Background subtraction is a very popular approach for foreground segmentation in a still scene image. In order to compensate for illumination changes, a background model updating process is generally employed, which leads to extra computation time. Many different methods have been proposed over the recent years. Furthermore, there are a number of object extraction algorithms proposed in the literature, and most approaches work efficiently only in constrained environments where the background is relatively simple and static. Nowadays, background modelling and subtraction algorithms are commonly used in object detection and tracking applications. The goal of employing these approaches is to obtain a clean background and then detect moving objects by comparing it with the current frame. In this paper, we use a novel fuzzy approach for background subtraction with a particular interest to the problem of silhouette detection. The detection results are then used to update the background in a fuzzy way. To demonstrate the advantages of fuzzy background subtraction, the standard versions are compared. Fuzzy system is much more efficient, robust and accurate compared with classical approaches. We extracted features from image regions, accumulated the feature information over time, fused high-level knowledge with low-level features and built a time-varying background model. Experimental results show that fuzzy approach is relatively more accurate than classical approach. © RPS 2012.