Exploring Lip Segmentation Techniques in Computer Vision: A Comparative Analysis
It addresses lip segmentation for computer vision applications like lip reading, focusing on lightweight techniques for IoT and edge computing, but is incremental as it compares existing methods without introducing new ones.
This study compared five state-of-the-art lip segmentation models (EHANet, Mask2Former, BiSeNet V2, PIDNet, and STDC1) on the CelebAMask-HQ dataset using a Raspberry Pi4, finding that Mask2Former and EHANet achieved the best mIoU scores, with inference times ranging from 1000 to 3000 milliseconds.
Lip segmentation is crucial in computer vision, especially for lip reading. Despite extensive face segmentation research, lip segmentation has received limited attention. The aim of this study is to compare state-of-the-art lip segmentation models using a standardized setting and a publicly available dataset. Five techniques, namely EHANet, Mask2Former, BiSeNet V2, PIDNet, and STDC1, are qualitatively selected based on their reported performance, inference time, code availability, recency, and popularity. The CelebAMask-HQ dataset, comprising manually annotated face images, is used to fairly assess the lip segmentation performance of the selected models. Inference experiments are conducted on a Raspberry Pi4 to emulate limited computational resources. The results show that Mask2Former and EHANet have the best performances in terms of mIoU score. BiSeNet V2 demonstrate competitive performance, while PIDNet excels in recall but has lower precision. Most models present inference time ranging from 1000 to around 3000 milliseconds on a Raspberry Pi4, with PIDNet having the lowest mean inference time. This study provides a comprehensive evaluation of lip segmentation models, highlighting their performance and inference times. The findings contribute to the development of lightweight techniques and establish benchmarks for future advances in lip segmentation, especially in IoT and edge computing scenarios.