ABSTRACT
Taking selfies is a common practice for smartphone users. Simultaneously capturing oneself and the desired background is not a trivial task, because it is often not possible to get a good view of both. Moreover, users often loose attention of their surroundings, thus taking a selfie also showed to lead to serious injuries. To ease the process of capturing selfies and to make it more safe, this work proposes forward selfies as a simple yet effective concept to account for both, risk and challenges. Forward selfies seamlessly combine images of the front-facing and the rear-facing smartphone camera. We propose a mobile app that builds on this concept and implements the selfie synthesis in a post-processing image composition stage. Thereby, we can take advantage of the commonly more advanced back-camera hardware, i.e., providing higher image resolutions, larger field of views, and different perspectives. Finally, we leverage built-in camera optimizations for independently (de-)focusing objects at different distances, such as for persons and backgrounds. We conclude that the concept of forward selfies can effectively address and solve certain challenges of capturing selfies, which we demonstrate by a simple app user interface.
Supplemental Material
- Yi-Tsung Hsieh and Mei-Chen Yeh. 2017. Head Pose Recommendation for Taking Good Selfies. In Proc. Workshop on Multimodal Understanding of Social, Affective and Subjective Attributes (Mountain View, California, USA). ACM, New York, NY, USA, 55–60. https://doi.org/10.1145/3132515.3132518Google ScholarDigital Library
- Mahdi M. Kalayeh, Misrak Seifu, Wesna LaLanne, and Mubarak Shah. 2015. How to Take a Good Selfie?. In Proc. International Conference on Multimedia(Brisbane, Australia). ACM, New York, NY, USA, 923–926. https://doi.org/10.1145/2733373.2806365Google ScholarDigital Library
- Zhanghan Ke, Kaican Li, Yurou Zhou, Qiuhua Wu, Xiangyu Mao, Qiong Yan, and Rynson WH Lau. 2020. Is a Green Screen Really Necessary for Real-Time Portrait Matting?arxiv:2011.11961 [cs.CV]Google Scholar
- Jitender Singh Virk and Abhinav Dhall. 2019. Garuda: A Deep Learning Based Solution for Capturing Selfies Safely. In Proc. International Conference on Intelligent User Interfaces: Companion (Marina del Ray, California). ACM, New York, NY, USA, 43–44. https://doi.org/10.1145/3308557.3308669Google ScholarDigital Library
- Mei-Chen Yeh and Hsiao-Wei Lin. 2014. Virtual Portraitist: Aesthetic Evaluation of Selfies Based on Angle. In Proc. ACM International Conference on Multimedia (Orlando, Florida, USA). ACM, New York, NY, USA, 221–224. https://doi.org/10.1145/2647868.2656401Google ScholarDigital Library
Recommendations
Personality and selfies
Selfies, or pictures taken of oneself and shared on social media, have become a worldwide phenomenon. In the present research, we examine the relationship between narcissism, both vulnerable and grandiose, and the frequency of and motivations behind ...
Built-in face recognition for smart photo sharing in mobile devices
ICME '11: Proceedings of the 2011 IEEE International Conference on Multimedia and ExpoThis paper presents a smart photo sharing application for mo bile devices based on an efficient yet powerful face recognition engine. The system allows registering subjects either from live video (mobile camera) or from still images, linking the ...
A New Multi-Camera Dataset with Surveillance, Mobile and Stereo Cameras for Tracking, Situation Analysis and Crime Scene Investigation Applications
ICVIP '18: Proceedings of the 2018 2nd International Conference on Video and Image ProcessingNowadays, cameras are ubiquitous. In the event of a crime or terrorist attack, plenty of video data can be collected from surveillance cameras or mobile phone cameras from witnesses. This paper presents a new dataset, "IOSB-4D," which includes data from ...
Comments