information Distance (NID) which approximates theoretical Kolmogorov complexity 4 is used for genre classification in compressed video which reflects good performance. Classifying content in a specific genre is also of research interest particularly in sports genre.…”