Video Multiple Classification Algorithm Based on SVM (original) (raw)
Related papers
Content Based Video Classification Using SVM
INTERNATIONAL JOURNAL OF RECENT TRENDS IN ENGINEERING & RESEARCH, 2019
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.
Content-Based Video Classification Using Support Vector Machines
Lecture Notes in Computer Science, 2004
In this paper, we investigate the problem of video classification into predefined genre. The approach adopted is based on spatial and temporal descriptors derived from short video sequences (20 seconds). By using support vector machines (SVMs), we propose an optimized multiclass classification method. Five popular TV broadcast genre namely cartoon, commercials, cricket, football and tennis are studied. We tested our scheme on more than 2 hours of video data and achieved an accuracy of 92.5%.
Video Classification:A Literature Survey
At present, so much videos are available from many resources. But viewers want video of their interest. So for users to find a video of interest work has started for video classification. Video Classification literature is presented in this paper. There are mainly three approaches by which process of video classification can be done. For video classification, features are derived from three different modalities: Audio, Text and Visual. From these features, classification has been done. At last, these different approaches are compared. Advantages and Dis-advantages of each approach/method are described in this paper with appropriate applications.
A Review of Video Classification Techniques
2017
Assistant Professor, Information Technology Department, G.H. Patel College of Engineering & Technology, Gujarat, India Trainee Assistant Professor, Information Technology Department, G.H. Patel College of Engineering & Technology, Gujarat, India ---------------------------------------------------------------------------***--------------------------------------------------------------------------Abstract Video classification literature has been reviewed and techniques for the same are provided here in this paper. Classification process in general requires features based on which one can distinguish among the categories. These features are mainly taken from text, audio or visual content of the video. Based on that mainly three classification techniques are there as discussed here. Based on the application user has to select the method and features. Pros and cons of each method are mentioned in this paper with suitable applications.
News video classification using SVM-based multimodal classifiers and combination strategies
Proceedings of the tenth ACM international conference on Multimedia - MULTIMEDIA '02, 2002
Video classification is the first step toward multimedia content understanding. When video is classified into conceptual categories, it is usually desirable to combine evidence from multiple modalities. However, combination strategies in previous studies were usually ad hoc. We investigate a meta-classification combination strategy using Support Vector Machine, and compare it with probability-based strategies. Text features from closedcaptions and visual features from images are combined to classify broadcast news video. The experimental results show that combining multimodal classifiers can significantly improve recall and precision, and our meta-classification strategy gives better precision than the approach of taking the product of the posterior probabilities.
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, 2021
In recent years, there has been a rapid development in web users and sufficient bandwidth. Internet connectivity, which is so low cost, makes the sharing of information (text, audio and videos) more common and faster. This video content needs to be analyzed for prediction it class in different purpose for the users. Many machines learning approach has been developed for the classification of video to save people time and energy. There are a lot existing review papers on video classification, but they have some limitations such as limitation of analysis, badly structured, not mention research gaps or findings, not clearly describe advantages, disadvantages, and future work. But our review paper almost overcomes these limitations. This study attempts to review existing video-classification procedures and to examine the existing methods of video-classification comparatively and critically and to recommend the most effective and productive process. First of all, our analysis examines the classification of videos with taxonomical details, latest application, process and datasets information. Secondly, overall inconvenience, difficulties, shortcomings and potential work, data, performance measurements with the related recent relation in science, deep learning and the model of machine learning. Study on video classification systems using their tools, benefits, drawbacks, as well as other features to compare the techniques they have used also constitutes a key task of this review. Lastly, we also present a quick summary table based on selected features. In terms of precision and independence extraction functions, the RNN(Recurrent Neural Network), CNN(Convolutional Neural Network) and combination approach performs better than the CNN dependent method.
2019
A multiclass classification framework based on the content of videos proposed in this paper. It is flexible to inherit standard ratings to motion pictures as class labels, prescribed by the Motion Picture Association of America (MPAA). Initially, the concept of transfer learning utilized for feature extraction using Google's inception V3 model from Data set prepared by extending the Hollywood-2 dataset and Internet Movie Database (IMDB) referred to as Extended Data Set (EDS). A modified version of the support vector machine (SVM) by combining Principal Component Analysis (PCA) projected to attain classification tasks.PCA incorporated for feature dimensionality reduction to decrease the classification complexity of multiclass SVM. Experiments illustrate a comparative analysis that the proposed, modified version combination of SVM-PCA with Inception V3 showing improved performance than classical classification algorithms like Naive Bayes (NV), Random Forest (RF), Multi-class SVM (...
A Survey on Classification of Videos using Data Mining Techniques
Videos are in huge demand today. The internet is flooded with videos of all types like movie trailers, songs, security cameras etc. we can find so many genres but the only difficulty we face is the proper search of these videos. Sometimes we are irritated and get sick of the irrelevant search result. To sort out this difficulty we aim to classify videos on the basis of different attributes. Here in this paper we survey the video classification literature. Much work has been done in this field and much is awaited. We describe the general features chosen and summarize the research in this area. We conclude with ideas for further research.
Video Classification Using Low-Level Components and Computable Features Assessment
International Journal of New Technology and Research, 2018
Video classifications are usually tailored towards categorizing videos into one or more predefined categories (e.g. genres) using the contexts associated with such categories. This limits their application to only "production videos" (i.e. video produced and edited for a viewing audience). We seek to make the classification criteria more flexible by classifying videos using low-level computable features that can be determined for any type of video independent of the context associated with its predetermined genre. The methodology adopted was based on choosing unrestricted computable features for developing a classification scheme. It extracted and analyzed the low-level components (key frames) and computable features (such as dominant color, lighting condition, and color dynamics) from sample videos. It then generated a model SVM classifier that was able to discriminate between tested videos to be classified. It finally, developed an interactive application to automate the extraction and analysis process.
In this paper, Content Based Video Retrieval Systems performance is analysed and compared for three different types of feature vectors. These types of features are generated using three different algorithms; Block Truncation Coding (BTC) extended for colors, Kekre's Fast Codebook Generation (KFCG) algorithm and Gabor filters. The feature vectors are extracted from multiple frames instead of using only key frames or all frames from the videos. The performance of each type of feature is analysed by comparing the results obtained by two different techniques; Euclidean Distance and Support Vector Machine (SVM). Although a significant number of researchers have expressed dissatisfaction to use image as a query for video retrieval systems, the techniques and features used here provide enhanced and higher retrieval results while using images from the videos. Apart from higher efficiency, complexity has also been reduced as it is not required to find key frames for all the shots. The system is evaluated using a database of 1000 videos consisting of 20 different categories. Performance achieved using BTC features calculated from color components is compared with that achieved using Gabor features and with KFCG features. These performances are compared again with the performances obtained from systems using SVM and the systems without using SVM.