Linguistic steganography is used for hiding information in the multimedia data in a traditional approach. For that, we are taking an image and converting the text into bits like 0's and 1's. In this paper, we are using both image and text dataset. Nowadays, providing secure data with confidentiality and integrity has become a big challenge in the present world. To improve the security of these existing parameters, we have proposed a methodology by referring through various reference papers and existing methodologies that can provide and attain confidentiality and integrity by utilizing various algorithms to provide a collective result. We have used algorithms like support vector machine (SVM), recurrent neural network (RNN), and convolutional neural network (CNN). For higher security, steganography algorithm is employed to mix with this algorithm. By applying the above algorithms, we will be doing encoding for providing more security. Image quality will not be loosed and there will be efficiency in decoding the information by doing encoding. If any users attack the code, due to the techniques that we used in our encoding, enhancing more security will be provided.
This article presents the Joints and Trajectory-pooled 3D-Deep Positional Attention-based Bidirectional Recurrent convolutional Descriptors (JTPADBRD) for recognizing the human activities from video sequences. At first, the video is partitioned into clips and these clips are given as input of a two-stream Convolutional 3D (C3D) network in which the attention stream is used for extracting the body joints locations and the feature stream is used for extracting the trajectory points including spatiotemporal features. Then, the extracted features of each clip is needed to aggregate for creating the video descriptor. Therefore, the pooled feature vectors in all the clips within the video sequence are aggregated to a video descriptor. This aggregation is performed by using the PABRNN that concatenates all the pooled feature vectors related to the body joints and trajectory points in a single frame. Thus, the convolutional feature vector representations of all the clips belonging to one video sequence are aggregated to be a descriptor of the video using Recurrent Neural Network (RNN)-based pooling. Besides, these two streams are multiplied with the bilinear product and end-to-end trainable via class labels. Further, the activations of fully connected layers and their spatiotemporal variances are aggregated to create the final video descriptor. Then, these video descriptors are given to the Support Vector Machine (SVM) for recognizing the human behaviors in videos. At last, the experimental outcomes exhibit the considerable improvement in Recognition Accuracy (RA) of the JTDPABRD is approximately 99.4% achieved on the Penn Action dataset as compared to the existing methods.
Objective: To learn different geometric features of body joints from video frames, as well as trajectory point coordinates, for Human Activity Recognition (HAR). Methods: Joints and Trajectory-pooled 3D-Deep Geometric Positional Attention-based Hierarchical Bidirectional Recurrent convolutional Descriptors (JTDGPAHBRD)-based HAR framework is proposed. This framework considers the skeleton graph to extract geometric features such as joints, edges, and surfaces, along with the trajectory point coordinates. A new 3D-deep convolutional network with View Conversion (VC) and Temporal Dropout (TD) layers is designed that uses a Positional Attention-based Hierarchical Bidirectional Recurrent Neural Network (PAHBRNN) to learn more discriminatory high-level features. Then, a Fully Connected Layer (FCL) is applied to get the Video Descriptor (VD) of a particular frame. Moreover, the obtained VD is classified by the Support Vector Machine (SVM) classifier to recognize various kinds of human activities. Findings: The test findings show that the JTDGPAHBRD framework using the Penn Action database achieves a recognition rate of 99.7% compared to the existing HAR frameworks. Novelty: This framework has significantly improved the recognition of human activities. Thus, it represents a promising framework for the HAR.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.