OPTIMAL AND FAST HAND GESTURE RECOGNITION MODEL USING FASTER R-CNN

2019 ◽  
Vol 12 ◽  
Author(s):  
Kathirvel Sundaramoorthy ◽  
Murugaboopathi G ◽  
Ramaprabha Marimuthu
Keyword(s):  
Gesture Recognition ◽  
Computation Time ◽  
Hand Gesture Recognition ◽  
Hand Gesture ◽  
Important Research ◽  
Recognition Model ◽  
Computer Interfaces ◽  
Human Computer Interfaces ◽  
Important Research Topic ◽  
Efficient Recognition

Due to the advancements in computer vision, gesture recognition becomes an important research topic and is widely used for human-computer interfaces. Among gesture recognition models, the hand gesture is highly preferable because of its application in various applications like healthcare, gaming, etc. Though numerous hand gesture recognition models exist, none of these methods attained an efficient and faster detection rate in different situations. In this paper, we introduce an optimal and fast hand gesture recognition model using Faster R-CNN. The use of Faster R-CNN leads to efficient recognition at a faster rate. To evaluate the results of the Faster R-CNN model, we employ this model to a set of two benchmark hand gesture dataset. The experimental outcomes demonstrate that the Faster R-CNN model gains enhanced performance over the standard methods in terms of accuracy and computation time.

scholarly journals Implementation and Performance Analysis of Different Hand Gesture Recognition Methods

2019 ◽  
pp. 13-20
Author(s):  
Md. Manik Ahmed ◽  
Md. Anwar Hossain ◽  
A F M Zainul Abadin
Keyword(s):  
Computer Vision ◽  
Human Computer Interaction ◽  
Gesture Recognition ◽  
Optimization Technique ◽  
Light Condition ◽  
Hand Gesture Recognition ◽  
Hand Gesture ◽  
Model Accuracy ◽  
Recognition Model ◽  
Computer Interaction

In recent few years, hand gesture recognition is one of the advanced grooming technologies in the era of human computer interaction and computer vision due to a wide area of application in the real world. But it is a very complicated task to recognize hand gesture easily due to gesture orientation, light condition, complex background, translation and scaling of gesture images. To remove this limitation, several research works have developed which is successfully decrease this complexity. However, the intention of this paper is proposed and compared four different hand gesture recognition system and apply some optimization technique on it which ridiculously increased the existing model accuracy and model running time. After employed the optimization tricks, the adjusted gesture recognition model accuracy was 93.21% and the run time was 224 seconds which was 2.14% and 248 seconds faster than an existing similar hand gesture recognition model. The overall achievement of this paper could be applied for smart home control, camera control, robot control, medical system, natural talk, and many other fields in computer vision and human-computer interaction.

Connectionist Temporal Classification Model for Dynamic Hand Gesture Recognition using RGB and Optical flow Data

2020 ◽  
Vol 17 (4) ◽  
pp. 497-506
Author(s):  
Sunil Patel ◽  
Ramji Makwana
Keyword(s):  
Neural Network ◽  
Optical Flow ◽  
Gesture Recognition ◽  
Hand Gesture Recognition ◽  
Classification Model ◽  
Hand Gesture ◽  
Flow Data ◽  
Dynamic Hand Gesture Recognition ◽  
Connectionist Temporal Classification

Automatic classification of dynamic hand gesture is challenging due to the large diversity in a different class of gesture, Low resolution, and it is performed by finger. Due to a number of challenges many researchers focus on this area. Recently deep neural network can be used for implicit feature extraction and Soft Max layer is used for classification. In this paper, we propose a method based on a two-dimensional convolutional neural network that performs detection and classification of hand gesture simultaneously from multimodal Red, Green, Blue, Depth (RGBD) and Optical flow Data and passes this feature to Long-Short Term Memory (LSTM) recurrent network for frame-to-frame probability generation with Connectionist Temporal Classification (CTC) network for loss calculation. We have calculated an optical flow from Red, Green, Blue (RGB) data for getting proper motion information present in the video. CTC model is used to efficiently evaluate all possible alignment of hand gesture via dynamic programming and check consistency via frame-to-frame for the visual similarity of hand gesture in the unsegmented input stream. CTC network finds the most probable sequence of a frame for a class of gesture. The frame with the highest probability value is selected from the CTC network by max decoding. This entire CTC network is trained end-to-end with calculating CTC loss for recognition of the gesture. We have used challenging Vision for Intelligent Vehicles and Applications (VIVA) dataset for dynamic hand gesture recognition captured with RGB and Depth data. On this VIVA dataset, our proposed hand gesture recognition technique outperforms competing state-of-the-art algorithms and gets an accuracy of 86%

Sign in / Sign up

Export Citation Format

Share Document