{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T17:21:57Z","timestamp":1771003317364,"version":"3.50.1"},"reference-count":9,"publisher":"SAGE Publications","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"published-print":{"date-parts":[[2021,11,1]]},"abstract":"<jats:p>Each pixel can be classified in the image by the semantic segmentation. The segmentation detection results of pixel level can be got which are similar to the contour of the target object. However, the results of semantic segmentation trained by Fully convolutional networks often lead to the loss of detail information. This paper proposes a CRF-FCN model based on CRF optimization. Firstly, the original image is detected based on feature pyramid networks, and the target area information is extracted, which is used to train the high-order potential function of CRF. Then, the high-order CRF is used as the back-end of the complete convolution network to optimize the semantic image segmentation. The algorithm comparison experiment shows that our algorithm makes the target details more obvious, and improves the accuracy and efficiency of semantic segmentation.<\/jats:p>","DOI":"10.3233\/jcm-214867","type":"journal-article","created":{"date-parts":[[2021,4,6]],"date-time":"2021-04-06T13:04:30Z","timestamp":1617714270000},"page":"1405-1415","source":"Crossref","is-referenced-by-count":2,"title":["Fully convolutional networks semantic segmentation based on conditional random field optimization"],"prefix":"10.1177","volume":"21","author":[{"given":"Qian","family":"Wu","sequence":"first","affiliation":[{"name":"Suzhou Vocational University, Suzhou, Jiangsu 215104, China"},{"name":"Mechanical Information Research Center of Jiangsu University, Zhenjiang, Jiangsu 212013, China"}]},{"given":"Jinan","family":"Gu","sequence":"additional","affiliation":[{"name":"Mechanical Information Research Center of Jiangsu University, Zhenjiang, Jiangsu 212013, China"}]},{"given":"Chen","family":"Wu","sequence":"additional","affiliation":[{"name":"Suzhou Vocational University, Suzhou, Jiangsu 215104, China"}]},{"given":"Jin","family":"Li","sequence":"additional","affiliation":[{"name":"Suzhou Vocational University, Suzhou, Jiangsu 215104, China"}]}],"member":"179","reference":[{"issue":"10","key":"10.3233\/JCM-214867_ref2","doi-asserted-by":"crossref","first-page":"837","DOI":"10.1016\/j.imavis.2004.02.009","article-title":"Randomized RANSAC with T D tree test","volume":"22","author":"Matas","year":"2004","journal-title":"Image and Vision Computing"},{"key":"10.3233\/JCM-214867_ref3","unstructured":"J.D. Lafferty, A. Mccallum and Pereira, FCN Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data, in: Proceedings of the Eighteenth International Conference on Maching Learning, 2001, pp.\u00a0282\u2013289."},{"key":"10.3233\/JCM-214867_ref4","doi-asserted-by":"crossref","unstructured":"J. Long, E. Shelhamer and T. Darell, Fully convolutional networks for semantic segmentation, in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"10.3233\/JCM-214867_ref7","doi-asserted-by":"crossref","unstructured":"H. Noh, S. Hong and B. Han, Learning Deconvolution Network for Semantic Segmentation, in: IEEE International Conference on Computer Vision, 2015, pp. 1520\u20131528.","DOI":"10.1109\/ICCV.2015.178"},{"key":"10.3233\/JCM-214867_ref9","doi-asserted-by":"crossref","unstructured":"J. Long, E. Shelhamer and T. Darell, Fully convolutional networks for semantic segmentation, in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"10.3233\/JCM-214867_ref10","unstructured":"A. Krizhevsky, I. Sutskever and G.E. Hinton, ImageNet classification with deep convolutional, in: Conference on Neural Information Processing Systems, 2012, pp. 1097\u20131105."},{"key":"10.3233\/JCM-214867_ref12","doi-asserted-by":"crossref","unstructured":"M. Golpardaz, M.S. Helfroush and H. Danyal, Nonsubsampled contourlet transform-based conditional random field for SAR images segmentation, Signal Processing 174 (2020), 107623.","DOI":"10.1016\/j.sigpro.2020.107623"},{"key":"10.3233\/JCM-214867_ref13","doi-asserted-by":"crossref","first-page":"170266","DOI":"10.1016\/j.patcog.2020.107266","article-title":"Saliency detection using a deep conditional random field network","volume":"103","author":"Qiu","year":"2020","journal-title":"Pattern Recognition"},{"key":"10.3233\/JCM-214867_ref15","doi-asserted-by":"crossref","first-page":"153364","DOI":"10.1016\/j.aeue.2020.153364","article-title":"A semantic-based scene segmentation using convolutional neural networks","volume":"125","author":"Shaaban","year":"2020","journal-title":"AEU \u2013 International Journal of Electronics and Communications"}],"container-title":["Journal of Computational Methods in Sciences and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JCM-214867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T16:31:54Z","timestamp":1771000314000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JCM-214867"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,1]]},"references-count":9,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.3233\/jcm-214867","relation":{},"ISSN":["1472-7978","1875-8983"],"issn-type":[{"value":"1472-7978","type":"print"},{"value":"1875-8983","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,1]]}}}