Computational efficiency of the Gabor transform

The two-dimensional Gabor transform has been proposed as a model of the visual receptive field of the simple cells of the mammalian striate cortex. The authors analyze the computational steps needed to achieve this transformation and present typical execution times for several computers. The use of an adaptive iteration step size is shown to improve performance significantly. Computational requirements are examined for both sequential and parallel computers. A parallel computer with global addition capability and with a processor for each pixel could perform a Gabor transform in real time. On existing computers, real-time performance is not possible for moderate sized images. Sequential computers show better cost/performance ratios than parallel machines.<
>