• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.13 no.4
• /
• pp.468-475
• /
• 1991

Skeletal class III malocclusion with aterior deep bite is difficult to manage properly, especially in case of mild mandibular prognathism. We have designed lower anterior segmental osteotomy for improving the lower third of the facial contour. Considerable improvement of esthetic facial contour with correction of cross bite in anterior incisors was observed in patients with mandibular prognathism.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1405-1419
• /
• 2018

An image fusion method is proposed on the basis of depth model segmentation to overcome the shortcomings of noise interference and artifacts caused by infrared and visible image fusion. Firstly, the deep Boltzmann machine is used to perform the priori learning of infrared and visible target and background contour, and the depth segmentation model of the contour is constructed. The Split Bregman iterative algorithm is employed to gain the optimal energy segmentation of infrared and visible image contours. Then, the nonsubsampled contourlet transform (NSCT) transform is taken to decompose the source image, and the corresponding rules are used to integrate the coefficients in the light of the segmented background contour. Finally, the NSCT inverse transform is used to reconstruct the fused image. The simulation results of MATLAB indicates that the proposed algorithm can obtain the fusion result of both target and background contours effectively, with a high contrast and noise suppression in subjective evaluation as well as great merits in objective quantitative indicators.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.134-141
• /
• 2023

We present a novel method aimed at refining ground truth data through regularization and modification, particularly applicable when working with the original ground truth set. Enhancing the performance of deep neural networks is achieved by applying regularization techniques to the existing ground truth data. In many machine learning tasks requiring pixel-level segmentation sets, accurately delineating objects is vital. However, it proves challenging for thin and elongated objects such as blood vessels in X-ray coronary angiography, often resulting in inconsistent generation of ground truth data. This method involves an analysis of the quality of training set pairs - comprising images and ground truth data - to automatically regulate and modify the boundaries of ground truth segmentation. Employing the active contour model and a recursive ground truth generation approach results in stable and precisely defined boundary contours. Following the regularization and adjustment of the ground truth set, there is a substantial improvement in the performance of deep neural networks.

• Archives of Craniofacial Surgery
• /
• v.19 no.1
• /
• pp.48-50
• /
• 2018

Bony anomaly caused by lip tie is not many reported yet. There was a case of upper lip tie wrapping into the anterior premaxilla. We represent a case of severe upper lip tie of limited lip motion, upper lips curling inside, and alveolar hypoplasia. Male patient was born on June 3, 2016. He had a deep philtral sulcus, low vermilion border and deep cupid's bow of upper lip due to tension of short, stout and very tight frenulum. His upper lip motion was severely restricted in particular lip eversion. There was anterior alveolar hypoplasia with deep sulcus in anterior maxilla. Resection of frenulum cord with Z-plasty was performed at anterior premaxilla and upper lip sulcus. Frenulum was tightly attached to gingiva through gum and into hard palate. Width of frenulum cord was about 1 cm, and length was about 3 cm. He gained upper lip contour including cupid's bow and normal vermilion border after the surgery. This case is severe upper lip tie showing the premaxillary hypoplasia, abnormal lip motion and contour for child. Although there is mild limitation of feeding with upper lip tie child, early detection and treatment are needed to correct bony growth.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.171-176
• /
• 2022

CNN is a type of deep learning and is a neural network used to process images or image data. The filter traverses the image and extracts features of the image to distinguish the image. Deep learning has the characteristic that the more data, the better models can be made, and CNN uses a method of artificially increasing the amount of data by means of data augmentation such as rotation, zoom, shift, and flip to compensate for the weakness of less data. When learning CNN, we would like to check whether outline image learning is helpful in improving performance compared to conventional data augmentation techniques.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.65-70
• /
• 2024

Tool wear is considered an important issue in manufacturing and engineering, as worn tools can negatively impact productivity and product quality. Given that the wear status of tools plays a decisive role in the production process, measuring tool wear is a key task. Consequently, there is significant attention in manufacturing fields on the precise measurement of tool wear. Current domestic methods for measuring wear are limited in terms of speed and efficiency, with traditional methods being time-consuming and reliant on subjective evaluation. To address these issues, we developed a measurement module implementing the DeepContour algorithm, which uses image processing technology for rapid measurement and evaluation of tool wear. This algorithm accurately extracts the tool's outline, assesses its condition, determines the degree of wear, and proves more efficient than existing, subjective, and time-consuming methods. The main objective of this paper is to design and apply in practice an algorithm and measurement module that can measure and evaluate tool wear using image processing technology. It focuses on determining the degree of wear by extracting the tool's outline, assessing its condition, and presenting the measured value to the operator.

• Archives of Plastic Surgery
• /
• v.36 no.6
• /
• pp.707-713
• /
• 2009

Purpose: The deep inferior epigastric perforator(DIEP) free flap is well known as an ideal donor site for the breast reconstruction. The flap can provide huge amount of fat tissue for breast and buttock contour, while it is also very useful as a thin skin flap to reconstruct the upper and lower extremities. We used a DIEP free flap in various site reconstructions besides the breast and would like to reinsure the usefulness of this flap. Methods: Twenty nine consecutive patients who underwent DIEP free flap surgery from 2001 January to 2007 December were reviewed. The case constituted seven male patients and twenty two female patients. There were sixteen breast reconstructions, five face reconstructions, five lower extremity reconstructions, two upper extremity reconstructions, and one buttock contour reconstruction. All clinical data were based on the patient's medical records. Results: All DIEP free flaps survived without major complications. There was no hematoma, seroma, or partial necrosis. The donor sites were closed primarily with linear scar on lower abdomen. The thinnest part of flap was 0.7 cm in thickness. The size of the largest flap was $38{\times}13cm$. The flaps were used in various types of skin and adipose tissue, adipose tissue only, and skin only according to the requirement of recipient site. Conclusion: The DIEP free flap was enough to provide a thin and huge flap for both breast and extremity reconstructions. It was able to provide versatile designs with sufficient adipose tissue. So we use it for 3 - dimentional face and buttock contour reconstructions. The DIEP free flap is a valuable reconstructive donor for face, upper and lower extremity in addition to breast without compromising the integrity of abdominal wall.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.36 no.4
• /
• pp.161-167
• /
• 2014

Purpose: The reconstruction of mandibular defects poses many difficulties due to the unique, complex shape of the mandible and the temporomandibular joints. With development of microvascular anastomosis, free tissue transplantation techniques, such as deep circumflex iliac artery (DCIA) flap and fibular free flap (FFF), were developed. The DCIA offers good quality and quantity of bone tissue for mandibular segmental defect and implant for dental rehabilitation. Virtual surgical planning (VSP) and stereolithography-guided osteotomy are currently successfully applied in three-dimensional mandibular reconstruction, but most use FFF. There are only a few articles on reconstruction with the DCIA that assess the postoperative results. Methods: Three patients admitted during a five month period (April of 2013 to August of 2013) underwent resection of mandible and DCIA musculo-osseous reconstruction using a VSP and stereolithographic modeling and assessment of outcomes included technical accuracy, esthetic contour, and functional outcomes. Results: This technique yielded iliac bone segment with excellent apposition and duplication of the preoperative plan. Flap survival was 100 percent and all patients maintained preoperative occlusion and contour. Conclusion: Based on our experience, we offer considerations and logically consistent protocols by classification of mandibular defects, and demonstrate the benefits in VSP and stereolithographic modeling of mandibular reconstructive surgery with DCIA flap.

• The Journal of Korea Robotics Society
• /
• v.14 no.2
• /
• pp.139-149
• /
• 2019

In this paper, we present auto-annotation tool and synthetic dataset using 3D CAD model for deep learning based object detection. To be used as training data for deep learning methods, class, segmentation, bounding-box, contour, and pose annotations of the object are needed. We propose an automated annotation tool and synthetic image generation. Our resulting synthetic dataset reflects occlusion between objects and applicable for both underwater and in-air environments. To verify our synthetic dataset, we use MASK R-CNN as a state-of-the-art method among object detection model using deep learning. For experiment, we make the experimental environment reflecting the actual underwater environment. We show that object detection model trained via our dataset show significantly accurate results and robustness for the underwater environment. Lastly, we verify that our synthetic dataset is suitable for deep learning model for the underwater environments.

• The Journal of Advanced Prosthodontics
• /
• v.7 no.4
• /
• pp.271-277
• /
• 2015

PURPOSE. This study was to evaluate the marginal fit of two CAD-CAM anatomic contour zirconia crown systems compared to lithium disilicate glass-ceramic crowns. MATERIALS AND METHODS. Shoulder and deep chamfer margin were formed on each acrylic resin tooth model of a maxillary first premolar. Two CAD-CAM systems (Prettau$^{(R)}$Zirconia and ZENOSTAR$^{(R)}$ZR translucent) and lithium disilicate glass ceramic (IPS e.max$^{(R)}$press) crowns were made (n=16). Each crown was bonded to stone dies with resin cement (Rely X Unicem). Marginal gap and absolute marginal discrepancy of crowns were measured using a light microscope equipped with a digital camera (Leica DFC295) magnified by a factor of 100. Two-way analysis of variance (ANOVA) and post-hoc Tukey's HSD test were conducted to analyze the significance of crown marginal fit regarding the finish line configuration and the fabrication system. RESULTS. The mean marginal gap of lithium disilicate glass ceramic crowns (IPS e.max$^{(R)}$press) was significantly lower than that of the CAD-CAM anatomic contour zirconia crown system (Prettau$^{(R)}$Zirconia) (P<.05). Both fabrication systems and finish line configurations significantly influenced the absolute marginal discrepancy (P<.05). CONCLUSION. The lithium disilicate glass ceramic crown (IPS e.max$^{(R)}$press) had significantly smaller marginal gap than the CAD-CAM anatomic contour zirconia crown system (Prettau$^{(R)}$Zirconia). In terms of absolute marginal discrepancy, the CAD-CAM anatomic contour zirconia crown system (ZENOSTAR$^{(R)}$ZR translucent) had under-extended margin, whereas the CAD-CAM anatomic contour zirconia crown system (Prettau$^{(R)}$Zirconia) and lithium disilicate glass ceramic crowns (IPS e.max$^{(R)}$press) had overextended margins.