Documente Academic
Documente Profesional
Documente Cultură
Abstract- Images convey relevant data and information in biological detected with the help of image processing. [4]Image processing
sciences. Digital image processing and the image analysis technology plays a crucial role in the detection of plant diseases since it
have a vital role in biology and agricultural sectors. Automatic detection provides best results and reduces the human efforts.
of plant diseases and cultivation of healthy plants is of great importance
and agricultural automation.[1] The case of a plant, the term disease is The image processing could be used in the field of agriculture
defined as any impairment happening to the normal physiological for several applications. It includes detection of diseased leaf,
function , producing characteristic symptoms. The studies of plant stem or fruit, to measure the affected area by disease, to
diseases refer to studying the visually observable patterns of a particular determine the color of the affected area. Pepper cultivation is one
plant. The identification of plants, leaves, stems and finding out the pests of the most remunerative farming enterprises in India. Black
or diseases, or its percentage is found very effective in the successful pepper is the most commonly used spice in the world. Its
cultivation of crops. The naked eye observation is the approach adopted successful growth was reported in areas where the temperature
by many of the farmers for the detection and identification of plant ranges from 15-400C. The pepper plants give the better
diseases. It requires continuous monitoring and found less useful on cultivation if sufficient requirement is provided. [5,6, 7]Plant
large farms. Also, the farmers are unaware of non -native diseases. [1,2] disease is one of the main causes which degrade the quantity and
With the aid of imaging technology the plant disease detection systems quality of the product. The naked eye observation by the experts
automatically detect the symptoms that appear on the leaves and stem of is approach usually taken in identification and detection of plants.
a plant and helps in cultivating healthy plants in a farm. These systems
[4,8]This approach is time consuming in huge farms or land
monitor the plant such as leaves and stem and any variation observed
from its characteristic features, variation will be automatically identified
areas. This paper discusses the importance of image processing
and also will be informed to the user. This paper provides an evaluative techniques in detection and identification of plant diseases in the
study on the existing disease detection systems in plants. earlier stages and thereby the quality of the product could be
increased.
Keywords: Plant diseases, Image Segmentation, masking, disease LITERATURE SURVEY
detection, feature extraction
Different methodologies had been discussed by various
INTRODUCTION researchers in detecting and identifying plant diseases.Revathi et
al propossed a system to classify the Cotton Leaf Spot Diseases
The external appearance is the most important quality Using Image Processing Edge Detection Techniques. The edge
attribute of agriculture products. This outer appearance greatly detection based image segmentation had been done initially.
affects their point of - sale value and consumer’s buying Hiary and Bani –Ahamed carried out the disease detection using a
behavior. Therefore , the quality inspecting and grading systems three-fold mechanism. In this, at first, the infected region was
are essential in agricultural field to cultivate good healthy plants. identified using k-means clustering. Next extracting the features
[1] using color co-occurrence methodology and finally classification
Plant diseases cause a major production and economic losses is done by NN’s. Arivazhagan et al., proposed a four step process
in the agricultural industry. The disease management is a for classification of the disease. First a color transformation
challenging task.[3] Usually the diseases or its symptoms such as structure for the input RGB image is created then the green pixels
colored spots or streaks are seen on the leaves or stem of a plant. are masked and removed using a threshold value in the
In plants. most of the leaf diseases are caused by fungi, bacteria, segmentation process. Then compute the texture feature using
and viruses. The diseases caused due to these organisms are color co- occurrence method finally, the extracted features are
characterized by different visual symptoms that could be passed through the classifier. The image segmentation is done
observed in the leaves or stem of a plant[2,4]. Usually, these using Otsu method in “Grading Method of Leaf Spot Disease
symptoms are detected manually. With the help of image Based on Image Processing” by ShenWeizheng andWu Yachun.
processing, Automatic detection of various diseases can be The RGB image values were converted into HSI color model, and
the value of H plane are taken for the further analysis. Dhaygude interpretation. To avoid these limitations, the acquired RGB
and Kumbhar proposed the detection algorithm consists mainly images were converted into HSV format. After the conversion
four steps the RGB image are converted into HSV plane. The from RGB to HSV, the hue and saturation components are taken
masking process is done by using the values of mostly green for further analysis since these two components contain most of
colored pixels. Next useful segments are extracted out using the information. Computations from RGB to HSV are carried out
segmentation techniques from the value of SGDM matrices on a per pixel basis.
generated. Camargo and J.S. Smith describes an image processing
method that identifies visual symptoms of plant diseases by Image Segmentation
analyzing the colored images. The segmentation process is carried out in two phases,
METHODOLOGY (i)The masking process and (ii)threshold based segmentation.
The methodology adopted in this work can be subdivided into (i)Masking of green pixels
the following set of subsections as shown in the figure below. Masking of pixels means the pixel value in an image set to
zero or some other value. Since the green color indicates the
healthy region of the plant leaves, to find the diseased portion it is
better to avoid green region to increase the speed of processing.
When the intensity of the green pixels is greater than the pre-
defined value, then all those values set to zero. After masking,
pixels with zeros values are discarded. In masking process
diseased portion of the leaf is identified using the H and S plane
values and a value of “1” is allocated to the particular portion.
Rest of the regions a value of “0” is given. As a result a binary
image containing only ones and zeros is obtained. Thus the
diseased area of the leaves can be extracted out.
(ii)Threshold based Segmentation
Similarity based segmentation is adopted to segment the input
images on the basis of similarity in the intensity or gray levels in
an image. This type of threshold based method is simple but very
Fig 1. Block Diagram Representation
powerful approach for segmenting images based on an image
space region. This method was usually used for light objects in a
First the leaf set images are taken with an image acquisition dark back ground or dark objects in a light background.
module and then desired preprocessing steps starts. The images Threshold based algorithm will choose a proper threshold value T
under analysis were then segmented by using threshold based to divide image’s pixels into several classes and separate objects
methods. The segmented results were used for deciding whether from the background. A binary image simply means an image
the pepper plant under observation are healthy or not. contains only values of zeros and ones. Then the binary image is
multiplied with the original RGB color image. In this way, the
Image acquisition
infected portion of the leaf is extracted.
The test leaf images are taken using a digital camera. Then
In this work the leaf mask and the damaged area mask thus
different image processing techniques are applied to the leaf or
generated are taken for the further analysis. The Damaged Area
stem which is captured by the camera. Proper illumination should
Mask was multiplied with the resized RGB image obtained after
be provided at the time of illumination. The images of leafs and
the pre-processing step. Since the mask contains only 1’s and 0’s
stem were taken from the same distance. Image acquisition
and in the mask the diseased portion of the leaves are having the
module should be placed at a constant distance with the plant
value of 1’s. When this image is multiplied with the RGB image,
during the time of capturing the images as it affects the accuracy
only the diseased portions will come out as a result of
of the system.
multiplication.
Color Transformation
Detection of the diseased portion
The RGB images were converted into HSV color space
The segmented output image shows the portion of the leaves
representation. In the RGB model each color appears in its
affected by a particular disease. Then the total affected area can
primary spectral components of red, green and blue and this
be calculated by counting the no of pixel values in the output
model is based on a Cartesian co-ordinate system. Though RGB
image. The Leaf Mask generated is an image which exactly
model matches to the human eye in such a way as strongly
separates the leaf portion and the entire background using the
perceptive to the primary colors, this model is not well suited for
values of the Saturation plane. This Leaf Mask could be used for
describing colors in terms that are practical for human
finding the total leaf area of a particular leaf. Here a value is
calculated which is called as the Damage Ratio (DR). This ratio
is calculated by dividing the damaged area by the total leaf area.
( )
DR = ×100 %
( )
The fig 5 shows the results of the test images for a set of 16
leaves in that 10 leaves are unhealthy and 6 leaves are healthy.