Pattern Spectrum and Multiscale Shape Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations
IEEE Transactions on Pattern Analysis and Machine Intelligence
The watershed transform: definitions, algorithms and parallelization strategies
Fundamenta Informaticae - Special issue on mathematical morphology
Spatial Size Distributions: Applications to Shape and Texture Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hybrid image segmentation using watersheds and fast region merging
IEEE Transactions on Image Processing
Improved techniques for automatic image segmentation
IEEE Transactions on Circuits and Systems for Video Technology
| Hi-index | 0.01 |
The process detecting and measuring granule named granular analysis is very important in mineral analysis. Classical methods for granular analysis are based on Matheron's sieving method. However, these methods are not adequate for mineral microscope image analysis. First, it is not an easy job to choose proper element structure for sieving process. Second, these traditional methods cannot exactly locate the position of each grain in the image. Third, the running cost of these methods on PC is too high to implement an online application. This paper proposes a granular analysis model based on improved watershed which is called varying-ladder watershed. The improved watershed overcomes the over-segment problem by adjusting the ladder height among successive steps and quickly segments the whole image into regions of different textures. Experiments show that using the proposed method gets accurate and detailed results and gains high computational performance.