Describes an approach to edge detection particularly suited for implementation on distributed-memory massively parallel MIMD machines. One of the main tasks of this work is the identification of an optimal edge threshold, i.e. the value of the luminance gradient allowing one to identify actual edge pixels. Such identification has been done by adopting a local approach, where the image is a-priori partitioned into small square windows, and the optimal threshold is selected by ranking the outputs produced by several thresholds inside each window. The innovative contributions of this work lie in the fact that, by partitioning the image in suitably small windows, the probability of having only one edge chain in each window is maximized (thus enhancing the effectiveness of the optimal threshold selection criterion), and the scalability of the application is ensured (due to the high number of simple processing tasks into which the algorithm is subdivided).<<ETX>>
[1]
John F. Canny,et al.
A Computational Approach to Edge Detection
,
1986,
IEEE Transactions on Pattern Analysis and Machine Intelligence.
[2]
Jitendra Malik,et al.
Scale-Space and Edge Detection Using Anisotropic Diffusion
,
1990,
IEEE Trans. Pattern Anal. Mach. Intell..
[3]
Virginio Cantoni,et al.
Multiprocessor computing for images
,
1988,
Proc. IEEE.
[4]
Les Kitchen,et al.
Edge Evaluation Using Local Edge Coherence
,
1981,
IEEE Transactions on Systems, Man, and Cybernetics.
[5]
Fredrik Bergholm,et al.
Edge Focusing
,
1987,
IEEE Transactions on Pattern Analysis and Machine Intelligence.
[6]
Maurice Milgram,et al.
Boundary Detection and Skeletonization with a Massively Parallel Architecture
,
1990,
IEEE Trans. Pattern Anal. Mach. Intell..