Bayesian optimization of histogram of oriented gradients (HOG) parameters for facial recognition.

Facial recognition is a rapidly growing field with applications in security, surveillance, and human-computer interaction. The performance of the Histogram of Oriented Gradients (HOG) algorithm, a popular feature extraction method for facial recognition, heavily relies on its parameter settings. Optimizing these parameters is crucial for achieving high accuracy. In this paper, we propose a novel approach to optimize HOG algorithm parameters and image size for facial recognition using a Tree-structured Parzen Estimator (TPE)-based Bayesian optimization technique. This optimization process effectively harnesses machine learning performance metrics as the objective function, enabling the algorithm to adapt and enhance its feature extraction capabilities. Extensive experiments conducted across multiple databases, including the AR Face Database, Extended Yale B Database, ORL Database, Yale Face Database, and Facepix, have yielded an exceptional recognition accuracy of 100%. Our optimized handcrafted HOG algorithm highlights the potential and continued relevance of parameter-based handcrafted feature extraction algorithms in computer vision, particularly in resource-constrained environments or applications requiring interpretability. [ABSTRACT FROM AUTHOR]