Expanding image by an arbitrary scale factor and thereby creating an enlarged image is a crucial image processing
operation. De-interlacing is an example of such operation where a video field is enlarged in vertical direction with 1 to 2
scale factor. The most advanced de-interlacing algorithms use a few consequent input fields to generate one output
frame. In order to save hardware resources in video processors, missing lines in each field may be generated without
reference to the other fields. Line doubling, known as “bobbing”, is the simplest intra field de-interlacing method.
However, it may generate visual artifacts. For example, interpolation of an inserted line from a few neighboring lines by
vertical filter may produce such visual artifacts as “jaggies.” In this work we present edge adaptive image up-scaling
and/or enhancement algorithm, which can produce “jaggies” free video output frames. As a first step, an edge and its
parameters in each interpolated pixel are detected from gradient squared tensor based on local signal variances. Then,
according to the edge parameters including orientation, anisotropy and variance strength, the algorithm determines
footprint and frequency response of two-dimensional interpolation filter for the output pixel. Filter’s coefficients are
defined by edge parameters, so that quality of the output frame is controlled by local content. The proposed method may
be used for image enlargement or enhancement (for example, anti-aliasing without resampling). It has been hardware
implemented in video display processor for intra field de-interlacing of video images.