• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.53-59
• /
• 2008

Recently, vision-based hand gesture recognition techniques have been developed for assisting elderly and disabled people to control home appliances. Frequently occurred problems which lower the hand gesture recognition rate are due to the inter-person variation and intra-person variation. The recognition difficulty caused by inter-person variation can be handled by using user dependent model and model selection technique. And the recognition difficulty caused by intra-person variation can be handled by using fuzzy logic. In this paper, we propose multivariate fuzzy decision tree learning and classification method for a hand motion recognition system for multiple users. When a user starts to use the system, the most appropriate recognition model is selected and used for the user.

• 전자공학회논문지 IE
• /
• v.45 no.4
• /
• pp.47-53
• /
• 2008

A new intra-field deinterlacing algorithm with edge direction vector (EDV) in the image block is introduced. This proposed filter is suitable to the region with high motion or scene change. We first introduce an EDV, which is computed by Sobel mask used edge map, so that filer resolution of the edge direction can be acquired. The proposed EDV oriented deinterlacing system operates by identifying small pixel variations in five orientations, $26.5^{\circ}$, $45^{\circ}$, $90^{\circ}$, $135^{\circ}$, and $153.5^{\circ}$. The EDV values work as inputs of Sobel mask and return edge direction degree and confidence parameters. Based on edge direction degree and confidence parameters the missing pixel is computed. The results of computer simulations demonstrate that the proposed method outperforms a number of intra-field deinterlacing methods in the literature.

• Journal of Broadcast Engineering
• /
• v.13 no.1
• /
• pp.137-151
• /
• 2008

H.264/AVC is showed high coding efficiency more than previous video coding standard by using new coding tools. Specially, Variable block-based motion estimation and Rate-Distortion Optimization are very important coding tools in H.264/AVC. These coding tools have high coding efficiency, however the encoder complexity greatly increase due to these coding tools. In this paper, we propose early SKIP mode decision and selective inter/intra mode decision to reduce the computational complexity. Simulation results show that the proposed method could reduce encoding time of the overall sequences by 30% on average than JM 10.2 without noticeable degradation of coding efficiency. Besides, the proposed method runs over twice as fast as the previous proposed Fast Coding Mode Selection method (FCMS)[5].

• Clinical Pain
• /
• v.20 no.2
• /
• pp.99-104
• /
• 2021

Objective: To confirm the safety of Intra-articular (IA) injection on the ipsilateral adhesive capsulitis (AC) after breast cancer surgery. Methods: Between January 2017 and May 2020, we retrospectively studied 29 patients after breast cancer surgery who underwent IA injection in the glenohumeral joint for AC in aseptic procedure. Results: There were no side effects or complications such as lymphedema or cellulitis in the patients. There was a significant improvement in pain score and range of motion (ROM) at the 1st, 3rd, and 6th months visits compared to the baseline (p<0.05). The presence or absence of axillary lymph node dissection and radiation therapy had no significant difference in improvement of ROM. But, in rotator cuff syndrome (RCS) group, there was a significant difference in improvement of shoulder IR in patients without RCS. Conclusion: IA Injection on the ipsilateral AC after breast cancer surgery was safe and even effective to improve pain and shoulder ROM. Ipsilateral IA injection can be a good treatment for breast cancer surgery patients suffering from AC.

• Physical Therapy Rehabilitation Science
• /
• v.11 no.4
• /
• pp.454-463
• /
• 2022

Objective: The purpose of this study was to compare concurrent validity and test-retest reliability based on Craniovertebral angle of 'Angles video goniometer', a smart phone application for convenient range of motion measurement, and 'Image J', an analysis software with high reliability and validity. This was conducted to find out whether 'Angle video goniometer' can be used clinically. Design: Cross-sectional study Methods: Fifty subjects were imaged laterally, and the angle of the head and spine was measured using Image J and the Angles video goniometer, respectively, in a resting posture and a chin in posture. The level of concurrent validity between the two measurement methods and the level of inter-rater reliability and intra-rater reliability were analyzed. Results: For forty participants, the concurrent validity between Image J and Angles video goniometer showed very high validity with ICC of 0.997(0.995~0.999) and 0.994(0.994~0.998), CVME% 0.71~0.72%, SEM% 0.31~0.34, MDC% 0.86~0.94. The test-retest intra-rater reliability showed very high reliability ICC 0.994(0.991~0.996), CVME% 0.71%, SEM% 0.31~0.43, MDC% 0.86~1.19%. The test-retest inter-rater showed very high reliability ICC 0.995(0.992~0.997), CVME% 0.71%, SEM% 0.43~0.59%, MDC% 1.20~1.62% Conclusions: Angles video goniometer', a smartphone application, is a device with very high reliability and validity for craniovertebral angle measurement in healthy adults, and it is a device that can be easily used in clinical practice.

• The Journal of Korean Physical Therapy
• /
• v.35 no.6
• /
• pp.177-184
• /
• 2023

Purpose: The purpose of this study was to compare the concurrent validity and test-retest reliability of 'KPIMT Torticollis Protractor', a smart phone and I-pad application for convenient range of motion measurement, and 'Image J', an analysis software with high reliability and validity, according to head tilt and active cervical rotation angle. This was done to determine the clinical utility of 'KPIMT Torticollis Protractor'. Methods: Head tilt and active cervical spine rotation angles of 40 children with congenital muscular torticollis were measured using Image J and KPIMT Torticollis Protractor, respectively. The level of concurrent validity and inter-rater and intra-rater reliability between the two measurement methods were analyzed. Results: For forty participants, the concurrent validity between Image J and KPIMT Torticollis Protractor showed very high validity with ICC of ICC 0.977 (0.995-0.999), 0.994 (0.994-0.998), CV_ME% 0.71-0.72%, SEM% 0.31-0.34%, MDC% 0.86-0.94%. The test-retest intra-rater reliability showed very high reliability ICC 0.911 (0.911-0.966), CV_ME% 0.71%, SEM% 0.34-0.36%, MDC% 0.81-0.94%. The test-retest inter-rater showed very high reliability ICC 0.936 (0.933-0.957), CV_ME% 0.70%, SEM% 0.34-0.35%, MDC% 0.81-0.83%. Conclusion: The KPIMT Torticollis Protractor, a smart phone and IPD application, is a highly reliable and valid device for angle measurement in children with congenital myotonia and can be easily used in clinical practice.

• Journal of KIISE:Software and Applications
• /
• v.29 no.1_2
• /
• pp.114-125
• /
• 2002

In this paper, we are proposing a hierarchical segmentation method that first segments the video data into units of shots by detecting cut and dissolve, and then decides types of camera operations or object movements in each shot. In our previous work[1], each picture group is divided into one of the three detailed categories, Shot(in case of scene change), Move(in case of camera operation or object movement) and Static(in case of almost no change between images), by analysing DC(Direct Current) component of I(Intra) frame. In this process, we have designed two-stage hierarchical neural network with inputs of various multiple features combined. Then, the system detects the accurate shot position, types of camera operations or object movements by searching P(Predicted), B(Bi-directional) frames of the current picture group selectively and hierarchically. Also, the statistical distributions of macro block types in P or B frames are used for the accurate detection of cut position, and another neural network with inputs of macro block types and motion vectors method can reduce the processing time by using only DC coefficients of I frames without decoding and by searching P, B frames selectively and hierarchically. The proposed method classified the picture groups in the accuracy of 93.9-100.0% and the cuts in the accuracy of 96.1-100.0% with three different together is used to detect dissolve, types of camera operations and object movements. The proposed types of video data. Also, it classified the types of camera movements or object movements in the accuracy of 90.13% and 89.28% with two different types of video data.

• Journal of the Korean Arthroscopy Society
• /
• v.8 no.2
• /
• pp.115-118
• /
• 2004

Purpose: The purpose of this study is to measure the internal and external rotation of shoulder and compare with normal volunteer and patients diagnosed as SLAP lesion. Materials and Methods: Thirty-eight cases (group 1) who had SLAP lesions at shoulder arthroscopy and fourty young volunteers(group 2) were analyzed retrogradely with medical record, intra-operative arthroscopic photo & video for SLAP lesions and the ROM of shoulder Under the interscalene anesthesia, the range of motion of internal rotation and external rotation were measured on flxed scapula and 90 degree abduction of shoulder, and the same method for group 2. We analyzed the results with two sample T-test and Wisconsin signed ranks test. Results: There was a significant difference between group 1 and group 2 for the ROM of shoulder. (IR; p<0.001,ER; p<0.001).For the group 1, internal and external rotation with the arm abducted 90 averaged 50 and 64 degrees and for the group 2, internal and external rotation averaged 77 and 90 degrees with significant difference(IR; p<0.001,ER; p<0.001).Conclusion: The range of motion of shoulder, especially internal and external rotation significantly decreased in SLAP lesions. Our results suggest that a limited rotational motion of shoulder closely related with SLAP lesion.

• Journal of Korean Foot and Ankle Society
• /
• v.24 no.2
• /
• pp.87-93
• /
• 2020

Purpose: This study evaluated the clinical results of surgical treatment with minimally invasive plate osteosynthesis for treating displaced intra-articular fractures of the calcaneus in comparison with conventional lateral extensile approach plate osteosynthesis. Materials and Methods: Of 79 cases of Sanders type II or III calcaneus fractures, 15 cases treated with the minimally invasive calcaneal plate (group M) and 64 cases treated with lateral extensile approach calcaneal plate (group E) were identified. After successful propensity score matching considering age, sex, diabetes mellitus history, and Sanders type (1:3 ratio), 15 cases (group M) and 45 cases (group E) were matched and the demographic, radiologic, and clinical outcomes were compared between the two groups. Results: The median time of surgery from injury was 2.0 days in group M and 6.0 days in group E (p=0.014). At the six months follow-up, group M showed results comparable with those of group E in radiographic outcomes. In the clinical outcomes, group M showed better postoperative American Orthopaedic Foot and Ankle Society (AOFAS) and visual analogue scale (VAS) scores than did group E (p=0.001, p=0.008). A greater range of subtalar motion was achieved at the six months follow-up in group M (inversion 20.0° vs. 10.0°, p=0.002; eversion 10.0° vs. 5.0°, p=0.025). Although there were no significant differences in complications between the two groups (1 [6.7%] vs. 7 [15.6%], group M vs. group E; p=0.661), there was only one sural nerve injury and no wound dehiscence and deep infection in group M. Conclusion: Minimally invasive plate osteosynthesis showed superior clinical outcomes compared with that of the conventional lateral extensile approach plate osteosynthesis in Sanders type II or III calcaneus fractures. We suggest applying minimally invasive plate osteosynthesis in Sanders type II or III calcaneus fractures.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.5
• /
• pp.42-53
• /
• 2000

Efficient implementation of pre-filtering has been an important issue in video sequence coding, because it can remove camera noise and improve coding efficiency dramatically This paper introduces a novel pre-filtering scheme that is performed inside a video encoder The proposed pre-filtering is based on the approximated generalized Wiener filtering and two-dimensional discrete cosine transform (DCT) factorization. and is achieved by scaling the DCT coefficients of original image blocks for intra block coding and those of motion-compensated error blocks for inter block coding, respectively Even though the pre-filtering operation is embedded in a video encoder, its additional computational complexity is marginal compared to the encoding process, and the overall architecture of the conventional video encoder is maintained In spite of its simplicity, the proposed pre-filtering scheme provides good filtering and coding performance for noisy video sequences.