Paper Info
Title
Applying Transfer Learning to Recognize Clothing Patterns Using a Finger-Mounted Camera.
Abstract
Color identification tools do not identify visual patterns or allow users to quickly inspect multiple locations, which are both important for identifying clothing. We are exploring the use of a finger-based camera that allows users to query clothing colors and patterns by touch. Previously, we demonstrated the feasibility of this approach using a small, highly-controlled dataset and combining two image classification techniques commonly used for object recognition. Here, to improve scalability and robustness, we collect a dataset of fabric images from online sources and apply transfer learning to train an end-to-end deep neural network to recognize visual patterns. This new approach achieves 92% accuracy in a general case and 97% when tuned for images from a finger-mounted camera.
Year
DOI
Venue
2018
10.1145/3234695.3241015
ASSETS
Keywords
Field
DocType
Visually impaired users,wearables,pattern recognition
Computer vision,Wearable computer,Computer science,Transfer of learning,Clothing,Robustness (computer science),Human–computer interaction,Artificial intelligence,Contextual image classification,Artificial neural network,Cognitive neuroscience of visual object recognition,Scalability
Conference
ISBN
Citations 
PageRank 
978-1-4503-5650-3
0
0.34
References 
Authors
10
3
Name
Order
Citations
PageRank
Lee Stearns1164.26
Leah Findlater21668101.05
Jon Froehlich32516207.07