A multiresolution image segmentation technique based on pyramidal segmentation and fuzzy clustering

Abstract

In this paper, an unsupervised image segmentation technique is presented, which combines pyramidal image segmentation with the fuzzy c-means clustering algorithm. Each layer of the pyramid is split into a number of regions by a root labeling technique, and then fuzzy c-means is used to merge the regions of the layer with the highest image resolution. A cluster validity functional is used to find the optimal number of objects automatically. Segmentation of a number of synthetic as well as clinical images is illustrated and two fully automatic segmentation approaches are evaluated, which determine the left ventricular volume (LV) in 140 cardiovascular magnetic resonance (MR) images. First fuzzy c-means is applied without pyramids. In the second approach the regions generated by pyramidal segmentation are merged by fuzzy c-means. The correlation coefficients of manually and automatically defined LV lumen of all 140 and 20 end-diastolic images were equal to 0.86 and 0.79, respectively, when images were segmented with fuzzy c-means alone. These coefficients increased to 0.90 and 0.93 when the pyramidal segmentation was combined with fuzzy c-means. This method can be applied to any dimensional representation and at any resolution level of an image series. The evaluation study shows good performance in detecting LV lumen in MR images.

Automatic image-based segmentation of the heart from CT scans

“…These works deal with different strategies for approaching the segmentation task, including image-driven algorithms [10][11][12][13], probabilistic atlases [14,15], fuzzy clustering [16], deformable models [17][18][19], neural networks [20], active appearance models [21,22], anatomical-based landmarks [23], or level set and its variations [24,25]. A comprehensive review of techniques commonly used in cardiac image segmentation can be found in Kang et al [5].…”

Đánh Giá Hiệu Năng Của Thuật Toán Phân Cụm Mờ Bán Giám Sát Cho Bài Toán Phân Đoạn Ảnh Nha Khoa

“…Phân đoạn ảnh là giai đoạn đầu tiên trong quá trình xử lý ảnh và đóng vai trò rất quan trọng [16,24] trong quá trình này. Phân đoạn ảnh cũng là công việc khó khăn nhất của xử lý ảnh.…”

“…Một số nghiên cứu gần đây cho thấy các thuật toán phân cụm mờ bán giám sát rất hiệu quả trong nhiều lĩnh vực như xử lý ảnh [5,14,24], nhận dạng mẫu, nhận dạng khuôn mặt [1,17], đánh giá rủi ro [4], dự báo phá sản [18]. Đặc biệt là trong xử lý ảnh với các ảnh màu và ảnh y học.…”

An Overview of Semi-Supervised Fuzzy Clustering Algorithms

“…Fuzzy clustering is an important tool in pattern recognition and knowledge discovery from databases and it has been applied in many practical applications such as image segmentation [1]- [3], face recognition [4], [5], risk assessment [6], geographic demographic analysis [7], intrusion detection [8], [9], bankruptcy prediction [10], etc. In recent studies, some additional information provided by users is engaged in the input of fuzzy clustering to guide, monitor and control the process of clustering [6]- [10].…”