作者: Roman M. Palenichka
关键词: Relevance (information retrieval) 、 Function (engineering) 、 Artificial intelligence 、 Image (mathematics) 、 TRACE (psycholinguistics) 、 Object detection 、 Operator (computer programming) 、 Computer science 、 Mathematical morphology 、 Computer vision 、 Human visual system model
摘要: The goal of the image analysis approach presented in this paper was two-fold. Firstly, it is development a computational model for visual attention humans and animals, which consistent with known psychophysical experiments neurology findings early vision mechanisms. Secondly, model-based design an operator computer vision, capable to detect, locate, trace objects interest images fast way. proposed operator, named relevance function, local that has maximums at centers locations supposed or their relevant parts. This several advantageous features detecting due function utilization maximum likelihood decision.