Affiliation:
1. Colourlab, Department of Computer Science, Norwegian University of Science and Technology (NTNU), 2815 Gjøvik, Norway
Abstract
Spectral Filter Array cameras provide a fast and portable solution for spectral imaging. Texture classification from images captured with such a camera usually happens after a demosaicing process, which makes the classification performance rely on the quality of the demosaicing. This work investigates texture classification methods applied directly to the raw image. We trained a Convolutional Neural Network and compared its classification performance to the Local Binary Pattern method. The experiment is based on real SFA images of the objects of the HyTexiLa database and not on simulated data as are often used. We also investigate the role of integration time and illumination on the performance of the classification methods. The Convolutional Neural Network outperforms other texture classification methods even with a small amount of training data. Additionally, we demonstrated the model’s ability to adapt and scale for different environmental conditions such as illumination and exposure compared to other methods. In order to explain these results, we analyze the extracted features of our method and show the ability of the model to recognize different shapes, patterns, and marks in different textures.
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference30 articles.
1. Zhou, D. (2006). Texture Analysis and Synthesis Using a Generic Markov-Gibbs Image Model. [Ph.D. Thesis, University of Auckland].
2. Recent applications of image texture for evaluation of food qualities—A review;Zheng;Trends Food Sci. Technol.,2006
3. Automated fabric defect detection—A review;Ngan;Image Vis. Comput.,2011
4. Feature-based image patch approximation for lung tissue classification;Song;IEEE Trans. Med. Imaging,2013
5. Digital pathology and image analysis in tissue biomarker research;Hamilton;Methods,2014
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献