• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.1
• /
• pp.11-18
• /
• 2001

In this paper, we proposed the image compression algorithm using triangular feature based GHA. In feature extraction, the input images are divided into eight areas of triangular shape, that has positional information for face image compression. The proposed algorithm reduces blocking effects in image reconstruction and contains informations of face feature and shapes of face as input images are divided into eight. We used triangular feature extraction for positional information and GHA for shape information of face images. Simulation results show that the proposed algorithm has a better performance than the block based K-means and non-parsed image based GHA in PSNR at the same bpp.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.15-18
• /
• 2008

This paper proposes a method to reconstruct the 3-D face using structured light image. First of all, we suppose that each sight vector of a projector and camera are parallel. We project the structured light in the shape of lattice on the background to acquire the reference-structured light image. This image is used to calibrate the projector and camera. Since then, we acquire the face-structured light image which is projected the same structured light on the face. These two structured light images are used to reconstruct the 3-D face through the variation which is measured from the positional difference of feature vectors. In our experiment result, we could reconstruct the 3-D face image as recognize through these simple devices.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.877-893
• /
• 2022

With the development of deep learning, face inpainting has been significantly enhanced in the past few years. Although image inpainting framework integrated with generative adversarial network or attention mechanism enhanced the semantic understanding among facial components, the issues of reconstruction on corrupted regions are still worthy to explore, such as blurred edge structure, excessive smoothness, unreasonable semantic understanding and visual artifacts, etc. To address these issues, we propose a Learnable Structure Knowledge of Fusion Network (LSK-FNet), which learns a prior knowledge by edge generation network for image inpainting. The architecture involves two steps: Firstly, structure information obtained by edge generation network is used as the prior knowledge for face inpainting network. Secondly, both the generated prior knowledge and the incomplete image are fed into the face inpainting network together to get the fusion information. To improve the accuracy of inpainting, both of gated convolution and region normalization are applied in our proposed model. We evaluate our LSK-FNet qualitatively and quantitatively on the CelebA-HQ dataset. The experimental results demonstrate that the edge structure and details of facial images can be improved by using LSK-FNet. Our model surpasses the compared models on L1, PSNR and SSIM metrics. When the masked region is less than 20%, L1 loss reduce by more than 4.3%.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.27 no.3
• /
• pp.288-297
• /
• 2005

Rehabilitation of the paralyzed face as a result of trauma or surgery remains a daunting task. Complete restoration of emotionally driven symmetric facial motion is still unobtainable, but current techniques have enhanced our ability to improve this emotionally traumatic deficit. Problems of mass movement and synkinesis still plague even the best reconstructions. The reconstructive techniques used still represent a compromise between obtainable symmetry and motion at the expense of donor site deficits, but current techniques continue to refine and limit this morbidity. In chronically paralyzed face, direct nerve anastomosis, nerve graft, or microvascular-muscle graft is not always possible. In this case, regional muscle transposition is tried to reanimate the eyelid and lower face. Regional muscle includes maseeter muscle, temporalis muscle and anterior belly of the digastric muscle. Temporalis muscle is preferred because it is long, flat, pliable and wide-motion of excursion. In order to reanimate the upper and lower eyelid, Upper eyelid Gold weight implantion and lower eyelid shortening and tightening is mainly used recently, because this method is very simple, easy and reliable.

• Archives of Reconstructive Microsurgery
• /
• v.23 no.1
• /
• pp.40-43
• /
• 2014

A submental artery perforator flap was applied to the defect site after surgical excision of basal cell carcinoma on the right lower face. Three points were beneficial: it was perfect for assuring the safe margin of the mandibular branch of the facial nerve as well as intact platysma muscle, functionally; harvesting the flap was much easier than that of submental artery flap, surgically; and the color and contour were well matched aesthetically.

• Korean Journal of Head & Neck Oncology
• /
• v.4 no.1
• /
• pp.21-28
• /
• 1988

Skin replacement in large cheek defects after excision of benign or malignant tumor on the face is a challenging task. The physical characteristics of cheek skin are matched best by adjacent skin. Various methods of reconstructing of the facial surface such as forehead flap, distant flap, or a full thickness or split thickness skin graft have replaced adjacent tissue for coverage in many cases. We have reviewed ten cases of aesthetic reconstruction of the face after resection of the facial skin tumor within the last 5 years. The first group of 3 patients were reconstructed with split thickness skin graft from the scalp or lower abdomen. The second group of patients were reconstructed with cheek flap. The third group of 3 patients were reconstructed with cervicofacial flap. The last 2 patients were reconstructed with nasolabial flap & island falp respectively. The advantages from our experience with various method of coverage are its hidden donor area & good color match with the facial skin & increased success rate.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.35-49
• /
• 2004

This paper proposes a new glasses removal method from color frontal facial image to generate gray glassless facial image. The proposed method is based on recursive PCA reconstruction. For the generation of glassless images, the occluded region by glasses should be found, and a good reconstructed image to compensate with should be obtained. The recursive PCA reconstruction Provides us with both of them simultaneously, and finally produces glassless facial images. This paper shows the effectiveness of the proposed method by some experimental results. We believe that this method can be applied to removing other type of occlusion than the glasses with some modification and enhancing the performance of a face recognition system.

• Archives of Craniofacial Surgery
• /
• v.11 no.1
• /
• pp.13-18
• /
• 2010

Purpose: Nasal defect can be caused by excision of tumor, trauma, inflammation from foreign body reaction. Nose is located in the middle of face and protruded, reconstruction should be done in harmony with size, shape, color, and textures. We report various methods of nasal reconstruction using local flaps. Methods: From March 1998 to July 2008, 36 patients were operated to reconstruct the nasal defects. Causes of the nasal defects were tumor (18 cases), trauma (11 cases), inflammation from foreign body reaction (5 cases) and congenital malformation (2 cases). The sites of the defects were ala (22 cases), nasal tip (8 cases) and dorsum (6 cases). The thickness of the defects was skin only (5 cases), dermis and cartilagenous layer (7 cases) and full-thickness (24 cases). According to the sites and thickness of the defects, various local flaps were used. Most of alar defects were covered by nasolabial flaps or bilobed flaps and the majority of dorsal and tip defects were covered by paramedian forehead flaps. Small defects below $0.25 cm^2$ were covered with composite graft or full-thickness skin graft. Results: The follow-up period was 14 months. Partial flap necrosis was observed in a case, and one case of infection was reported, it was improved by wound revision and antibiotics. Nasal reconstruction with various local flaps could provide satisfactory results in terms of color and texture match. Conclusion: The important factors of nasal reconstruction are the shape of reconstructed nose, color, and texture. Nasolabial flap is appropriate method for alar or columellar reconstruction and nasolabial island flap is suitable for tip defect. The defect located lateral wall could be reconstructed with bilobed flap for natural color and texture. Skin graft should be considered when the defect could not afford to be covered by adjacent local flap. And entire nasal defect or large defect could be reconstructed by paramedian forehead flap.

• Archives of Craniofacial Surgery
• /
• v.23 no.1
• /
• pp.17-22
• /
• 2022

Background: Reconstruction of large facial defects is challenging as both functional and cosmetic results must be considered. Reconstruction with forehead flaps on the face is advantageous; nonetheless, reconstruction of large defects with forehead flaps alone results in extensive scarring on the donor site. In our study, the results of reconstruction using a combination of forehead flaps and other techniques for large facial defects were evaluated. Methods: A total of 63 patients underwent reconstructive surgery using forehead flaps between February 2005 and June 2020 at our institution. Reconstruction of a large defect with forehead flaps alone has limitations; because of this, 22 patients underwent a combination of procedures and were selected as the subjects of this study. This study was retrospectively conducted by reviewing the patients' medical records. Additional procedures included orbicularis oculi musculocutaneous (OOMC) V-Y advancement flap, cheek advancement flap, nasolabial V-Y advancement flap, grafting, and simultaneous application of two different techniques. Flap survival, complications, and recurrence of skin cancer were analyzed. Patient satisfaction was evaluated using questionnaires. Results: Along with reconstructive surgery using forehead flaps, nasolabial V-Y advancement flap was performed in nine patients, local advancement flap in three, OOMC V-Y advancement flap in two, grafting in five, and two different techniques in three patients. No patient developed flap loss; however, cancer recurred in two patients. The overall patient satisfaction was high. Conclusion: Reconstruction with a combination of forehead flaps and other techniques for large facial defects can be considered as both functionally and cosmetically reliable.

• Archives of Plastic Surgery
• /
• v.41 no.1
• /
• pp.50-56
• /
• 2014

Background The aim of this study was to determine the efficacy of lateral intercostal artery perforator-based adipofascial free flaps for facial reconstruction in patients with facial soft tissue deficiency. Methods We conducted a retrospective study of five consecutive patients diagnosed with facial soft tissue deficiency who underwent operations between July 2006 and November 2011. Flap design included the area containing the perforators. A linear incision was made along the rib, which had the main intercostal pedicle. First, we dissected below Scarpa's fascia as the dorsal limit of the flap. Then, the adipofascial flap was elevated from the medial to the lateral side, including the perforator that pierces the serratus anterior muscle after emerging from the lateral intercostal artery. After confirming the location of the perforator, pedicle dissection was performed dorsally. Results Dominant perforators were located on the sixth to eighth intercostal space, and more than four perforators were found in fresh-cadaver angiography. In the clinical case series, the seventh or eighth intercostal artery perforators were used for the free flaps. The mean diameter of the pedicle artery was 1.36 mm, and the mean pedicle length was 61.4 mm. There was one case of partial fat necrosis. No severe complications occurred. Conclusions This is the first study of facial contour reconstruction using lateral intercostal artery perforator-based adipofascial free flaps. The use of this type of flap was effective and can be considered a good alternative for restoring facial symmetry in patients with severe facial soft tissue deficiency.