임베디드 시스템을 위한 고속의 손동작 인식 알고리즘

황동현; 장경식
July 2017
Journal of the Korea Institute of Information & Communication En;Jul2017, Vol. 21 Issue 7, p1349
Academic Journal
In this paper, we propose a fast hand-gesture recognition algorithm for embedded system. Existing hand-gesture recognition algorithm has a difficulty to use in a low performance system such as embedded systems and mobile devices because of high computational complexity of contour tracing method that extracts all points of hand contour. Instead of using algorithms based on contour tracing, the proposed algorithm uses concentric-circle tracing method to estimate the abstracted contour of fingers, then classify hand-gestures by extracting features. The proposed algorithm has an average recognition rate of 95% and an average execution time of 1.29ms, which shows a maximum performance improvement of 44% compared with algorithm using the existing contour tracing method. It is confirmed that the algorithm can be used in a low performance system such as embedded systems and mobile devices.


Related Articles

  • Grassmann manifold-based semi-supervised feature mapping algorithm and its video object recognition application. LI Shufang; ZENG Xianhua; FENG Xiao // Journal of Chongqing University of Posts & Telecommunications (N;Apr2014, Vol. 26 Issue 2, p265 

    This paper considers the set of videos to subspaces, and uses semi-supervised laplacian eigenmap which is based on metric of the similarity between subspaces and the classes information of labeled subspaces which could nonlinear map the video set to a low dimensional euclidean space. This paper...

  • 面向智能家居的挥手识别算法. 杨硕; 吉爱萍 // Journal of Image & Graphics;Oct2016, Vol. 21 Issue 10, p1357 

    Objective Controlling household appliances by hand gesture is one the trends in smart home systems. Hand-gesture recognition is a developing field in human-computer interaction. In the past decades, many gesture-recognition algorithms were developed for tracking and recognizing various hand...

  • LSTM-based dynamic probability continuous hand gesture trajectory recognition. Chengfeng Jian; Junjie Li; Meiyu Zhang // IET Image Processing;2019, Vol. 13 Issue 12, p2314 

    In the field of continuous hand-gesture trajectory recognition, aiming at the problems of existing a lot of noise for handwriting trajectories, and difficult to segment multiple continuous hand gestures accurately, a long short-term memory-based dynamic probability (DP-LSTM) method is proposed....

  • Static Hand-Gesture Recognition Using HOG and Improved LBP Features. Youdong Ding; Haibo Pang; Xuechun Wu // International Journal of Digital Content Technology & its Applic;Nov2011, Vol. 5 Issue 11, p236 

    This paper presents a static hand-gesture recognition approach which is used classify static gestures. The features used in our approach are the cascade of the HOG (Histograms of Oriented Gradients) and improved LBP (Local Binary Pattern). The features makes full use of the correlation and the...

  • A Novel Recognition Algorithm Based on Optimal Wavelet Packet and Non-Negative Matrix Factorization for Extracting Pathologic Features of Plant Image. Yin Laiwu; Chen Deyun; Li Changcheng; Chen Dong // International Journal of Signal Processing, Image Processing & P;Oct2013, Vol. 6 Issue 5, p89 

    This paper presents a new recognition algorithm for plant pathology images based on the Non-negative Matrix Factorization, the proposed algorithm is combined with optimal wavelet packet basis to recognize patterns and conduct data encoding in the internet of things oriented intelligent...

  • Facial Expression Feature Extraction Based on FastLBP. Ya Zheng; Xiuxin Chen; Chongchong Yu; Cheng Gao // Journal of Software (1796217X);Nov2013, Vol. 8 Issue 11, p2790 

    The methods of facial expression feature extraction based on traditional LBP have some drawbacks such as complexity, high dimension of feature vectors, which may reduce the efficiency of subsequent recognition process. To solve the above problems, this paper proposes an improved LBP...

  • A Comparative Survey on the Fast Computation of Geometric Moments. Abu Dalhoum, Abdel Latif Ibrahim // European Journal of Scientific Research;Dec2008, Vol. 24 Issue 1, p104 

    This paper demonstrates different geometric moments algorithms used in pattern recognition and object detection. Those algorithms are fast in comparison to the direct computation. Due to the nature of image data and/or object data and the moment order that is required, most of those algorithms...

  • Fast Search for MPEG Video Clips Using Adjacent Pixel Intensity Difference Quantization Histogram Feature. Feifei Lee; Qiu Chen; Kotani, Koji; Ohmi, Tadahiro // World Academy of Science, Engineering & Technology;Jun2009, Issue 30, p733 

    In this paper, we propose a novel fast search algorithm for short MPEG video clips from video database. This algorithm is based on the adjacent pixel intensity difference quantization (APIDQ) algorithm, which had been reliably applied to human face recognition previously. An APIDQ histogram is...

  • An Improved PCA Algorithm for Fast Face Recognition. Pengli Lu; Xingbin Jiang // International Journal of Advancements in Computing Technology;Jan2013, Vol. 5 Issue 2, p429 

    The traditional Principal Component Analysis (PCA) can not satisfy the needs of practical application for the influence of the change of illumination, expression and so on. In this paper, an improved PCA algorithm is proposed for fast face recognition. First, after a candidate set being selected...

  • Feature Recognition of Froth Images Based on Energy Distribution Characteristics. WU Yanpeng; PENG Xiaoqi; ZHANG Jianzhi; JIANG Qian // Sensors & Transducers (1726-5479);Sep2014, Vol. 179 Issue 9, p180 

    This paper proposes a determining algorithm for froth image features based on the amplitude spectrum energy statistics by applying Fast Fourier Transformation to analyze the energy distribution of various-sized froth. The proposed algorithm has been used to do a froth feature analysis of the...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics