Content-based image retrieval has been keenly developed in numerous fields. This provides more active management and retrieval of images than the keyword-based method. So the content based image retrieval becomes one of the liveliest researches in the past few years. In a given set of objects, the retrieval of information suggests solutions to search for those in response to a particular description. The set of objects which can be considered are documents, images, videos, or sounds. This paper proposes a method to retrieve a multi-view face from a large face database according to color and texture attributes. Some of the features used for retrieval are color attributes such as the mean, the variance, and the color image's bitmap. In addition, the energy, and the entropy which based on the gray level values in an image is too considered as the features. In addition to statistical approaches, models of artificial intelligence produce a desirable methodology that enhances performance in information retrieval systems, and the genetic algorithm depicts one of them. The GA is preferred for its power and because it can be used without any specific information of the domain. The experimental results conclude that using GA gives a good performance and it decreases the average search time to (60.15 milliseconds) compared with (722.25milliseconds) for traditional search.
Background and Aim: due to the rapid growth of data communication and multimedia system applications, security becomes a critical issue in the communication and storage of images. This study aims to improve encryption and decryption for various types of images by decreasing time consumption and strengthening security. Methodology: An algorithm is proposed for encrypting images based on the Carlisle Adams and Stafford Tavares CAST block cipher algorithm with 3D and 2D logistic maps. A chaotic function that increases the randomness in the encrypted data and images, thereby breaking the relation sequence through the encryption procedure, is introduced. The time is decreased by using three secure and private S-Boxes rather than using si
... Show More
(11)
(2)
(1)
(63)
(56)
Correct grading of apple slices can help ensure quality and improve the marketability of the final product, which can impact the overall development of the apple slice industry post-harvest. The study intends to employ the convolutional neural network (CNN) architectures of ResNet-18 and DenseNet-201 and classical machine learning (ML) classifiers such as Wide Neural Networks (WNN), Naïve Bayes (NB), and two kernels of support vector machines (SVM) to classify apple slices into different hardness classes based on their RGB values. Our research data showed that the DenseNet-201 features classified by the SVM-Cubic kernel had the highest accuracy and lowest standard deviation (SD) among all the methods we tested, at 89.51 % 1.66 %. This
... Show More
(1)
(40)
(35)
(123)
(124)
(57)
(57)
Social media is known as detectors platform that are used to measure the activities of the users in the real world. However, the huge and unfiltered feed of messages posted on social media trigger social warnings, particularly when these messages contain hate speech towards specific individual or community. The negative effect of these messages on individuals or the society at large is of great concern to governments and non-governmental organizations. Word clouds provide a simple and efficient means of visually transferring the most common words from text documents. This research aims to develop a word cloud model based on hateful words on online social media environment such as Google News. Several steps are involved including data acq
... Show More
(8)
(3)
The demand for single photon sources in quantum key distribution (QKD) systems has necessitated the use of weak coherent pulses (WCPs) characterized by a Poissonian distribution. Ensuring security against eavesdropping attacks requires keeping the mean photon number (µ) small and known to legitimate partners. However, accurately determining µ poses challenges due to discrepancies between theoretical calculations and practical implementation. This paper introduces two experiments. The first experiment involves theoretical calculations of µ using several filters to generate the WCPs. The second experiment utilizes a variable attenuator to generate the WCPs, and the value of µ was estimated from the photons detected by the BB
... Show More
This paper presents a proposed neural network algorithm to solve the shortest path problem (SPP) for communication routing. The solution extends the traditional recurrent Hopfield architecture introducing the optimal routing for any request by choosing single and multi link path node-to-node traffic to minimize the loss. This suggested neural network algorithm implemented by using 20-nodes network example. The result shows that a clear convergence can be achieved by 95% valid convergence (about 361 optimal routes from 380-pairs). Additionally computation performance is also mentioned at the expense of slightly worse results.