%0 Report
%4 sid.inpe.br/mtc-m21c/2019/12.16.14.40
%2 sid.inpe.br/mtc-m21c/2019/12.16.14.40.50
%@ INPE-1194-PE/111
%T Edge detection in images: a hypothesis testing approach
%D 1978
%9 RPQ
%P 26
%A Mascarenhas, Nelson Delfino D'Avila,
%A Prado, Lucila Oliveira da Costa,
%I Instituto Nacional de Pesquisas Espaciais
%C São José dos Campos
%K image processing, edge detection, statistical decision theory.
%X New statistical techniques for the edge detection problem in images are developed. The image is modeled by signal and noise which are independent, additive, Gaussian and autorregressive in two dimensions. The optimal solution, in tens of statistical decision theory, leads to a test which decides among multiple, composite, overlapping hypotheses. A computationally attractive suboptimal test, involving non -overlapping hypotheses, is proposed. Resulte are presented with simulated data and real cate lute images. A comparison with standard gradient techniques is made.
%@language en
%3 INPE-1194.pdf