Active Shape and Appearance Models

Cootes, Timothy F.; Roberts, Martin G.; Babalola, Kola; Taylor, Chris

doi:10.1007/978-0-387-09749-7_6

Cited by 10 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analysis took place at the GO-LAB ("Gedragsfysiologisch Onderzoekslaboratorium": "Behavioral-Physiological Research Laboratory") at Tilburg University. The FaceReader software finds a patient's face and creates a 3D Active Appearance Model of the face (46). In addition, FaceReader uses deep artificial network analysis to recognize patterns in the face (47).…”

Section: Facial Emotion Expression Analysismentioning

confidence: 99%

Facial Emotion Expression and the Inducibility of Myocardial Ischemia During Cardiac Stress Testing: The Role of Psychological Background Factors

et al. 2022

View full text Add to dashboard Cite

ObjectiveNegative emotional states, such as anger and anxiety, are associated with the onset of myocardial infarction and other acute clinical manifestations of ischemic heart disease. The likelihood of experiencing these short-term negative emotions has been associated with long-term psychological background factors such as depression, generalized anxiety, and personality factors. We examined the association of acute emotional states preceding cardiac stress testing (CST) with inducibility of myocardial ischemia and to what extent psychological background factors account for this association.MethodsEmotional states were assessed in patients undergoing CST (n = 210; mean [standard deviation] age = 66.9 [8.2] years); 91 (43%) women) using self-report measures and video recordings of facial emotion expression. Video recordings were analyzed for expressed anxiety, anger, sadness, and happiness before CST. Psychological background factors were assessed with validated questionnaires. Single-photon emission computed tomography was used to evaluate inducibility of ischemia.ResultsIschemia occurred in 72 patients (34%). Emotional states were not associated with subsequent inducibility of ischemia during CST (odds ratio between 0.93 and 1.04; p values > .50). Psychological background factors were also not associated with ischemia (odds ratio between 0.96 and 1.06 per scale unit; p values > .20) and did not account for the associations of emotional states with ischemia.ConclusionsEmotional states immediately before CST and psychological background factors were not associated with the inducibility of ischemia. These findings indicate that the well-documented association between negative emotions with acute clinical manifestations of ischemic heart disease requires a different explanation than a reduced threshold for inducible ischemia.

show abstract

Section: Facial Emotion Expression Analysismentioning

confidence: 99%

Facial Emotion Expression and the Inducibility of Myocardial Ischemia During Cardiac Stress Testing: The Role of Psychological Background Factors

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Grayscale feature, Gabor feature and LTP feature are used for feature extraction. AdaBoost face detector based on Haar feature [12]and facial landmarks localizer based on ASM [13] (modified from Stasm [14]) is used for image localization. Result ROC curve and table is shown in Fig.…”

Section: Preparationsmentioning

confidence: 99%

Automatic Eyeglasses Removal of Frontal Facial Images for Face Recognition

Ying

Chen

2014

AMM

View full text Add to dashboard Cite

As the most common type of facial occlusion, eyeglasses may cause great accuracy degradation in face recognition. In this paper, we proposed an improved approach on automatically detecting and removing eyeglasses from grayscale facial images. First, we normalized a face image by the result of face detection and eyes localization. Then we used a fast judging method to detect eyeglasses’ presence. For images with eyeglasses, we used PCA reconstruction error and edge feature to determine the occluded area, and synthesized the area through image inpainting. Experimental results show that our approach can detect the presence of eyeglasses very accurately and obtain generally natural looking images without eyeglasses. In face recognition test, our approach greatly contributed to the accuracy of recognition, achieving higher improvement than other approaches such as simple PCA reconstruction, iterative error compensation, and weighted fusion.

show abstract

“…A variety of anatomical shape models have also been proposed to describe both the common geometric features and the geometric variability among instances of the population for shape analysis applications. 20 – 27 To date, these have not been systematically explored for the purpose of constructing SOMs that capture realistic anatomical variations for use in imaging system optimization.…”

Section: Introductionmentioning

confidence: 99%

Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks

Zhou

Bhadra²,

Brooks

et al. 2022

J. Med. Imag.

View full text Add to dashboard Cite

Purpose: To objectively assess new medical imaging technologies via computer-simulations, it is important to account for the variability in the ensemble of objects to be imaged. This source of variability can be described by stochastic object models (SOMs). It is generally desirable to establish SOMs from experimental imaging measurements acquired by use of a well-characterized imaging system, but this task has remained challenging.Approach: A generative adversarial network (GAN)-based method that employs AmbientGANs with modern progressive or multiresolution training approaches is proposed. AmbientGANs established using the proposed training procedure are systematically validated in a controlled way using computer-simulated magnetic resonance imaging (MRI) data corresponding to a stylized imaging system. Emulated single-coil experimental MRI data are also employed to demonstrate the methods under less stylized conditions. Results:The proposed AmbientGAN method can generate clean images when the imaging measurements are contaminated by measurement noise. When the imaging measurement data are incomplete, the proposed AmbientGAN can reliably learn the distribution of the measurement components of the objects.Conclusions: Both visual examinations and quantitative analyses, including task-specific validations using the Hotelling observer, demonstrated that the proposed AmbientGAN method holds promise to establish realistic SOMs from imaging measurements.

show abstract

Active Shape and Appearance Models

Cited by 10 publications

References 37 publications

Facial Emotion Expression and the Inducibility of Myocardial Ischemia During Cardiac Stress Testing: The Role of Psychological Background Factors

Facial Emotion Expression and the Inducibility of Myocardial Ischemia During Cardiac Stress Testing: The Role of Psychological Background Factors

Automatic Eyeglasses Removal of Frontal Facial Images for Face Recognition

Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks

Contact Info

Product

Resources

About