Yazar "Jasim, Zinah Khalid Jasim" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim
    Öğe
    An improved image steganography security and capacity using ant colony algorithm optimization
    (Tech Science Press, 2024) Jasim, Zinah Khalid Jasim; Kurnaz, Sefer
    This advanced paper presents a new approach to improving image steganography using the Ant Colony Optimization (ACO) algorithm. Image steganography, a technique of embedding hidden information in digital photographs, should ideally achieve the dual purposes of maximum data hiding and maintenance of the integrity of the cover media so that it is least suspect. The contemporary methods of steganography are at best a compromise between these two. In this paper, we present our approach, entitled Ant Colony Optimization (ACO)-Least Significant Bit (LSB), which attempts to optimize the capacity in steganographic embedding. The approach makes use of a grayscale cover image to hide the confidential data with an additional bit pair per byte, both for integrity verification and the file checksum of the secret data. This approach encodes confidential information into four pairs of bits and embeds it within uncompressed grayscale images. The ACO algorithm uses adaptive exploration to select some pixels, maximizing the capacity of data embedding while minimizing the degradation of visual quality. Pheromone evaporation is introduced through iterations to avoid stagnation in solution refinement. The levels of pheromone are modified to reinforce successful pixel choices. Experimental results obtained through the ACO-LSB method reveal that it clearly improves image steganography capabilities by providing an increase of up to 30% in the embedding capacity compared with traditional approaches; the average Peak Signal to Noise Ratio (PSNR) is 40.5 dB with a Structural Index Similarity (SSIM) of 0.98. The approach also demonstrates very high resistance to detection, cutting down the rate by 20%. Implemented in MATLAB R2023a, the model was tested against one thousand publicly available grayscale images, thus providing robust evidence of its effectiveness.
  • [ X ]
    Öğe
    Human identification with finger vien image using deep learning
    (IEEE, 2021) Jasim, Zinah Khalid Jasim; Mohammed, Alaa Hamid; Elwiya, Lina; Al-Jabbari, Baraa Dhafer; Alhaji, Haitham
    The technical term for body measurements and estimates is called biometrics. It refers to metrics related to human characteristics. Biometrics classification is using in computer science as a form of identification and access control. Classification is one of the pattern recognition methods that consist of grouping similar data into classes. Automated personal identification using vascular biometrics. The Convolutional Neural Network (CNN) has demonstrated its remarkable ability to learn biometric traits that can provide a robust and accurate match. This thesis aims to develop a robust finger-vein identification system using CNN. Since finger vein lies under the human body, so they need Near Infrared (NIR) light and camera for acquiring, the finger-vein require spectrum light with the camera to capture. The capture images need to pass through several stages, including reprocessing, pattern extraction, and matching, to decide to get an individual ID. This research proposes an efficient deep learning model to build a robust finger vein identification system. After images preprocessing and vein pattern extraction, feature extraction and matching are performed by the proposed CNN model, which has one input layer and more than one hidden layer and one output layer. The first hidden layer is known as the convolution layer its plays the role of feature extraction and produces features map, followed by the pooling layer, which acts as a filter to remove unwilling features, and batch Normalization layer to speed up the training process. The system presented 99.78 % accuracy which is remarkable when compared with several researches.
  • [ X ]
    Öğe
    Retinal fundus images of optical disk detection
    (IEEE, 2021) Elwiya, Lina; Mohammed, Alaa Hamid; Jasim, Zinah Khalid Jasim
    Optical circle identification (OD) is a significant advance in the programmed division and investigation of pictures of the retina. In this article, another approach is proposed for recognizing RE cutoff points from shading retinal fundus pictures. Morphological factors and differentiation improvement methods are utilized related to a Gaussian contrast (DOG) channel to acquire an OD limit. Our proposed calculation makes a high progress rate with comparative computational time. The exhibition of our proposed strategy was assessed on 1660 pictures addressing six freely accessible informational collections; STARE, DRIVE, ARIA, DIARETDB1, DIARETDB0, and MESSIDOR informational indexes. The trial results show that the pictures from the DRIVE, ARIA, DIARETDB1 and DIARETDB0 datasets have a 100% achievement rate, which is superior to the precision of the most recent age techniques, which is under 99% for the ARIA, DIARETDB1 and DIARETDB0 informational indexes. While coming to 98.8% and 99.83% for the STARE and MESSIDOR datasets individually, the calculation runs with a normal computational season of 1.2 seconds.