• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.4
• /
• pp.328-336
• /
• 2012

In this paper, we propose a robust fingertip extraction and extended Continuously Adaptive Mean Shift (CAMSHIFT) based robust hand gesture recognition for natural human-like HRI (Human-Robot Interaction). Firstly, for efficient and rapid hand detection, the hand candidate regions are segmented by the combination with robust $YC_bC_r$ skin color model and haar-like features based adaboost. Using the extracted hand candidate regions, we estimate the palm region and fingertip position from distance transformation based voting and geometrical feature of hands. From the hand orientation and palm center position, we find the optimal fingertip position and its orientation. Then using extended CAMSHIFT, we reliably track the 2D hand gesture trajectory with extracted fingertip. Finally, we applied the conditional density propagation (CONDENSATION) to recognize the pre-defined temporal motion trajectories. Experimental results show that the proposed algorithm not only rapidly extracts the hand region with accurately extracted fingertip and its angle but also robustly tracks the hand under different illumination, size and rotation conditions. Using these results, we successfully recognize the multiple hand gestures.

• Journal of Korea Multimedia Society
• /
• v.13 no.2
• /
• pp.316-323
• /
• 2010

In this paper, we propose fingertip extraction and hand motion recognition method for augmented reality applications. First, an input image is transformed into HSV color space from RGB color space. A hand area is segmented using double thresholding of H, S value, region growing, and connected component analysis. Next, the end points of the index finger and thumb are extracted using morphology operation and subtraction for a virtual keyboard and mouse interface. Finally, the angle between the end points of the index finger and thumb with respect to the center of mass point of the palm is calculated to detect the touch between the index finger and thumb for implementing the click of a mouse button. Experimental results on various input images showed that our method segments the hand, fingertips, and recognizes the movements of the hand fast and accurately. Proposed methods can be used the input interface for augmented reality applications.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.9
• /
• pp.345-350
• /
• 2018

This study is an algorithm for detecting vein pattern features important for finger vein recognition. The feature detection algorithm is important because it greatly affects recognition results in pattern recognition. The recognition rate is degraded because the reference is changed according to the finger position change. In addition, the image obtained by irradiating the finger with infrared light is difficult to separate the image background and the blood vessel pattern, and the detection time is increased because the image preprocessing process is performed. For this purpose, the presented algorithm can be performed without image preprocessing, and the detection time can be reduced. SWDA (Down Slope Trace Waveform) algorithm is applied to the finger vein images to detect the fingertip position and vein pattern. Because of the low infrared transmittance, relatively dark vein images can be detected with minimal detection error. In addition, the fingertip position can be used as a reference in the classification stage to compensate the decrease in the recognition rate. If we apply algorithms proposed to various recognition fields such as palm and wrist, it is expected that it will contribute to improvement of biometric feature detection accuracy and reduction of recognition performance time.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.267-270
• /
• 1997

Oxygen saturation is an important parameter in clinical fields; fetal monitoring, apnea, emergency medicine etc. Because of monitoring patients continuously, pulse oximeter that measures oxigen saturation non-invasively is regarded attentively. But, though research about accuracy of signal extraction has been developed, it actually plays a supplementary part in hospital for not trusting the principle of measurement by clinicians. In this paper focusing on these things, first we suggested simple mathematical modelling on separating do components, ac components andnoise components in optical signal transmitted from fingertip or earlobe, and then we considered oxygen saturation computing algorithm using integral ratio of pulsating components. Last, we analyzed its effect by comparing received data.

• Journal of Dental Anesthesia and Pain Medicine
• /
• v.21 no.4
• /
• pp.345-355
• /
• 2021

Background: This study aimed to evaluate the efficacy of external vibrating devices and counterstimulation on a child's dental anxiety, apprehension, and pain perception during local anesthetic administration. Methods: This was a prospective, randomized, parallel-arm, single-blinded interventional, clinical trial. One hundred children aged 4-11 years, requiring pulp therapy or extraction under local anesthesia (LA), were recruited and allocated equally into two groups (1:1) based on the interventions used: Group BD (n = 50) received vibration using a Buzzy^® device {MMJ Labs, Atlanta, GE, USA} as a behavior guidance technique; Group CS (n = 50) received counterstimulation for the same technique. Anxiety levels [Venham's Clinical Anxiety Rating Scale (VCARS), Venham Picture Test (VPT), Pulse oximeter {Gibson, Fingertip Pulse Oximeter}, Beijing, China)] were assessed before, during, and after LA administration, while pain perception [Wong-Baker Faces Pain Rating Scale (WBFPS), Visual Analogue Scale (VAS)] was evaluated immediately after injection. Statistical analysis was performed using the Student's t-test to assess the mean difference between the two groups and the repeated measures ANOVA for testing the mean difference in the pulse rates. Statistical significance was set at P < 0.05. Results: Significant differences in mean pulse rate values were observed in both groups. In contrast, the children in the BD group had higher diminution (P < 0.05), whereas the mean VCARS and VPT scores were conspicuous (P < 0.05). Based on the mean WBFPS and VAS scores, delayed pain perception after LA injection was more prominent in the BD group than in the CS group. Conclusion: External vibration using a Buzzy^® device is comparatively better than counterstimulation in alleviating needle-associated anxiety in children requiring extraction and pulpectomy.

• Journal of Biomedical Engineering Research
• /
• v.19 no.1
• /
• pp.25-32
• /
• 1998

This paper is based on the design and analysis computing model of oxygen saturation with the pulse oximeter using the integral ratio of pulsating components. In our proposed algorithm. we modeled the transmitted optical signal in fingertip or earlobe to DC component $A_{dc}$ pulsating component $A_a\;Sinwt$, noise component $A_{noise}$ and etc.. To separate the pulsating components and DC components efficiently, we defined the signal average to DC components. Also we presented the way to eliminate the noise using integral ratio. To acquire a linearity of correlation graph for pulsating components ratios and non invasive oxygen saturation. we intensively observed on the oxygen saturations in the range of 75-100% in consideration of the error range of simulator. Also, for real time processing we experimented on changing the period of area calculating cycle from 1 to 6. The functional evaluation of the algorithm is compared with the method using the amplitude ratio of pulsating components frequently seen with pulse oximeter. The result was that our algorithm with 4 cycles of area calculating cycle which considered to be best fit by 1% to the existing method. Moreover r , the decision coefficient showing the correlation of regression graph with real data, proved better result of 0.985 than 0.970.

• Journal of Korea Game Society
• /
• v.10 no.2
• /
• pp.49-56
• /
• 2010

In this paper, we propose a control method of virtual hand by the recognition of a user's hand in the virtual reality game environment. We display virtual hand on the game screen after getting the information of the user's hand movement and the direction thru input images by camera. We can utilize the movement of a user's hand as an input interface for virtual hand to select and move the object. As a hand recognition method based on the vision technology, the proposed method transforms input image from RGB color space to HSV color space, then segments the hand area using double threshold of H, S value and connected component analysis. Next, The center of gravity of the hand area can be calculated by 0 and 1 moment implementation of the segmented area. Since the center of gravity is positioned onto the center of the hand, the further apart pixels from the center of the gravity among the pixels in the segmented image can be recognized as fingertips. Finally, the axis of the hand is obtained as the vector of the center of gravity and the fingertips. In order to increase recognition stability and performance the method using a history buffer and a bounding box is also shown. The experiments on various input images show that our hand recognition method provides high level of accuracy and relatively fast stable results.