Blooming flower recognition by using eigenvalues of shape features

Wooi-Nee Tan; Racheal Sem; Yi-Fei Tan

doi:10.1117/12.2064504

16 April 2014 Blooming flower recognition by using eigenvalues of shape features

Wooi-Nee Tan, Racheal Sem, Yi-Fei Tan

Proceedings Volume 9159, Sixth International Conference on Digital Image Processing (ICDIP 2014); 91591R (2014) https://doi.org/10.1117/12.2064504
Event: Sixth International Conference on Digital Image Processing, 2014, Athens, Greece

Abstract

This paper introduces the concept of eigenvalues in describing the shape features of blooming flowers, and implements the idea in recognizing the blooming flowers automatically. The input images of blooming flowers are taken from natural scene in the form of RGB images. The proposed method first segments and crops the targeted flower object, then calculates four shape features to form a 2 × 2 matrix. Eigenvalues of the matrix computed from the testing set are then used to compare with those eigenvalues of the reference set. The advantage of utilizing the idea of eigenvalues is that the dimension of parameters used in comparison can be reduced. Based on the experimental result on database which consists of 5 types of flowers with a total of 46 images, a recognition rate of 80.43% is achieved.

Citation Download Citation

Wooi-Nee Tan, Racheal Sem, and Yi-Fei Tan "Blooming flower recognition by using eigenvalues of shape features", Proc. SPIE 9159, Sixth International Conference on Digital Image Processing (ICDIP 2014), 91591R (16 April 2014); https://doi.org/10.1117/12.2064504

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available