• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.199-206
• /
• 2023

This study utilizes deep learning algorithms to automatically classify construction waste into three categories: wood waste, plastic waste, and concrete waste. Two models, VGG-16 and ViT (Vision Transformer), which are convolutional neural network image classification algorithms and NLP-based models that sequence images, respectively, were compared for their performance in classifying construction waste. Image data for construction waste was collected by crawling images from search engines worldwide, and 3,000 images, with 1,000 images for each category, were obtained by excluding images that were difficult to distinguish with the naked eye or that were duplicated and would interfere with the experiment. In addition, to improve the accuracy of the models, data augmentation was performed during training with a total of 30,000 images. Despite the unstructured nature of the collected image data, the experimental results showed that VGG-16 achieved an accuracy of 91.5%, and ViT achieved an accuracy of 92.7%. This seems to suggest the possibility of practical application in actual construction waste data management work. If object detection techniques or semantic segmentation techniques are utilized based on this study, more precise classification will be possible even within a single image, resulting in more accurate waste classification

• Journal of Bio-Environment Control
• /
• v.31 no.4
• /
• pp.270-278
• /
• 2022

This study was conducted using deep learning technology to classify for 'Mihwang' peach maturity with RGB images and fruit quality attributes during fruit development and maturation periods. The 730 images of peach were used in the training data set and validation data set at a ratio of 8:2. The remains of 170 images were used to test the deep learning models. In this study, among the fruit quality attributes, firmness, Hue value, and a^* value were adapted to the index with maturity classification, such as immature, mature, and over mature fruit. This study used the CNN (Convolutional Neural Networks) models for image classification; VGG16 and InceptionV3 of GoogLeNet. The performance results show 87.1% and 83.6% with Hue left value in VGG16 and InceptionV3, respectively. In contrast, the performance results show 72.2% and 76.9% with firmness in VGG16 and InceptionV3, respectively. The loss rate shows 54.3% and 62.1% with firmness in VGG16 and InceptionV3, respectively. It considers increasing for adapting a field utilization with firmness index in peach.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.6
• /
• pp.572-579
• /
• 2022

The analysis of foreign aircraft appearing suddenly in air defense identification zones requires a lot of cost and time. This study aims to develop a pre-trained model that can identify neighboring military aircraft based on aircraft photographs available on the web and present a model that can determine which aircraft corresponds to based on aerial photographs taken by allies. The advantages of this model are to reduce the cost and time required for model classification by proposing a pre-trained model and to improve the performance of the classifier by data augmentation of edge-detected images, cropping, flipping and so on.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.859-864
• /
• 2006

Mean shift 는 데이터의 특징을 잘 살려내는 None-parametric 방법으로, 특히 영상처리분야에서 많은 각광을 받아왔다. 하지만 좋은 결과를 보장하는 뛰어난 성능에도 불구하고, 높은 메모리소요와 긴 처리시간에 기인하여, 비디오처리 등의 분야에 적용하기엔 현실적인 제약점이 있다. 상기한 제약점을 극복하기 위해, 본 시스템은 비디오를 분석하여 전경과 후경으로 나눈다. 본 논문은 전경으로 분류된 부분에 대해 각 분리된 개체를구분하고, 좌표변환(coordinate shift)을 실행하여 연산을 할 비디오의 연산의 규모를 줄이는 방법론을 제시한다. 이러한 처리로 매우 많은 처리시간이 단축됨을 실험을 통해 알 수 있었다. 다음으로, 나뉘어진 전경에 3D mean shift를 적용하여 생성된 결과물에 대하여 3D cluster data structure 를 생성하고, 이를 이동하여 인터랙티브 에디팅이 가능하도록 하였다. 후경으로 나뉜 데이터는 이미지 한 장으로 축약이 되며, 2D mean shift 기반의 interactive cartooning system 을 통하여 만화화가 된다. 본 논문은 만화 특유의 단순한 톤을 표현하기 위해, 세밀한 분할이 필요한 부분과 그렇지 않은 부분을 따로 구분하여 처리하는 레이어처리방법을 제안한다. 위의 과정을 여러 실사이미지에 적용, 실험해본 결과 기존의 연구결과에 비해 매우 짧은 시간 내에 대상의 특징이 잘 나타낸 양질의 결과물이 생성되었다. 이러한 결과물은 출판, 영상편집분야 등 여러 분야에서 요긴하고 간편하게 사용될 수 있을 것으로 생각된다.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.611-614
• /
• 2023

갈비뼈 병변 진단 과정은 방사선 전문의가 CT 스캐너를 통해 생성된 2 차원 CT 이미지들을 해석하며 진행된다. 병변의 위치를 파악하고 정확한 진단을 내리기 위해 수백장의 2차원 CT 이미지들이 세밀하게 검토되며 갈비뼈를 분류한다. 본 연구는 이런 노동 집약적 작업의 문제점을 개선시키기 위해 Biaxial Rib Segmentation(BARS)을 제안한다. BARS 는 흉부 CT 볼륨의 관상면과 수평면으로 구성된 2 차원 이미지들을 U-Net 모델에 학습한다. 모델이 산출한 세그멘테이션 마스크들의 조합은 서로 다른 평면의 공간 정보를 보완하며 3 차원 갈비뼈 볼륨을 재건한다. BARS 의 성능은 DSC, Recall, Precision 지표를 사용해 평가하며, DSC 90.29%, Recall 89.74%, Precision 90.72%를 보인다. 향후에는 이를 기반으로 순차적 갈비뼈 레이블링 연구를 진행할 계획이다.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.559-561
• /
• 2022

인공지능 시대에 들어서면서 개인 맞춤형 환경을 제공하기 위하여 사람의 감정을 인식하고 교감하는 기술이 많이 발전되고 있다. 사람의 감정을 인식하는 방법으로는 얼굴, 음성, 신체 동작, 생체 신호 등이 있지만 이 중 가장 직관적이면서도 쉽게 접할 수 있는 것은 표정이다. 따라서, 본 논문에서는 정확도 높은 얼굴 감정 식별을 위해서 Convolution Block Attention Module(CBAM)의 각 Gate와 Residual Block, Skip Connection을 이용한 Identity- CBAM Module을 제안한다. CBAM의 각 Gate와 Residual Block을 이용하여 각각의 표정에 대한 핵심 특징 정보들을 강조하여 Context 한 모델로 변화시켜주는 효과를 가지게 하였으며 Skip-Connection을 이용하여 기울기 소실 및 폭발에 강인하게 해주는 모듈을 제안한다. AI-HUB의 한국인 감정 인식을 위한 복합 영상 데이터 세트를 이용하여 총 6개의 클래스로 구분하였으며, F1-Score, Accuracy 기준으로 Identity-CBAM 모듈을 적용하였을 때 Vanilla ResNet50, ResNet101 대비 F1-Score 0.4~2.7%, Accuracy 0.18~2.03%의 성능 향상을 달성하였다. 또한, Guided Backpropagation과 Guided GradCam을 통해 시각화하였을 때 중요 특징점들을 더 세밀하게 표현하는 것을 확인하였다. 결과적으로 이미지 내 표정 분류 Task에서 Vanilla ResNet50, ResNet101을 사용하는 것보다 Identity-CBAM Module을 함께 사용하는 것이 더 적합함을 입증하였다.

• Cartoon and Animation Studies
• /
• s.32
• /
• pp.263-288
• /
• 2013

This research is about effects which frontal-flat cameras have on narrative films. This kind of confined camera angles make the audience have a sense of tension which is barely defined logically. I think the tension comes from aleatorism. The paper is a research on how aleatorism is working on what kind of value, and what kind of effects it has on narrative films. Russian Formalism had argued they had to meet aesthetic values by totally excluding narratives. It can be said that this was a practice for Brecht's estrangement that a sensitive arousal prohibits the audience immersing into excessive empathy and then make them have a reflective thought. But occasionally, optical arousals in narrative films induce deeper immersion into contemplation rather than reflective thought. I intend to find cases regarding this textualising Front-flat camera angles in narrative films and analysing their contents. To do this, I suggest a more specified definition of 'aleatorism'. Because the concept of the aleatorism is different between an aspect of static image like paintings or photographs and narrative contents like cinema. It is divided into approach through form and approach through content. And I also suggest an operative definition about 'Frontal-flat camera angle' with a several confinements because its formal definition is very flexible depending on audience. The case analysis will be done with a form of discourse discerning two aspects of form and content. Conclusively, Frontal-flat camera angle in narrative film is basically have an effect of attention by optical stimuli. But it cannot be said that this always means deterioration of narrative value. Depending on causality of episodes in the whole story, aleatorism which Frontal-flat camera angle has can support immersed contemplation regarding following narrative rather than reflective thought regarding amusing aesthetics.

• Korean Journal of Poultry Science
• /
• v.49 no.3
• /
• pp.157-165
• /
• 2022

Chickens are a species of vertebrate with varying colors. Various colors of chickens must be classified to find color-related genes. In the past, color scoring was performed based on human visual observation. Therefore, chicken colors have not been measured with precise standards. In order to solve this problem, a computer vision approach was used in this study. Image quantization based on k-means clustering for all pixels of RGB values can objectively distinguish inherited colors that are expressed in various ways. This study was also conducted to determine whether plumage color differences exist in the reciprocal cross lines between two breeds: black Yeonsan Ogye (YO) and White Leghorn (WL). Line B is a crossbred line between YO males and WL females while Line L is a reciprocal crossbred line between WL males and YO females. One male and ten females were selected for each F₁ line, and full-sib mating was conducted to generate 883 F₂ birds. The results indicate that the distribution of light and dark colors of k-means clustering converged to 7:3. Additionally, the color of Line B was lighter than that of Line L (P<0.01). This study suggests that the genes underlying plumage colors can be identified using quantification values from the computer vision approach described in this study.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.4
• /
• pp.187-198
• /
• 2020

With the cultural background of whiteness I did examine the universal meaning of absolute good, the special of psychosis, and the fantastic of femininity and memory/record. As an example I analyzed the symbolic meaning of white used in Korean films. Unconditional goodness, white as a generality: White color in all the films of good-evil confrontation falls into this category. The most obvious and the simplest configuration are the black-white dichotomy. In Nameless Gangster: Rules of Time(2011), The Merciless(2016), Asura: The City of Madness(2016) and The Bad Guys: Reign of Chaos(2019), white is the absolute good but it is not limited to a fair key figure. Paradoxically, black is not given only to the side of absolute evil. White is used to be a flexible visual device that reflects the socio-political situation without changing the meaning of the general good. Psychosis and pills, white as a peculiarity: The visual function that emphasizes sado-masochism in the absolute good and the universal symbol of white extends to psychotic specificities such as hysteria. In all the films creating horror, white symbolizes the mentally disabled and the pill for healing. Femininity and haunted white: White of absolute good is expressed by the socio-cultural tendency of femininity and the black-white contrast of vision is applied to the gender difference. In general the women's sexuality is emphasized in color red, but white is arranged in the background. In TaeGukGi: Brotherhood Of War(2004), 71: Into The Fire(2010), My Way(2011), The Front Line(2011), Roaring Currents(2014), Northern Limit Line(2015), The Battle: Roar to Victory(2019) and Battle of Jangsari(2019), white given to female figures sticks to the traditional femininity such as motherhood, sacrifice and weakness. The concept of specters is applied to desires, memories/records, history, fantasy, virtual/reality and social media images. The film history capturing to list memories and moments brings up the specters of socio-political genealogy. Most of films aiming for socio-political change are its examples and white constituting Mise-en-scene records to remember a historical event in Peppermint Candy(2000), The Attorney(2013) and A Taxi Driver(2017).

• Korean Journal of Heritage: History & Science
• /
• v.57 no.1
• /
• pp.126-144
• /
• 2024

The chrysanthemum vine pattern box from the Goryeo Dynasty expresses in great detail the representative features of Goryeo Dynasty lacquerware with mother-of-pearl, such as engraving patterns on the surface of fine mother-of-pearl, expressing vine stems using metal wires, and twisting metal wires to form the boundaries of each patterns. While the lacquerware with mother-of-pearl that remains today from the Goryeo Dynasty has the form of a sutra box and a box with lid, the chrysanthemum vine pattern box that is the subject of this study is in the shape of a box with a separate lid and body, making it difficult to estimate the purpose of production or the stored contents. In this study, we attempted to confirm the formative characteristics of the chrysanthemum vine pattern box in order to confirm its original form, and to investigate its structure and production technique through X-ray transmission. In addition, we attempted to identify the use and production purpose of the box by classifying and comparing the previously known lacquerware with mother-ofpearl from the Goryeo Dynasty by type. As a result of the investigation, fabric was confirmed the bottom of body and inner box through X-ray images. Through this, it was confirmed that the 'Mogsimjeopichilgi'(wooden core grabbing fabric technique) of wrapping the object with fabric was used. And through wood grain, it was possible to confirm the wooden board composition of the part presumed to be the restored part and the part presumed to have had existing Jangseog. In addition, it was confirmed that the joints were connected in a Majdaeim(part to part). Based on the survey results, a total of 14 pieces, including 9 Sutra boxes, 3 boxes, and 2 small boxes, that remain from the Goryeo Dynasty were classified by type and examined for similarity. Among them, there is a "Chrysanthemum Vine Pattern Sutra Box" from a private collection in Japan, a "Black Lacquered Chrysanthemum Arabesque Bun Sutra Box" from the Tokugawa Art Museum, a "Sutra Holder" from the British Museum, and a "Small Box with a Mother-of-Pearl Chrysanthemum Vine Pattern" from a private collection in Korea. The pattern composition of five points was most similar to the subject of this study. As a result of comparing the damage pattern, formative characteristics, and structural features of each part, it is presumed that the sutra holder in the British Museum was transformed into its current form from the original the chrysanthemum vine patterned box. Lastly, in order to confirm the purpose of production, that is, the use of this box, we investigated examples of Tripitaka Koreana printed version produced at a time similar to the social atmosphere of Goryeo at the time. Following the Mongol(元) invasion after the Goryeo military regime at the time, sutras appeared to pray for the stability of the nation and the soul of an individual, and with the development of domestic printing and paper in the 13th century, it gradually coincided with the transition from a scroll to a folded form, and the form of a box changed from a box. It is believed that the storage method also changed.