Patch-Based Denoising with K-Nearest Neighbor and SVD for Microarray Images

Steganography was originally developed to hide and transmit sensitive information. One major advancement in this field is the ability to hide data within digital images. Significant progress has been made, demonstrating effective methods for concealing data. Various techniques have been used, including statistical steganography, distortion techniques, and the Discrete Cosine Transform (DCT). However, the Least Significant Bit (LSB) method is particularly important and remains the most widely used. Researchers have developed methods based on these principles, such as pseudorandom permutation. This paper introduces the Most Match Parity Bit Approach (MMPB-A), which is based on the LSB method. MMPB-A strategically identifies the parity bits of selected pixels to embed information in cover images. It uses a six-bit encryption for each symbol, allowing ample space to hide information while preserving similarity and secrecy. Additionally, encoding hidden data indices in a three-bit code enhances data concealment and ensures greater confidentiality.

show abstract

Patch-Based Denoising with K-Nearest Neighbor and SVD for Microarray Images

Cited by 3 publications

References 34 publications

A novel density-based adaptive k nearest neighbor method for dealing with overlapping problem in imbalanced datasets

A novel density-based adaptive k nearest neighbor method for dealing with overlapping problem in imbalanced datasets

cDNA Microarray Image Segmentation Based on Deep Convolutional Neural Network

Exposing the most match parity bit approach (MMPB-A) for data concealment in digital images

Contact Info

Product

Resources

About