Effective Recognition of Stereo Image Concealed Media of Interpolation Error with Difference Expansion

Effective Recognition of Stereo Image Concealed Media of Interpolation Error with Difference Expansion

Hemalatha J. (Thiagarajar College of Engineering, India) and Kavitha Devi M. K. (Thiagarajar College of Engineering, India)
DOI: 10.4018/978-1-5225-0193-0.ch010
OnDemand PDF Download:
No Current Special Offers


In this chapter, a new data conceal technique is anticipated for digital images. The method computes the interpolation error of the image by using histogram shifting method and difference expansion. With the expectation of embedding high payload and less distortion, the undisclosed data has embedded in the interpolating error. Additionally for hiding the data, reversible data hiding technique is used. The histogram deviation is used as evidence for resulting the data conceal in the stereo images. To our best knowledge, by extracting the statistical feature from the image subsample works as steganalysis scheme. To enhance the revealing rate precision the well known support vector machine acts as classifier. In addition to that the experimental results show that the proposed steganalysis method has enhanced the detection exactness of the stego images.
Chapter Preview

Interpolation And Reversible Data Hiding

Interpolation Methods

In digital images, interpolation ensues at some stage. The process of finding the function value at a particular position lies between the samples. It occurs owing to resizing an image, or maps an image from one pixel to other. Each and every time increasing or reducing the number of pixels and remapping arise on the scenarios such as image rotation, lens distortion correction. Whenever the interpolation is performing, there might be some quality loss in the resultant image, and it can be minimized. The fundamental thought of interpolation is by knowing the data and calculates the values at some unknown point. By putting on the low pass filter over the discrete signal, the bandwidth can be reduced for a particular. The image quality can be greatly achieved based on the interpolation technique used.

The interpolation technique can be broadly divided into two categories namely statistical and deterministic interpolation technique. In the deterministic techniques, among the sample point certain variation can be considered. While in statistical method, the signal can be approximated by reducing the estimation error. When comparing to deterministic methods the statistical method are computationally inefficient. Occasionally two dimension interpolation is problematic to define. In case of gridded data n dimension interpolation function can be termed as the multiplication of n 1-dimension interpolation functions.

In the deterministic method the subsequent methods are used namely nearest neighbor, spline, and linear interpolation techniques.

Nearest Neighbor Interpolation or Pixel Replication

In this technique the nearest sample point on the input image is assigned to the corresponding output pixel. The kernel is defined in the following Equation 1,

(1) where 978-1-5225-0193-0.ch010.m02 denotes the kernel for nearest neighbor and 978-1-5225-0193-0.ch010.m03 denotes the sample point. Whenever changes occur by large range, the nearest neighbor interpolation technique resulted in image with blockier effect.

Complete Chapter List

Search this Book: