PERFORMANCE OF FACIAL EXPRESSION RECOGNITION USING CNN AND DRLBP

Facial expression recognition is a crucial task in computer vision with applications in fields such as emotion detection, human-computer interaction, and affective computing. This research presents a novel approach that combines a convolutional neural network (CNN) classifier with the Dynamic Regional Local Binary Patterns (DRLBP) proposed method for accurate and efficient facial expression recognition. The proposed method follows a systematic process that begins with the collection of a diverse dataset of facial images displaying different expressions, along with their corresponding labels. The DRLBP algorithm is then utilized to extract discriminative features from the facial images. Unlike traditional Local Binary Patterns (LBPs), the DRLBP algorithm dynamically selects regions of interest based on facial landmarks or key points, allowing for effective capturing of expressive facial regions.The performance of the proposed method can be evaluated using various metrics such as accuracy, precision, recall, or F1 score, by leveraging the strengths of both CNNs and the DRLBP algorithm, the combined approach achieves accurate and robust facial expression recognition. CNNs excel in learning complex hierarchical representations, while DRLBP effectively captures expressive facial regions. The integration of these two methods presents promising prospects for the development of advanced facial expression recognition systems with numerous practical applications.