In this paper, a new modification was proposed to enhance the security level in the Blowfish algorithm by increasing the difficulty of cracking the original message which will lead to be safe against unauthorized attack. This algorithm is a symmetric variable-length key, 64-bit block cipher and it is implemented using gray scale images of different sizes. Instead of using a single key in cipher operation, another key (KEY2) of one byte length was used in the proposed algorithm which has taken place in the Feistel function in the first round both in encryption and decryption processes. In addition, the proposed modified Blowfish algorithm uses five Sboxes instead of four; the additional key (KEY2) is selected randomly from additional Sbox5, the fifth Sbox is formed in GF(28) and it is variable to increase the complexity of the proposed algorithm. The obtained results were tested using many criteria: correlation criteria, number of pixels change rate (NPCR) and mean square error (MSE). These tested factors were approved by the output results which demonstrated that the correlation of image elements in the proposed algorithm was significantly reduced during the encryption operation. Also, the algorithm is very resistant to attempts of breaking the cryptographic key since two keys were used in the encryption/ decryption operations which lead to increase the complexity factor in the proposed algorithm.
In the present work, an image compression method have been modified by combining The Absolute Moment Block Truncation Coding algorithm (AMBTC) with a VQ-based image coding. At the beginning, the AMBTC algorithm based on Weber's law condition have been used to distinguish low and high detail blocks in the original image. The coder will transmit only mean of low detailed block (i.e. uniform blocks like background) on the channel instate of transmit the two reconstruction mean values and bit map for this block. While the high detail block is coded by the proposed fast encoding algorithm for vector quantized method based on the Triangular Inequality Theorem (TIE), then the coder will transmit the two reconstruction mean values (i.e. H&L)
... Show MoreMost recognition system of human facial emotions are assessed solely on accuracy, even if other performance criteria are also thought to be important in the evaluation process such as sensitivity, precision, F-measure, and G-mean. Moreover, the most common problem that must be resolved in face emotion recognition systems is the feature extraction methods, which is comparable to traditional manual feature extraction methods. This traditional method is not able to extract features efficiently. In other words, there are redundant amount of features which are considered not significant, which affect the classification performance. In this work, a new system to recognize human facial emotions from images is proposed. The HOG (Histograms of Or
... Show More
(2)
(1)
(40)
(39)
Chacha 20 is a stream cypher that is used as lightweight on many CPUs that do not have dedicated AES instructions. As stated by Google, that is the reason why they use it on many devices, such as mobile devices, for authentication in TLS protocol. This paper proposes an improvement of chaha20 stream cypher algorithm based on tent and Chebyshev functions (IChacha20). The main objectives of the proposed IChacha20 algorithm are increasing security layer, designing a robust structure of the IChacha20 to be enabled to resist various types of attacks, implementing the proposed algorithm for encryption of colour images, and transiting it in a secure manner. The test results proved that the MSE, PSNR, UQI and NCC metrics
... Show More
(4)
(1)
Semantic segmentation is effective in numerous object classification tasks such as autonomous vehicles and scene understanding. With the advent in the deep learning domain, lots of efforts are seen in applying deep learning algorithms for semantic segmentation. Most of the algorithms gain the required accuracy while compromising on their storage and computational requirements. The work showcases the implementation of Convolutional Neural Network (CNN) using Discrete Cosine Transform (DCT), where DCT exhibit exceptional energy compaction properties. The proposed Adaptive Weight Wiener Filter (AWWF) rearranges the DCT coefficients by truncating the high frequency coefficients. AWWF-DCT model reinstate the convolutional l
... Show More
(1)
(1)
(3)
(3)
(1)
With the rapid development of smart devices, people's lives have become easier, especially for visually disabled or special-needs people. The new achievements in the fields of machine learning and deep learning let people identify and recognise the surrounding environment. In this study, the efficiency and high performance of deep learning architecture are used to build an image classification system in both indoor and outdoor environments. The proposed methodology starts with collecting two datasets (indoor and outdoor) from different separate datasets. In the second step, the collected dataset is split into training, validation, and test sets. The pre-trained GoogleNet and MobileNet-V2 models are trained using the indoor and outdoor se
... Show More
(2)
In many areas, such as simulation, numerical analysis, computer programming, decision-making, entertainment, and coding, a random number input is required. The pseudo-random number uses its seed value. In this paper, a hybrid method for pseudo number generation is proposed using Linear Feedback Shift Registers (LFSR) and Linear Congruential Generator (LCG). The hybrid method for generating keys is proposed by merging technologies. In each method, a new large in key-space group of numbers were generated separately. Also, a higher level of secrecy is gained such that the internal numbers generated from LFSR are combined with LCG (The adoption of roots in non-linear iteration loops). LCG and LFSR are linear structures and outputs
... Show More
(8)
(5)