Deep plant: A deep learning approach for plant classification / Lee Sue Han
Plant classification systems developed by computer vision researchers have helped botanists to recognize and identify unknown plant species more rapidly. Hitherto, the majority of computer vision approaches have been focused on designing sophisticated algorithms to achieve a robust feature repres...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://studentsrepo.um.edu.my/8758/ http://studentsrepo.um.edu.my/8758/1/Lee_Sue_Han.pdf http://studentsrepo.um.edu.my/8758/6/sue_han.pdf |
| Summary: | Plant classification systems developed by computer vision researchers have helped botanists
to recognize and identify unknown plant species more rapidly. Hitherto, the majority of
computer vision approaches have been focused on designing sophisticated algorithms
to achieve a robust feature representation for plant data. For many morphological leaf
features pre-defined by botanists, researchers use hand-engineering approaches for their
characterization. They look for the procedures or algorithms that maximize the use of
leaf databases for plant predictive modelling, but this results in leaf features which are
liable to change with different leaf data and feature extraction techniques. As a solution,
the first part of the thesis proposes a novel framework based on Deep Learning (DL) to
solve the ambiguities of leaf features that are deemed important for species discrimination.
The leaf features are first learned directly from the raw representations of input data
using Convolutional Neural Networks (CNN), and then the chosen features are exploited
based on a Deconvolutional Network (DN) approach. Besides using solely a single leaf
organ to recognize plant species, numerous studies have employed DL methods to solve
multi-organ plant classification problem. They focus on generic feature as such the holistic
representation of a plant image, disregarding its organ features. In such case, irrelevant
features might be erroneously captured especially when they appear to be discriminative
for species recognition. Therefore, the second part of the thesis proposes a new hybrid
generic-organ CNN architecture. Specifically, it can go beyond the regular generic description
of a plant, integrating the organ-specific features together with the generic features
to explicitly force the designed network to focus on the organ regions during species
classification. Modelling the relationship between different plant views (or organs) is important as these images captured from a same plant share overlapping characteristics
which are useful for species recognition. The existing CNN based approaches can only
capture the similar region-wise patterns within an image but not the structural patterns of
a plant composed of varying number of plant views images composed of one or more organs.
The third part of the thesis proposes a novel framework of plant structural learning
based on Recurrent Neural Networks (RNN), namely the Plant-StructNet. Specifically, it
takes into consideration contextual dependencies between varying plant views capturing
one or more organs of a plant and optimizes them for species classification. In summary,
the collective impact of the above contributions have constituted to achieve a more practical
and feasible framework towards the applications of plant identification. Empirical
studies show that the proposed frameworks outperform the state-of-the-art (SOTA) methods
in Flavia (S. G. Wu et al., 2007a) and PlantClef2015 plant dataset (Joly et al., 2015).
These findings can serve as reference sources for the research community working on
plant identification, and also help to support the future work in this area. |
|---|