Gabor feature-based apple quality inspection using kernel principal component analysis

Bin Zhu, Lu Jiang, Yaguang Luo, Yang Tao

Research output: Contribution to journalArticlepeer-review

43 Scopus citations

Abstract

Automated inspection of apple quality involves computer recognition of good apples and blemished apples based on geometric or statistical features derived from apple images. This paper introduces a Gabor feature-based kernel principal component analysis (PCA) method by combining Gabor wavelet representation of apple images and the kernel PCA method for apple quality inspection using near-infrared (NIR) imaging. First, Gabor wavelet decomposition of whole apple NIR images was employed to extract appropriate Gabor features. Then, the kernel PCA method with polynomial kernels was applied in the Gabor feature space to handle non-linear separable features. The results show the effectiveness of the Gabor-based kernel PCA method in terms of its absolute performance and comparative performance compared to the PCA, kernel PCA with polynomial kernels, Gabor-based PCA and the support vector machine methods. Using the proposed Gabor kernel PCA eliminated the need for local feature segmentation, but also resolved the non-linear separable problem. An overall 90.6% recognition rate was achieved.

Original languageEnglish (US)
Pages (from-to)741-749
Number of pages9
JournalJournal of Food Engineering
Volume81
Issue number4
DOIs
StatePublished - Aug 2007
Externally publishedYes

Keywords

  • Apple quality inspection
  • Gabor wavelet
  • Gabor-based kernel PCA
  • Kernel PCA
  • Near-infrared
  • Principal component analysis (PCA)

ASJC Scopus subject areas

  • Food Science

Fingerprint

Dive into the research topics of 'Gabor feature-based apple quality inspection using kernel principal component analysis'. Together they form a unique fingerprint.

Cite this