Learning-based leaf image recognition frameworks

Jou Ken Hsiao, Li Wei Kang*, Ching Long Chang, Chih Yang Lin

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)


Automatic plant identification via computer vision techniques has been greatly important for a number of professionals, such as environmental protectors, land managers, and foresters. In this chapter, we propose two learning-based leaf image recognition frameworks for automatic plant identification and conduct a comparative study between them with existing approaches. First, we propose to learn sparse representation for leaf image recognition. In order to model leaf images, we learn an over-complete dictionary for sparsely representing the training images of each leaf species. Each dictionary is learned using a set of descriptors extracted from the training images in such a way that each descriptor is represented by linear combination of a small number of dictionary atoms. Second, we also propose a general bag-of-words (BoW) model-based recognition system for leaf images, mainly used for comparison. We experimentally compare the two learning-based approaches and show unique characteristics of our sparse representation- based framework. As a result, efficient leaf recognition can be achieved on public leaf image dataset based on the two proposed methods. We also show that the proposed sparse representation-based framework can outperform our BoWbased one and state-of-the-art approaches, conducted on the same dataset.

Original languageEnglish
Pages (from-to)77-91
Number of pages15
JournalStudies in Computational Intelligence
Publication statusPublished - 2015
Externally publishedYes


  • Bag-of-words (BoW)
  • Dictionary learning
  • Leaf image recognition
  • Plant identification
  • Sparse representation

ASJC Scopus subject areas

  • Artificial Intelligence


Dive into the research topics of 'Learning-based leaf image recognition frameworks'. Together they form a unique fingerprint.

Cite this