You are on page 1of 3

Intelligent System for Aiding Farming Process

Sahil Khedeskar Mohit Rokade Bhargav Patil Tatwadarshi P.N.


Computer Engineering Computer Engineering Computer Engineering Asst. Prof. (Computer Engg.)
VIVA Institute of VIVA Institute of VIVA Institute of VIVA Institute of
Technology Technology Technology Technology
Mumbai, India Mumbai, India Mumbai, India Mumbai, India
sahil.khedaskar@gmail.com mohitrokade9@gmail.com bhargavpatil1996@gmail.com tatwardarshipn@gmail.com

Abstract—Modern agriculture requires field machinery segmenting shape is incomplete, it is needed to take many
capable of precise and repeatable operations based on models of resources to record the boundaries of the over-segment results.
systems and processes. The efficiency of the design process and
the performance of the mechanisms can be improved In computer vision, picture division is the way toward
considerably through concurrent, integrated development. Such parceling an advanced picture into various sections. The
advanced systems with modern feedback controllers can generate objective of division is to disentangle or potentially change the
significant demands for data processing and require substantial portrayal of a picture into something that is more important
communications bandwidth. and less demanding to examine. Picture division is regularly
There are many systems at present that can identify plant, detect used to find articles and limits in pictures. All the more
disease of plants that makes farming easy but there is no such absolutely, picture division is the way toward allotting a mark
system which can help a person learn agriculture in real time. to each pixel in a picture to such an extent that pixels with a
Looking at present climatic conditions the conventional farming similar name share certain attributes [1].
techniques are not that useful, there is need in upgrading that
process. Although government takes seminars by going to Division is for the most part the primary stage in any
villages and help them to learn modern farming techniques but it endeavor to dissect or translate a picture consequently [3].
requires lot of time. This system will be an intelligent system for Division conquers any hindrance between low-level picture
aiding farming process. This system makes use of image preparing and abnormal state picture handling. A few sorts of
processing techniques like grey scale conversion, image division procedure will be found in any application including
segmentation, characteristics extraction and Artificial Neural the discovery, acknowledgment, and estimation of items in
Network as Classification. With the help of this the system can pictures.
identifies the Stage of a plant and with the help of this
information actions are suggested to the user for proper farming. Machine learning is firmly identified with (and frequently
Information that can help farmers upgrade their farming covers with) computational insights, which likewise
techniques or teach a common man the perfect techniques of concentrates on expectation making using PCs. It has solid
farming instantly by a picture. connections to scientific enhancement, which conveys
techniques, hypothesis and application spaces to the field.
Keywords—Image Processing; Artificial Neural Network Machine learning is here and there conflated with information
[ANN]. mining, where the last subfield concentrates more on
exploratory information examination and is known as
unsupervised learning. Machine learning can likewise be
I. INTRODUCTION unsupervised and be utilized to learn and set up standard
behavioral profiles for different elements and afterward used
Image processing is a technique to transform an image into
to discover significant inconsistencies.
digital form and execute some actions on it, in order to get a
better image or to extract some useful data from it. It is a form
of signal dispensation in which input is image and the system
process that image using efficient algorithms, and output may II. RELATED WORK
be image or features associated with that image. Usually By using the image processing techniques like image
Image Processing system includes treating images as two segmentation, grayscale conversion, feature extraction, edge
dimensional signals while applying already set signal detection, etc. it is easy to identify the further processes on
processing methods to them. The processing stages start with any image. Machine learning is a platform where there are
image segmentation. There is some expectation from image
different algorithms, which can be applied for the different
segmentation algorithms. First of them is the speed. While
processes at the different stages for any image. These
segmenting an image, we do not want to spend much time.
The second is good shape connectivity of the object. This algorithms help the image processing techniques to identify
insure better results in image recognition. If the result of the stages of the plants using image segmentation, grayscale
conversion, feature extraction, comparison image using ANN B. Image Segmentation
Algorithm. After the gray scale conversion of the image, the image is
divided into various segments. With the help of
segmentation the system separates the layer of the image.
III. PROPOSED WORK
With a single threshold, it transforms a greyscale or colour
The working of the system can be explained using process image into a binary image considered as a binary region
flow diagram. In this system we are going to identify the map.
various stages and lifecycle of the mustard plant. The system
will take an image as the input. With the help of grayscale
conversion the system will convert the image into black and C. Articial Neural Network
white. Segmentation will divide the grayscale output in ANN is used to classify the image. It will make class of
different layers. ANN will help the different layers to perform different set of image. This class will define the various
different kinds of transformations on their inputs. The feature stages of the plant. Once the image are classified according
extraction will take the color and shape of the leaves to to their stages then it applies extraction of features from
identify the stage of the plant and depending on the stages the this particular image and store it to database which will
system will do the prediction. Comparison of the image is feathers used for the comparison.
done after extraction to identify the approximate age of the
plant. And finally we get the predicted output.

Fig.1. System Flow

A. Gray Scale Conversion

The image of the spinach plant is converted into gray scale


format:- Fig.2. ANN Classification [15]
To convert an RGB image to grayscale, system have to use
the RGB2GRAY command from the Image Processing D. Characteristics Extraction
Toolbox. In image processing, feature extraction starts from an
initial set of measured data and builds derived values.
This method will convert the image into black and white. When the input data to an algorithm is too large to be
There are three types of formulas: processed and it is suspected to be redundant, then it can
Normal Grayscale:- be transformed into a reduced set of features. Feature
(max(red, green, blue)+min(red, green, blue)) extraction involves reducing the amount of resources
2 required to describe a large set of data. The important
Average Grayscale:- characters on the spinach plant like colour and shape i.e.
Red+Green+Blue the features of it are extracted to detect the plant stage.
3
Luminious Grayscale:-
(0.21Red+0.71Blue+0.02Green) E. Comparison
The key features on the plants and that feeded into the
Luminious Grayscale conversion is the most efficient system are compared. After comparing the key feature the
method for the conversion of image into black and white. system shows the result of the different stages of the
spinach plant. After classifying the different stages of the
plant it will identify the age of the plant
REFERENCES
[1] Kumar, Vinod, Tauj Lal, Piyush Dhuliya, and Diwaker Pant. "A study
and comparison of different image segmentation algorithms."In
Advances in Computing, Communication, & Automation
(ICACCA)(Fall), International Conference on, IEEE, 2016 pp. 1-6.
[2] Acuña, Rafael Guillermo Gonzalez, Junli Tao, and Reinhard Klette.
"Generalization of Otsu's binarization into recursive colour image
segmentation." In Image and Vision Computing New Zealand (IVCNZ),
2015 International Conference on, IEEE, 2015 pp. 1-6.
[3] Devbrat Arya, Jaimala Jha. “A Review on Content Based Image
Retrieval Using Feature Extraction ” International Journal of Advanced
Research in Computer Science and Software Engineering Vol 3,
March 2016.
[4] Le Hoang Thai, Tran Son Hai, Nguyen Thanh Thuy . “Image
Classification using Support Vector Machine and Artificial Neural
Network” International Journal on Information Technology and
Computer Science,2012, pp 32-38 .
[5] Fang, Yihang, Xingyu Wang, Pujuan Shi, Chengda Lin, and Ruifang
Zhai. "Automatic identification of two growth stages for rapeseed plant:
Three leaf and four leaf stage." In Agro-Geoinformatics (Agro-
geoinformatics), 2015 Fourth ]International Conference on, IEEE, 2015
pp. 148-153.
[6] Singh, Vijai, and A. K. Misra. "Detection of unhealthy region of plant
leaves using Image Processing and Genetic Algorithm." In Computer
Engineering and Applications (ICACEA), 2015 International
Conference on Advances in, IEEE 2015, pp. 1028-1032.
[7] Petrellis, Nikos. "A smart phone image processing application for plant
disease diagnosis." In Modern Circuits and Systems Technologies
(MOCAST), 2017 6th International Conference on, IEEE 2017, pp. 1-4.
[8] Chi, Hung-Lin, Jian Chai, Changzhi Wu, Junxiang Zhu, Xiangyu Wang,
and Chongyi Liu. "Scaffolding progress monitoring of LNG plant
maintenance project using BIM and image processing technologies." In
Research and Innovation in Information Systems (ICRIIS), 2017
International Conference on, IEEE 2017, pp. 1-6.
[9] Souza, Gustavo B., Gabriel M. Alves, Alexandre LM Levada, Paulo E.
Fig.3. System Architecture Cruvinel, and Aparecido N. Marana. "A Graph-Based Approach for
Contextual Image Segmentation" In Graphics, Patterns and Images
(SIBGRAPI), 2016 29th SIBGRAPI Conference on, IEEE, 2016 pp.
IV. RESULT ANALYSIS 281-288.
[10] Le Bris, Arnaud, Francois Tassin, and Nesrine Chehata. "Contribution
After the system is provided with the image it will apply of texture and red-edge band for vegetated areas detection and
various image processing techniques on it. The main goal of identification." In Geoscience and Remote Sensing Symposium
the system is that it will predict the approximate age of the (IGARSS), 2013 IEEE International, IEEE 2013, pp. 4102-4105.
plant and will determine stage of its life cycle and will provide [11] Radha, R., and S. Jeyalakshmi. "An effective algorithm for edges and
veins detection in leaf images." In Computing and Communication
the user with accurate information about the further farming Technologies (WCCCT), 2014 World Congress on, IEEE 2014, pp. 128-
techniques required. This will be helpful in aiding farming 131.
process, and in turn increase the productivity of the farm. [12] Quraishi, Md Iqbal, J. Pal Choudhury, and Mallika De. "Image
recognition and processing using Artificial Neural Network." In Recent
Advances in Information Technology (RAIT), 2012 1st International
V. CONCLUSION Conference on, IEEE 2012, pp. 95-100.
[13] Tichkule, Shivani K., and Dhanashri H. Gawali. "Plant diseases
After extensive research and analysis of various research detection using image processing techniques." In Green Engineering and
papers it can be concluded that there is no system present Technologies (IC-GET), 2016 Online International Conference on, IEEE
which could predict the lifecycle stage of a plant and its 2016, pp. 1-6.
approximate age. So, the proposed system will identify the [14] Anju Bala, Aman Kumar Sharma. “Color Image Segmentation Using K-
means Clustering and Morphological Edge Detector” International
approximate age and will provide with proper and accurate Journal of Latest Trend in Engineering and Technology., 2016.
farming techniques which will help farmers upgrade to [15] “https://www.pinterest.com/pin/389913280214536127/artificial-neural-
modern techniques of agriculture. network-example” last accessed on 23/02/2018

You might also like