For over a decade now, agriculture has been the key source of income in India. In a country like India, which is developing now, agriculture provides a huge number of employment opportunities. According to a study, a huge population of the country, around 60-70% of the country depends on agriculture. Most of the work related to farming in India is being done manually because most of the farmers lack the technical knowledge required to do it in a modern way. Pesticides are being sprayed presently on the plants by the farmers but it will have bad effects on the people who consume them. Farmers have no proper idea of what type of crop can be grown on the type of soil they are working on. When different types of diseases affect the plants, where the main part of the plant that gets affected is the leaf, they will suffer a huge loss economically. There will also be a significant decrease in the production of the plants. A leaf is one of the most important parts of the plants. The most challenging job for both the farmers and researchers is the identification of the disease that has affected the leaf. For identifying the plant diseases, farmers need to adapt to many modern techniques. Through this paper, we will be surveying different plants and their diseases and also the various advanced techniques that can be used to detect these diseases.
The present economy of the Indian subcontinent is highly dependent on agriculture. 70% of India’s rural households still depend on agriculture where around 82% of the farmers are small and marginal. In 2017, total food grain production was estimated to be around 275 million tones. This makes the detection of plant diseases a very important thing. Indian agriculture is composed of many crops like rice, millets, wheat and other commercial crops like jute, opium, rubber. The main source of strength for all these crops is leaves and roots. Many different factors affect the leaves of the plants which result in the exposure of the plant to disease and when the same process is observed throughout the nation, it leads to a decrease in crop production. All this can be avoided by detecting the diseases in plants as early as possible. To properly avoid this situation we need to detect the disease as accurately as possible. While the number of diseases that affect the crop is very high, farmers very often fail to identify them in time and also fail to take the precautions required properly. One way to resolve this issue is by using the image processing techniques which are known for their efficiency and one can rely on them as they have always proved to be useful. These methods might prove to be helpful for the farmers to decrease their effort in treating the plants. A large number of ideas have been proposed by scientists for detecting diseases. In this paper, we will be surveying various diseases that affect the plant and the methods and techniques proposed by various researchers to detect them.
Many types of measures have been taken by the agriculture department for treating and avoiding the plants from being affected by various diseases depending on the season. One way through which we can help this situation where farmers have to manually observe the plants is, with the help of automation, where we can use the image processing techniques. Throughout a huge number of years, lots of researchers have conducted many experiments on the leaves of plants to identify a type of disease. Through the automation that we mentioned earlier, we can identify a type of disease as early as possible and by doing so, we can avoid the damage to the plants as much as possible in its early stages itself. We have already mentioned various types of diseases that can be observed in various plants and through observation, we understand that there is a need for continuation of the research to achieve the required levels of results. The task of identifying the diseases is becoming difficult as the time moves on, because finding pathologists is becoming a tough job nowadays. This automation helps us to prevent huge amounts of effort put by the farmers to identify a disease. Moreover, this also helps us to reduce the number of pesticides used for plants and thus helps in reducing its bad effects on the people and animals who consume them.
 In this paper, we will discuss about a process where there are four steps mainly involved in developing the processing scheme, the first one among the steps is, for RBG image which will be given as the input, firstly, a structure of the color transformation is created as, for color descriptor, HSI is used. Also, this RGB is used for the generation of color. In the following step, green pixels are firstly masked and are then removed, with the help of the threshold value. After that, by using the threshold level that is pre-computed, removal of the green pixels followed by their masking is done.
 This paper discusses some of the diseases that are observed:
[a]Bacterial blight: This is caused mainly by bacteria and is observed in many plants, but the most common plant that gets affected by this disease is the pomegranate. In the fruits which are affected by this disease, we can observe some brownish-black spots, with cracks passing over them. [b] Fruit spot: Here, in this disease, light brownish spots can be observed on the fruit which will then become large and then go on to become the blackish spots on the fruit, this infection might be very dangerous as it might cause death to the plant. The main reason for its cause is the fungus and also, such conditions are favored by rainfall.
 This paper tells us about a different approach for the same problem, here we discuss a mobile application which has been developed by adding some simple machine learning. Here firstly, some features are extracted, like the total number of the spots, the area and the level of the grayness. After this in the coming time, we can extract some more complex features like color histograms, also this is capable of ignoring the histograms that are difficult to separate from their background. Based on the “if-else”, method, several conclusions can be drawn based on which disease has affected the plant.
 This paper shows us the various types of diseases that can be observed on the plant leaves, some of the diseases that we can observe here are,
[a] Koleroga: Arecanut is the plant that is most commonly affected by this disease. Fungus phytophthorapalmivora is the main cause of this disease.
[b] Rust: This disease is mostly observed on the lower side of the leaf surfaces. During the initial stages, spots are raised, on the leaves. The spots become reddish as time goes on. Leaf postulates then turn into yellowish color and then eventually gets turned into blackish color.
[c] Leaf curl: The main symptom that comes with this disease is the curling of the leaf. It can be caused by a type of virus, a genus taphrina, or a fungus.
 This paper tells us about deep learning. Deep learning can be stated as a section of the machine learning algorithms that consists of the sequential layers. For each layer, the input is taken from the output of the preceding layer. We can say that the learning process can be unsupervised. The representation algorithms help us in making the optimizations for finding the most convenient way for representing the data. In deep learning, we do not need to perform the feature extraction task and the classification task, as in deep learning the feature extraction is automatically done.
 In this paper, we will discuss a system, which mainly consists of two parts, the first one of them being the disease feature analysis and the plant leaf disease classification. Here, the plant leaf’s feature extraction is done in a manual way, where the proposed methodology only consists of disease feature extraction and classification
Through this paper, we surveyed various diseases that affect the plants used in the agricultural field, the symptoms that are observed in the plants for the respective diseases and the cause for that. Mainly, we conclude by saying that by automating the process by using image processing techniques, we can reduce the efforts, time and money that are spent in curing the disease.
- Vijai Singh, Varsha, Prof. A.K. Mishra, International Conference on Advances in pc Engineering and Applications (ICACEA) IMS Engineering school, Ghaziabad, Asian nation (2015)
- MrunmayeeDhakate, Ingole A. B, study on pomegranate plant disease identification.
- Nikos Petrellis, “Plant Lesion Charecterisatio for Disease Recognition”, 2nd International Conference on Frontiers of Signal Processing(2016)
- SanthoshKumar.S, B.K. Raghavendra, “Disease detection of assorted plant leaf exploitation Image process techniques”, fifth International Conference on Advanced Computing & Communication Systems (ICACCS) (2019)
- MelikSardogan, AdemTuncer, YunusOzen, “Plant Leaf Disease Detection and Classification based on CNN with LVQ Algorithm”.
- Chaowalithkhitthuk, ArthitSrikaew, KittiAttakitmongcol, PrayothKumsawat, “Plant Leaf Disease Diagnosis from Color Imagery, Using Co-Occurrence Matrix and Artificial Intelligence System “.