We present Genie Pro, a new software tool for image analysis produced by the ISIS (Intelligent Search in Images and Signals) group at Los Alamos National Laboratory. Like the earlier GENIE tool produced by the same group, Genie Pro is a general purpose adaptive tool that derives automatic pixel classification algorithms for satellite/aerial imagery, from training input provided by a human expert. Genie Pro is a complete rewrite of our earlier work that incorporates many new ideas and concepts. In particular, the new software integrates spectral information; and spatial cues such as texture, local morphology and large-scale shape information; in a much more sophisticated way. In addition, attention has been paid to how the human expert interacts with the software: Genie Pro facilitates highly efficient training through an interactive and iterative “training dialog”. Finally, the new software runs on both Linux and Windows platforms, increasing its versatility. We give detailed descriptions of the new techniques and ideas in Genie Pro, and summarize the results of a recent evaluation of the software.
This research focuses on a quantitative evaluation of images produced by multi-resolution 3D texture-based volume rendering methods. Volume rendering techniques utilize nearly all the data in a
volumetric data set to construct an image, so using coarser versions of the original data may negatively impact the display quality of the images produced. The trade-offs between a more efficient use of memory space needed to store a multi-resolution representation versus the potential sacrifice of image quality are characterized by visual inspection and by two image quality measurements: root mean
square error (RMSE) and normalized mutual information (NMI).
RMSE is a traditional image quality measurement and NMI is a recent technique used in image processing and human vision research that incorporates image entropies into a concise, intuitive information-based measurement to quantify information content. Using image entropy as a measure of information can help determine if there is some kind of structural artifact in the image, so it may compliment RMSE, which is often used to identify random error.
The analysis of images produced from multi-resolution volume rendering experiments indicates that there is additional merit in looking at information-based measurements of image quality as well as
using traditional measurements to identify and quantitatively evaluate regions of mismatch.