Open AccessTest-object recognition in thermal images
Author(s) -
A. V. Mingalev,
А. В. Белов,
I. M. Gabdullin,
R. R. Agafonova,
S. N. Shusharin
Publication year - 2019
Publication title -
kompʹûternaâ optika
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.491
H-Index - 29
eISSN - 2412-6179
pISSN - 0134-2452
DOI - 10.18287/2412-6179-2019-43-3-402-411
Subject(s) - convolutional neural network , artificial intelligence , pattern recognition (psychology) , computer science , robustness (evolution) , deep learning , cognitive neuroscience of visual object recognition , object detection , computer vision , object (grammar) , biochemistry , chemistry , gene
The paper presents a comparative analysis of several methods for recognition of test-object position in a thermal image when setting and testing characteristics of thermal image channels in an automated mode. We consider methods of image recognition based on the correlation image comparison, Viola-Jones method, LeNet classificatory convolutional neural network, GoogleNet (Inception v.1) classificatory convolutional neural network, and a deep-learning-based convolutional neural network of Single-Shot Multibox Detector (SSD) VGG16 type. The best performance is reached via using the deep-learning-based convolutional neural network of the VGG16-type. The main advantages of this method include robustness to variations in the test object size; high values of accuracy and recall parameters; and doing without additional methods for RoI (region of interest) localization.