Abstract
Image segmentation is one of the most important and fundamental tasks in image processing and techniques based on image thresholding are typically simple and computationally efficient. However, the image segmentation results depend heavily on the chosen image thresholding methods. In this paper, histogram is integrated with the Parzen window technique to estimate the spatial probability distribution of gray-level image values, and a novel criterion function is designed. By optimizing the criterion function, an optimal global threshold is obtained. The experimental results for synthetic real-world and images demonstrate the success of the proposed image thresholding method, as compared with the OTSU method, the MET method and the entropy-based method.
Original language | English |
---|---|
Pages (from-to) | 117-129 |
Number of pages | 13 |
Journal | Pattern Recognition |
Volume | 41 |
Issue number | 1 |
DOIs | |
Publication status | Published - 1 Jan 2008 |
Keywords
- Image segmentation
- Parzen window
- Thresholding
ASJC Scopus subject areas
- Software
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence