Building and using flexible models incorporating grey-level information

Cootes, Timothy F.; Taylor, Chris; Lanitis, Andreas; Cooper, D. H.; Graham, James

doi:10.1109/iccv.1993.378212

Cited by 72 publications

(72 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This normalization makes the profile more invariant to changes in lighting [12]. The magnitude of displacements is determined by the distance between the model point and a point on the normal to the model boundary, minimizing the distance of the mean normalized derivative model profile at the corresponding landmark and the normalized bone weighted derivative profile at the model point.…”

Section: Dxa Decompositionmentioning

confidence: 99%

“…The perpendicular line is centered at landmark j with length q. The e − th element of the derivative model profile is calculated by subtracting the intensity at the e − 1 − th point on the perpendicular line from the intensity at the e + 1 − th point on the perpendicular line [12]. After normalizing the derivative model profile, the mean normalized derivative model profile is computed by averaging the normalized derivative model profiles of the training set as follows:…”

Section: Training Distal Radius Modelmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced Distal Radius Segmentation in DXA Using Modified ASM

Lee

Cho

2011

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThe active shape model (ASM) has been widely adopted by automated bone segmentation approaches for radiographic images. In radiographic images of the distal radius, multiple edges are often observed in the near vicinity of the bone, typically caused by the presence of thin soft tissue. The presence of multiple edges decreases the segmentation accuracy when segmenting the distal radius using ASM. In this paper, we propose an enhanced distal radius segmentation method that makes use of a modified version of ASM, reducing the number of segmentation errors. To mitigate segmentation errors, the proposed method emphasizes the presence of the bone edge and downplays the presence of a soft tissue edge by making use of Dual energy X-ray absorptiometry (DXA). To verify the effectiveness of the proposed segmentation method, experiments were performed with 30 distal radius patient images. For the images used, compared to ASM-based segmentation, the proposed method improves the segmentation accuracy with 47.4% (from 0.974 mm to 0.512 mm).

show abstract

Section: Dxa Decompositionmentioning

confidence: 99%

Section: Training Distal Radius Modelmentioning

confidence: 99%

Enhanced Distal Radius Segmentation in DXA Using Modified ASM

Lee

Cho

2011

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…First, a statistical shape model of a pedestrian was built using automatically segmented pedestrian contours from sequences obtained by a stationary camera (so that we can do background subtraction). We use well-established computer vision techniques (see [22] and [23]) to build a LPDM (Linear Point Distribution Model). We fit a NURB (Non-Uniform Rational B-spline) to each extracted contour using least squares curve approximation to points on the contour [21].…”

Section: Tracking Pedestrians From a Moving Vehiclementioning

confidence: 99%

Quasi-Random Sampling for Condensation

Philomin

Duraiswami

Davis

2000

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The problem of tracking pedestrians from a moving car is a challenging one. The Condensation tracking algorithm is appealing for its generality and potential for real-time implementation. However, the conventional Condensation tracker is known to have di culty with high-dimensional state spaces and unknown motion models. This paper presents an improved algorithm that addresses these problems by using a simplified motion model, and employing quasi-Monte Carlo techniques to e ciently sample the resulting tracking problem in the high-dimensional state space. For N sample points, these techniques achieve sampling errors of O(N 31 ), as opposed to O(N 31/2 ) for conventional Monte Carlo techniques. We illustrate the algorithm by tracking objects in both synthetic and real sequences, and show that it achieves reliable tracking and significant speed-ups over conventional Monte Carlo techniques.

show abstract

“…Furthermore, to allow arbitrary variation in positions of control points over time will lead to instability in tracking. Cootes et al [2][3] [4] proposed the ASM/AAM algorithms, in which tracking is based on face detection and recognition. However the tracking results depend on the model's initial position and the variations contained in the training set, which makes it difficult to deal with occlusions.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Network Enhanced Prediction for Multiple Facial Feature Tracking

Huang¹,

Su²

2005

ELCVIA

View full text Add to dashboard Cite

It is challenging to track multiple facial features simultaneously in video while rich facial expressions are presented in a human face. To accurately predict the positions of multiple facial features' contours is important and difficult. This paper proposes a multi-cue prediction model based tracking algorithm. In the prediction model, CAMSHIFT is used to track the face in video in advance, and facial features' spatial constraint is utilized to roughly obtain the positions of facial features. Second order autoregressive process (ARP) based dynamic model is combined with graphical model (Bayesian network) based dynamic model. Incorporating ARP's quickness into graphical model's accurateness, we obtain the fusion of the prediction. Finally the prediction model and the measurement model are integrated into the framework of Kalman filter. The experimental results show that our algorithm can accurately track multiple facial features with varied facial expressions.

show abstract

Building and using flexible models incorporating grey-level information

Cited by 72 publications

References 8 publications

Enhanced Distal Radius Segmentation in DXA Using Modified ASM

Enhanced Distal Radius Segmentation in DXA Using Modified ASM

Quasi-Random Sampling for Condensation

Bayesian Network Enhanced Prediction for Multiple Facial Feature Tracking

Contact Info

Product

Resources

About