This paper presents a real-time visual processing theory that explains various perceptual grouping and segmentation phenomena, including the grouping of textured images, randomly defined images, and images built from periodic scenic elements. The theory explains how local feature processing and emergent features work together to segment a scene, how segmentations may arise across image regions without luminance differences, and how segmentations may override local image properties in favor of global statistical factors. The theory is based on the interaction of three systems: the Boundary Contour (BC) System, the Feature Contour (FC) System, and the Object Recognition (OR) System. The BC System is defined by a hierarchy of orientationally tuned interactions, which can be divided into two subsystems: the OC filter and the CC loop. The OC filter generates inputs to the CC loop, which contains successive stages of spatially short-range competitive interactions and spatially long-range cooperative interactions. Feedback between these stages synthesizes a global context-sensitive segmentation from possible local groupings. The BC System provides a unified explanation of several Gestalt rules and suggests explanations for the architecture of the striate and prestriate visual cortices. The BC System also embodies new ideas about geometry, online statistical decision theory, and the resolution of uncertainty in quantum measurement systems. Computer simulations confirm the formal competence of the BC System as a perceptual grouping system. The properties of the BC System are compared with probabilistic and artificial intelligence models of segmentation. The total network suggests a new approach to the design of computer vision systems and promises to provide a universal set of rules for perceptual grouping of scenic edges, textures, and smoothly shaded regions. The paper discusses the role of illusory contours in perceptual grouping, the discounting of the illuminant, featural filling-in, and the differences between boundary contours and feature contours. It also addresses the boundary-feature tradeoff, the parallel induction by edges versus perpendicular induction by line ends, and the cooperative-competitive feedback signaling in CC loops. The paper concludes with a discussion of form perception versus object recognition and the anatomical locations of the BC System, FC System, and OR System in the visual cortex.This paper presents a real-time visual processing theory that explains various perceptual grouping and segmentation phenomena, including the grouping of textured images, randomly defined images, and images built from periodic scenic elements. The theory explains how local feature processing and emergent features work together to segment a scene, how segmentations may arise across image regions without luminance differences, and how segmentations may override local image properties in favor of global statistical factors. The theory is based on the interaction of three systems: the Boundary Contour (BC) System, the Feature Contour (FC) System, and the Object Recognition (OR) System. The BC System is defined by a hierarchy of orientationally tuned interactions, which can be divided into two subsystems: the OC filter and the CC loop. The OC filter generates inputs to the CC loop, which contains successive stages of spatially short-range competitive interactions and spatially long-range cooperative interactions. Feedback between these stages synthesizes a global context-sensitive segmentation from possible local groupings. The BC System provides a unified explanation of several Gestalt rules and suggests explanations for the architecture of the striate and prestriate visual cortices. The BC System also embodies new ideas about geometry, online statistical decision theory, and the resolution of uncertainty in quantum measurement systems. Computer simulations confirm the formal competence of the BC System as a perceptual grouping system. The properties of the BC System are compared with probabilistic and artificial intelligence models of segmentation. The total network suggests a new approach to the design of computer vision systems and promises to provide a universal set of rules for perceptual grouping of scenic edges, textures, and smoothly shaded regions. The paper discusses the role of illusory contours in perceptual grouping, the discounting of the illuminant, featural filling-in, and the differences between boundary contours and feature contours. It also addresses the boundary-feature tradeoff, the parallel induction by edges versus perpendicular induction by line ends, and the cooperative-competitive feedback signaling in CC loops. The paper concludes with a discussion of form perception versus object recognition and the anatomical locations of the BC System, FC System, and OR System in the visual cortex.