Exit Menu

Image segmentation

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.

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.

This project will involve programming, signal processing, machine learning, mathematical analysis and require good writing ability for presentation of technical work.

An ideal candidate will have a very good Master degree or a First Class Bachelor degree.

How to apply

If you are interested in applying for the above PhD topic please follow the steps below:

  1. Contact the supervisor by email or phone to discuss your interest and find out if you woold be suitable. Supervisor details can be found on this topic page. The supervisor will guide you in developing the topic-specific research proposal, which will form part of your application.
  2. Click on the 'Apply here' button on this page and you will be taken to the relevant PhD course page, where you can apply using an online application.
  3. Complete the online application indicating your selected supervisor and include the research proposal for the topic you have selected.

Good luck!

This is a self funded topic

Brunel offers a number of funding options to research students that help cover the cost of their tuition fees, contribute to living expenses or both. See more information here: https://www.brunel.ac.uk/research/Research-degrees/Research-degree-funding. The UK Government is also offering Doctoral Student Loans for eligible students, and there is some funding available through the Research Councils. Many of our international students benefit from funding provided by their governments or employers. Brunel alumni enjoy tuition fee discounts of 15%.