Content Based Video Retrieval Using Convolutional Neural Network

Iqbal, Saeed; Qureshi, Adnan N.; Lodhi, Awais M.

doi:10.1007/978-3-030-01054-6_12

Cited by 8 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the d values become smaller, the result will be good between two (query video and database video) and hence the results will be greater when claimed. Where features are extracted from query video as well as dataset video and find the most similar video are retrieved from the database, which is near to query video contents and follow the most well-known equation (Euclidean distance measurement) that is most efficient distance measurement equation, which is proved through experimental results (Iqbal et al, 2018).…”

Section: Euclidian Distance-based Similaritymentioning

confidence: 99%

“…After the experiment shows that from the single feature system the multiple feature system performs better. Iqbal et al (2018) used the digital image processing method (Eigenface, the histogram of gradients, active appearance model, and Haar features) on Query Process Model that retrieved a list of videos from a database. And clustering method (k mean, SVM, and K-Nearest Neighbor) and consequence (testing and training) are with their confusion matrix (specificity and Sensitivity).…”

Section: Literature Reviewmentioning

confidence: 99%

“…Currently, most of the data is unstructured such as images, video, text, and music. In information retrieval, content-wise video retrieval is the basic problem (Iqbal et al, 2018). The related video retrieval denotes the work of retrieving the same video gathering, by the user input query to the system.…”

Section: Introductionmentioning

confidence: 99%

“…Convolutional Neural Network design provide a correct statement on behalf of stating inputs digital data and call the network to compile these properties to the design. A reduce the number of parameters to the next function makes that more efficient to implement the network (Iqbal et al, 2018). In the current era of information technology, digital data is played a vital role in law enforcement, office work, and entertainment, and everywhere in life.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Efficient Content Based Video Retrieval System by Applying AlexNet on Key Frames

Hussain

Ahmad²,

Hussain³

et al. 2022

ADCAIJ

View full text Add to dashboard Cite

The video retrieval system refers to the task of retrieving the most relevant video collection, given a user query. By applying some feature extraction models the contents of the video can be extracted. With the exponential increase in video data in online and offline databases as well as a huge implementation of multiple applications in health, military, social media, and art, the Content-Based Video Retrieval (CBVR) system has emerged. The CBVR system takes the inner contents of the video frame and analyses features of each frame, through which similar videos are retrieved from the database. However, searching and retrieving the same clips from huge video collection is a hard job because of the presence of complex properties of visual data. Video clips have many frames and every frame has multiple properties that have many visual properties like color, shape, and texture. In this research, an efficient content-based video retrieval system using the AlexNet model of Convolutional Neural Network (CNN) on the keyframes system has been proposed. Firstly, select the keyframes from the video. Secondly, the color histogram is then calculated. Then the features of the color histogram are compared and analyzed for CBVR. The proposed system is based on the AlexNet model of CNN and color histogram, and extracted features from the frames are together to store in the feature vector. From MATLAB simulation results, the proposed method has been evaluated on benchmark dataset UCF101 which has 13320 videos from 101 action categories. The experiments of our system give a better performance as compared to the other state-of-the-art techniques. In contrast to the existing work, the proposed video retrieval system has shown a dramatic and outstanding performance by using accuracy and loss as performance evaluation parameters.

show abstract

Section: Euclidian Distance-based Similaritymentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficient Content Based Video Retrieval System by Applying AlexNet on Key Frames

Hussain

Ahmad²,

Hussain³

et al. 2022

ADCAIJ

View full text Add to dashboard Cite

show abstract

“…Similar to face detection, popular open-source solutions exist for object detection, e.g., the YOLOv3 architecture with 80 of the most common objects, including human bodies, animals, and various everyday items (Lin et al, 2014). The YOLOv3 architecture is pretrained on COCO, which is the most popular dataset for object detection (Iqbal et al, 2018). The YOLOv3 neural network with 53 layers produces bounding boxes around each object making both exact locations and object sizes available (Fukushima, 1975;LeCun et al, 1989).…”

Section: Frame-level Featuresmentioning

confidence: 99%