We propose a method for human activity recognition in videos, based on shape analysis. We define local shape descriptors for interest points on the detected contour of the human a...
In many applied problems in the context of pattern recognition, the data often involve highly asymmetric observations. Normal mixture models tend to overfit when additional compone...
In this paper, we take a predefined geometry shape as a constraint for accurate shape alignment. A shape model is divided in two parts: fixed shape and active shape. The fixed shap...
This paper presents a feature point tracking algorithm using optical flow under the non-prior training active feature model (NPTAFM) framework. The proposed algorithm mainly focus...
Sangjin Kim, Jinyoung Kang, Jeongho Shin, Seongwon...
Extended Abstract: We are exploring new techniques for active contour models (popularly known as “snakes”[1]) by combining active segmentation models with the constrained impli...