TY - GEN
T1 - ReCog
AU - Ahmetovic, Dragan
AU - Sato, Daisuke
AU - Oh, Uran
AU - Ishihara, Tatsuya
AU - Kitani, Kris
AU - Asakawa, Chieko
N1 - Funding Information:
We would like to thank all the participants who took part in our user study. This work was sponsored in part by Shimizu Corporation and Uptake (Carnegie Mellon University Machine Learning for Social Good fund).
Publisher Copyright:
© 2020 ACM.
PY - 2020/4/21
Y1 - 2020/4/21
N2 - We present ReCog, a mobile app that enables blind users to recognize objects by training a deep network with their own photos of such objects. This functionality is useful to differentiate personal objects, which cannot be recognized with pre-trained recognizers and may lack distinguishing tactile features. To ensure that the objects are well-framed in the captured photos, ReCog integrates a camera-aiming guidance that tracks target objects and instructs the user through verbal and sonification feedback to appropriately frame them. We report a two-session study with 10 blind participants using ReCog for object training and recognition, with and without guidance. We show that ReCog enables blind users to train and recognize their personal objects, and that camera-aiming guidance helps novice users to increase their confidence, achieve better accuracy, and learn strategies to capture better photos.
AB - We present ReCog, a mobile app that enables blind users to recognize objects by training a deep network with their own photos of such objects. This functionality is useful to differentiate personal objects, which cannot be recognized with pre-trained recognizers and may lack distinguishing tactile features. To ensure that the objects are well-framed in the captured photos, ReCog integrates a camera-aiming guidance that tracks target objects and instructs the user through verbal and sonification feedback to appropriately frame them. We report a two-session study with 10 blind participants using ReCog for object training and recognition, with and without guidance. We show that ReCog enables blind users to train and recognize their personal objects, and that camera-aiming guidance helps novice users to increase their confidence, achieve better accuracy, and learn strategies to capture better photos.
KW - object recognition
KW - photography guidance
KW - visual impairment
UR - http://www.scopus.com/inward/record.url?scp=85091302319&partnerID=8YFLogxK
U2 - 10.1145/3313831.3376143
DO - 10.1145/3313831.3376143
M3 - Conference contribution
AN - SCOPUS:85091302319
T3 - Conference on Human Factors in Computing Systems - Proceedings
BT - CHI 2020 - Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
PB - Association for Computing Machinery
Y2 - 25 April 2020 through 30 April 2020
ER -