Hand gesture recognition using a neural network shape fitting technique

Stergiopoulou, E.; Papamarkos, Nikos

doi:10.1016/j.engappai.2009.03.008

Cited by 224 publications

(108 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There are mainly two general approaches towards extracting the features [3,41]: (i) appearance-based and (ii) model-based. 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%

“…Hand landmarks localization is performed in many gesture recognition systems, but usually it is limited to detecting fingertips of extended digits [6,14,17,25,45,54,57], as well as finding the wrist [11,32] and palm region [6,47,51]. This is certainly helpful for estimating a hand pose, when combined with the analysis of some shape features extracted from the hand silhouette or contour.…”

Section: Overview Of Vision-based Gesture Recognitionmentioning

confidence: 99%

“…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%

“…Also, adapting the skin model [21,62] to a presented scene increases the precision of segmenting skin regions. These techniques are utilized in a number of gesture recognition systems [4,51]. The difficulty of hand region extraction heavily depends on the lighting and background conditions imposed during image acquisition, and in many works on gesture recognition a controlled background is assumed [54] or the hand region extraction is simplified using some markers [2].…”

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 4 more Smart Citations

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

Section: Gesture Recognition Processmentioning

confidence: 99%

Section: Overview Of Vision-based Gesture Recognitionmentioning

confidence: 99%

Section: Overview Of Vision-based Gesture Recognitionmentioning

confidence: 99%

Section: Gesture Recognition Processmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Hand landmarks detection and localization in color images

Grzejszczak

Kawulok

Gałuszka

2015

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

Gesture recognition from RGB images using convolutional neural network‐attention based system

Barbhuiya

Karsh

Jain

2022

Concurrency and Computation

View full text Add to dashboard Cite

Hand gestures can be categorized based on their applications as conversational, manipulative, controlling, and communicative gestures. Hand gesture recognition is an aspect of human action recognition, which plays a notable role in communication among the deaf and dumb community. Accurate recognition and classification of hand gestures with similar postures is still a complex problem. The main objective of this work is to employ deep learning based convolutional neural networks for human action recognition. This article introduces a convolutional neural network based on VGG16 architecture with an attention approach to mitigate the issue. Incorporating an attention-based module with the VGG16 architecture is the prime reason for potentially learning distinguishing image features by the network. Besides, the proposed robust system collectively recognizes and classifies all the available 36 hand gesture classes of the Massey database, where most previous work selected only a few distinguishable gestures. Experimental results show that the average recognition accuracy for characters with similar hand postures like "m" and "n" is better than the state-of-the-art networks. Additionally, the proposed method attains about 3% higher recognition accuracy than the state-of-the-art networks for all gesture classes. The efficacy of the proposed architecture has also been validated via precision, recall, and F-score.

show abstract