Hand landmarks detection and localization in color images

Grzejszczak, Tomasz; Kawulok, Michał; Gałuszka, Adam

doi:10.1007/s11042-015-2934-5

Cited by 55 publications

(19 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the Hand Gesture Recognition (HGR) (Grzejszczak et al 2016;Nalepa and Kawulok 2014;Kawulok et al 2014) which contains the gestures from Polish Sign Language ('P' in the gesture's ID) and American Sign Language ('A'). We only used the subsample of HGR which has all 25 hand feature point locations, as some annotations do only include the feature points which are visually visible.…”

Section: Hand Gestures Datasetmentioning

confidence: 99%

“…Fig. 7, last row) do suffer in quality as both statistical shape model and piecewise affine transformation require outer shape annotations, whereas annotations of HGR (Grzejszczak et al 2016;Nalepa and Kawulok 2014;Kawulok et al 2014) only provide inner shape annotations. This also explains the observed thinness of the generated fingers.…”

Section: Extending Regularised Gagan To Generate Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks

et al. 2019

View full text Add to dashboard Cite

Deep generative models have significantly advanced image generation, enabling generation of visually pleasing images with realistic texture. Apart from the texture, it is the shape geometry of objects that strongly dictates their appearance. However, currently available generative models do not incorporate geometric information into the image generation process. This often yields visual objects of degenerated quality. In this work, we propose a regularized Geometry-Aware Generative Adversarial Network (GAGAN) which disentangles appearance and shape in the latent space. This regularized GAGAN enables the generation of images with both realistic texture and shape. Specifically, we condition the generator on a statistical shape prior. The prior is enforced through mapping the generated images onto a canonical coordinate frame using a differentiable geometric transformation. In addition to incorporating geometric information, this constrains the search space and increases the model's robustness. We show that our approach is versatile, able to generalise across domains (faces, sketches, hands and cats) and sample sizes (from as little as ∼ 200−30,000 to more than 200,000). We demonstrate superior performance through extensive quantitative and qualitative experiments in a variety of tasks and settings. Finally, we leverage our model to automatically and accurately detect errors or drifting in facial landmarks detection and tracking in-the-wild.

show abstract

Section: Hand Gestures Datasetmentioning

confidence: 99%

Section: Extending Regularised Gagan To Generate Backgroundmentioning

confidence: 99%

Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks

et al. 2019

View full text Add to dashboard Cite

show abstract

“…While segmentation of healthy skin from standard camera images has also been the subject of prior research [4], [5], [6], [7], [8], little work to date has focused on skin segmentation in situations where skin may be diseased, such as standard camera images used for documentation and diagnosis in a primary care setting ( Fig. 1).…”

Section: Introductionmentioning

confidence: 99%

Segmentation of Both Diseased and Healthy Skin From Clinical Photographs in a Primary Care Setting

Codella

Anderson

Philips

et al. 2018

2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

This work presents the first segmentation study of both diseased and healthy skin in standard camera photographs from a clinical environment. Challenges arise from varied lighting conditions, skin types, backgrounds, and pathological states. For study, 400 clinical photographs (with skin segmentation masks) representing various pathological states of skin are retrospectively collected from a primary care network. 100 images are used for training and fine-tuning, and 300 are used for evaluation. This distribution between training and test partitions is chosen to reflect the difficulty in amassing large quantities of labeled data in this domain. A deep learning approach is used, and 3 public segmentation datasets of healthy skin are collected to study the potential benefits of pretraining. Two variants of U-Net are evaluated: U-Net and Dense Residual U-Net. We find that Dense Residual U-Nets have a 7.8% improvement in Jaccard, compared to classical U-Net architectures (0.55 vs. 0.51 Jaccard), for direct transfer, where fine-tuning data is not utilized. However, U-Net outperforms Dense Residual U-Net for both direct training (0.83 vs. 0.80) and fine-tuning (0.89 vs. 0.88). The stark performance improvement with fine-tuning compared to direct transfer and direct training emphasizes both the need for adequate representative data of diseased skin, and the utility of other publicly available data sources for this task.

show abstract

“…In addition to original and ground truth binary skin mask images, it includes hand feature points locations in separate files. Figure 5.4 shows some of the 1,558 samples available (Grzejszczak et al, 2016;Kawulok et al, 2014;Nalepa and Kawulok, 2014).…”

Section: Hgrmentioning

confidence: 99%

“…A small set of 85 was obtained in gray (44) and uncontrolled (41) background; the lighting was uniform. The third group contains 574 images in controlled background (green tone), using uniform lighting conditions (Grzejszczak et al, 2016;Kawulok et al, 2014;Nalepa and Kawulok, 2014).…”

Section: Hgrmentioning

confidence: 99%

Human skin segmentation using correlation rules on dynamic color clustering

Faria¹

View full text Add to dashboard Cite

Human skin is made of a stack of different layers, each of which reflects a portion of impinging light, after absorbing a certain amount of it by the pigments which lie in the layer. The main pigments responsible for skin color origins are melanin and hemoglobin. Skin segmentation plays an important role in a wide range of image processing and computer vision applications. In short, there are three major approaches for skin segmentation: rule-based, machine learning and hybrid. They differ in terms of accuracy and computational efficiency. Generally, machine learning and hybrid approaches outperform the rule-based methods but require a large and representative training dataset and, sometimes, costly classification time as well, which can be a deal breaker for real-time applications. In this work, we propose an improvement, in three distinct versions, of a novel method for rule-based skin segmentation that works in the YCbCr color space. Our motivation is based on the hypotheses that: (1) the original rule can be complemented and, (2) human skin pixels do not appear isolated, i.e. neighborhood operations are taken into consideration. The method is a combination of some correlation rules based on these hypotheses. Such rules evaluate the combinations of chrominance Cb, Cr values to identify the skin pixels depending on the shape and size of dynamically generated skin color clusters. The method is very efficient in terms of computational effort as well as robust in very complex images.

show abstract

Hand landmarks detection and localization in color images

Cited by 55 publications

References 57 publications

Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks

Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks

Segmentation of Both Diseased and Healthy Skin From Clinical Photographs in a Primary Care Setting

Human skin segmentation using correlation rules on dynamic color clustering

Contact Info

Product

Resources

About