Histogram of Oriented Gradients (HOG)
The Histogram of Oriented Gradients (HOG) is a feature descriptor used in computer vision and image processing for object detection and recognition. It captures the structure or shape of objects in an image by analyzing the distribution of gradient orientations within localized portions of the image.
To create a HOG descriptor, an image is first divided into small connected regions called cells. For each cell, the gradient is calculated, which represents the change in intensity or color at each pixel. The gradients are then used to compute a histogram of the orientations of these gradients, usually binned into a fixed number of angles. The histograms from neighboring cells are then combined to form a feature vector that describes the entire image or a specific region of interest.
HOG is particularly effective because it is robust to changes in illumination and can capture the edges and contours that are crucial for identifying objects. It is commonly used in pedestrian detection and other applications where distinguishing between different shapes and forms is essential.
HOG descriptors are typically combined with machine learning classifiers, such as Support Vector Machines (SVM), to improve accuracy in detecting objects within images. Overall, HOG has become a foundational technique in the field of computer vision due to its effectiveness and efficiency.