Image Preprocessing Approaches Toward Better Learning Performance with CNN

Abstract

Convolutional neural networks (CNNs) are at the forefront of computer vision, relying heavily on the quality of input data determined by the preprocessing method. An excessive preprocessing approach will result in poor learning performance. This study critically examines the impact of advanced image preprocessing techniques on convolutional neural networks (CNNs) in facial recognition. Emphasizing the importance of data quality, we explore various preprocessing approaches, including noise reduction, histogram equalization, and image hashing. Our methodology involves feature visualization to improve facial feature discernment, training convergence analysis, and real-time model testing. The results demonstrate significant improvements in model performance with the preprocessed data set: average precision, recall, precision, and F1 score enhancements of 4.17%, 3.45%, 3.45%, and 3.81%, respectively. Furthermore, real-time testing shows a 21% performance increase and a 1.41% reduction in computing time. This study not only underscores the effectiveness of preprocessing in boosting CNN capabilities, but also opens avenues for future research in applying these methods to diverse image types and exploring various CNN architectures for a complete understanding.