Face Detection on Mobile: Five Implementations and Analysis
This work addresses the need for efficient face detection in mobile applications like access control and driver tracking, but it is incremental as it adapts existing methods without introducing new algorithms.
The paper tackled the problem of balancing algorithm quality and complexity for face detection on mobile devices by adapting five algorithms and analyzing their inference times across different devices and resolutions, finding that cascaded algorithms are faster on scenes without faces while BlazeFace is slower.
In many practical cases face detection on smartphones or other highly portable devices is a necessity. Applications include mobile face access control systems, driver status tracking, emotion recognition, etc. Mobile devices have limited processing power and should have long-enough battery life even with face detection application running. Thus, striking the right balance between algorithm quality and complexity is crucial. In this work we adapt 5 algorithms to mobile. These algorithms are based on handcrafted or neural-network-based features and include: Viola-Jones (Haar cascade), LBP, HOG, MTCNN, BlazeFace. We analyze inference time of these algorithms on different devices with different input image resolutions. We provide guidance, which algorithms are the best fit for mobile face access control systems and potentially other mobile applications. Interestingly, we note that cascaded algorithms perform faster on scenes without faces, while BlazeFace is slower on empty scenes. Exploiting this behavior might be useful in practice.