Charles R Dyer, Marijke F Augustein, 2012/3/15, A model-based approach is developed for recovering three-dimensional surface
orientation from a single two-dimensional polygonal contour or point pattern. Two planar object models are analyzed rectangles and arbitrary point patterns. We define an iterative procedure which efficiently computes both the correspondence between model and image features (line segments) and the correct surface orientation.
- "This research provides useful information for DNA-based fingerprinting, breeding, ecological studies, and diversity assessment of elm germplasm"
Guo GD, Fu Y, Dyer CR, et al., IEEE Transactions on Image Processing 17 (7): 1178-1188 Jul 2008. In this paper, we introduce the age manifold learning scheme for extracting face aging features and design a locally adjusted robust regressor for learning and prediction of human ages. The novel approach improves the age estimation accuracy significantly over all previous methods.
- "Segmentation of elastographic images using a coarse-to-fine active contour model"
Liu W, Zagzebski JA, Varghese T, et al., Ultrasound in Medicine and Biology 32 (3): 397-408 Mar 2006. This paper presents an automated segmentation approach for thermal coagulations on 3-D elastographic data to obtain both area and volume information rapidly.
- "Learning from examples in the small sample case: Face expression recognition"
Guo GD, Dyer CR, IEEE Transactions on Systems Man and Cybergenetics Part B-Cybergenetics 35 (3): 477-488 Jun 2005. A pairwise framework for feature selection, instead of using all classes simultaneously, is presented. Experimental results compare the method with three others: a simplified Bayes classifier, support vector machine, and AdaBoost.