Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Supreetha, R.Has files: No

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Ocular Region Segmentation Model for Diagnosis of Microbial Keratitis Using Slit-Lamp Photography
    (Institute of Electrical and Electronics Engineers Inc., 2023) Supreetha, R.; Sowmya Kamath, S.; Mayya, V.
    Corneal disease, a prevalent cause of global blindness, can lead to severe complications such as Microbial Keratitis, an inflammatory condition of the cornea often caused by bacterial or fungal infections. Early detection and timely treatment are crucial to prevent vision loss associated with this condition. Slit-lamp photography, a standard tool for ocular examination, is commonly employed for diagnosis. To address the growing demand for ophthalmology specialists, numerous studies have explored the use of Deep Learning (DL) algorithms to achieve precise and accurate segmentation of ocular structures, including the cornea, from slit-lamp photography images. In this study, an ocular region segmentation model trained on heterogeneous slit-lamp image datasets for improving learning performance is presented. Various data augmentation strategies are experimented with, and optimization techniques are incorporated. Experiments revealed that the model outperformed several state-of-the-art works concerning Dice score. Furthermore, the model can also be utilized for the unsupervised learning task of mask generation, as the segmentation findings are on par with the ground truth. © 2023 IEEE.
  • No Thumbnail Available
    Item
    Implementing Reversible and Lossless Data Hiding Within Encrypted Images
    (Institute of Electrical and Electronics Engineers Inc., 2024) Supreetha, R.; Lobo, P.A.
    In the realm of data protection, cryptography and steganography stand out as effective methods. Cryptography involves securing data through encryption and decryption processes, while steganography focuses on concealing data within other data. Combining these methodologies creates a strong approach for concealing data within encrypted images, enhancing overall security. Chaotic cryptography has gained prominence due to its effectiveness in encrypting and decrypting images. To reduce the compatibility challenges between certain data hiding techniques and chaotic cryptography, two types of process is devised and put into practice. The first method involves interpolation technique and Least Significant Bit (LSB) data hiding within the chaotic encryption framework. The interpolation technique enhances the compatibility of information insertion within encrypted images. LSB data hiding involves replacing LSB bits of pixels with the secret data. In the second method, a prediction error technique is done along with chaotic encryption. In this, significant effectiveness in securely hiding data within encrypted images is achieved. Chaotic encryption is integrated into both methods to guarantee the confidentiality and protection of the embedded data. In each method, the concealed data is seamlessly embedded within the encrypted image, and upon reception, the information can be accurately extracted. A comparative analysis is conducted based on various parameters, including Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM), computation time, and embedding rate © 2024 IEEE.