Abstract
Image semantic segmentation is a popular research direction in the computer vision field. Semantic segmentation algorithms based on deep learning outperforms the traditional methods. Fully convolutional neural network (FCN) whose fully connected layers are transformed into convolution layers is a kind of convolutional neural network (CNN). In this paper, FCN is used to operate the image semantic segmentation, which could take input of arbitrary size image and implement end-to-end segmentation task. Due to the limited number of training images, some layers are fine-tuned from AlexNet and the dataset is enlarged by mirroring. The hierarchical feature maps from FCN are combined to improve the segmentation effect. Conditional random fields (CRF) is used on the segmentation result of FCN, which takes into account the positional relationship and color features between any two pixels. Experiments show that our method could refine the segmentation result of FCN, especially using CRF as post-processing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Papandreou, G., Chen, L.C., Murphy, K.P., et al.: Weakly and semi-supervised learning of a deep convolutional network for semantic image segmentation. In: IEEE International Conference on Computer Vision. IEEE, pp. 1742–1750 (2015)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. eprint arXiv:1411.4038 (2014)
Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. CoRR, vol. abs/1505.04366 (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097–1105. Curran Associates Inc. (2012)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Computer Vision and Pattern Recognition, pp. 1–9. IEEE (2014)
Tajbakhsh, N., Shin, J.Y., Gurudu, S.R., et al.: Convolutional neural networks for medical image analysis: fine tuning or full training. IEEE Trans. Med. Imaging 35(5), 1 (2016)
Lecun, Y., Boser, B., Denker, J.S., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
Shotton, J., Winn, J., Rother, C., et al.: Textonboost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context. Int. J. Comput. Vis. 81(1), 2–23 (2009)
Philipp, K., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Advances in Neural Information Processing Systems, pp. 109–117 (2012)
Jia, Y.Q., Evan Shelhamer, E., Jeff, D., et al.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)
Everingham, M., Gool, L.V., Williams, C.K.I., et al.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, H., Qian, X., Li, W. (2017). Image Semantic Segmentation Based on Fully Convolutional Neural Network and CRF. In: Yuan, H., Geng, J., Bian, F. (eds) Geo-Spatial Knowledge and Intelligence. GRMSE 2016. Communications in Computer and Information Science, vol 698. Springer, Singapore. https://doi.org/10.1007/978-981-10-3966-9_27
Download citation
DOI: https://doi.org/10.1007/978-981-10-3966-9_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3965-2
Online ISBN: 978-981-10-3966-9
eBook Packages: Computer ScienceComputer Science (R0)