Cover Image

Gesture Recognition : Theory and Applications /

Gesture Recognition: Theory and Applications covers this important topic in computer science and language technology that has a goal of interpreting human gestures via mathematical algorithms. The book begins by examining the computer vision-based gesture recognition method, focusing on the theory a...

Full description

Bibliographic Details
Main Author: Miao, Qiguang
Corporate Author: ScienceDirect (Online service)
Other Authors: Li, Yunan, Liu, Xiangzeng, Liu, Ruyi
Format: eBook
Language:English
Published: Amsterdam, Netherlands ; Oxford, United Kingdom ; Cambridge MA : Elsevier, [2024]
Subjects:
Gesture recognition (Computer science)
Human-computer interaction.
Electronic books.
Online Access:Connect to the full text of this electronic book
Table of Contents:
  • Front Cover
  • Gesture Recognition
  • Copyright Page
  • Contents
  • 1 Basic concepts and development of gesture recognition
  • 1.1 Principles of gesture recognition
  • 1.1.1 Gesture in human society
  • 1.1.2 Gesture and human-computer interaction
  • 1.2 Development of gesture recognition algorithms
  • 1.2.1 Methods based on handicraft features
  • 1.2.2 Methods based on probabilistic graphical model
  • 1.2.3 Methods based on bag of visual words
  • 1.2.4 Methods based on neural network
  • 1.3 Current challenges in the field of gesture recognition
  • 1.4 Summary
  • References
  • 2 Common datasets in the field of gesture recognition
  • 2.1 Image-based gesture dataset
  • 2.1.1 American Sign Language fingerspelling dataset
  • 2.1.2 MU HandImages ASL gesture dataset
  • 2.1.3 LaRED gesture dataset
  • 2.1.4 Marcel gesture dataset
  • 2.1.5 Senz3D gesture dataset
  • 2.2 Video-based gesture dataset
  • 2.2.1 20BN-jester dataset
  • 2.2.2 RWTH-PHOENIX-weather dataset
  • 2.2.3 CSL series datasets
  • 2.2.4 DEVISIGN sign language dataset
  • 2.2.5 CGD series datasets
  • 2.2.5.1 CGD 2011
  • 2.2.5.2 CGD 2013
  • 2.2.5.3 CGD 2016
  • 2.2.6 Traffic police gesture dataset
  • 2.2.7 SKIG dataset
  • 2.2.8 EgoGesture dataset
  • 2.2.9 MSRC-12 dataset
  • 2.2.10 NvGesture dataset
  • 2.3 Dataset summary
  • 2.4 Summary
  • References
  • 3 Gesture recognition method based on handicraft features
  • 3.1 Hand region segmentation
  • 3.1.1 Edge information-based segmentation methods
  • 3.1.1.1 Edge operator-based segmentation approach
  • 3.1.1.2 Active contour model-based segmentation
  • 3.1.2 Motion analysis-based segmentation methods
  • 3.1.2.1 Background subtraction-based segmentation
  • 3.1.2.2 Interframe difference threshold-based method
  • 3.1.2.3 Optical flow field-driven segmentation
  • 3.1.3 Skin color feature-based segmentation methods
  • 3.1.4 Summary
  • 3.2 Gesture feature extraction
  • 3.2.1 Haar-like features
  • 3.2.2 Local binary pattern features
  • 3.2.3 SIFT features
  • 3.2.3.1 Build Gaussian difference pyramid
  • 3.2.3.2 Determine location of keypoints
  • 3.2.3.2.1 Primary selection of keypoints
  • 3.2.3.2.2 Adjustment of keypoints
  • 3.2.3.2.3 Removal of edge effects
  • 3.2.3.3 Direction of keypoints
  • 3.2.3.4 Construction of keypoint descriptors
  • 3.2.4 SURF features
  • 3.2.4.1 Construction of scale space
  • 3.2.4.2 Location of keypoints
  • 3.2.4.3 Determination of the direction of feature points
  • 3.2.4.4 Generation of feature descriptors
  • 3.2.5 Features of histogram of oriented gradient
  • 3.2.6 Features of histogram of oriented optical flow
  • 3.2.7 Summary
  • 3.3 Gesture recognition
  • 3.3.1 Template matching
  • 3.3.2 Finite-state machine
  • 3.3.3 Dynamic time warping
  • 3.4 Summary
  • References
  • 4 Gesture recognition method based on convolutional neural network
  • 4.1 Basic operations of deep convolutional neural network
  • 4.1.1 Characteristics of convolutional neural network
  • 4.1.1.1 Local connection