• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.11
• /
• pp.5605-5623
• /
• 2016

We propose a face recognition method that utilizes the LCP face descriptor. The proposed method applies a LoG mask to extract a face contour response, and employs the LCP algorithm to produce a binary pattern representation that ensures high recognition performance even under the changes in illumination, noise, and aging. The proposed LCP algorithm produces excellent noise reduction and efficiency in removing unnecessary information from the face by extracting a face contour response using the LoG mask, whose behavior is similar to the human eye. Majority of reported algorithms search for face contour response information. On the other hand, our proposed LCP algorithm produces results expressing major facial information by applying the threshold to the search area with only 8 bits. However, the LCP algorithm produces results that express major facial information with only 8-bits by applying a threshold value to the search area. Therefore, compared to previous approaches, the LCP algorithm maintains a consistent accuracy under varying circumstances, and produces a high face recognition rate with a relatively small feature vector. The test results indicate that the LCP algorithm produces a higher facial recognition rate than the rate of human visual's recognition capability, and outperforms the existing methods.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.08a
• /
• pp.389-390
• /
• 2012

In this study, we fabricate a superhydrophobic surface made of hierarchical nanostructures that combine wax crystalline structure with moth-eye structure using vacuum cluster system and measure their hydrophobicity and durability. Since the lotus effect was found, much work has been done on studying self-cleaning surface for decades. The surface of lotus leaf consists of multi-level layers of micro scale papillose epidermal cells and epicuticular wax crystalloids [1]. This hierarchical structure has superhydrophobic property because the sufficiently rough surface allows air pockets to form easily below the liquid, the so-called Cassie state, so that the relatively small area of water/solid interface makes the energetic cost associated with corresponding water/air interfaces smaller than the energy gained [2]. Various nanostructures have been reported for fabricating the self-cleaning surface but in general, they have the problem of low durability. More than two nanostructures on a surface can be integrated together to increase hydrophobicity and durability of the surface as in the lotus leaf [3,5]. As one of the bio-inspired nanostructures, we introduce a hierarchical nanostructure fabricated with a high vacuum cluster system. A hierarchical nanostructure is a combination of moth-eye structure with an average pitch of 300 nm and height of 700 nm, and the wax crystalline structure with an average width and height of 200 nm. The moth-eye structure is fabricated with deep reactive ion etching (DRIE) process. $SiO_2$ layer is initially deposited on a glass substrate using PECVD in the cluster system. Then, Au seed layer is deposited for a few second using DC sputtering process to provide stochastic mask for etching the underlying $SiO_2$ layer with ICP-RIE so that moth-eye structure can be fabricated. Additionally, n-hexatriacontane paraffin wax ($C_{36}H_{74}$) is deposited on the moth-eye structure in a thermal evaporator and self-recrystallized at $40^{\circ}C$ for 4h [4]. All of steps are conducted utilizing vacuum cluster system to minimize the contamination. The water contact angles are measured by tensiometer. The morphology of the surface is characterized using SEM and AFM and the reflectance is measured by spectrophotometer.

• The Journal of the Korea Contents Association
• /
• v.14 no.11
• /
• pp.7-15
• /
• 2014

This paper proposed a recognition algorithm of human facial expressions using the PCA and the template matching. Firstly, face image is acquired using the Haar-like feature mask from an input image. The face image is divided into two images. One is the upper image including eye and eyebrow. The other is the lower image including mouth and jaw. The extraction of facial components, such as eye and mouth, begins getting eye image and mouth image. Then an eigenface is produced by the PCA training process with learning images. An eigeneye and an eigenmouth are produced from the eigenface. The eye image is obtained by the template matching the upper image with the eigeneye, and the mouth image is obtained by the template matching the lower image with the eigenmouth. The face recognition uses geometrical properties of the eye and mouth. The simulation results show that the proposed method has superior extraction ratio rather than previous results; the extraction ratio of mouth image is particularly reached to 99%. The face recognition system using the proposed method shows that recognition ratio is greater than 80% about three facial expressions, which are fright, being angered, happiness.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.29-40
• /
• 2022

In this paper, we studied a system that detects and analyzes the pathological features of diabetic retinopathy using Mask R-CNN and a Random Forest classifier. Those are one of the deep learning techniques and automatically diagnoses diabetic retinopathy. Diabetic retinopathy can be diagnosed through fundus images taken with special equipment. Brightness, color tone, and contrast may vary depending on the device. Research and development of an automatic diagnosis system using artificial intelligence to help ophthalmologists make medical judgments possible. This system detects pathological features such as microvascular perfusion and retinal hemorrhage using the Mask R-CNN technique. It also diagnoses normal and abnormal conditions of the eye by using a Random Forest classifier after pre-processing. In order to improve the detection performance of the Mask R-CNN algorithm, image augmentation was performed and learning procedure was conducted. Dice similarity coefficients and mean accuracy were used as evaluation indicators to measure detection accuracy. The Faster R-CNN method was used as a control group, and the detection performance of the Mask R-CNN method through this study showed an average of 90% accuracy through Dice coefficients. In the case of mean accuracy it showed 91% accuracy. When diabetic retinopathy was diagnosed by learning a Random Forest classifier based on the detected pathological symptoms, the accuracy was 99%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.6B
• /
• pp.1041-1049
• /
• 2000

A face recognition algorithm for the user identification procedure of automatic teller machine(ATM), as an application of the still image processing techniques is proposed in this paper. In the proposed algorithm, face recognition techniques, especially, face region detection, eye and mouth detection schemes, which can distinguish abnormal faces from normal faces, are proposed. We define normal face, which is acceptable, as a face without sunglasses or a mask, and abnormal face, which is non-acceptable, as that wearing both, or either one of them. The proposed face recognition algorithm is composed of three stages: the face region detection stage, the preprocessing stage for facial feature detection and the eye and mouth detection stage. Experimental results show that the proposed algorithm can distinguish abnormal faces from normal faces accurately from restrictive sample images.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.841-846
• /
• 2006

A real time system realization for binocular eyeball tracking cursor on the computer monitor screen is presented in the paper. The processing for searching iris and tracking the cursor are that a facial is acquired by the small CCD camera, convert it into binary image, search for the eye two using the five region mask method in the eye surroundings and the side four points diagonal positioning method is searched the each iris. The tracking cursor is matched by measuring the iris central moving position, The cursor controlling is achieved by comparing two related distances between the iris maximum moving and the cursor moving to calculate the moving stance from gazing position and screen. The experimental result are obtained by examining some adults person on the system.

• (The) Research of the performance art and culture
• /
• no.22
• /
• pp.5-43
• /
• 2011

Before the Korean War, Korean mask dramas had been performed as parts of seasonal customs and had been passed down in connection with various seasonal events, such as village rites, tug of war, torch fighting, Jisinbabgi(stepping on evil spirits), Gilnori, and Sattonoreum. However, after the Korean War, the dramas were played independently regardless of those seasonal events; thus, they have lost their original functions and meanings. After the Korean War, the lion dance in the Bukcheong lion mask play included two lions (as opposed to one lion prior to the Korean War) and the Aeonesung and Sadang dances were added. The scene in which a lion eats a child changed to a lion eating a rabbit doll. Furthermore, whereas mask types used to be diverse, they are now standardized to one type of lion mask. In the Yangju Byulsandae-nori, eight monks and Waejangnye, Aesadang appeared in 'Aesadang Bubgonori', but now the Malddugi mask character is added. Current performances omit sexually suggestive scenes. In the pre-Korean War version of the old man and old woman act, the old man sang a song to the soul of the dead woman, but now a shaman appears and performs an exorcism. In the dialogues, vulgar and sexual statements have been shortened as many audience members are women and children. Regarding the appearance of the masks, the lotus leaf, the monk with Scabies, and sannim masks have been significantly changed. Bongsantalchum has also changed, especially in the old monk act. Previously, two Somu used to appear whereas now only one appears. The scene of the shoe seller's and the monkey's departure is also different. Furthermore, while the former masks once had big eye holes on each side of the nose, now the masks have smaller holes on the eyes.

• KSBB Journal
• /
• v.28 no.6
• /
• pp.387-393
• /
• 2013

In this study, the domestic onion skin has been used to investigate the anti-wrinkle effect of the ethanolic extract. The onion skin has been known to contain a large amount of antioxidant including quercetin. Solvent extraction by 80% ethanol was carried out of the onion skin. The high amount of quercetin have been identified using HPLC as a bioactive compound. The extraction yield of the quercetin increased according to temperature up to $80^{\circ}C$. Two different antioxidant assays (DPPH and ABTS) were performed to determine the free-radical scavenging activity of onion skin extracts. The antioxidant activities ($EC_{50}$ of DPPH) of the vitamin C and the onion extracts were 2.2 and $5.09{\mu}g/mL$, respectively. The results of ABTS tests were 2.33 (of vitamin C) and $2.40{\mu}g/mL$ (of the onion extracts), respectively. In a clinical study, a panel of 10 female volunteers between the ages of 30 and 40 (mean age: 42 years) was given a mask pack containing 1% of this extracts for 4 weeks. It was shown that a highly significant reduction in the deep and moderate wrinkled was obtained with those treated with this onion extracts as compared to the control group. The reduction in deep wrinkles increased with time. Eye wrinkle were reduced statistically significant (p<0.05). The application of the proper topical cream and mask pack containing onion skin extracts has therefore shown to be effective enhancing anti-wrinkle activities.

• Progress in Medical Physics
• /
• v.18 no.1
• /
• pp.1-6
• /
• 2007

A system to non-invasively fix and monitor eye by a head mounted display (HMD) with a CCD camera for stereotactic radiotherapy (SRS) of uveal melanoma has been developed and implemented clinically. The eye fixing and monitoring system consists of a HMD showing patient a screen for fixing eyeball, a CCD camera monitoring patient's eyeball, and an immobilization mask. At flrst, patient's head was immobilized with a mask. Then, patient was Instructed to wear HMD, to which CCD camera was attached, on the mask and see the given reference point on its screen. While patient stared at the given point in order to fix eyeball, the camera monitored Its motion. Four volunteers and one patient of uveal melanoma for SRS came into this study. For the volunteers, setup errors and the motion of eyeball were analyzed. For the patient, CT scans were peformed, with patient's wearing HMD and fixing the eye to the given point. To treat patient under the same condition, daily CT scans were also peformed before every treatment and the motion of lens was compared to the planning CT Setup errors for four volunteers were within 1mm and the motion of eyeball was fixed within the clinically acceptable ranges. For the patient with uveal melanoma, the motion of lens was fixed within 2mm from daily CT scans. An eye fixing and monitoring system allowed Immobilizing patient as well as monitoring eyeball and was successfully implemented in the treatment of uveal melanoma for SRS.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.637-654
• /
• 2023

In recent years, the number of users has been increasing with the rapid development of earth observation satellites. In response, the Committee on Earth Observation Satellites (CEOS) has been striving to provide user-friendly satellite images by introducing the concept of Analysis Ready Data (ARD) and defining its requirements as CEOS ARD for Land (CARD4L). In ARD, a mask called an Unusable Data Mask (UDM), identifying unnecessary pixels for land analysis, should be provided with a satellite image. UDMs include clouds, cloud shadows, terrain shadows, etc. Terrain shadows are generated in mountainous terrain with large terrain relief, and these areas cause errors in analysis due to their low radiation intensity. previous research on terrain shadow detection focused on detecting terrain shadow pixels to correct terrain shadows. However, this should be replaced by the terrain correction method. Therefore, there is a need to expand the purpose of terrain shadow detection. In this study, to utilize CAS500-4 for forest and agriculture analysis, we extended the scope of the terrain shadow detection to shaded areas. This paper aims to analyze the potential for terrain shadow detection to make a terrain shadow mask for South and North Korea. To detect terrain shadows, we used a Hill-shade algorithm that utilizes the position of the sun and a surface's derivatives, such as slope and aspect. Using RapidEye images with a spatial resolution of 5 meters and Sentinel-2 images with a spatial resolution of 10 meters over the Korean Peninsula, the optimal threshold for shadow determination was confirmed by comparing them with the ground truth. The optimal threshold was used to perform terrain shadow detection, and the results were analyzed. As a qualitative result, it was confirmed that the shape was similar to the ground truth as a whole. In addition, it was confirmed that most of the F1 scores were between 0.8 and 0.94 for all images tested. Based on the results of this study, it was confirmed that automatic terrain shadow detection was well performed throughout the Korean Peninsula.