Histogram Analysis Using a Scale-Space Approach
IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Image Processing
Toward Optimal Active Learning through Sampling Estimation of Error Reduction
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Object-based visual attention for computer vision
Artificial Intelligence
Tissue segmentation in ultrasound images by using genetic algorithms
Expert Systems with Applications: An International Journal
A hierarchical evolutionary algorithm for automatic medical image segmentation
Expert Systems with Applications: An International Journal
A modified support vector machine and its application to image segmentation
Image and Vision Computing
IEEE Transactions on Information Technology in Biomedicine
IEEE Transactions on Information Technology in Biomedicine
Edge Enhancement Nucleus and Cytoplast Contour Detector of Cervical Smear Images
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hi-index | 12.05 |
Computer-aided automatic analysis of microscopic leukocyte is a powerful diagnostic tool in biomedical fields which could reduce the effects of human error, improve the diagnosis accuracy, save manpower and time. However, it is a challenging to segment entire leukocyte populations due to the changing features extracted in the leukocyte image, and this task remains an unsolved issue in blood cell image segmentation. This paper presents an efficient strategy to construct a segmentation model for any leukocyte image using simulated visual attention via learning by on-line sampling. In the sampling stage, two types of visual attention, ''bottom-up'' and ''top-down'' together with the movement of the human eye are simulated. We focus on a few regions of interesting and sample high gradient pixels to group training sets. While in the learning stage, the SVM (support vector machine) model is trained in real-time to simulate the visual neuronal system and then classifies pixels and extracts leukocytes from the image. Experimental results show that the proposed method has better performance compared to the marker controlled watershed algorithms with manual intervention and thresholding-based methods.