An intermediate representation suitable for the 2-D recognition of the 3-D objects, from a single intensity image is proposed. Determination of the intermediate representation fro...
Super-resolution image zooming is possible when the image has some geometric regularity. We introduce a general class of non-linear inverse estimators, which combines linear estima...
The fingerprint verification methods include minutiae-based and image-based methods. The minutiae-based method has been frequently used, but it has limitations in performance. Thes...
Jong Ku Kim, Seung-Hoon Chae, Sung Jin Lim, Sung B...
In this work, homomorphic image modeling is used to make the exhaustive block-matching algorithm (EBMA) more human vision system (HVS) aware, thus yielding visually pleasing seque...
We present Transitive Closure based visual word formation technique for obtaining robust object representations from smoothly varying multiple views. Each one of our visual words ...