Utilizing Convolutional Neural Networks for Image Classification and Securing Mobility of People With Physical and Mental Disabilities in Cloud Systems

Abstract

Image recognition is widely used for detecting human obstructions and identifying people with disabilities. The accuracy of identifying images of handicapped people is powered by image classification techniques that are based on deep learning methodologies. Specifically, convolutional neural networks are employed to improve image classification of people with mental and physical disabilities. In this research, images of people with different disabilities are used to extract hidden features that symbolize each disability. Three different deep learning image classifiers are built to classify images of people in wheelchairs, blind people, and people with Down syndrome. A security technique is developed that is based on multiprotocol label switching headers to secure the image mobility over cloud nodes. The proposed approach is validated by measuring the impact of the deep learning image classifiers on image classification and securing image mobility on cloud system performance. The experimental results show the effectiveness of the proposed approach in improving image prediction of disabled people and enhancing the performance of securing image mobility in cloud systems.INDEX TERMS deep learning, image classification, wide convolutional neural networks, image feature maps, securing image mobility, MPLS header

Privacy-Preserving Cloud Computing: Ecosystem, Life Cycle, Layered Architecture and Future Roadmap

“…In contrast with [330] that authors have analyzed several neural network prediction services from the perspective of privacy-preserving, the privacy of the model, and the query are considered as well as examined several proposals and introduced an optimized neural network prediction scheme that brings about high accuracy, model privacy, and low overheads in the outsourcing setting. Moreover, In [331], different features have been created to symbolize each disability, then by these features, the image of people with a disability such as wheelchairs, blind people, and people with Down syndrome have been classified. The authors' result in [331] has demonstrated that the level of securing image mobility in Cloud systems has been improved.…”

“…Moreover, In [331], different features have been created to symbolize each disability, then by these features, the image of people with a disability such as wheelchairs, blind people, and people with Down syndrome have been classified. The authors' result in [331] has demonstrated that the level of securing image mobility in Cloud systems has been improved. In addition, the authors have introduced a framwork that provides training and testing data privacy in [332], this framwork is a secure cloud-intelligent network that is supported by privacy-preserving machine learning similar to [333] that authors have introduced a framwork called SPDDL (Secure and Privacy-preserving distributed deep learning) for secure and privacy-preserving Distributed Deep Learning (DDL) that makes better security, efficiency, and functionality and preserves users identities from external adversaries.…”

Down syndrome markers classification via dense neural network in ultrasound foetal image

“…In 2020, I. Hababeh et al, [17] proposed a wide convolution neural network method for secure image mobility of disabling and Down syndrome people. The work focus on the classification of the medical image of people with Down syndrome and physical disability.…”

Deep Learning in Computer Real-time Graphics and Image Using the Visual Effects of Non-photorealistic Rendering of Ink Painting

“…Finally, the image is converted back to the RGB color space, and the conversion is as follows: CNN successively convolves the receptive field information of the input image through the features map (filter) [28] to obtain the image features information (features map) that is unchanged in translation, rotation and scaling, and then transmits the information to the higher layers in turn. When the CNN is trained for target recognition, the target information represented by the image features information becomes more and more clear as the number of layer increases [29]. The content of the photo is obtained by a random image matching the feature response of a photo in a certain layer of CNN [30].…”