Earticle

초록

영어

This paper proposes a method of distinguishing edible mushrooms from non-edible mushrooms using Principal Component Analysis (PCA) algorithm. This system functions by projecting a mushroom image onto a feature space that spans the significant variations among known set of mushroom images. Mushrooms possess certain significant features such as its stalk size, cap shape etc, and PCA extracts these dominant features and these are the eigenvectors of the set of mushrooms. The projection operation characterizes individual mushroom images by a weighted sum of the eigenvector features and hence to recognize a particular mushroom, so it is necessary only to compare these weights to those individual ones. The performance of the proposed method showed around 85% ~96% success rate that increases with the number of training images, and hence proves to be a reliable algorithm for the recognition of mushrooms.

목차

Abstract
 1. Introduction
 2. Principal Component Analysis
  2.1. Principal Component Analysis Work Flow
  2.2. PCA Algorithm
 3. Mushroom Databases
 4. Test and Results Analysis
  4.1. Reasons for Successful Detection
  4.2. Reasons for Errors
 5. Analysis of Accuracy and Execution Time
 6. Conclusion
 References

키워드

저자

• Ashwin Subramaniam [ Department of Electronics Engineering, Hannam University, Daejeon, Korea ]
• Byung-Joo Oh [ Department of Electronics Engineering, Hannam University, Daejeon, Korea ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Software Engineering and Its Applications

• 간기

  월간

• pISSN

  1738-9984

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605