Open AccessFeature Extraction of Tea Leaf Images using Dual-Tree Complex Wavelet Transform and Gray Level Co-occurrence Matrix
Author(s) -
Bambang Iswanto,
Alma,
Iwan Sugihartono
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2019/1/012092
Subject(s) - artificial intelligence , pattern recognition (psychology) , gray level , complex wavelet transform , feature extraction , co occurrence matrix , computer science , wavelet , principal component analysis , computer vision , wavelet transform , mathematics , discrete wavelet transform , image (mathematics) , image processing , image texture
Feature extraction is a very important part of machine learning to analyze and find relationships between objects of different categories. This paper aims to analyze the feature vectors of the tea leaf image produced by using a combination of dual-tree complex wavelet transform and gray level co-occurrence matrix techniques. The tea leaf image consists of four different categories, each representing different phases of tea growth and were acquired using a visible camera from eight different orientations. Feature extraction using Principle Component Analysis (PCA) shows that the texture features can identify a different category of the leaf images without being significantly affected by the difference in scale and orientation of the images.