TY - JOUR
T1 - Environmental microorganism classification using conditional random fields and deep convolutional neural networks
AU - Kosov, Sergey
AU - Shirahama, Kimiaki
AU - Li, Chen
AU - Grzegorzek, Marcin
PY - 2018/5/1
Y1 - 2018/5/1
N2 - The labeling of Environmental Microorganisms (EM) which help decomposing pollutants, plays a fundamental role for establishing sustainable ecosystem. We propose an environmental microorganism classification engine that can automatically analyze microscopic images using Conditional Random Fields (CRF) and Deep Convolutional Neural Networks (DCNN). First, to effectively represent scarce training images, a DCNN pre-trained for image classification using a large amount of data is re-purposed to our feature extractor that distils pixel-level features in microscopic images. In addition, pixel-level classification results by such features can be refined using global features that describe the whole image in toto. Finally, our CRF model localizes and classifies EMs by considering the spatial relations among DCNN-based features, and their relations to global features. The experimental results have shown 94.2% of overall segmentation accuracy and up to 91.4% mean average precision of the results.
AB - The labeling of Environmental Microorganisms (EM) which help decomposing pollutants, plays a fundamental role for establishing sustainable ecosystem. We propose an environmental microorganism classification engine that can automatically analyze microscopic images using Conditional Random Fields (CRF) and Deep Convolutional Neural Networks (DCNN). First, to effectively represent scarce training images, a DCNN pre-trained for image classification using a large amount of data is re-purposed to our feature extractor that distils pixel-level features in microscopic images. In addition, pixel-level classification results by such features can be refined using global features that describe the whole image in toto. Finally, our CRF model localizes and classifies EMs by considering the spatial relations among DCNN-based features, and their relations to global features. The experimental results have shown 94.2% of overall segmentation accuracy and up to 91.4% mean average precision of the results.
UR - http://www.scopus.com/inward/record.url?scp=85044640362&partnerID=8YFLogxK
U2 - 10.1016/j.patcog.2017.12.021
DO - 10.1016/j.patcog.2017.12.021
M3 - Journal articles
AN - SCOPUS:85044640362
VL - 77
SP - 248
EP - 261
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
SN - 0167-8655
ER -