Occluded Face Detection using InceptionResNetV1

Face recognition and detection in real-world scenarios often encounter significant difficulties due to partial occlusions caused by objects such as glasses, masks, and hats. Traditional face detection models struggle with these occlusions, leading to decreased accuracy and reliability. This study addresses the challenge of occluded face detection by leveraging the InceptionResNetV1 architecture. Our method harnesses the advanced feature extraction capabilities of InceptionResNetV1, which combines the strengths of Inception and ResNet architectures, to enhance the robustness of face detection under various occlusions The experimental results indicate that our model not only improves detection accuracy but also maintains high precision and recall rates under different occlusion conditions. This work presents a significant step forward in developing robust face detection systems capable of operating effectively in real-world environments.