Date of Publication :25th July 2024

Abstract:The ongoing global health crisis has underscored the importance of implementing preventive measures, Face masks have a vital role in reducing the transmission of illnesses that are infectious. ML methods are frequently employed to streamline the identification of masks for the face, which has gained significant prominence in this field. This work introduces a novel approach for identifying face masks using a Gradient Boosting Classifier in the domain of machine learning. The proposed method utilizes a vast dataset of facial photos, both with and without masks, and use feature extraction techniques to capture crucial attributes. The Gradient Boosting Classifier, an effective ensemble learning algorithm, is employed to train a strong model capable of accurately distinguishing between masked and unmasked faces. The algorithm's capacity to systematically improve the performance of less effective learners boosts the prototype's capacity to hold intricate categorization challenges. The results of the experiment validate the effectiveness of the Gradient Boosting Classifier in achieving a high degree of accuracy, sensitivity, and specificity in recognizing face masks. The performance of the model is assessed using a range of datasets that represent different climatic conditions and demographic features. Furthermore, when compared to other machine learning methods, the suggested technique demonstrates greater performance. The sophisticated face mask recognition system tend to have potential applied in the fields of public health, surveillance, and safety monitoring. It provides a non-invasive and efficient approach to enforcing mask-wearing regulations. Integrating machine learning algorithms for face mask recognition supports wider community wellbeing exertions to manage the spread of transmissible diseases as society adapts to changing standards.

Reference :