Even a slight change in image aquisition environment makes recognition of objects or patterns difficult. This paper proposes a mathematical morphology operation for feature extraction intensitive to intensity variation. A gray-scale hit-or-miss transform operator is applied to a shared-weigh neural network for feature extraction process. For real world application, the neural network is applied to recognition of numbers in vehicle license plate. Experimental resu;ts demonstrate that the gray-scale hit-or-miss transform can reduce rffects caused by lighting conditions.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.