Mean Shift: A Robust Approach Toward Feature Space Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Mean Shift, Mode Seeking, and Clustering
IEEE Transactions on Pattern Analysis and Machine Intelligence
A decision-theoretic generalization of on-line learning and an application to boosting
EuroCOLT '95 Proceedings of the Second European Conference on Computational Learning Theory
Robust analysis of feature spaces: color image segmentation
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
EUROMICRO '03 Proceedings of the 29th Conference on EUROMICRO
A Comparative Study of Texture Features for the Discrimination of Gastric Polyps in Endoscopic Video
CBMS '05 Proceedings of the 18th IEEE Symposium on Computer-Based Medical Systems
Detecting Informative Frames from Wireless Capsule Endoscopic Video Using Color and Texture Features
MICCAI '08 Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention, Part II
Texture analysis for ulcer detection in capsule endoscopy images
Image and Vision Computing
Interactive image segmentation by maximal similarity based region merging
Pattern Recognition
Computer-aided small bowel tumor detection for capsule endoscopy
Artificial Intelligence in Medicine
An mean shift based gray level co-occurrence matrix for endoscope image diagnosis
ICMB'10 Proceedings of the Second international conference on Medical Biometrics
Iterated graph cuts for image segmentation
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
Hi-index | 0.00 |
Gastroscopy is one of the most important ways for diagnosing gastric cancer. Computer-aided detection of gastroscopic images is helpful in improving the accuracy of gastric cancer diagnosis. This paper proposes a method for lesion detection of gastroscopic images. Mean-shift segmentation is initially applied to reduce the information interference caused when global image or rectangular block serves as an identification area. A well performed three-dimensional color histogram feature is extracted from YCbCr color space. Mean shift-based Color Wavelet Covariance (MS-CWC) is proposed to reduce the cost of computing. Finally, after comparing Perceptron with AdaBoost, the latter is selected to train the classifier for detecting abnormal regions in gastroscopic images. Experiments show that the proposed method is feasible for lesion detection of gastroscopic images; the false negative rate(FNR), false positive rate(FPR), and error rates(ER) are 15.50%, 16.89%, and 16.35%, respectively.