정보과학회 논문지 (Journal of KIISE)

  • 제42권12호
  • /
  • Pages.1474-1479
  • /
  • 2015
  • /
  • 2383-630X(pISSN)
  • /
  • 2383-6296(eISSN)
한국정보과학회 (Korean Institute of Information Scientists and Engineers)
권호 표지
DOI QR코드

DOI QR Code

MapReduce 기반 분산 이미지 특징점 추출을 활용한 빠르고 확장성 있는 이미지 검색 알고리즘

A Fast and Scalable Image Retrieval Algorithms by Leveraging Distributed Image Feature Extraction on MapReduce

  • 투고 : 2015.07.22
  • 심사 : 2015.09.15
  • 발행 : 2015.12.15
⟨ 이전 논문 다음 논문 ⟩

초록

IoT 시대를 맞아 모바일 기기의 급격한 성능 향상에 힘입어 폭발적으로 증가하는 멀티미디어 빅데이터의 빠른 처리가 요구되고 있다. 하지만, 이런 환경의 대격변 속에서도 이미지 검색 연구 분야에서는 정확도 향상에 주로 초점을 맞춘 나머지, 고해상도 멀티미디어 데이터 Query에 대한 빠른 처리 측면에서는 제대로 대응하지 못하고 있다. 이에 우리는 이미지 검색만을 분산화한 선행연구와 달리 MapReduce 기반 분산 이미지 특징점 추출 기법을 활용하여 정확도는 유지하면서 빠른 응답시간을 확보하며, BIRCH 인덱싱을 기반으로 메모리 확장성까지 해결한 새로운 분산 이미지 검색 알고리즘을 제안한다. 그리고 제안하는 분산 이미지 검색 알고리즘의 정확도, 처리시간, 확장성에 대한 실험을 통해 뛰어난 성능을 확인한다.

With mobile devices showing marked improvement in performance in the age of the Internet of Things (IoT), there is demand for rapid processing of the extensive amount of multimedia big data. However, because research on image searching is focused mainly on increasing accuracy despite environmental changes, the development of fast processing of high-resolution multimedia data queries is slow and inefficient. Hence, we suggest a new distributed image search algorithm that ensures both high accuracy and rapid response by using feature extraction of distributed images based on MapReduce, and solves the problem of memory scalability based on BIRCH indexing. In addition, we conducted an experiment on the accuracy, processing time, and scalability of this algorithm to confirm its excellent performance.

키워드

과제정보

연구 과제번호 : 단말 협업형 Giga급 스마트 클라우드릿 핵심기술 개발

연구 과제 주관 기관 : 정보통신기술진흥센터

참고문헌

  1. Yan, T., Ganesan, D., & Manmatha, R., Distributed image search in camera sensor networks. Proc. of the 6th ACM conference on Embedded network sensor systems, pp. 155-168, 2008.
  2. Qin, C., Bao, X., Roy Choudhury, R., & Nelakuditi, S., Tagsense: a smartphone-based approach to automatic image tagging, Proc. of the 9th international conference on Mobile systems, applications, and services, pp. 1-14, 2011.
  3. Chatzichristofis, S. A., Zagoris, K., Boutalis, Y. S., & Papamarkos, N., Accurate image retrieval based on compact composite descriptors and relevance feedback information, International Journal of Pattern Recognition and Artificial Intelligence, Vol. 24, No. 2, pp. 207-244, 2010. https://doi.org/10.1142/S0218001410007890
  4. Zhang, J., Liu, X., Luo, J., & Lang, B., Dirs: Distributed image retrieval system based on mapreduce, Pervasive Computing and Applications (ICPCA), 2010 5th International Conference on IEEE, pp. 93-98, 2010.
  5. Moise, D., Shestakov, D., Gudmundsson, G., & Amsaleg, L., Indexing and searching 100M images with Map-Reduce, Proc. of the 3rd ACM conference on International conference on multimedia retrieval, pp. 17-24, 2013.
  6. Chatzichristofis, S. A., & Boutalis, Y. S., CEDD: color and edge directivity descriptor: a compact descriptor for image indexing and retrieval, Computer Vision Systems, pp. 312-322, 2008.
  7. Lowe, D. G., Object recognition from local scaleinvariant features, In Computer vision, 1999, The proceedings of the seventh IEEE international conference on IEEE, Vol. 2, pp. 1150-1157, 1999.
  8. Dean, J., & Ghemawat, S., MapReduce: simplified data processing on large clusters, Communications of the ACM, Vol. 51, No. 1, pp. 107-113, 2008. https://doi.org/10.1145/1327452.1327492
  9. Muja, M., & Lowe, D. G., Scalable nearest neighbor algorithms for high dimensional data, Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 36, No. 11, pp. 2227-2240, 2014. https://doi.org/10.1109/TPAMI.2014.2321376
  10. Bentley, J. L., Multidimensional binary search trees used for associative searching, Communications of the ACM, Vol. 18, No. 9, pp. 509-517, 1975. https://doi.org/10.1145/361002.361007
  11. Aly, M., Munich, M., & Perona, P., Distributed kd-trees for retrieval from very large image collections, Proc. of the British Machine Vision Conference (BMVC), 2011.
  12. Zhang, T., Ramakrishnan, R., & Livny, M., BIRCH: an efficient data clustering method for very large databases, ACM SIGMOD Record, Vol. 25, No. 2, pp. 103-114, 1996. https://doi.org/10.1145/235968.233324