Design of Secure Image Fusion Technique Using Cloud for Privacy-Preserving and Copyright Protection

Kumar, Ashwani

doi:10.4018/ijcac.2019070102

Cited by 46 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the growing demand for automatic interpretation of human action, action recognition has caught the attention in both academia and industry [16]. Analyzing and understanding a person's action in a video is necessary for a wide range of applications, such as web video classification [17], assisting the visually impaired [8], surveillance and security.…”

Section: Action Recognitionmentioning

confidence: 99%

Deep action: A mobile action recognition framework using edge offloading

Zhang

Duan

et al. 2021

Peer-to-Peer Netw. Appl.

View full text Add to dashboard Cite

Recording users' lives as short-form videos has been an emerging trend with the advance of mobile devices. The videos contain a wealth of information that requires a significant amount of computation to retrieve. In this paper, we propose Deep action, a framework that leverages edge offloading to enable human actions recognition on mobile devices. Deep action first samples frames from a video according to the accuracy requirement. The sampled frames are then compressed and fed into deep learning models to generate an action label. Considering the varying conditions of the wireless connection, we design an online scheduler to strategically offload compressed video snippets to the edge server. Furthermore, we use OpenCL to implement the video compression-related operations on mobile GPU, such that the model inference and video compression can operate in parallel on the mobile device. We implement Deep action on the Android OS and evaluate it on a commercial off-the-shelf mobile device and an edge server. The performance evaluation demonstrates that Deep action brings up to 19 × and 13 × execution speedup, compared to the local-only and remote-only strategies, respectively.

show abstract

Section: Action Recognitionmentioning

confidence: 99%

Deep action: A mobile action recognition framework using edge offloading

Zhang

Duan

et al. 2021

Peer-to-Peer Netw. Appl.

View full text Add to dashboard Cite

show abstract

“…In fast RCNN, Ren et al [12] has used 16 architectures in convolution layers to achieve detection and classification accuracy on datasets. Kumar et al [30][31][32] proposed a method to detect the objects with audio device in real time for blind people using deep neural network. Figure 1 demonstrates the architecture of Faster RCNN.…”

Section: Faster Rcnnmentioning

confidence: 99%

Object detection in real time based on improved single shot multi-box detector algorithm

Kumar¹,

Zhang

Lyu

2020

J Wireless Com Network

Self Cite

119

View full text Add to dashboard Cite

In today’s scenario, the fastest algorithm which uses a single layer of convolutional network to detect the objects from the image is single shot multi-box detector (SSD) algorithm. This paper studies object detection techniques to detect objects in real time on any device running the proposed model in any environment. In this paper, we have increased the classification accuracy of detecting objects by improving the SSD algorithm while keeping the speed constant. These improvements have been done in their convolutional layers, by using depth-wise separable convolution along with spatial separable convolutions generally called multilayer convolutional neural networks. The proposed method uses these multilayer convolutional neural networks to develop a system model which consists of multilayers to classify the given objects into any of the defined classes. The schemes then use multiple images and detect the objects from these images, labeling them with their respective class label. To speed up the computational performance, the proposed algorithm is applied along with the multilayer convolutional neural network which uses a larger number of default boxes and results in more accurate detection. The accuracy in detecting the objects is checked by different parameters such as loss function, frames per second (FPS), mean average precision (mAP), and aspect ratio. Experimental results confirm that our proposed improved SSD algorithm has high accuracy.

show abstract

“…[5], [6]. Kumar et al [7][8][9][10][11][12] proposed different buyer seller watermarking protocol to provide secure and private transaction between the communicating parties.In general the benefits of the cloud are in the form of revolution, different serious issues and challenges are reported by cloud computing [13], [14]. These issues are connectivity and fault-tolerance capability adequate security etc [15].…”

Section: Related Workmentioning

confidence: 99%

Secret Image Digitization Over Public Cloud Through Cbtv Based Image Fusion

Gupta¹,

Kumar²

2019

IJITEE

Self Cite

View full text Add to dashboard Cite

Data security in the modern world is a challenging aspect faced by common man in almost every field-either technical or non-technical. Particularly in Public Clouds where the data is openly available across the internet, customers are not much exposed to the working environment and the diverse spread of data across world wide geographic locations. Intruders attempt to misuse this data to serve their own commercial purpose. The government of India proposed NAD (National Academic Depository) which is a secure zone for people to deposit their valuable certificates rather than carrying to places. Towards this end, the goal of current work is to strengthen the security of certificates being loaded into the depositories by applying Image fusion technique through CBTV (Cloud Based Threshold Value). The proposed method gives a unique solution to prove authenticity of users by generating the secret image using image fusion technique integrated with public key infrastructure on the cloud prior to outsourcing. This is particularly useful to protect the patient health care reports to hide the disease description etc, which may otherwise have unintended consequences. The entire fusion is not disclosed at the cloud server end. The performance of the proposed approach, can be measure by calculating the robustness of the secret image (fused image) against different types of image processing attacks such as salt & pepper noise, Gaussian noise, JPEG compression, speckle noise, geometric noise etc. is calculated while stored at the cloud and effective results are achieved.

show abstract

Design of Secure Image Fusion Technique Using Cloud for Privacy-Preserving and Copyright Protection

Cited by 46 publications

References 19 publications

Deep action: A mobile action recognition framework using edge offloading

Deep action: A mobile action recognition framework using edge offloading

Object detection in real time based on improved single shot multi-box detector algorithm

Secret Image Digitization Over Public Cloud Through Cbtv Based Image Fusion

Contact Info

Product

Resources

About