본문 바로가기
KERD
논문KCI 등재

CLIP 기반 분석을 통한 한국 신사실파 작가 분류

Identification of Korean Neo-Realism Artists Through CLIP-Based Analysis

박소은|박소정|최종원|이보아|임유민|백서현
한국컴퓨터정보학회 (The Korean Society Of Computer And Information)|2024.12|한국컴퓨터정보학회논문지 (Journal of The Korea Society of Computer and Information)|제29권 제12호|pp. 317-328|DOI https://doi.org/10.9708/jksci.2024.29.12.317

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

컴퓨테이셔널 분석한국 회화신사실파K-평균 군집화대조적 언어-이미지 사전 학습
주제분류컴퓨터학

초록

본 연구는 이미지 데이터를 기반으로 회화 작품의 특징을 분석하고 작가를 자동으로 분류하기 위한 새로운 방법론을 제안한다. 서양 예술작품에 초점을 맞춘 선행 연구와 달리, 한국 작가군(i.e. 신사실파)의 데이터 셋을 구축하여 활용했다. CLIP 모델의 이미지 인코더를 통해 작품의 의미적 특징을벡터 공간으로 변환하였으며 텍스트의 설명과 함께 학습함으로써 이미지의 의미를 더 풍부하게 이해하였다. 이에 더해 색상 정보는 RGB 및 HSV 색공간 분석으로, 질감 특성은 GLCM 기반 분석으로추출되었다. 이렇게 통합된 특징 벡터는 K-평균 군집화를 통해 분석되었고, 높은 분류 정확도(87.4%) 를 기록했다. 본 연구는 비지도 학습 환경에서도 이미지 간 유사성을 효과적으로 식별하고 작가별작품을 정확히 분류할 수 있음을 입증했으며, 각 군집의 대표 이미지 분석을 통해 고유한 색조와 질감 특성을 제시하여 작품의 조형적 특징과 예술적 경향성을 식별하는 데 기여했다.

Abstract

This study proposes a methodology for analyzing artwork features and classifying artists using image data. Unlike prior research focused on Western artworks, it builds and utilizes a dataset of Korean Neo-Realism (i.e. Shinsasilpa) artists. The image encoder of the CLIP model transformed the semantic features of the artwork into a vector space and, by learning together with the textual description, more deeply understood the meaning of the image. Furthermore, hue information via RGB and HSV color space analysis, and texture characteristics through GLCM-based analysis. These features were integrated into representative feature vectors and analyzed with K-means clustering, achieving 87.4% classification accuracy. Visualization results demonstrated the model's effectiveness in identifying image similarities and accurately classifying artworks in an unsupervised learning context, while highlighting unique hue and texture characteristics of each cluster, revealing formal and artistic tendencies in artworks.

참고문헌 (49)

  1. L. Shamir, "Computer analysis of art", Journal on Computing and Cultural Heritage(JOCCH), 5(2), pp.1~11 (2012)[DOI]
  2. N. Viswanathan, "Artist identification with convolutional neural networks, Standford193CS231N Report", 1~8 (2017)
  3. M. Kim, "Complementary Quantitative Approach to Unsolved Issues in Art History : Similarity of Visual Features in the Paintings of Vermeer and His Probable Mentors", Leonardo, 52(2), pp.164~174 (2019)[DOI]
  4. L. Shamir, "Impressionism, expressionism, surrealism : Automated recognition of painters and schools of art", ACM Transactions on Applied Perception(TAP), 7(2), pp.1~17 (2010)[DOI]
  5. E. Cetinic, "Fine-tuning convolutional neural networks for fine art classification", Expert Systems with Applications, 114, pp.107~118 (2018)[DOI]
  6. B. Saleh, "Toward automated discovery of artistic influence", Multimedia Tools and Applications, 75(7), pp.3565~3591 (2016)[DOI]
  7. Identifying the real van gogh with brushstroke textons, "L. van der Maaten", Tilburg University, ~ (2009)
  8. B. Saleh, "A unified framework for painting classification", 2015 IEEE International Conference on Data Mining Workshop (ICDMW), pp.1254~1261 (2015)
  9. J. Zujovic, "Classifying paintings by artistic genre : An analysis of features & classifiers", 2009 IEEE International Workshop on Multimedia Signal Processing, pp.1~5 (2009)
  10. E. Gultepe, "Predicting and grouping digitized paintings by style using unsupervised feature learning", Journal of cultural heritage, 31, pp.13~23 (2018)[DOI]
  11. J. Chen, "Comparison of machine learning techniques for artist identification, Standford193CS231N Report", 1~7 (2018)
  12. I. E. Berezhnoy, "Authentic : computerized brushstroke analysis", 2005 IEEE International Conference on Multimedia and Expo, pp.1586~1588 (2005)
  13. H. J. van den Herik, "Future Directions for Intelligent Systems and Information Sciences", pp.129~147 (2000), Physica
  14. F. Lamberti, "Computer-assisted analysis of painting brushstrokes : digital image processing for unsupervised extraction of visible features from van Gogh’s works", EURASIP Journal on Image and Video Processing, 2014, pp.1~17 (2014)[DOI]
  15. C. R. Johnson, "Image processing for artist identification", IEEE Signal Processing Magazine, 25(4), pp.37~48 (2008)[DOI]
  16. R. G. Condorovici, "Artistic genre classification for digitized painting collections", UPB Scientific Bulletin, 75(3), pp.75~86 (2013)
  17. D. G. Stork, "Computer vision and image analysis of art" (2010), SPIE (The international society for optics and photonics), and IS&T (The Society for Imaging Science and Technology)
  18. Q. Yu, "An image classification approach for painting using improved convolutional neural algorithm", Soft Computing, 28(1), pp.847~873 (2023)[DOI]
  19. S. Banerji, "Painting classification using a pre-trained convolutional neural network", Computer Vision, Graphics, and Image Processing, 10481, pp.168~179 (2017)[DOI]
  20. K. A. Jangtjik, "A CNN-LSTM framework for authorship classification of paintings", 2017 IEEE International Conference on Image Processing (ICIP), pp.2866~2870 (2017), IEEE
  21. K. Mondal, "Categorization of artwork images based on painters using CNN", Journal of Physics: Conference Series, 1818(1), pp.1088~ (2021)[DOI]
  22. J. M. Fortuna-Cervantes, "Evaluation of CNN Models with Transfer Learning in Art Media Classification in Terms of Accuracy and Class Relationship", Computación y Sistemas, 28(1), pp.233~244 (2024)[DOI]
  23. X. Zhang, "Style classification of media painting images by integrating ResNet and attention mechanism", Heliyon, 10(6) (2024)[DOI]
  24. Q. Li, "Research on automatic classification method of artistic styles based on attention mechanism convolutional neural network", International Journal of Low-Carbon Technologies, 19, pp.2018~2023 (2024)[DOI]
  25. L. Zeng, "Improved Painting Image Style Classification of ResNet based on Attention Mechanism", 2023International Conference on Advances in Electrical Engineering and Computer Applications (AEECA), pp.724~729 (2023), IEEE
  26. L. Tao, "Design and Implementation of Painting Classification System Based on Double Attention Network", 2021 6th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS), pp.55~55 (2021), IEEE
  27. A. Polak, "Hyperspectral imaging combined with data classification techniques as an aid for artwork authentication", Journal of Cultural Heritage, 26, pp.1~11 (2017)[DOI]
  28. T. Sahu, "Classification and aesthetic evaluation of paintings and artworks", 2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), pp.179~183 (2017), IEEE
  29. G. Castellano, "A deep learning approach to clustering visual arts", International Journal of Computer Vision, 130(11), pp.2590~2605 (2022)[DOI]
  30. C. Sandoval, "Adversarial learning approach to unsupervised labeling of fine art paintings", IEEE Access, 9, pp.81969~81985 (2021)[DOI]
  31. Abas, F. S., "Classification of painting cracks for content-based analysis", Machine Vision Applications in Industrial Inspection XI, 5011, pp.149~160 (2003)
  32. Liu, S., "Novel features for art movement classification of portrait paintings", Image and Vision Computing, 108, pp.104121~ (2021)[DOI]
  33. Andronache, I., "CAN COMPLEXITY MEASURES WITH HIERARCHICAL CLUSTER ANALYSIS IDENTIFY OVERPAINTED ARTWORK?", Scientific Culture, 10(1) (2024)[DOI]
  34. Xu, K., "Automated Artist Identification Using Deep Learning and Transfer Learning Techniques", Science and Technology of Engineering, Chemistry and Environmental Protection, 1(8) (2024)[DOI]
  35. Zeng, L., "Improved Painting Image Style Classification of ResNet based on Attention Mechanism", 2023 International Conference on Advances in Electrical Engineering and Computer Applications(AEECA), pp.724~729 (2023)
  36. Nunez-Garcia, I., "Classification of Paintings by Artistic Style Using Color and Texture Features", Computación y Sistemas, 26(4), pp.1503~1514 (2023)[DOI]
  37. WANG, Q., "Painting Style Recognition and Classification Based on Convolutional Neural Network and Multi-Kernel Learning", Intelligent Computing Technology and Automation (2024)[DOI]
  38. Zhong, S. H., "Fine-art painting classification via two-channel dual path networks", International Journal of Machine Learning and Cybernetics, 11, pp.137~152 (2020)[DOI]
  39. Kelek, M. O., "Painter classification over the novel art painting data set via the latest deep neural networks", Procedia Computer Science, 154, pp.369~376 (2019)[DOI]
  40. Park, J. S., "Optimizing CNN Structure to Improve Accuracy of Artwork Artist Classification", Journal of The Korea Society of Computer and Information, 28(9), pp.9~15 (2023)[DOI]
  41. Deng, Y., "Selective clustering for representative paintings selection", Multimedia Tools and Applications, 78, pp.19305~19323 (2019)[DOI]
  42. Espinosa Zuniga Javier Jesus, "Artificial Intelligence Perspectives on Mexican Art : A Case Study", American Journal of Science, Engineering and Technology, 8(1), pp.63~70 (2023)[DOI]
  43. Park, J. M., "The Concept of Abstraction in New Realism Group : New Interpretation on Geometric Abstraction from Its Own Point of View", Korean Bulletin of Art History, 38, pp.240~276 (2012)[DOI]
  44. Joo, S. J., "A Study on the Sublime in YOO YOUNGKUK's Abstract Paintings: Focusing on works since the 1960s", Master, Aesthetics & Art History, pp.2023
  45. Kim, H. S., "Study on the Colors of Kim Whan-ki's Painting", The Journal of Art Theory & Practice(JATP), (3), pp.155~172 (2005)
  46. Kang, H. S., "Rereading Neo-Realistic School as Avant-garde in the Early 20th Century : Focusing on the Influence of Surrealism", The Journal of Aesthetics and Science of Art(JASA), 71, pp.138~160 (2024)[DOI]
  47. Haralick, R. M., "Textural features for image classification", IEEE Transactions on systems, man, and cybernetics, 6, pp.610~621 (1973)[DOI]
  48. Jeong, J. M., "Masterpieces of modern Korean painting", pp.54~171 (2014), Culture books
  49. Kim, Y. N., "Korean Art of the 20th Century 2 : A Time of Change and Challenge", pp.240~465 (2010), Yekyong

관련 논문AI추천

주조색과 밝기 정보를 이용한 인상주의 작품 분석김철기한국디자인트렌드학회 · 한국디자인포럼2010 · 제29호회화 이미지 검색을 위한 언어 기반 의미론적 임베딩김유현, 김태섭, 박효빈, 이지원, 최동걸한국차세대컴퓨팅학회 · 한국차세대컴퓨팅학회 논문지2025 · 제21권 제3호멀티모달 AI 기반 미술 해설 코스웨어 개발 : 중등 미술 교육과정을 대상으로유진, 주경, 오효정, 최유리한국문화교육학회 · 문화예술교육연구2025 · 제20권 제3호참조영상의 색 조화 패턴을 활용한 색상 변환 기법이원용한국지식정보기술학회 · 한국지식정보기술학회 논문지2019 · 제14권 제5호시각 및 언어 모델을 활용한 인터랙티브 미술 감상 AI 도슨트 시스템김민, 곽현정, 김민수, 안치욱, 이원주, 이형록, 조영복, 최예준한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2025 · 제30권 제6호미확인 작품 식별을 위한 Feature 선정 및 유사도 비교 시스템 구축김주성, 김현수, 박경엽, 신동명한국소프트웨어감정평가학회 · 한국소프트웨어감정평가학회 논문지2021 · 제17권 제1호

이 간행물의 다른 논문 (31건)

제한된 계산 자원 하에서 실시간 계란 결함 검출을 위한 RT-DETR과 YOLOv8의 비교 분석김보영, 문지훈, 강남일, 차예찬pp. 1-11온-보드 항공 표적 탐지 모델 성능 개선: 형상 정보와 혼합 정밀도 연산의 활용박인구, 황보라, 박준형, 최용호, 문종원pp. 13-20생성형 인공지능을 활용한 3D 모델 생성 성능 비교 연구이병권pp. 21-28RAG 기반 모델의 성능 향상을 위한 문장화 추출 방법론김남규, 남명국pp. 29-39도심항공 모빌리티 경로 예측을 위한 딥러닝 모델 비교 연구이준원, 윤혜원, 윤승원, 김정훈, 장다현, 박태원, 이규철pp. 41-49
원문 보기