Detection of linear and cubic interpolation in JPEG compressed images

A novel algorithm is introduced that can detect the presence of interpolation in images prior to compression as well as estimate the interpolation factor. The interpolation detection algorithm exploits a periodicity in the second derivative signal of interpolated images. The algorithm performs well for a wide variety of interpolation factors, both integer factors and non-integer factors. The algorithm performance is noted with respect to a digital camera\´s "digital zoom" feature. Overall the algorithm has demonstrated robust results and might prove to be useful for situations where an original resolution of the image determines the action of an image processing chain.