About the Project
Image segmentation has many applications in biomedical and many other fields. It is essential for target detection and identification. The project will review existing algorithms and develop new and improved ones. As often used fuzzy c-means clustering (FCM) algorithm is sensitive to noise, local spatial information is introduced to an objective function to improve the robustness of the FCM algorithm for image segmentation. However, the introduction of local spatial information often leads to a high computational complexity, arising out of an iterative calculation of the distance between pixels within local spatial neighbours and clustering centres. Aims are to improve accuracy and to reduce complexity.
This project will involve programming, signal processing, machine learning, mathematical analysis, and good writing ability for presentation of technical work. An ideal candidate will have a very good Master degree or a First Class Bachelor degree.
References
Below are some publications from my group. These will give you good indications of the work we have done already and the developments of our ideas, techniques, and implementations.
1. T Lei, P Liu, X Jia, X Zhang, H Meng, and A K Nandi, "Automatic fuzzy clustering framework for image segmentation", IEEE Transactions on Fuzzy Systems, DOI: 10.1109/TFUZZ.2019.2930030, accepted, 2019.
2. T Lei, X Jia, T Liu, S Liu, H Meng, and A K Nandi, "Adaptive morphological reconstruction for seeded image segmentation", IEEE Transactions on Image Processing, DOI: 10.1109/TIP.2019.2920514, vol. 28, no. 11, pp. 5510-5523, 2019.
3. T Lei, X Jia, Y Zhang, S Liu, H Meng, and A K Nandi, "Superpixel-based fast fuzzy C-means clustering for color image segmentation", IEEE Transactions on Fuzzy Systems, DOI: 10.1109/TFUZZ.2018.2889018, vol. 27, no. 9, pp. 1753-1766, 2019.
4. T Lei, Y Zhang, Z Lv, S Liu, S Liu, and A K Nandi, "Landslide inventory mapping from bi-temporal images using deep convolution networks", IEEE Geoscience and Remote Sensing Letters, DOI: 10.1109/LGRS.2018.2889307, vol. 16, no. 6, pp. 982-986, 2019.
5. T Lei, X Jia, Y Zhang, L He, H Meng, and A K Nandi, "Significantly fast and robust fuzzy C-means clustering algorithm based on morphological reconstruction and membership filtering", IEEE Transactions on Fuzzy Systems, DOI: 10.1109/TFUZZ.2018.2796074, vol. 26, no. 5, pp. 3027-3041, 2018.
6. T Lei, D Xue, Z Lv, S Li, Y Zhang, and A K Nandi, "Unsupervised change detection using fast fuzzy clustering for landslide mapping from very high-resolution images", Remote Sensing, DOI: 10.3390/RS10091381, vol. 10, no. 9, 1381 (23 pages), 2018.