Professional Documents
Culture Documents
Batch 09 Paper Presentation
Batch 09 Paper Presentation
Nandini G1, Roopashree S2, Sai Sharanya3, Shilpa Saboo4, Sandeep Kumar5
1,2,3,4B.E, Dept. Of Computer science & Engineering, Cambridge Institute of Technology, Karnataka, India
5Associate Professor, Dept. Of Computer science & Engineering, Cambridge Institute of Technology, Karnataka,
India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Plant recognition systems that developed by recognition seems as a challenging and unsolved issue. This is
computer vision researchers, help botanists in faster because a plant in nature has a very similar shape and color.
recognition and detection of unknown plant species. Until now, In addition to plants leaf morphological variations such as
multiple studies focused on the process or algorithms that changes in the size, texture, shape, venation, and so on, has
been added to this challenging issue.
maximize use of botanical datasets for plants prediction
modeling, but this method depends on leaf characteristics Deep learning is a new and modern method for image
which can be changed with botanical data and different processing and data analysis that show high potential and
feature extraction techniques. On the other hand, recently, due promising results. Deep learning has been successful in
to the popularity and successful implementation of deep various fields and recently entered in the field of agronomy
learning-based methods in various areas such as image and food products. Therefore, leaf recognition based on deep
classification, object detection, and speech recognition, the learning methods has attracted more attention.
researchers directed from traditional feature based methods
to deep learning. In this research, one more efficient method 2. LITERATURE SURVEY
presented that use transfer learning to recognize plant for leaf
classification, which first uses a pre-trained deep neural In [1], Introduced a novel approach for classification of
network model for learning useful leaf characteristics directly plants which was based on the characterization of texture
from the input data representation. Then use a Multiclass SVM properties. They have utilized a combined classifier learning
classifier for leaf classification. It is seen that transfer learning vector quantization along with the radial basis function. The
from a large dataset to limited botanical dataset in plant proposed systems ability to classify and recognize a plant
recognition task is well done. The proposed method is from a small part of the leaf is its advantageous thing. This
evaluated on two well-known botanical datasets and has system is mostly applicable as the combined classifier
succeeded in achieving an accuracy of more than 91% method produced high performance far superior to other
respectively. The results show that despite the large change in tested methods as its correct recognition rate was 98.7%
the number of classes in these two datasets, the proposed which has been revealed in the result.
method, have a good performance and show the better result
than methods based on the hand-crafted feature and other In [2], Proposed a method that incorporates shape, vein,
methods based on the deep learning in terms of memory and color, and texture features. They have used probabilistic
precision. neural networks (PNN) as a classifier for the plant leaf
classification. Commonly several methods are there for
Key Words: Image acquisition, Image Pre-processing, GLCM plant leaf classification but none of them have captured color
Feature extraction, Multiclass SVM classifier. information, because color was not recognized as an
important aspect to the identification.
1. INTRODUCTION
In [3], Proposed a feature fusion technique using the Gabor
filter in the frequency domain and fusing the obtained
A good understanding of plants for help to recognize new
features with edge based feature extraction. The extracted
and rare plant species is essential for improving
features were trained using 10 fold cross validation and
pharmaceutical industries, the eco-system balance, agronomy
utilization and robustness. Botanists use variations on the tested with CART and RBF classifiers to measure its
leaf characteristics as a comparative tool for their study about accuracy.
plants. On the other hand, due to the progress of science and
genetic topics, many of the compound plants cannot In [4], This research paper introduced an approach that
recognize by ordinary people or even expert people in this combines relatively simple methods which used shape and
field. For this reason, tried to use computer vision or machine texture features. The shape-based method extracts the
learning techniques to solve this issue. In computer vision, contour signature from every leaf and then calculates the
despite the many efforts that have been conducted, plant dissimilarities between them. The orientations of edge
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 1
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 07 | July 2020 www.irjet.net p-ISSN: 2395-0072
gradients are used to analyze the macro-texture of the leaf. and labeling large amounts of data in a particular domain is
The results of these methods are then combined with the costly and time consuming issues, and may even be
help of incremental classification algorithm which provides impossible. Therefore, in many cases, the idea of collecting a
81.1%accuracy. large number of data in a particular domain may not be
acceptable. This problem poses a challenge and makes it
In [5], This paper concentrates mainly on the procedure of difficult to use deep learning models.
how the test feature can be compared with the database. The
database is created with different kinds of leaf and other 4. PROPOSED METHODOLOGY
purpose leaves. For the execution of test leaf a test image is
captured and the parameter is tested. With this the leaf This approach can be a case study to provide improved
which gives the closest match will be labeled. accuracy in identification of proper plant leaves. It will a
great help for horticulture and botanical industry as this
In [6], Current study used the image processing techniques framework can be used as an automated tool that can
in order to classification of plants based on leaves classify or identify the proper leaf. So that this work can
recognition. Two methods called the Gray-Level Co-
provide an helping hand to the skilled farmers in identifying
occurrence matrix (GLCM) and Principal Component
the plant categories
Analysis (PCA) algorithms have been applied to extract the
leaves texture features. To classify 13 kinds of plants with 65
new or deformed leaves as test images, the Algorithms are
4.1 Image Acquisition
trained by 390 leaves. The findings indicate thatthe accuracy The first step of the system is image acquisition. The image
of PCA method with 98% come out to be more efficiency of a leaf of the plant to be recognized is captured and fed to
compare to the GLCM method with 78% accuracy. the system. Since our system is currently a desktop app, we
have to locate the image via the user interface.
In [7], The important aspect is to develop a system which
classifies the plants. In this paper a novel framework for 4.2 Image Pre-processing
recognizing and identifying plants is been proposed. In this
paper leaves can be recognized based on certain methods. Pre-processing is used to get the outer shape of the image
The recognition of the leaves is done based on feature from the colored image of the leaf and to remove any kind of
extraction method and the Zernike moments. Shape, vein, external noises present in an image. The main idea of
color and texture features have been used to identify the leaf preprocessing is to enhance the image details so that
and neural network approach is used to classify them and it features are clearly found for further processing.
provides accurate results in less time.
In any way, the training of a new deep learning model ⦁Contrast Returns a measure of the intensity contrast
from the beginning requires a lot of data, cost, more between a pixel and its neighbour over the whole image.
computing resources and hours, in some cases, days of Contrast is 0 for a constant image.
training. On the other hand, in real applications, collecting
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 07 | July 2020 www.irjet.net p-ISSN: 2395-0072
Input Leaf
Feature extract
and classification
Classification
Train Database
Classified results
Fig -2: Proposed System Architecture Fig -4: The sample dataset of leaf images
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 07 | July 2020 www.irjet.net p-ISSN: 2395-0072
6.2 Select the leaf image from Test Dataset 8. FUTURE SCOPE
Next step in the future work, different classifiers will be
tested based on our dataset and the results will be recorded.
Here in this project we are considering texture feature.
However, we may have to consider images that contain many
leaves in order to test the ability of the classifiers and we are
looking to consider leaf margins, veins for better
identification of confusing leaves. We can also build a mobile
application of the proposed system, using this one can easily
and efficiently classify the leaves.
ACKNOWLEDGEMENT
We are thankful for our project guide, Prof. Sandeep Kumar
who supported us during the project completion and also
helped us to improve the manuscripts significantly.
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 4
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 07 | July 2020 www.irjet.net p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 5