We describe a 3-D object recognition system from gray-scale images. It uses “subjective contours” as well as luminance edges (physical contours). In this paper, we suppose two kinds of subjective contours based on psychological and physiological findings: (1) Subjective contours that are automatically generated as by-products in the lower level processes of visual system. Alignment and proximity of physical contours and line ends promote generating such contours. The edge detection process involved in this kind of subjective contours are modeled by BCS neural network (Grossberg & Carpenter, 1985) in our system. (2) Subjective contours that represent a hypothesis of segmentation with volumes in the higher level process. The volumes have primitive shapes and they are components of object models. We used geons (Biederman, 1987) for describing object models. Higher level process groups both physical and subjective contours that are detected in the lower level process into the most probable geons, by found features such as line junctions and curvatures of lines. We describe the idea of recognition system that combines lower and higher level processes. We applied it to partially shaded images, arrangement of lines and partly degraded image.