2026-05-23T22:12:40Zhttps://keep.lib.asu.edu/oai/requestoai:keep.lib.asu.edu:node-1587462024-12-23T18:01:48Zoai_pmh:alloai_pmh:repo_items158746
https://hdl.handle.net/2286/R.I.62936
http://rightsstatements.org/vocab/InC/1.0/
2020
52 pages
Masters Thesis
Academic theses
Text
eng
Tallman, Riley
Yang, Yezhou
Liang, Jianming
Chen, Yinong
Arizona State University
Masters Thesis Computer Science 2020
This work solves the problem of incorrect rotations while using handheld devices.Two new methods which improve upon previous works are explored. The first method<br/>uses an infrared camera to capture and detect the user’s face position and orient the<br/>display accordingly. The second method utilizes gyroscopic and accelerometer data<br/>as input to a machine learning model to classify correct and incorrect rotations.<br/>Experiments show that these new methods achieve an overall success rate of 67%<br/>for the first and 92% for the second which reaches a new high for this performance<br/>category. The paper also discusses logistical and legal reasons for implementing this<br/>feature into an end-user product from a business perspective. Lastly, the monetary<br/>incentive behind a feature like irRotate in a consumer device and explore related<br/>patents is discussed.
Artificial Intelligence
Computer vision
Mobile computing
irRotate - Automatic Screen Rotation Based on Face Orientation using Infrared Cameras