Edge detection is a fundamental task in computer vision, crucial for various applications such as object recognition and image segmentation. This paper presents a novel approach to edge detection using structured forests, which leverages the inherent structure in local image patches to learn both accurate and computationally efficient edge detectors. The method formulates the problem of predicting local edge masks within a structured learning framework applied to random decision forests. By robustly mapping structured labels to a discrete space, standard information gain measures can be evaluated, leading to real-time performance that is orders of magnitude faster than competing state-of-the-art methods. The approach achieves state-of-the-art results on the BSDS500 and NYU Depth datasets while demonstrating strong cross-dataset generalization. The paper also discusses related work in edge detection and structured learning, and provides a detailed explanation of the structured random forest training process. Finally, the authors highlight the potential of their approach as a general-purpose edge detector, suitable for various vision applications.Edge detection is a fundamental task in computer vision, crucial for various applications such as object recognition and image segmentation. This paper presents a novel approach to edge detection using structured forests, which leverages the inherent structure in local image patches to learn both accurate and computationally efficient edge detectors. The method formulates the problem of predicting local edge masks within a structured learning framework applied to random decision forests. By robustly mapping structured labels to a discrete space, standard information gain measures can be evaluated, leading to real-time performance that is orders of magnitude faster than competing state-of-the-art methods. The approach achieves state-of-the-art results on the BSDS500 and NYU Depth datasets while demonstrating strong cross-dataset generalization. The paper also discusses related work in edge detection and structured learning, and provides a detailed explanation of the structured random forest training process. Finally, the authors highlight the potential of their approach as a general-purpose edge detector, suitable for various vision applications.