Image processing Techniques to Forecast Plant Disease

Image processing Techniques to Forecast Plant Disease A Synopsis on A Feasibility Study on The Prediction/Forecasting of Disease for Plant Leaf Using Image processing Techniques by Chaitali Pandya   INDEX PAGE (JUMP TO) Introduction Scope of the proposed study Review of work already done on the subject Objectives of the proposed study Research Methodology Hypotheses to be tested Tentative Chapterization Bibliography Introduction India is a country where the agricultural plays a very important role. Here more than 70% depends on agriculture. Demand of agricultural industry, is increased day by day, so it is very important for the plant to grow effectively and increase its yield. The crop may be fruits or vegetables. For that it is very much important that a plant has to be monitored its growth period at the time of crop. Image processing is used as a tool to observe the diseases on leaves of plants during farming from plantation up to harvesting. This study might help to forecast a plant leaf diseases. Importance/Rationale of proposed Investigation The demand of the agriculture industry increases day by day, it is very much important for the plant to grow effectively and gives the maximum output or harvest. For doing so, it is essential to monitor the plant and plant leaf during its growth period, as well as, at the time of harvest. Scope of the proposed study The research only considers the plants of the vegetables that are of any type. Digital Images of defective leaf of a plant. The study only considers the Image processing toolbox for converting the image. The study modifies the existing algorithm to convert image to text to perform the disease forecasting. Review of work already done on the subject A web based tool named as Identificator is used to help the people who are not experts in identifying plant diseases in a particular way, which is totally based on the picture selection and/or little text descriptions. It is applicable when no suitable images exists, which represents the symptoms on a specific sample of plant tissues. User can access this system from anywhere, it can be said as a multi accessed system, because the multi-access key of identification has to be generated, and it from the remote side or desktop computers or smart phone operators can easily use it. In this, the user selects pictures approaching the symptoms and the system gives the most probable disease.[1] The other study for the identification of symptoms of a plant diseases, where the images are colored is a machine vision system. The region, where the diseases found, in the digital pictures were improved, separated, and a set of features were removed from each of them. Inputs to a Support Vector Machine (SVM) features were then used as classifier and tests were performed to identify the best organized model. [2] One study based on leaf image has been done. Some chemicals applied to the plants on the periodic basis. This kind of technique was only applied to the plants where the leaves already have been defected with the disease. Hundreds of chili plants were observed to perform disease forecasting. To detect disease on the chili plant leaf, the image processing technique plays a very important and useful role. This system will help farmers for the future monitoring and plantation.[3] One study has already been done, in that a quantitative and qualitative optimization criteria for the co-operative evolutionary optimization method had been used, that involved a user and system (CEUS) for problems. The model, which is named as interactive evolutionary computation (IEC) model, system and user plays the own role for the evolution, such as individual replica or evaluation. Exactly in the opposite side, the proposed CEUS allows the user to dynamically change the allocation of search roles between the system and user, resulting in immediate optimization of qualitative and quantitative objective functions without increasing user exhaustion. To achieve above mentioned optimization, it is better that a combination of user evaluation prediction and the integration of interactive and non-interactive EC would be used.[4] Objectives of the proposed study The main objective of this research is to maximize the cost-effective, reliable harvesting to the agriculture industry. With regarding of doing so, the study will seek following objectives: To provide the tool to forecast/predict plant diseases for the vegetables. The study may give the solution to the problem where the crop of any vegetable will not give the expected results. To forecast how the plant leaf got defected in concern with the diseases. It may give the partial solution of the diseases by image of plant leaves. Research Methodology In this research study, different image processing techniques might be used. First digital image will be taken of the plant leaf. Image editing software MATLAB will be used to convert the image using image processing toolbox. A survey on the image will be done in the qualitative and quantitative situations. Data might be collected from the specified region(s)/ farm(s). Comparison of the data which is taken from the digital image with the actual data to forecast the disease. Hypotheses to be tested Sources of Information Sources of the information would be the farm or a nursery from where the digital pictures might be taken on a specific interval to study whether the leaves are affected with any specific diseases or not. Tools and Techniques of Research Tools that will going to be used is the MATLAB R2010a (image editing software) with image editing tool ,that will help to convert the image into the text, those texts will be used for the future reference. Tentative Chapterization There might be the following chapters in the PhD thesis : Title page Abstract (with keywords) Table of contents List of tables List of figures Abbreviations Statement of original authorship Acknowledgments 1 Introduction 2 Literature review 3 Methodology 4 Analysis of data 5 Conclusions and implications Bibliography Appendices Bibliography Nakayama, S. O. (2014). User-system cooperative evolutionary computation for both quantitative and qualitative objective optimization in image processing filter design. Applied Soft Computing , 203 218. Jhuria, M. a. (2013). Image processing for smart farming: Detection of disease and fruit grading. Shimla. Elad, I. P. (2012). Identificator: A web-based tool for visual plant disease identification, a proof of concept with a case study on strawberry. 144 154. Husin, Z. a. (2012). Feasibility Study on Plant Chili Disease Detection Using Image Processing Techniques. (pp. 291-296). IEEE. Smith, A. C. (2009). Image pattern classification for the identification of disease causing agents in plants . Computers and Electronics in Agriculture , 121 125. Zhou, Y. C. (2010). Plant root image processing and analysis based on 2D scanner., (pp. 1216-1220). [1] Elad, I. P. (2012). [2] (Smith, 2009) [3] (Husin, 2012) [4] Satoshi Ono and Hiroshi Maeda and Kiyomasa Sakimoto and Shigeru Nakayama