Automatic Video Classification: A Review

Abstract

INTRODUCTION: In last few years number of internet users and available bandwidth has been increased exponentially. The availability of internet with such a low cost is making audiovisual content a more popular and easier form of information exchange. The internet is having a huge amount of this audiovisual content and to classify and choose a particular type of video is becoming a difficult task. A number of video classification methods (like text, audio and video feature extraction) have been proposed by researcher's community OBJECTIVES: This work is carried out to give a review of different video classification techniques and give a comparative analysis of available video classification techniques and to suggest the most accurate and efficient method of video classification. METHODS: Text, Audio and Visual video classification techniques. RESULTS: It has been observed that a combination of audio and visual feature extraction can provide better results. CONCLUSION: There are various methods of video classification either by using text, audio or video extraction. The text feature extraction is the least used method of video classification. The audio and visual feature extraction is being used in various applications but as we can understand that both the audio and visual feature extractions are having equal importance in video feature extraction but if we use combination of both these approaches, the results in form of accuracy of video classification can be further improved.

Enhancing multi-class web video categorization model using machine and deep learning approaches

“…-Definition 6. The maximum value TF-IDF of extracted features (FCall) assigned to FAall, if it greater than TF-IDF (FAall), denoted by FAall_TF-IDF as defined in (10).…”

“…However, given the massive number of videos on the web, users face difficulties in accurately retrieving and obtaining the videos they need [5], [6]. The best method to examine, extract and classify web videos on the basis of content similarity is web video categorization (WVC) [7]- [10]. As the number of videos on the web has increased exponentially, the traditional way of manually processing video categorization has become time consuming and thus requires much effort [11].…”

Deep Learning for Video Classification: A Review

“…However, the review provided is not comprehensive and lacks in concise information, coverage of topic, datasets, analysis of state-of-art approaches, and research limitations. (iv) Rani et al [8] also conducted a recent review on video classification methods, their review covers some recent video classification approaches and summary-based description of some recent works. This review has also some limitations including the missing analysis of recent state-of-art approaches, and short description of topics covered.…”