On advances in differential-geometric approaches for 2D and 3D shape analyses and activity recognition

Srivastava, Anuj; Turaga, Pavan; Kurtek, Sebastian

doi:10.1016/j.imavis.2012.03.006

Cited by 29 publications

(20 citation statements)

References 142 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A rich statistical theory for shape analysis supported the analysis of shape variation [19,8]. Advances in statistics, computer vision and computer graphics provided large body of tools for shape representation and quantification, including formalisation of the statistical shape analysis, shape descriptors and similarity measures [54,44,7]. Among others, these include: deformable templates [51], geometric descriptors [52], geodesic representations [9], and level sets [55].…”

Section: State Of the Artmentioning

confidence: 99%

Persistent homology to analyse 3D faces and assess body weight gain

et al. 2016

View full text Add to dashboard Cite

In this paper we analyse patterns in face shape variation due to weight gain. We propose the use of persistent homology descriptors to get geometric and topological information about the configuration of anthropometric 3D face landmarks. In this way, evaluating face changes boils down to comparing the descriptors computed on 3D face scans taken at different times. By applying dimensionality reduction techniques to the dissimilarity matrix of descriptors, we get a space in which each face is a point and face shape variations are encoded as trajectories in that space. Our results show that persistent homology is able to identify features which are well-related to overweight, and may help assessing individual weight trends. The research was carried out in the context of the European project SEMEOTICONS, which developed a multisensory platform which detects and monitors over time facial signs of cardio-metabolic risk.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Persistent homology to analyse 3D faces and assess body weight gain

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Among the methods for estimating a hand pose, there are solutions based on localizing hand landmarks [6,17,45,51,54], extracting hand shape features [36,37,56], or fitting the parameters of a 3D hand model [15,49,59]. In the last case, subspace learning (linear [15] or non-linear [59]) is applied so as to improve the searching process in a large database of hand images obtained from the model.…”

Section: Overview Of Vision-based Gesture Recognitionmentioning

confidence: 99%

“…The former methods involve analysis of the hand silhouette shape [36,37,56] and detecting the landmarks [6,17,45,51,54], which is the main scope of the work reported here and are given more attention in the subsequent section. The model-based methods [15,49,59] are focused on fitting a predefined 3D hand model to an image subject to the analysis-the 3D model parameters form the feature vector which may be further processed.…”

Section: Gesture Recognition Processmentioning

confidence: 99%

“…Introduction of the Kinect sensor has greatly improved the capacities of gesture recognition [29-31, 42, 52], however in order to increase the accessibility of touchless interfaces, more effective solutions based on computer vision would help in taking advantage of large popularity and low price inherent to standard 2D cameras. The vision-based systems [6,8,14,17,25,32,37,45,47,49,51,54,56,57,59] still do not allow for recognizing the gestures with sufficient accuracy, which brings the need for developing new image analysis algorithms for gesture recognition. One of the major problems here, addressed in this paper, is concerned with detecting and localizing hand landmarks, such as fingertips, joints, or phalanges.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hand landmarks detection and localization in color images

Grzejszczak

Kawulok

Gałuszka

2015

Multimed Tools Appl

View full text Add to dashboard Cite

This paper introduces a new method for detecting and localizing hand landmarks in 2D color images. Location of the hand landmarks is an important source of information for recognizing hand gestures, effectively exploited in a number of recent methods which operate from the depth maps. However, this problem has not yet been satisfactorily solved for 2D color images. Here, we propose to analyze the skin-presence masks, as well as the directional image of a hand using the distance transform and template matching. This makes it possible to detect the landmarks located both at the contour and inside the hand masks. Moreover, we performed an extensive experimental study to compare the proposed method with a number of state-of-the-art algorithms. The obtained quantitative and qualitative results clearly indicate that our approach outperforms other methods, which may help improve the existing gesture recognition systems.

show abstract

“…These methods rely on statistical learning theory where the variations of objects shapes are captured during training which involves analysis of expert annotated training images. In particular, in an annotated training image there is a plurality of points manually set along the contour of an object leading to the concept of a point distribution model (PDM; Srivastava, 2012). Given a set of training images, each one associated with a fixed number of expert-annotated landmarks, a statistical shape model is created and then used in combination with a set of independent landmark detectors to regularize their output.…”

Section: Introductionmentioning

confidence: 99%

Principal Geodesic Analysis Boundary Delineation With Superpixel-Based Constraints

Baran

Tabor

2017

Image Anal Stereol

View full text Add to dashboard Cite

In this paper an algorithm for accurate delineation of object boundaries is proposed. The method employs a superpixel algorithm to obtain an oversegmentation of the input image, used as a constraint in the task. A shape model is built by applying Principal Geodesic Analysis on angular representation of automatically placed uniformly distant landmark points. The shape model is used to detect the boundaries of an object on a given image by iterative elongation of a partial boundary along borders of superpixels. Contrary to many stateof-the-art methods, the proposed approach does not need an initial boundary. The algorithm was tested on two natural and two synthetic sets of images. Mean Dice coefficients between 0.91 and 0.97 were obtained. In almost all cases the object was found. In areas of relatively high gradient magnitude the borders are delineated very accurately, though further research is needed to improve the accuracy in areas of low gradient magnitude and automatically select the parameters of the proposed error function.

show abstract

On advances in differential-geometric approaches for 2D and 3D shape analyses and activity recognition

Cited by 29 publications

References 142 publications

Persistent homology to analyse 3D faces and assess body weight gain

Persistent homology to analyse 3D faces and assess body weight gain

Hand landmarks detection and localization in color images

Principal Geodesic Analysis Boundary Delineation With Superpixel-Based Constraints

Contact Info

Product

Resources

About