×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerIn recent years, there has been a considerable rise in the applications in which object or image categorization is beneficial for example, analyzing medicinal images, assisting persons to organize their collections of photos, recognizing what is around self-driving vehicles, and many more. These applications necessitate accurately labeled datasets, in their majority involve an extensive diversity in the types of images, from cats or dogs to roads, landscapes, and so forth. The fundamental aim of image categorization is to predict the category or class for the input image by specifying to which it belongs. For human beings, this is not a considerable thing, however, learning computers to perceive represents a hard issue that has become a broad area of research interest, and both computer vision techniques and deep learning algorithms have evolved. Conventional techniques utilize local descriptors for finding likeness between images, however, nowadays; progress in technology has provided the utilization of deep learning algorithms, especially the Convolutional Neural Networks (CNNs) to auto-extract representative image patterns and features for classification The fundamental aim of this paper is to inspect and explain how to utilize the algorithms and technologies of deep learning to accurately classify a dataset of images into their respective categories and keep model structure complication to a minimum. To achieve this aim, must focus precisely and accurately on categorizing the objects or images into their respective categories with excellent results. And, specify the best deep learning-based models in image processing and categorization. The developed CNN-based models have been proposed and a lot of pre-training models such as (VGG19, DenseNet201, ResNet152V2, MobileNetV2, and InceptionV3) have been presented, and all these models are trained on the Caltech-101 and Caltech-256 datasets. Extensive and comparative experiments were conducted on this dataset, and the obtained results demonstrate the effectiveness of the proposed models. The obtained results demonstrate the effectiveness of the proposed models. The accuracy for Caltech-101 and Caltech-256 datasets was (98.06% and 90%) respectively.
The security of communications in various transmitted information’s forms such as video, audio, image, and even text and preserving them from attackers has become of great importance in the age of the Internet and cellular networks. Perhaps one of the most important media used to transmit information is digital images. They are distinguished from video and audio by their lack of complexity, and at the same time they are distinguished from text by the possibility of containing more information. Due to the necessity of transmitting huge amounts of information via digital images through additive white Gaussian noise (AWGN) channels for various applications. This transmission of images over unsecured channels is vulnerable to many attacks that must be protected by information security tools. In this research, a hybrid chaos-based system was developed to encrypt and secure images and send them via an orthogonal frequency division multiplexing (OFDM) channel, which leads to transferring large amounts of transmitted information in a short time, with very little interference between the data, and maintaining the transfer rate. Two chaotic techniques, Rossler and Modified Chau system, are used together to create a secret encryption key. This combination of chaotic systems provides highly random sensitive keys with amplitude of 10252 that are difficult to predict by the attacker and which makes restoring the original image very difficult in the event of a very small change in the chaotic parameters. Many tests were conducted to determine the strength of the proposed system, including statistical and differential analysis and entropy to verify the strength of the image security approach, in addition to applying some types of attacks to the encrypted image, such as noise and cropping different parts of the image. It is clear that the proposed scheme has strong immunity to these attacks. This was proven by the comparative experimental results. The entropy ratio was very excellent compared to the rest of the results obtained in the rest of the research. This was also the case with the values of (NPCR), (UACI), (NPCR), and Mean Square Error (MSE) was also very good as compared with other researches in the literature. The proposed security approach for OFDM gave a low link and a low bit error rate. And a higher signal-to-noise ratio (PSNR).