• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.5
• /
• pp.53-63
• /
• 2019

To provide a hand gesture interface through deep learning in mobile environments, research on the light-weighting of networks is essential for high recognition rates while at the same time preventing degradation of execution speed. This paper proposes a method of real-time recognition of written characters in the air using a finger on mobile devices through the light-weighting of deep-learning model. Based on the SSD (Single Shot Detector), which is an object detection model that utilizes MobileNet as a feature extractor, it detects index finger and generates a result text image by following fingertip path. Then, the image is sent to the server to recognize the characters based on the learned OCR model. To verify our method, 12 users tested 1,000 words using a GALAXY S10+ and recognized their finger with an average accuracy of 88.6%, indicating that recognized text was printed within 124 ms and could be used in real-time. Results of this research can be used to send simple text messages, memos, and air signatures using a finger in mobile environments.

• Journal of Life Science
• /
• v.13 no.1
• /
• pp.42-46
• /
• 2003

Photoplethysmogram is widely used to measure heart rate and arterial blood oxygen saturation in human. This paper describes radial pulse waves recorded by photoplethysmogram with 940 nm wavelength infra red light. Radial pulse waves were varied according to the recording site. When recorded on the skin over radial artery, the radial pulse wave was inverted, comparing to the photoplethysmogram at fingertip. The mechanism of inverted pulse wave seemed to be caused by the change of the blood volume in the subcutaneous tissue between radial artery and the skin, which was reduced during systolic period and increased during diastolic period of the cardiac cycle. These results suggest that radial arterial wall may reflect infra red ray.

• Archives of Plastic Surgery
• /
• v.35 no.3
• /
• pp.312-315
• /
• 2008

Purpose: Amelanotic melanoma represents a melanoma with an absence or a small number of melanin pigments and comprises 2% of all melanomas. These melanomas are frequently misdiagnosed, probably because of its nonspecific clinical features and difficulty in diagnosis, resulting in delayed diagnosis and treatment. We report a patient with amelanotic melanoma, who underwent surgical treatment with sentinel lymph node biopsy using gamma probe. Methods: A 32-year-old female was presented with a slowly growing ill-defined, hypopigmented nonerythematous lesion with nail defect on right index finger tip. Preoperative punch biopsy was performed, showing an amelanotic melanoma. Sentinel lymph node biopsy was done using gamma probe(Crystal probe system, CRYSTAL PHOTONICS GmbH, Germany) and confirmed no evidence of regional lymph node metastases. The patient underwent amputation at the proximal interphalangeal joint. Results: Histopathologic findings showed superficial spreading melanoma. There were no melanin pigments in Hematoxylin & Eosin stain but positive immunohistochemical stainings for S-100 protein and Hmb45, which were consistent with amelanotic melanoma. Patient's postoperative course was uneventful without any complication and had no evidence of recurrence of tumor in 6 months follow-up period. Conclusion: Amelanotic melanoma is extremely rare subtype of malignant melanoma with histopathologic findings of atypical melanocytes without melanin pigments. Early detection is crucial since survival is strongly related to tumor thickness and tissue invasion at the time of diagnosis. Wide excision is the treatment of choice and other conjunctive therapy has not been successful.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.2
• /
• pp.29-36
• /
• 2008

In this paper we propose a real-time method to estimate a pointing region from two camera images. In general, a pointing target exists in the face direction when a human points to something. Therefore, we regard the direction of pointing as the straight line that connects the face position with the fingertip position. First, the method extracts two points in the face and the fingertips region by using detecting the skin color of human being. And we used the 3D geometric information to obtain a pointing detection and its region. In order to evaluate the performance, we have build up an ICIGS(Interactive Cinema Information Guiding System) with two camera and a beam project.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1686-1694
• /
• 2014

In this paper, a new scheme to recognize a finger shape in the depth image captured by Kinect is proposed. Rigid transformation of an input finger shape is pre-processed for its robustness against the shape angle of input fingers. After extracting contour map from hand region, observing the change of contour pixel location is performed to calculate rotational compensation angle. For the finger shape recognition, we first acquire three pixel points, the most left, right, and top located pixel points. In the proposed algorithm, we first acquire three pixel points, the most left, right, and top located pixel points for the finger shape recognition, also we use geometrical features of human fingers such as Euclidean distance, the angle of the finger and the pixel area of hand region between each pixel points to recognize the finger shape. Through experimental results, we show that the proposed algorithm performs better than old schemes.