• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.486-493
• /
• 2023

In this paper, we propose an automatic hand gesture area extraction and recognition technique using FMCW radar-based point cloud and LSTM. The proposed technique has the following originality compared to existing methods. First, unlike methods that use 2D images as input vectors such as existing range-dopplers, point cloud input vectors in the form of time series are intuitive input data that can recognize movement over time that occurs in front of the radar in the form of a coordinate system. Second, because the size of the input vector is small, the deep learning model used for recognition can also be designed lightly. The implementation process of the proposed technique is as follows. Using the distance, speed, and angle information measured by the FMCW radar, a point cloud containing x, y, z coordinate format and Doppler velocity information is utilized. For the gesture area, the hand gesture area is automatically extracted by identifying the start and end points of the gesture using the Doppler point obtained through speed information. The point cloud in the form of a time series corresponding to the viewpoint of the extracted gesture area is ultimately used for learning and recognition of the LSTM deep learning model used in this paper. To evaluate the objective reliability of the proposed technique, an experiment calculating MAE with other deep learning models and an experiment calculating recognition rate with existing techniques were performed and compared. As a result of the experiment, the MAE value of the time series point cloud input vector + LSTM deep learning model was calculated to be 0.262 and the recognition rate was 97.5%. The lower the MAE and the higher the recognition rate, the better the results, proving the efficiency of the technique proposed in this paper.

• Journal of Platform Technology
• /
• v.6 no.1
• /
• pp.3-8
• /
• 2018

This paper proposes a technique for recognizing online handwritten cursive data obtained by tracing a motion trajectory while a user is in the 3D space based on a convolution neural network (CNN) algorithm. There is a difficulty in recognizing the virtual character input by the user in the 3D space because it includes both the character stroke and the movement stroke. In this paper, we divide syllable into consonant and vowel units by using labeling technique in addition to the result of localizing letter stroke and movement stroke in the previous study. The coordinate information of the separated consonants and vowels are converted into image data, and Korean handwriting recognition was performed using a convolutional neural network. After learning the neural network using 1,680 syllables written by five hand writers, the accuracy is calculated by using the new hand writers who did not participate in the writing of training data. The accuracy of phoneme-based recognition is 98.9% based on convolutional neural network. The proposed method has the advantage of drastically reducing learning data compared to syllable-based learning.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.12
• /
• pp.1-7
• /
• 2021

The deep learning image processing technique was used to prevent accidents in lathe work caused by worker negligence. During lathe operation, when the chuck is rotated, it is very dangerous if the operator's hand is near the chuck. However, if the chuck is stopped during operation, it is not dangerous for the operator's hand to be in close proximity to the chuck for workpiece measurement, chip removal or tool change. We used YOLO (You Only Look Once), a deep learning image processing program for object detection and classification. Lathe work images such as hand, chuck rotation and chuck stop are used for learning, object detection and classification. As a result of the experiment, object detection and class classification were performed with a success probability of over 80% at a confidence score 0.5. Thus, we conclude that the artificial intelligence deep learning image processing technique can be effective in preventing incidents resulting from worker negligence in future manufacturing systems.

• The Korean Journal of Emergency Medical Services
• /
• v.21 no.1
• /
• pp.99-109
• /
• 2017

Purpose: There is no recommended bag-squeezing technique for emergency medical providers to maintain correct tidal volume during mechanical ventilation. This study compared the tidal volume of two different bag-squeezing techniques during mechanical ventilation. Methods: The subjects were 38 paramedic students who were trained in airway management techniques. Two different bag-squeezing techniques were used with a bag valve mask on an intubated manikin: a conventional technique and a finger-marked, in which the bag is squeezed until the thumb and the middle finger come into contact. Hand size and grip strength were measured and analyzed statistically. Results: The mean tidal volumes for the finger-marked were significantly higher than those for the conventional technique ($542.6{\pm}35.92mL$ versus $338.0{\pm}111.15 mL$, p<.001). There was a correlation between the two techniques (Pearson $x^2=1.160$, p<.001). The subject's characteristics, including sex, hand size, and grip strength, showed no correlation with tidal volume. Conclusion: A finger-marked bag-squeezing technique provides adequate and correct tidal volumes during mechanical ventilation.

• Archives of Plastic Surgery
• /
• v.41 no.4
• /
• pp.312-316
• /
• 2014

This is a review article of the wide-awake approach to hand surgery. More than 95% of all hand surgery can now be performed without a tourniquet. Epinephrine is injected with lidocaine for hemostasis and anesthesia instead of a tourniquet and sedation. This is sedation-free surgery, much like a visit to a dental office. The myth of danger of using epinephrine in the finger is reviewed. The wide awake technique is greatly improving results in tendon repair, tenolysis, and tendon transfer. Here, we will explain its advantages.

• Steel and Composite Structures
• /
• v.15 no.3
• /
• pp.267-279
• /
• 2013

This article describes a simple and cost effective fabrication procedure by using hand lay-up technique that is employed for the manufacturing of thin-walled axi-symmetric composite shell structures with carbon, glass and hybrid woven fabric composite materials. The hand lay-up technique is very commonly used in aerospace and marine industries for making the complicated shell structures. A generic fabrication procedure is presented in this paper aimed at manufacture of plain Carbon Fabric Reinforced Plastic (CFRP) and Glass Fabric Reinforced Plastic (GFRP) shells using hand lay-up process. This paper delivers a technical breakthrough in fabrication of composite shell structures without any joints and wrinkling. The manufacture of stiffened CFRP shells, laminated CFRP shells and hybrid (carbon/glass/epoxy) composite shells which are valued by the aerospace industry for their high strength-to-weight ratio under axial loading have also been addressed in this paper. A fabrication process document which describes the major processing steps of the composite shell manufacturing process has been presented in this paper. A study of microstructure of the glass fabric/epoxy composite, carbon fabric/epoxy composite and hybrid carbon/glass/fabric epoxy composites using Scanning Electron Microscope (SEM) has been also carried out in this paper.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.24 no.3
• /
• pp.440-447
• /
• 2000

The effects of DP finishing conditions including process technique and finishing agent on the mechanical properties and hand of cotton fabrics were investigated. 100% cotton fabrics were treated with NMA/DMDHEU and NMA/YF using wet-fixation and steam-fixation process. For comparison, conventional pad-dry-cure process was used with DMDHEU. After DP finishing, tensile and compressional resilience increased and bending hysteresis decreased, resulting in the improvement of dimensional stability of cotton fabric. WF and SF process rendered fabrics better shear properties, tensile energy, and compressional linearity and energy than PDC process. However, SF process produced fabrics with higher geometrical roughness than WF process. After DP finishing, primary hand values except Koshi increased, resulting in the increase of total hand value of cotton fabric.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.1
• /
• pp.172-179
• /
• 2002

In a robot/vision system, the vision sensor, typically a CCD array sensor, is mounted on the robot hand. The problem of determining the relationship between the camera frame and the robot hand frame is refered to as the hand-eye calibration. In the literature, various methods have been suggested to calibrate camera and for sensor registration. Recently, one-step approach which combines camera calibration and sensor registration is suggested by Horaud & Dornaika. In this approach, camera extrinsic parameters are not need to be determined at all configurations of robot. In this paper, by modifying the camera model and including the lens distortion effect in the perspective transformation matrix, a new one-step approach is proposed in the hand-eye calibration.

• Journal of Korea Multimedia Society
• /
• v.22 no.4
• /
• pp.424-431
• /
• 2019

In this paper, we propose a real-time hand gesture recognition algorithm to eliminate the inconvenience of using hand controllers in VR applications. The user's 3D hand coordinate information is detected by leap motion sensor and then the coordinates are generated into two dimensional image. We classify hand gestures in real-time by learning the imaged 3D hand coordinate information through SSD(Single Shot multibox Detector) model which is one of CNN(Convolutional Neural Networks) models. We propose to use all 3 channels rather than only one channel. A sliding window technique is also proposed to recognize the gesture in real time when the user actually makes a gesture. An experiment was conducted to measure the recognition rate and learning performance of the proposed model. Our proposed model showed 99.88% recognition accuracy and showed higher usability than the existing algorithm.

• Journal of Digital Contents Society
• /
• v.10 no.2
• /
• pp.319-326
• /
• 2009

In this paper, we present an algorithm which recognize hand shape in real time using only image without adhering separate sensor. Hand recognizes using edge orientation histogram, which comes under a constant quantity of 2D appearances because hand shape is intricate. This method suit hand pose recognition in real time because it extracts hand space accurately, has little computation quantity, and is less sensitive to lighting change using color information in complicated background. Method which reduces recognition error using principal component analysis(PCA) method to can recognize through hand shape presentation direction change is explained. A case that hand shape changes by turning 3D also by using this method is possible to recognize. Human interface system manufacture technique, which controls a home electric appliance or game using, suggested method at experience could be applied.