Histograma de Gradientes Orientados (HOG)
El Histograma de Gradientes Orientados (HOG) es un descriptor de características utilizado en visión por computadora and procesamiento de imágenes for detección de objetos 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 vector de características que describe toda la imagen o una región de interés específica.
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 detección de peatones and other applications where distinguishing between different shapes and forms is essential.
HOG descriptors are typically combined with machine learning classifiers, such as Máquinas de Vectores de Soporte (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.