Advanced Evaluation Method for Video Retrieval System

Journal of Theoretical and Applied Information Technology, 2023

Over the past ten years, researchers have studied the Content Based Video Retrieval System, based on numerous applications, advancements, and technologies. In video retrieval systems, there is still a requirement for the high-level semantic elements as and the processing of low level materials. As a result, it inspires and motivates a lot of academics to learn more about the content Retrieval and to make more useful and effective while creating system applications. Analysis of video for retrieval of key aspects is regarded as earlier work. In this instance, input videos from YouTube are watched for analysis. After that, foreground segmentation is carried out to find a lot of tiny subset objects since each subset must identify the foreground video class. Given for feature extraction is the split region. In this study, four distinct methods for extracting features�chromatic moment, blur, color variety, and reflection features are taken into consideration. The high dimensionality characteristics are removed from the retrieved features using Principal Component Analysis since they may affect classification accuracy. The feature vectors are taken into account while combining all of the parts. The Nave Bayes classifier is used to complete the classification process. Metrics including accuracy, precision, recall, and F-measure are used to gauge how effectively video retrieval is performed. The predicted model outperforms the current strategy when the proposed model and the in-depth learning approach are compared.

Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016, 2017

We share the implementation details and testing results for video retrieval system based exclusively on features extracted by convolutional neural networks. We show that deep learned features might serve as universal signature for semantic content of video useful in many search and retrieval tasks. We further show that graph-based storage structure for video index allows to efficiently retrieving the content with complicated spatial and temporal search queries.

SN Applied Sciences, 2019

Retrieval of videos efficiently and effectively has become a challenging issue nowadays and dealing with multi-concept videos is the center of focus. The aim of the work presented here is to propose an improved semantic concept-based video retrieval method using a novel ranked intersection filtering technique and a foreground driven concept co-occurrence matrix. In the proposed ranked intersection filtering technique, an intersection of ranked concept probability scores is taken from key-frames associated with a query shot to identify concepts to be used in retrieval. Convolutional neural network is used as a baseline. The proposed method is implemented using a classifier built with a fusion of asymmetrically trained deep CNNs to deal with data imbalance problem, a novel foreground driven concept co-occurrence matrix to exploit concept co-occurrence information and a ranked intersection filtering approach. Performance is evaluated by a measure, mean average precision on TRECVID multi-label dataset. The results are compared with state-of-the-art other existing methods in its class and shown its superiority.

ArXiv, 2021

Video content classification is an important research content in computer vision, which is widely used in many fields, such as image and video retrieval, computer vision. This paper presents a model that is a combination of Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) which develops, trains, and optimizes a deep learning network that can identify the type of video content and classify them into categories such as “Animation, Gaming, natural content, flat content, etc”. To enhance the performance of the model novel keyframe extraction method is included to classify only the keyframes, thereby reducing the overall processing time without sacrificing any significant performance.

International Journal for Research in Applied Science and Engineering Technology (IJRASET), 2021

In a Content Based Image Retrieval (CBIR) System, the task is to retrieve similar images from a large database given a query image. The usual procedure is to extract some useful features from the query image, and retrieve images which have similar set of features. For this purpose, a suitable similarity measure is chosen, and images with high similarity scores are retrieved. Naturally the choice of these features play a very important role in the success of this system, and high level features are required to reduce the "semantic gap". In this paper, we propose to use features derived from pre-trained network models from a deep-learning convolution network trained for a large image classification problem. This approach appears to produce vastly superior results for a variety of databases, and it outperforms many contemporary CBIR systems. We analyse the retrieval time of the method, and also propose a pre-clustering of the database based on the above-mentioned features which yields comparable results in a much shorter time in most of the cases.

2020

The Closed-Circuit Television (CCTV) footages plays a vital role in criminal investigations which helps to reduce cost, time and effort but still it has many challenges to face such as monitoring multiple cameras simultaneously, missing pre-eminent details or the object captured on video surveillance, excess storage of video data and spending huge time on watching the entire suspect video to collect the affirmation for investigations. The Motion Detection, Facial recognition, Automatic number plate recognition through CCTV streams a live report. From this, the identification of suspicious behaviour, like public inebriation or attaining thievery from the entire video content becomes very critical to deter the criminals. To meliorate all these situation, Content Based Video retrieval (CBVR) is efficiently used to analyze the video content of the CCTV Footages. The CBVR detects the shots and frames obtained from the CCTV Footages where it analyzes the Color, texture, shape and inter-fr...

Ingénierie Des Systèmes D'information, 2020

This paper intends to present main technique for feature extraction on multimeda getting well versed and a challenging task to handle big data. Analyzing and feature extracting valuable data from high dimensional dataset challenges the bounds of measurable methods and strategies. Conventional techniques in general have less performance while managing high dimensional datasets. Lower test size has consistently been an issue in measurable tests, which get bothered in high dimensional information due to more equivalent or higher component size than the quantity of tests. The intensity of any measurable test is legitimately relative to its capacity to lesser an invalid theory, and test size is a significant central factor in producing probabilities of errors for making substantial ends. Thus one of the effective methods for taking care of high dimensional datasets is by lessening its measurement through feature selection and extraction with the goal that substantial accurate data can be practically performed. Clustering is the act of finding hidden or comparable data in information. It is one of the most widely recognized techniques for realizing useful features where a weight is given to each feature without predefining the various classes. In any feature selection and extraction procedures, the three main considerations of concern are measurable exactness, model interpretability and computational multifaceted nature. For any classification model, it is important to ensure that the productivity of any of these three components isn't undermined. In this manuscript, a Weight Based Feature Extraction Model on Multifaceted Multimedia Big Data (WbFEM-MMB) is proposed which extracts useful features from videos. The feature extraction strategies utilize features from the discrete cosine methods and the features are extracted using a pre-prepared Convolutional Neural Network (CNN). The proposed method is compared with traditional methods and the results show that the proposed method exhibits better performance and accuracy in extracting features from multifaceted multimedia data.

Video retrieval is a young field which has its genealogy rooted in artificial intelligence, digital signal processing, statistics, natural language understanding, databases, psychology, computer vision, and pattern recognition. However, none of these parental fields alone has been able to directly solve the retrieval problem. In this paper we present a System that supports video mining from multimedia warehouse using multimodal feature has two stages, the first one is building the multimedia warehouse and the second one is retrieving the video from that multimedia warehouse. The Video Retrieval system includes various steps: Video Segmentation, Key frames Selection, Feature Extraction. For retrieving the video from warehouse, the retrieval subsystem processes the presented query, performs similarity matching operations and this can be done using Euclidian Distance Algorithm, and finally displays the result to end user.

 Abstract— Content based video retrieval (CBVR) utilizes the rich and varied video contents for video representation and retrieval. The contents can be broadly divided into static frame level contents, spacio-temporal contents, motion contents and high level semantic contents. Many successful techniques have been proposed in various literature which focus on these levels. Few of these recent ones are highlighted in this paper. Work done on static frame level use well researched techniques also used in CBIR. These are used when there is a wider variety of videos to retrieve. Techniques which use the dynamic contents work well on videos which have unique characteristic motions as their identifying factor. The temporal and motion information is utilized for retrieval purposes. The feature extraction methods used demonstrate varying degrees of computation complexity and performance. The extraction of high level semantic contents requires incorporation of techniques capable of utilizing the low and middle level video data to extract the topic or subject of the video. Analysis of high level semantic is performed using learning models promising higher level of satisfaction in retrieval. The recent trends in CBVR aim for this higher semantic retrieval. As low level contents are the base for extracting semantic content, improvements in handling of low level contents will also be necessary for contribution to this trend.

Traditional video retrieval methods fail to meet technical challenges due to large and rapid growth of multimedia data, demanding effective retrieval systems. In the last decade Content Based Video Retrieval (CBVR) has become more and more popular. The amount of lecture video data on the Worldwide Web (WWW) is growing rapidly. Therefore, a more efficient method for video retrieval in WWW or within large lecture video archives is urgently needed. This paper presents an implementation of automated video indexing and video search in large videodatabase. First of all, we apply automatic video segmentation and key-frame detection to extract the frames from video. At next, we extract textual keywords by applying on video i.e. Optical Character Recognition (OCR) technology on key-frames and Automatic Speech Recognition (ASR) on audio tracks of that video. At next, we also extractingcolour, texture and edge detector features from different method. At last, we integrate all the keywords and features which has extracted from above techniques for searching purpose.Finallysearch similarity measure is applied to retrieve the best matchingcorresponding videos are presented as ou