Online Program Home
My Program

Abstract Details

Activity Number: 297 - SPEED: Food, Environment, Biomedical Imaging and Physical System Visualization/Learning, Part 1
Type: Contributed
Date/Time: Tuesday, July 30, 2019 : 8:30 AM to 10:20 AM
Sponsor: ASA LGBT Concerns Committee
Abstract #306555
Title: Machine Learning and Deep Learning Based on Multiple View Images and Additional Information
Author(s): Zheng Xu* and Cong Wu
Companies: University of Nebraska-Lincoln and University of Nebraska-Lincoln
Keywords: machine learning; deep learning; multiple-view image; image regression; plant phenotyping; image processing

Machine learning methods especially deep learning have seen great success in statistical image analysis. A single image is used as the input of machine learning methods for the objectives of image segmentation, classification and regression. Machine learning based on multiple-view images have the advantage over machine learning based on image in one view. We propose methods which work for multiple-view images and compared the methods using one view. We illustrate the performance of machine learning methods using multiple view images in the application of plant image phenotyping. We illustrate the advantage of machine learning and deep learning using images from multiple angles over the methods using one-angle image based on agricultural crop images. We also find improved performance if additional information is used in machine learning and deep learning.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program