The science of information security has become a concern of many researchers, whose efforts are trying to come up with solutions and technologies that ensure the transfer of information in a more secure manner through the network, especially the Internet, without any penetration of that information, given the risk of digital data being sent between the two parties through an insecure channel. This paper includes two data protection techniques. The first technique is cryptography by using Menezes Vanstone elliptic curve ciphering system, which depends on public key technologies. Then, the encoded data is randomly included in the frame, depending on the seed used. The experimental results, using a PSNR within avera

A system was used to detect injuries in plant leaves by combining machine learning and the principles of image processing. A small agricultural robot was implemented for fine spraying by identifying infected leaves using image processing technology with four different forward speeds (35, 46, 63 and 80 cm/s). The results revealed that increasing the speed of the agricultural robot led to a decrease in the mount of supplements spraying and a detection percentage of infected plants. They also revealed a decrease in the percentage of supplements spraying by 46.89, 52.94, 63.07 and 76% with different forward speeds compared to the traditional method.

 Data Driven Requirement Engineering (DDRE) represents a vision for a shift from the static traditional methods of doing requirements engineering to dynamic data-driven user-centered methods. Data available and the increasingly complex requirements of system software whose functions can adapt to changing needs to gain the trust of its users, an approach is needed in a continuous software engineering process. This need drives the emergence of new challenges in the discipline of requirements engineering to meet the required changes. The problem in this study was the method in data discrepancies which resulted in the needs elicitation process being hampered and in the end software development found discrepancies and could not meet the need

The effectiveness of detecting and matching of image features using multiple views of a specified scene using dynamic scene analysis is considered to be a critical first step for many applications in computer vision image processing. The Scale invariant feature transform (SIFT) can be applied very successfully of typical images captured by a digital camera.
In this paper, firstly the SIFT and its variants are systematically analyzed. Then, the performances are evaluated in many situations: change in rotation, change in blurs, change in scale and change in illumination. The outcome results show that each algorithm has its advantages when compared with other algorithms

Image classification is the process of finding common features in images from various classes and applying them to categorize and label them. The main problem of the image classification process is the abundance of images, the high complexity of the data, and the shortage of labeled data, presenting the key obstacles in image classification. The cornerstone of image classification is evaluating the convolutional features retrieved from deep learning models and training them with machine learning classifiers. This study proposes a new approach of “hybrid learning” by combining deep learning with machine learning for image classification based on convolutional feature extraction using the VGG-16 deep learning model and seven class