• Publications
  • Influence
Digital image steganography: Survey and analysis of current methods
TLDR
This paper provides a state-of-the-art review and analysis of the different existing methods of steganography along with some common standards and guidelines drawn from the literature and some recommendations and advocates for the object-oriented embedding mechanism. Expand
A skin tone detection algorithm for an adaptive approach to steganography
TLDR
A new colour space is used which contains error signals derived from differentiating the grayscale map and the non-red encodedgrayscale version to show that luminance can be useful in the segregation of skin and non-skin clusters. Expand
Biometric Inspired Digital Image Steganography
TLDR
This paper proposes using human skin tone detection in colour images to form an adaptive context for an edge operator which will provide an excellent secure location for data hiding. Expand
A dynamic threshold approach for skin segmentation in color images
TLDR
Novel online learned dynamic thresholds are used to overcome the above drawbacks and the experimental results show that the method is robust in overcoming these drawbacks. Expand
Risk factors and tumor characteristics of interval cancers by mammographic density.
TLDR
Interval breast cancers in women with low mammographic density have the most aggressive phenotype, possibly indicating disparate genetic background of screen-detected breast cancers and interval breast cancers. Expand
ARDIS: a Swedish historical handwritten digit dataset
TLDR
Experimental results show that machine learning algorithms, including deep learning methods, provide low recognition accuracy as they face difficulties when trained on existing datasets and tested on ARDIS dataset, which proves that AR DIS dataset has unique characteristics. Expand
A hash-based image encryption algorithm
TLDR
A novel way of encrypting digital images with password protection using 1D SHA-2 algorithm coupled with a compound forward transform is described, which proves that the method is efficient and secure from a cryptographic point of view. Expand
Exploiting Voronoi diagram properties in face segmentation and feature extraction
TLDR
This paper seeks to present a novel face segmentation and facial feature extraction algorithm for gray intensity images (each containing a single face object) based on the Voronoi diagram, a well-known technique in computational geometry, which generates clusters of intensity values using information from the vertices of the external boundary of Delaunay triangulation. Expand
A secure and improved self-embedding algorithm to combat digital document forgery
TLDR
A 1D hash algorithm coupled with 2D iFFT (irreversible Fast Fourier Transform) to encrypt digital documents in the 2D spatial domain and allows legal or forensics expert gain access to the original document despite being manipulated. Expand
Enhancing Steganography in Digital Images
TLDR
This paper discusses the possibility of embedding data in the frames of video files with face instances present and calls it adaptive as it selects the specific region of interest (ROI) in the cover image where it can safely embed data. Expand
...
1
2
3
4
5
...