Skip to content

The identification of plant disease is the premise of the prevention of plant disease efficiently and precisely in a complex environment. Machine Learning algorithm this work attempt to predict in an earlier stage and outcomes are better.

Notifications You must be signed in to change notification settings

iamtariqul/Digital_Farmer-Plant_Diseases_Recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Digital Farmer: Deep Learning Based Plant Diseases Recognition

Aim and Scope

I arranged my questionaries into specific Categories and where we have 38 attributes of Questions, I use to expect Plant Disease. From the beginning assemble some standard credits from past work then accumulate other attributes from analyzing with horticulturists the Farmers Questionaries are finding the credits of a plant leaf that address a Plant's prosperity, therefore it will require some venture to anticipate which plant suffers or not. Here portray properties as questions: horticulturists and also farmers to predict disease before doing a formal screening test. It will be the most significant way to find Plant Diseases which gives a decision with less cost and less time.

Research Questions

I sorted my questionaries into certain Categories and where we have 38 ascribes of questions, I use to anticipate Plant Disease. From the outset we gather some standard credits from past work then we gather others ascribes from examining with horticulturists and the Farmers Questionaries are discovering the credits of a Plant leaf which address a Plant's well-being, consequently, it will require some investment to foresee which Plant endure or not. Here we depict our class of properties as questions: • Does a plant have any disease? • Does a plant have any infection? • What kind of disease the plant has? • What kind of plant this is? • Is the plant healthy?

Expected Outcome

By applying the AI strategy in the informational collection we got the yield result. This assessment works is done by using Machine Learning computation. Here we use Convolutional neural association and the investigation work got done with plant information and there are 38 traits. The enlightening files are disconnected into three educational assortments one train data, Valid data another tested instructive assortment. First applying computations into the arrangement enlightening assortment and planning instructive assortment arranged. By then using getting ready instructive assortment the computations applied to the significant and the test educational file. That is the test enlightening assortments work following the readiness educational assortments and choose accuracy. Making an expert system that endeavors to help a horticulturist to perceive issues with the plant. Because it is a man-made intellectual competence-based failure perceiving system, it will in general be thought and recognize this issue like a human. In these workplaces, people can recognize the issue of their plant. Making a specialist framework that attempts to assist a horticulturist to recognize issues with the plant. As a result, it is a man-made brainpower-based inability to recognize framework, so it tends to be thought and distinguish this issue like a human. For these offices, individuals can distinguish the issue of their plant.

Motivation

The agronomic essentials anyway in significantly different habits to those at present used this has offered climb to various new freedoms to help. So they should be attempted through non-perilous techniques Leaves are a touchy piece of plant, The appraisal of rustic accumulate Classification is dynamic. The main visual property is the leaf's surface and concealing. Thus, the gathering of leaf ailment is essential in evaluating agrarian produce, Like a person who has gained mastery over their craft, you must gain mastery over your life, and take your life out of neutral, no one can make this commitment for you, intentionally pursue your God-given purpose and maximize your divine potential, intentionally get rid of self-defeating habits and undermining relationships. expanding market worth and satisfying quality guidelines. Distinguishing and taking further dealings for additional dissemination of the illnesses is likewise useful. The interaction will be excessively lethargic, If the recognizable proof and order are done through physical methods, we need the specialist's help at times it will be blunder inclined and who are less accessible. The works arrange dependent on shading, size and so on if these quality strategies are recorded into the programmed framework by utilizing fitting system plan language then the exertion will be without blunder and quicker. extending market worth and fulfilling quality rules. Recognizing and taking further dealings for the extra spread of the ailments is similarly helpful. The connection will be exorbitantly torpid, If the conspicuous confirmation and request are done through actual strategies, we need the expert's help on occasion it will be goof slanted and who are less open. The work organized is reliant upon concealing, size, etc if these quality methodologies are recorded into the modified structure by using fitting framework plan language then the effort will be without botch and speedier. There are two guidelines ascribed to plant infection area AI strategies that should be cultivated, they are speed and accuracy. There is a need for making methods like modified plant ailment disclosure and request using leaf picture planning methodology. This will exhibit supportive procedures for farmers and will alert them at the ideal time before the spreading of the disease over the huge zone. The game plan is made out of four essential stages; in the principle stage we make a concealing change structure for the RGB leaf picture and subsequently, we apply concealing space change for the concealing change structure. By then the picture is assigned using the K-infers gathering methodology. In the resulting stage, an inconsequential part (a green area) inside the leaf zone is disposed of. In the third stage we, figure out the surface features of the distributed polluted thing. Finally, in the fourth stage, the removed features are gone through a pre-arranged neural organization."The agronomic essentials anyway in significantly different habits to those at present used this has offered climb to various new freedoms to help." [11]. At the point when a Farmer has those issues in the essential stage consistently thinks it is anything but a major issue, yet the issue will increment with expanding the Disease. Which was unsafe for a Plant, because solitary the early conclusion can lessen this issue. In those cases, our exploration will be more useful and gainful for the horticulturists and Farmers to anticipate Disease before doing a proper screening test. It will be the main method to discover Plant Diseases which gives a choice with less expense and less time.

There are two principal attributes of plant sickness location AI techniques that must be accomplished, they are speed and precision. There is a need for creating procedures like programmed plant illness discovery and order utilizing leaf picture preparation procedures. This will demonstrate a helpful strategy for ranchers and will alarm them at the perfect time before spreading the illness over an enormous zone. The arrangement is made out of four fundamental stages; in the main stage we make a shading change structure for the RGB leaf picture and afterward, we apply shading space change for the shading change structure. At that point, the picture is portioned utilizing the K-implies grouping procedure. In the subsequent stage, the pointless part (green territory) inside the leaf zone is eliminated. In the third stage, we figure the surface highlights for the portioned contaminated item. At long last, in the fourth stage, the extricated highlights are gone through a pre-prepared neural network.

Limitation of the existing system

In one paper they don't briefly implement any method and don't discuss computer tomography but they used this in their paper. Also, some paper has limitations when using a huge number of image will train then the algorithm to give better accuracy only. But when they applied this to the smallest number of images they don't get the expected outcome. Most of their proposed system is too costly. Some author only compared their result with the literature review but don't measure the percentage of the accuracy they only showed web-based detection. In one paper we saw that they focus only on RGB format but either without RGB format disease can be detected.

Summary

I work for plants where I use machine learning algorithms for better prediction. Predict disease in the earlier stages we take the necessary step for those plants and early treatment can reduce disease. There we use different machine learning algorithms such as convolutional neural networks. These techniques are performed in machine learning tools such as Anaconda, Python, and some libraries. At last, we understood that in the above research work machine learning techniques are applied in large datasets, and in our research work, we applied machine learning techniques in an autism behavior dataset. In this exploration, I work for plants where I use AI calculation for better expectations. Anticipating infection in the prior stage we make essential strides for those plants and early treatment can diminish sickness. There we utilize diverse AI calculations like Decision Tree and Random Forest. These procedures are acted in AI devices such as Anaconda, Python, and a few libraries. In last we comprehended that in the above research work, AI methods are applied in enormous datasets, and in our exploration work, we applied AI procedures in a chemical imbalance conduct dataset.

Research Project on Artificial Neural Network Architecture as well as weight optimization using Hybrid Meta-heuristic Techniques (using GOA algorithm and Simulated annealing). Developed a monitoring tool to analyze the website's availability, performance, and user experience and send alerts. All code was reviewed, perfected, and pushed to production. Web application uses a trained convolutional neural network to identify the disease present on a plant leaf. It consists of 38 classes of different healthy and diseased plant leaves. The 38 classes are:

  1. Apple-> Apple scab
  2. Apple-> Black rot
  3. Apple-> Cedar apple rust
  4. Apple-> healthy
  5. Blueberry-> healthy
  6. Cherry-> Powdery mildew
  7. Cherry-> healthy
  8. Corn-> Cercospora leaf spot (Gray leaf spot)
  9. Corn-> Common rust
  10. Corn-> Northern Leaf Blight
  11. Corn-> healthy
  12. Grape-> Black rot
  13. Grape-> Esca (Black Measles)
  14. Grape-> Leaf blight (Isariopsis Leaf Spot)
  15. Grape-> healthy
  16. Orange-> Haunglongbing (Citrus greening)
  17. Peach-> Bacterial spot
  18. Peach-> healthy
  19. Pepper, bell-> Bacterial spot
  20. Pepper, bell-> healthy
  21. Potato-> Early blight
  22. Potato-> Late blight
  23. Potato-> healthy
  24. Raspberry-> healthy
  25. Soybean-> healthy
  26. Squash-> Powdery mildew
  27. Strawberry-> Leaf scorch
  28. Strawberry-> healthy
  29. Tomato-> Bacterial spot
  30. Tomato-> Early blight
  31. Tomato-> Late blight
  32. Tomato-> Leaf Mold
  33. Tomato-> Septoria leaf spot
  34. Tomato-> Spider mites (Two-spotted spider mite)
  35. Tomato-> Target Spot
  36. Tomato-> Tomato Yellow Leaf Curl Virus
  37. Tomato-> Tomato mosaic virus
  38. Tomato-> healthy

Requirements:

  1. Python
  2. Tensorflow
  3. Keras
  4. Django
  5. PIL
  6. Numpy

Screenshots

Plant plant1

About

The identification of plant disease is the premise of the prevention of plant disease efficiently and precisely in a complex environment. Machine Learning algorithm this work attempt to predict in an earlier stage and outcomes are better.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published