Image HASHING allows compression, enhancement or other signal processing operations on digital images that are usually acceptable manipulations. Cryptographic hash functions are very sensitive to even single bit changes in image. Image HASHING is a sum of important quality features in quantized form. In this paper, we propose a novel image HASHING algorithm for authentication, which is more robust against various kinds of attacks. In the proposed approach, a short hash code is obtained using a minimum magnitude Center Symmetric Local Binary Pattern (CSLBP). The desirable discrimination power of image hash is maintained by modified Local Binary Pattern (LBP) based edge weight factor generated from gradient image. The proposed HASHING method extracts texture features using the CSLBP. The discrimination power of HASHING is increased by weight factor during the CSLBP histogram construction. The generated histogram is compressed to 1/4 of the original histogram by a minimum magnitude of CSLBP. The proposed method, has a two-fold advantage; first, it has small length, and second, it has an acceptable discrimination power. The experimental results are demonstrated by the hamming distance and the TPR, FPR, and ROC curves. Therefore, the proposed method successfully does a fair classification of content preserving and content changing images.

Embedding learning is an essential issue in Natural Language Processing (NLP) applications. Most existing methods measure the similarity between text chunks in a context using pre-trained word embedding. However, providing labeled data for model training is costly and time-consuming. So, these methods face downward performance when limited amounts of training data are available. This paper presents an unsupervised sentence embedding method that effectively integrates semantic HASHING into the Kernel Principal Component Analysis (KPCA) to construct embeddings of lower dimensions that can be applied to any domain. The experiments conducted on benchmark datasets highlighted that the generated embeddings are general-purpose and can capture semantic meanings from both small and large corpora.

Face recognition has become a crucial topic in recent decades, which offers important opportunities for applications in security surveillance, human-computer interaction, and forensics. However, it poses challenges, including uncontrolled environments, large datasets, and insufficiency of training data. In this paper, a face recognition system is proposed to iron out the above problems with a new framework based on a HASHING function in a three-stage filtering approach. At the first stage, candidate subjects are chosen using the Locality-Sensitive HASHING (LSH) function. We employ a voting system to select candidates via disregarding a large number of dissimilar identities considering their local features. At the second stage, a robust image HASHING based on Discrete Cosine Transform (DCT) coefficients is used to further refine the candidate images in terms of global visual information. Finally, the test image is recognized among selected identities using other visual information, resulting in further accuracy gains. Extensive experiments on FERET, AR, and ORL datasets show that the proposed method outperforms with a significant improvement in accuracy over the state-of-the-art methods.

This paper introduces a novel approach that adeptly navigates this trade-off, significantly enhancing the deployment efficiency of remote healthcare systems. The existing methodologies in remote healthcare networks typically face challenges in balancing robust security measures with the need for high-speed data transmission. This model meticulously selects from a pool of encryption methods — AES, RSA, ECC, DSA, Blowfish, TwoFish — and HASHING methods — Argon2, SHA1, SHA256, SHA512, MD5, Bcrypt — to tailor a solution that upholds high security while enhancing speed. The rationale behind employing GCN lies in its ability to efficiently handle the complex, non-linear relationships among different encryption and HASHING techniques, while Deep Dyna Q Learning dynamically adjusts hyperparameters to optimize for speed without compromising security.The results were compelling, showcasing an 8.5% improvement in energy efficiency, a 4.9% increase in speed, an 8.3% rise in throughput, a 5.9% enhancement in packet delivery ratio, and a 3.9% boost in communication consistency compared to existing methods. Notably, this enhanced performance was maintained even under various security threats, including Sybil, masquerading, spoofing, and spying attacks.