Abstract-This paper presents a SIFT algorithm adapted for 3D surfaces (called meshSIFT) and its applications to 3D face pose normalisation and recognition. The algorithm allows reliable detection of scale space extrema as local feature locations. The scale space contains the mean curvature in each vertex on different smoothed versions of the input mesh. The meshSIFT algorithm then describes the neighbourhood of every scale space extremum in a feature vector consisting of concatenated histograms of shape indices and slant angles. The feature vectors are reliably matched by comparing the angle in feature space.Using RANSAC, the best rigid transformation can be estimated based on the matched features leading to 84% correct pose normalisation of 3D faces from the Bosphorus database. Matches are mostly found between two face surfaces of the same person, allowing the algorithm to be used for 3D face recognition. Simply counting the number of matches allows 93.7% correct identification for face surfaces in the Bosphorus database and 97.7% when only frontal images are considered. In the verification scenario, we obtain an equal error rate of 15.0% to 5.1% (depending on the investigated face surfaces). These results outperform most other algorithms found in literature.
I. INTRODUCTIONReliable feature detection and matching on 3D face surfaces is useful for several biometrics related applications, such as pose normalisation, face recognition and modeling of face deformation. In this paper, we develop a feature detection and description method for meshes, based on the SIFT algorithm [1]. This algorithm, which we call meshSIFT, allows for accurate detection of scale space extrema on meshes and a rich description of the local feature neighbourhood of the detected scale-space extrema. In this paper, we validate the meshSIFT algorithm for pose normalisation and 3D face recognition. The experiments will be performed on an extensive database of 3D faces: the Bosphorus database [2] .The remainder of this section gives a brief overview of related work. In section II, we describe the newly developed meshSIFT algorithm for detection of scale space extrema and construction of local feature descriptors. In section III, the meshSIFT algorithm is tested on pose normalisation of 3D face scans and 3D-3D face recognition. Section IV discusses the performance of the developed algorithm. Section V, finally, concludes the paper and gives some directions for future work.
OBJECTIVES
We evaluated the outcome of patients in cardiogenic shock receiving a paracorporeal pulsatile biventricular assist device as a bridge to transplantation.
METHODS
We performed a retrospective single-centre analysis of all patients who received a Berlin Heart Excor® at our institution between 2004 and 2019.
RESULTS
A total of 97 patients (90 adults, 7 paediatric) were analysed. Eighty-four patients were in Interagency Registry for Mechanically Assisted Circulatory Support level 1 (80 adults, 4 paediatric). Diagnoses were dilated cardiomyopathy (n = 41), ischaemic cardiomyopathy (n = 17) or myocardial infarction (n = 4), myocarditis (n = 15), restrictive cardiomyopathy (n = 2), graft failure after heart transplant (n = 7), postcardiotomy heart failure (n = 5), postpartum cardiomyopathy (n = 3), congenital heart disease (n = 1), valvular cardiomyopathy (n = 1) and toxic cardiomyopathy (n = 1). All patients were in biventricular heart failure and had secondary organ dysfunction. The mean duration of support was 63 days (0–487 days). There was a significant decrease in creatinine values after assist device implantation (from 1.83 ± 0.79 to 1.12 ± 0.67 mg/dl, P = 0.001) as well as a decrease in bilirubin values (from 3.94 ± 4.58 to 2.65 ± 3.61 mg/dl, P = 0.084). Cerebral stroke occurred in 16 patients, bleeding in 15 and infection in 13 patients. Forty-eight patients died on support, while 49 patients could be successfully bridged to transplantation. Thirty-day survival and 1-year survival were 70.1% and 41.2%, respectively.
CONCLUSIONS
A pulsatile biventricular assist device is a reasonable therapeutic option in cardiogenic shock, when immediate high cardiac output is necessary to rescue the already impaired kidney and liver function of the patient.
The reattachment of the supra-aortic vessels during hybrid arch repair using a branched prosthesis is time consuming and sometimes technically challenging. Here, we describe the surgical technique of bridging the end-to-end anastomoses between the graft branches and the supra-aortic vessels by self-expanding covered stents to reduce suturing time, avoid anastomotic bleeding, enhance true lumen remodeling, and improve vessel alignment to the hybrid graft.
Abstract. Intra-shape deformations complicate 3D object recognition and retrieval and need therefore proper modeling. A method for inelastic deformation invariant object recognition is proposed, representing 3D objects by diffusion distance tensors (DDT), i.e. third order tensors containing the average diffusion distance for different diffusion times between each pair of points on the surface. In addition to the DDT, also geodesic distance matrices (GDM) are used to represent the objects independent of the reference frame. Transforming these distance tensors into modal representations provides a sampling order invariant shape descriptor. Different dissimilarity measures can be used for comparing these shape descriptors. The final object pair dissimilarity is the sum or product of the dissimilarities obtained by modal representations of the GDM and DDT. The method is validated on the TOSCA non-rigid world database and the SHREC 2010 dataset of non-rigid 3D models indicating that our method combining these two representations provides a more noise robust but still inter-subject shape variation sensitive method for the identification and the verification scenario in object retrieval.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.