DECISION TREES BASED IMAGE SEGMENTATION USING ENSEMBLE CLUSTERING

Lavi Yaron, Abdallah Loai

Abstract


In this study, we propose an improvement on a commonly used classification algorithm – Decision Tree. The mentioned improvement has been observed during segmentation of colored images. The method in which we improved the performance of a regular decision tree, involved clustering the data which was then used as the training set for the decision tree. The clustering algorithm used was K-Means. After running both regular and improved decision tree algorithms several times, on different images of animals in a diverse set of backgrounds, we concluded that the decision tree algorithm that was empowered by the clustering of K-Means, had higher confidence levels and performance.


Keywords


decision trees, k-means, computer vision, ensemble clustering

Full Text:

PDF

References


AbedAllah, L., & Shimshoni, I. (2012, September). k Nearest neighbours using ensemble clustering. Proceeding of International Conference on Data Warehousing and Knowledge Discovery. Vienna, Austria, pp. 265-278.

Gupta, S., Girshick, R., Arbeláez, P., & Malik, J. (2014, September). Learning rich features from RGB-D images for object detection and segmentation. In European Conference on Computer Vision (pp. 345-360). Springer, Cham.

Shotton, J., Johnson, M., & Cipolla, R. (2008, June). Semantic texton forests for image categorization and segmentation. In 2008 IEEE Conference on Computer Vision and Pattern Recognition (pp. 1-8). IEEE.

Permuter, H., Francos, J., & Jermyn, I. (2006). A study of Gaussian mixture models of color and texture features for image classification and segmentation. Pattern Recognition, 39(4), 695-706.

Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. CVPR (1), 1(511-518), 3.

Heumann, B. W. (2011). An object-based classification of mangroves using a hybrid decision tree—Support vector machine approach. Remote Sensing, 3(11), 2440-2460.

Schroff, F., Criminisi, A., & Zisserman, A. (2008, September). Object Class Segmentation using Random Forests. In BMVC(pp. 1-10).

Im, J., Jensen, J. R., & Tullis, J. A. (2008). Object‐based change detection using correlation image analysis and image segmentation. International Journal of Remote Sensing, 29(2), 399-423.


Refbacks

  • There are currently no refbacks.