Hand Gesture Recognition Using Deep Network Through Trajectory-to-Contour Based Images

Sarma, Debajit; Bhuyan, M. K.

doi:10.1109/indicon45594.2018.8987097

Cited by 12 publications

(14 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the performance of the proposed method, we have carried out experiments on two databases: 1) Palm's Graffiti Digits [22] and 2) Our in-house database [10]. The following sections elaborate on all the details during the implementation and evaluation processes.…”

Section: Experimentation and Resultsmentioning

confidence: 99%

“…(2). These steps are performed for all the hand gesture videos and the corresponding OFMT images obtained from our in-house dataset [10] are shown in Fig. (3).…”

Section: Mei-mhi Algorithm [4]mentioning

confidence: 99%

“…In this dataset, the subjects used tightly folded palms while performing the gestures. 2) In-house dataset: One limited in-house dataset [10] has been created with the help of three subjects.…”

Section: A Databasesmentioning

confidence: 99%

“…For a complex and changing background environment, segmentation may be very difficult due to the variation of shape and appearance of body/body-part depending on many factors like clothing, illumination variation, image resolution, etc. In [10], the authors used the skin segmentation method to segment the hand portion from the background. But this method had issues when there were some skin-color like objects present in the background.…”

Section: Introductionmentioning

confidence: 99%

“…This has motivated the development of learning robust and effective representations directly from raw data and deep learning provides a plausible way of automatically learning multiple level features. Indifference to hand-crafted features, there is a growing trend towards feature representations learned by deep neural networks [7], [10]- [12]. But, in deep learning techniques, the main requirement is lots of database samples.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Two-stream Fusion Model for Dynamic Hand Gesture Recognition using 3D-CNN and 2D-CNN Optical Flow guided Motion Template

Sarma¹,

Kavyasree²,

Bhuyan³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

The use of hand gestures can be a useful tool for many applications in the human-computer interaction community. In a broad range of areas hand gesture techniques can be applied specifically in sign language recognition, robotic surgery, augmented and virtual reality, etc. In the process of hand gesture recognition, proper detection, and tracking of the moving hand become challenging due to the varied shape and size of the hand. Here the objective is to track the movement of the hand irrespective of the shape, size and color of the hand. And, for this, a motion template guided by optical flow (OFMT) is proposed. OFMT is a compact representation of the motion information of a gesture encoded into a single image. In the experimentation, different datasets using bare hand with an open palm, and folded palm wearing green-glove are used, and in both cases, we could generate the OFMT images with equal precision. Recently, deep network-based techniques have shown impressive improvements as compared to conventional hand-crafted feature-based techniques. Moreover, in the literature, it is seen that the use of different streams with informative input data helps to increase the performance in the recognition accuracy. This work basically proposes-a two-stream fusion model for hand gesture recognition and a compact yet efficient motion template based on optical flow. Specifically, the twostream network consists of two layers-a 3D convolutional neural network (C3D) that takes gesture videos as input and a 2D-CNN that takes OFMT images as input. C3D has shown its efficiency in capturing spatio-temporal information of a video. Whereas OFMT helps to eliminate irrelevant gestures providing additional motion information. Though each stream can work independently, they are combined with a fusion scheme to boost the recognition results. We have shown the efficiency of the proposed two-stream network on two databases.

show abstract

Section: Experimentation and Resultsmentioning

confidence: 99%

“…(2). These steps are performed for all the hand gesture videos and the corresponding OFMT images obtained from our in-house dataset [10] are shown in Fig. (3).…”

Section: Mei-mhi Algorithm [4]mentioning

confidence: 99%

Section: A Databasesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%