Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Evaluations for Leaf Classification Using Combined Features of Shape and Texture

형태와 텍스쳐 특징을 조합한 나뭇잎 분류 시스템의 성능 평가

  • Kim, Seon-Jong (Department of Applied IT Engineering, Pusan National University) ;
  • Kim, Dong-Pil (Department of Landscape Architecture, Pusan National University)
  • 김선종 (부산대학교 IT응용공학과) ;
  • 김동필 (부산대학교 조경학과)
  • Received : 2012.05.20
  • Accepted : 2012.07.03
  • Published : 2012.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

There are many trees in a roadside, parks or facilities for landscape. Although we are easily seeing a tree in around, it would be difficult to classify it and to get some information about it, such as its name, species and surroundings of the tree. To find them, you have to find the illustrated books for plants or search for them on internet. The important components of a tree are leaf, flower, bark, and so on. Generally we can classify the tree by its leaves. A leaf has the inherited features of the shape, vein, and so on. The shape is important role to decide what the tree is. And texture included in vein is also efficient feature to classify them. This paper evaluates the performance of a leaf classification system using both shape and texture features. We use Fourier descriptors for shape features, and both gray-level co-occurrence matrices and wavelets for texture features, and used combinations of such features for evaluation of images from the Flavia dataset. We compared the recognition rates and the precision-recall performances of these features. Various experiments showed that a combination of shape and texture gave better results for performance. The best came from the case of a combination of features of shape and texture with a flipped contour for a Fourier descriptor.

길 옆이나 공원 또는 조경시설에는 많은 나무들을 포함하고 있다. 비록 많은 나무들이 쉽게 우리 주변에서 보이지만, 일반인들이 그 나무의 이름, 종류 및 정보들을 얻기가 힘든 경우도 있다. 나무의 이름이나 정보를 얻기 위하여 인터넷이나 서적을 이용하여 찾아 분류하여야 한다. 나무의 구성 요소는 잎, 꽃, 수피 등이 있는데, 일반적으로 나무의 잎을 이용하여 분류할 수 있다. 이는 잎이 형태, 잎맥 등의 정보를 포함하고 있기 때문이다. 잎의 형태는 나무의 종류를 결정하는데 중요한 역할을 하며, 또한 잎맥을 포함한 텍스쳐도 나무의 종류를 분류하는데 유용하게 사용된다. 본 논문에서는 형태와 텍스쳐를 조합한 특징들을 이용한 잎 분류 시스템에 대한 성능을 평가하였다. 형태 특징으로는 푸리에 기술자를 이용하였고, 텍스쳐 특징으로는 GLCM 또는 웨이브릿 기술자, 그리고 그들의 조합을 사용하였다. 그리고 사용된 데이터는 인터넷에서 용이하게 구할 수 있고, 분류 성능평가에 사용되는 Flavia 잎 데이터 셋을 사용하였다. 형태와 텍스쳐를 기반으로 하는 다양한 조합을 가진 분류 시스템의 성능을 인식률과 PR(precision-recall) 지수로 평가하고, 성능을 비교하였다. 성능평가 결과, 형태와 텍스쳐를 조합한 특징들을 갖는 시스템의 성능이 조합하지 않은 시스템의 성능보다 나아짐을 알 수 있었다.

Keywords

Acknowledgement

Supported by : Pusan National University

References

  1. Albregtsen, F., "Statistical Texture Measures Computed from Gray Level Co-occurrence Matrices", Nov. (2008), Available at Http: //www.uio.n o/studier/emner/matnat/ifi/INF4300/h08/und ervisningsmateriale/glcm.pdf(Accessed 8 Se pt., 2011)
  2. Beghin, T., J. S. Cope, P. Remagnino, and S. Barman, "Shape and Texture based Plant Leaf Classification", AVIVS, 2010.
  3. Ehsanirad, A., "Plant Classification based on Leaf Recognition", IJCSIS, Vol.8, No.4(2010).
  4. Gu, X., J.-X. Du, and X.-F. Wang, "Leaf Recognition based on the Combination of Wavelet Transform and Gaussian Interpolation", LNCS, Vol.3644(2005), 253-262.
  5. Jang, M.-S., Y.-S Cho, J.-H. Kim, and J.-C. Son, "Accelerometer-based Gesture Recognition for Robot Interface", Journal of Intelligence and Information Systems, Vol.17, No.1(2011), 53-69.
  6. Kebapci, H., B. Yanikoglu, and G. Unal, "Plant Image Retrieval Using Color, Shape, and Texture Features", The Computer Journal, April, 2010.
  7. Kim, K.-B., "Improved SIM Algorithm for Contents- based Image Retrieval", Journal of Intelligence and Information Systems, Vol.15, No.2(2009), 49-59.
  8. Kim, S.-J., "Performance Evaluation of Shape Descriptors for Gait Analysis based on Silhouette Sequence", Journal of Intelligence and Information Systems, Vol.15, No.4(2009), 51-62.
  9. Kim, S.-J, B.-W. Kim, and D.-P. Kim, "Tree Recognition for Landscape Using by Combination of Features of its Leaf, Flower, and Bark", SCIE, 2011.
  10. Nam, Y. and E. Hwang, "A shape-based retrievals scheme for leaf images", LNCS, Vol.3767 (2005), 876-887.
  11. Rahmadhani, M. and Y. Herdiyeni, "Shape and Vein Extraction on Plant Leaf Image Using Fourier and B-spline Modeling", AFITA 2010.
  12. Newsam, S. and C. Kamath, "Comparing Shape and Texture Features for Pattern Recognition in Simulation Data", SPIE, Vol.5672(2005), 106-117.
  13. Rahmadhani, M. and Y. Herdiyeni, "Automatic Plant Leaf Classification for a Mobile Field Guide", AFITA(2010), (2010), 306-310.
  14. Song, H.-S., "Design and Evaluation of ANFISbased Classification Model", Journal of Intelligence and Information Systems, Vol.15, No.3(2009), 151-165.
  15. Wu, S. G., F. S. Bao, E. Y. Xu, Y.-X. Wang, Y.-F. Chang, and Q.-L. Xiang, "A Leaf Recognition Algorithm for Plant Classification Using Probability Neural Network", IEEE International Symposium on Signal Processing and Information Technology, 2007. Available at http://flavia.sourceforge.net/ (Accessed 8 Sept., 2011).
  16. Zhang, D. S. and G. Lu, "A Comparative Study on Shape Retrieval Using Fourier Descriptors with Different Signature", ACCV2002: The 5th Asian Conference on Computer Vision, Jan., 2002.
  17. Zhang, D. S. and G. Lu, "Shape based Image Retrievals Using Generic Fourier Descriptors", Signal Processing and Image Communication, Vol.17(2002), 610-621.

Cited by

  1. 방향성 특징 기술자를 이용한 식물 잎 인식 vol.17, pp.3, 2012, https://doi.org/10.9717/kmms.2014.17.3.300
  2. Leaf Recognition Based on DPCNN and BOW vol.47, pp.1, 2018, https://doi.org/10.1007/s11063-017-9635-1