Printer Friendly

Disease identification in mango leaf using image processing.


A large variety of fruits are grown in India of which Pomegranate, apple, banana, grape, mango, are the major ones. Also, India is a large low cost producer of fruit and horticulture has huge export potential. Many farmers are depending on the fruits like Pomegranate, mango, and grape are because of suitable climate condition and soil. Fruit diseases are one of the crucial causes that reduces quantity and degrades quality of the agricultural products. plant diseases are because of environment change, water availability, temperature and many more. The ability of disease analysis in earlier stage is an important task.

Monitoring of health and disease on plant plays an important role in successful cultivation of crops in the farm. In early days, the monitoring and analysis of plant diseases were done manually by the expertise person in that field. Hence an smart resolution support system for control of fruit diseases is needed, with use some high-tech and practical technology to properly descend identify the flower, fruit, leaf diseases. The introduction to image processing technique used for mango disease detection, [11].

Segmentation has various method of image processing for plant disease detection. Common diseases of mango include gall midge infestation, black mildew hopper attack, mango malformation disease, pulp weevil, stem mioisonous chemicals to eradicate the disease in order to retain the crop yield. This problem can be solved by automating the monitoring process by use of advanced image processing techniques. The steps involved in disease detection are Digital image acquisition, Image pre-processing like noise removal, Color transformation, and histogram equalization, k-means Segmentation, anthracnose, alternaria leaf spots etc. These diseases are occurring due to the insects, bacterial, fungal and viral infection and these diseases affect the crop yield by infecting the leaves, flowers, fruits and stem. Infection in leaf causes the photosynthesis to be blocked and in due course of time it causes the plant to die. Identification of diseases or deficiency is usually carried out by farmers by frequent monitoring of the plant leaves, flowers, fruits or stem. For small scale farmers, early identification of disease is very much possible and able to control the insects by organic pesticides or by the use of minimal amount of chemical pesticides. For large scale farmers frequent monitoring and early identification of disease is not possible and it results in a severe outbreak of the disease and pest growth which cannot be controlled by organic means. In this situation farmers are forced to use the p, Feature extraction, and classification using the support vector machine algorithm which is a supervised learning algorithm. Leaf shape based disease identification are done in spatial and in frequency domain image processing. In case of the spatial domain image processing, basic geometric features of leaf such as diameter, area, perimeter, physiological length, width, etc. are identified. Based on these geometric features, digital morphological features such as rectangularity, circularity, etc. are calculated for identifying the diseased leaf. In this paper leaf based image processing is used to identify the disease and provide the control solution. [4].

I. Mango diseases Mangoes are affected by the following disease,

i. bacterial diseases

ii. fungal diseases

iii. insect infection

iv. other diseases and disorder

A. Bacterial Disease:

Bacterial diseases include any type of illness caused by bacteria. Bacteria are a type of microorganism, which are tiny forms of life that can only be seen with a microscope. The bacterial diseases affected in mango leaf named as Bacterial Canker (Xanthomonas mangiferae).This diseases symptoms are leaves, minute water soaked irregular to angular raised lesions is usually crowded at the apex as shown in figure 2.1. On young leaves halos are larger and distinct, while on older leaves, they are narrow could be observed only against light. Under severe infections, the leaf turns yellow and drop off. The diseases controlled by regular inspection of orchards, sanitation and seedling certification are recommended as retentive measures against the disease. Spray of copper based fungicides has been found effective in controlling bacterial canker.

B. Fungal Disease:

Fungi are important decomposers in all ecosystems because they can break down a wide variety of organic matter. The of fungus diseases affected in mango leaf named as Anthracnose (Colletotrichum gloeosporioides) as shown in figure 2.2. This disease symptoms is more common on young fruits and during transit and storage. Latent infection during pre-harvest stage is responsible for post harvest rots. On storage, black spots are produced. Initially the spots are round but later form large irregular blotches on the entire fruits the spots have large deep cracks and the fungus penetrates deep into the fruit causing extensive rotting. The diseases can be controlled by the following methods.

i. Pre-harvest infections can be managed by spraying copper based fungicides after completion of heavy showers.

ii. Post harvest infections can be managed as pre harvest sprays in the field to reduce the latent infection and treatment of the fruit with hot water/ fungicides after harvest to eradicate left over latent infection.

III. Image Processing Of Mango Leaf:

In this paper, mango disease are identified by using image processing technology. This process involved in the image processing are image acquisition, image pre-processing, image segmentation, feature extraction and disease identification as shown in figure 3.1.

A. Image acquisition:

The diseased leaf image is acquired using the digital camera ,the image is acquired from a certain uniform distance with sufficient lighting. The image background should provide a proper contrast to the leaf color. In this paper, mango leaf image with different disease based image dataset is prepared with both black and white background, based on the comparative study black background image provides better results and hence it is used for the disease identification of mango leaf.

B. Image pre-processing:

Pre-processing is a common name for operations with image at the lowest level of both input and output are intensity images. pre-processing is an improvement of the image data that suppresses unwanted distortions. Image acquired using the digital camera is pre-processed using the noise removal with averaging filter, color transformation and histogram equalization. Histogram based methods are very efficient compared to other image segmentation methods because they typically require only one pass through the pixels. In this technique, a histogram is computed from all of the pixels in the image ,and the peaks and valleys in the histogram are used to locate the clusters in the image.

C. RGB -to-HSV color conversion:

The HSV (ie. Hue, saturation, value)color model is often used by graphics designers, in addition to other well-known color models such as RGB(Red ,Green, Blue) and CMYK(Cyan, Magenta, Yellow, Black).Below is a simple RGB to HSV color converter function. Input the RGB values (in the range 0 to 255) and convert to HSV as shown in the figure 3.2.1.

D. H-Hue:

Hue is the term for the pure spectrum colors commonly referred to by the color are red, orange, yellow, blue, green violet. Which appear in the circle or rainbow.

Hue refers to the dominant color attribute as shown in figure 3.2.2 in the same way as perceived by a human observer.

E. S-Saturation:

Saturation is the strength or purity of the color and represents the amount of gray in proportion to the hue. A saturated color is pure and an unsaturated color has a large percentage of gray. Saturation refers to the amount of brightness or white light added to the hue as shown in the figure 3.2.3

F. V-Value:

In image processing normalization is a process that changes the range pixel intensity values. application include photographs with poor contrast due to glare, for example. Normalization is sometimes called contrast stretching or histogram stretching. Intensity refers to the amplitude of light. Figure 3.2.4 shows the V--image of the mango leaf.

IV. Segmentation:

Image segmentation is the process of partitioning digital image into multiple segments for easy analysis. In this paper image segmentation done by k-means algorithm. k-means is a least-squares partitioning method that divide a collection of objects into k groups. The algorithm iterates over two steps:

i. mean

ii. cluster

There are different image segmentation techniques like threshold based, edge based, cluster based and neural network based. One of the most efficient methods is the clustering method which again has multiple subtypes, k-means clustering, Fuzzy C-means clustering, subtractive clustering method etc. One of most used clustering algorithm is k-means clustering as shown in figure 3.3.1,2,3.

A. Clustering:

A cluster is therefore a collection of objects which are "similar" between them and are "dissimilar" to the objects belonging to other clusters.

B. k-clustering:

The k-means algorithm is an iterative technique that is used to partition an image into k cluster . The basic algorithm steps are

1. pick k cluster centers, either randomly or based on some heuristic method.

2. Assign each pixel in the image to the cluster that minimizes the distance between the pixel and the cluster center

3. re-compute the cluster centers by averaging all of the pixels in the cluster.

4. repeat steps 2 and 3 until convergence is attained (i.e. no pixels change clusters).K--means clustering is the faster when compared to other cluster and also n number of variables can be added. And it gives the result for different number of number of cluster and initial centroid values. So the proper number of number of cluster k and proper initial centroid are required for initialization.

V. Feature extraction:

Feature extraction starts from an initial set of measured data and builds derived value (features) intended to be information and non-redundant, facilitating the subsequent learning and generalization steps, and in some cases leading to better human. There are many feature extraction techniques implemented, such as the texture features based on gray-level co-occurrence matrix (GLCM) and spatial gray-level dependence matrices ((SGDM),texture features are Contrast, energy, local homogeneity, cluster shade and prominence are used ass features as shown in figure 3.4.1,2.


In this paper 70 disease mango leaf images are collected with each disease such as leaf samples are kept as a dataset. The RGB image and provides the classification accuracy with different number of training samples in image processing and Mat lab and the different types of clustering inputs, clustering of the original diseased leaf RGB image and clustering of the Hue part of the RGB to HSI color space converted image.. Result shows that the usage of HSI color space converted image provides a better result than the RGB image.

VII Symptoms and control of the mango disease:

The mango diseases are Alternaria leaf spot, black mildew hopper attack, gall midge infestation, stem miner, mango malformation these diseases mostly affect the mango leaf. Alternaria_leaf_spots ('Disease medical name:Alternaria alternata') Symptoms in mango is first it appear as small, brownish circular spots on the surface of leaves. Later on, high concentration of brown black spots occurs evenly over the leaf lamina. Symptoms are more prominent on the lower side of the leaves. The tender leaves are found to be more susceptible than mature ones. And Diseases control procedure are To avoid this disease is noticed on leaves, leaf stalks, stems, twigs, branches and fruits, initially producing water soaked lesions, later turning into typical canker On leaves. black mildew hopper attack Disease medical name: Oidium mangiferae .The symptoms can be noticed on the inflorescence, stalk of inflorescence, leaves and young fruits. The characteristics symptoms of disease are white superficial powdery growth of the fungus on these parts. And disease control procedure Pruning of diseased leaves and malformed panicles reduces primary inoculums. Three sprays of systemic fungicides during flowering season are recommended at 12-15 days intervals. 1st spray is recommended when there is 25% flowers opening.


The accurately detection and classification of the plant disease is very important for the successful cultivation of crop and getting good yield. This can be done using image processing technique. The type of disease is identified and possible control solution is recommended to the farmers. This paper can be developed as an expert system in a hand held device in the form of Android app or in the form of a low cost application specific board. From this method various plant disease are accurately identified and classified using image processing technique.


[1.] Manish Bhange, H.A. HingoliWala, 2015. "Smart Farming: Pomegranate Disease Using Image processing", Second International Symposium on computer Vision and the Internet (VisionNet'15).

[2.] Gaikwad, D.S., K.J. Karande, 2016. "Image Processing Approach for Grading And Identification of Diseases on pomegranate Fruit", International Journal of computer Science and Information Technologies,(IJCSIT) ISSN:0975-9646 7(2).

[3.] Vijai Singh, A.K. Misra, 2016. "Detection of plant leaf diseases using image Segmentation and soft computing techniques ".

[4.] Jayaprakash Sethupathy, Veni S, 2016." OpenCV Based Disease Identification of Mango Leaves", International journal of engineering and Technology, (IJET) ISSN:0975-4024, 8: 2016.

[5.] Muhammad Tariq Malik, Muhammad Ammar, "Mango Diseases And Their Management", Mango Research Institute, Multan.

[6.] Payne, A.B., K.B. Walsh, P.P. Subedi, 201. "Estimation of mango crop Yield using image analysis Segmentation method", Computer and electronics in Agriculture.

[7.] Ashwani Kumar, Rushikesh Borse, 201. "Image Processing For Smart Farming: Detection of Diseases and Fruit Grading," IEEE ICIIP, pp: 521-526.

[8.] Ghaiwat Savita, N, Arora Parul, Detection and classification of plant leaf diseases using image processing techniques.

[9.] Thangadurai, Dr.K., K. Padmavathi, 2014. "Computer Visionimage Enhancement For Plant Leaves Disease Detection", World Congress on Computing and Communication Technologies.

[10.] Monica Jhuria, Ashwani Kumar, and Rushikesh Borse, 2013. "Image Processing For Smart Farming: Detection Of Disease And Fruit Grading", Proceedings of the 2013 IEEE Second International Conference on Image Information Processing.

[11.] Patil, A.B., Sachin, D. Khirade, 2015. "Plant Disease detection using image processing", International Conference on computing communication control and automation.

(1) S. Sujatha, (2) N. Saravanan, (3) R. Sona

(1) hod/Eie/Adhiyamaan College Of Engineering

(2,3) ug Student/Eie/Adhiyamaan College Of Engineering

Received 28 January 2017; Accepted 22 March 2017; Available online 28 April 2017

Address For Correspondence:

S. Sujatha, hod/Eie/Adhiyamaan College Of Engineering

Caption: Fig. 2.1: Bacterial disease affected mango leaf.

Caption: Fig. 2.2: Fungus affected Mango leaf

Caption: Fig. 3.1: Block Diagram

Caption: Fig. 3.2.1: RGB to HSV Image

Caption: Fig. 3.2.2: H Image

Caption: Fig. 3.2.3: S Image

Caption: Fig. 3.2.4: V Image

Caption: Fig. 3.3.1: Object in cluster 1

Caption: Fig. 3.3.2: Object in cluster 2

Caption: Fig. 3.3.3: Object in cluster 3

Caption: Fig. 3.4.1: Maximum disease affected area

Caption: Fig. 3.4.2: Defective plant detection
COPYRIGHT 2017 American-Eurasian Network for Scientific Information
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 2017 Gale, Cengage Learning. All rights reserved.

Article Details
Printer friendly Cite/link Email Feedback
Author:Sujatha, S.; Saravanan, N.; Sona, R.
Publication:Advances in Natural and Applied Sciences
Article Type:Technical report
Geographic Code:9INDI
Date:Apr 30, 2017
Previous Article:A novel design of luo boost converter by using voltage super lift technique for solar energy.
Next Article:IOT based design and implementation of affordable home appliance control.

Terms of use | Privacy policy | Copyright © 2021 Farlex, Inc. | Feedback | For webmasters |