Digitalimageprocessingtechniquesfordetecting,quantifying资源-CSDN文库

需积分: 14 49 浏览量 2018-07-31 09:44:03 上传评论收藏 367KB PDF 举报

资源推荐

资源详情

资源评论

a SpringerOpen Journal

Barbedo SpringerPlus 2013, 2:660

http://www.springerplus.com/content/2/1/660

REVIEW Open Access

Digital image processing techniques for

detecting, quantifying and classifying plant

diseases

Jayme Garcia Arnal Barbedo

Abstract

This paper presents a survey on methods that use digital image processing techniques to detect, quantify and classify

plant diseases from digital images in the visible spectrum. Although disease symptoms can manifest in any part of the

plant, only methods that explore visible symptoms in leaves and stems were considered. This was done for two main

reasons: to limit the length of the paper and because methods dealing with roots, seeds and fruits have some

peculiarities that would warrant a specific survey. The selected proposals are divided into three classes according to

their objective: detection, severity quantification, and classification. Each of those classes, in turn, are subdivided

according to the main technical solution used in the algorithm. This paper is expected to be useful to researchers

working both on vegetable pathology and pattern recognition, providing a comprehensive and accessible overview

of this important field of research.

Introduction

Agriculture has become much more than simply a means

to feed ever growing populations. Plants have become

an important source of energy, and are a fundamental

piece in the puzzle to solve the problem of global warm-

ing . There are several diseases that affect plants w ith the

potential to cause devastating economical, social and eco-

logical losses. In this context, diagnosing diseases in an

accurate and timely way is of the utmost importance.

Thereareseveralwaystodetectplantpathologies.Some

disea ses do not have any visible symptoms associated,

or those appear only when it is too late to act. In those

cases, normally some kind of sophisticated analysis, usu-

ally by means of p owerful microscop es, is necessary. In

other cases, the signs can only be detected in parts of the

electromagnetic spectrum that are not visible to humans.

A common approach in this case is the use of remote

sensing techniques that explore multi and hyperspectral

image captures. The methods that adopt this approach

often employ digital image processing tools to achieve

their goals. However, due to their many p eculiarities and

to the extent of the literature on the subject, they will not

be treated in this paper. A large amount of information

Correspondence: jayme.barbedo@embrapa.br

Embrapa Agricultural Informatics, Campinas, SP, Brazil

on the subject can be found in the papers by Bock et al.

(2010), Mahlein et al. (2012) and Sankaran et al. (2010).

Most diseases, however, generate some kind of manifes-

tation in the visible spectrum. In the va st majority of the

cases , the diagnosis , or at least a first guess about the dis-

ease, is performed visually by humans. Trained raters may

be efficient in recognizing and quantifying diseases, how-

ever they have asso ciated some disadvantages that may

harm the efforts in many cases. Bock et al. (2010) list some

of those disadvantages:

•

Raters may tire and lose concentration, t hus

decreasing their accuracy.

•

There can be substantial inter- and intra-rater

variability (subjectivity).

•

There is a need to develop standard area diagrams to

aide assessment.

•

Training may need to be repeated to maintain

quality. Raters are expensive.

•

Visual rating can be destructive if samples are

collected in the field for assessment later in the

laboratory.

•

Raters are prone to various illusions (for example,

lesion number/size and area infected).

2013

Barbedo; licensee Springer. This is an Open Access article distributed under the terms of the Creative Commons

Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction

in any medium, provided the original work is properly cited.

Barbedo SpringerPlus 2013, 2:660 Page 2 of 12

http://www.springerplus.com/content/2/1/660

Be sides those disadvantages, it is important to consider

that some crops may extend for extremely large areas,

making monitoring a challenging task.

Depending on the application, many of those problems

may be solved, or at least reduced, by the use of digi-

tal images combined with some kind of image pro cessing

and, in some cases, pattern recognition and automatic

classific ation tools. Many systems have been proposed in

the last three decades, and this paper tries to organize

and present those in a meaningful and useful way, a s will

be seen in the next sec tion. Some critical remarks about

the directions taken by the researches on this subject are

presented in the concluding section.

Literature review

Vegetable pathologies may manifest in different par ts

of the plant. There are me thods exploring visual cues

present in almost all of those parts, like roots (Smith

and Dickson 1991), kernels (Ahmad et al. 1999), fruits

(Aleixos et al. 2002; Corkidi et al. 2005; López-García et al.

2010), stems and leaves. As commented before, this work

concentrates in the latter two, particularly leaves.

This section is divided into three subsections accord-

ing to the main purpose of the propo sed methods. The

subsections, in turn, are divided according to the main

technical solution employed in the algorithm. A sum-

marizing table containing infor mation about the cultures

considered and technical solutions adopted by each work

is presented in the concluding section.

Some characteristics are shared by most methods pre-

sented in this section: the images are captured using

consumer-level cameras in a controlled laboratory envi-

ronment, and the format used for the images is RGB

quantized with 8 bits. Therefore, unless stated otherwise,

those are the conditions under which the described meth-

ods operate. Also, vir tually all methods cited in this paper

apply some kind of preprocessing to clean up the images,

thus this information will be omitted from now on, unless

some peculiarity warrants more detailing.

Detection

Because the information gathered by applying image pro-

cessing techniques often allows not only dete cting the

disea se, but also estimating its severity, there are not many

methods focused only in the detection problem. There are

two main situations in which simple detection applies:

•

Partial classification: when a disease has to be

identified amidst several possible pathologies, it may

be convenient to perform a partial classification, in

which candidate regions are classified as being the

result of the disease of interest or not, instead of

applying a complete classification into any of the

possible diseases. This is the case of the method by

Abdullah et al. (2007), which is described in

Section ‘Neural networks’.

•

Real-time monitoring: in this case, the system

continuously monitor the crops, and issues an alarm

as soon as the disease of interest is detected in any of

the plants. The papers by Sena Jr et al. (2003) and

Story et al. (2010) fit into this context. Both proposals

are also described in the following.

Neural networks

The method proposed by Abdullah et al. (2007) tries

to discriminate a given diseas e (corynespora)fromother

pathologies that affect rubber tree leaves. The algorithm

does not employ any kind of segmentation. Instead, Prin-

cipal Component Analysis is applied directly to the RGB

values of the pixels of a low resolution (15 × 15 pixels)

image of the leaves. The first two principal components

are then fed to a Multilayer Perceptron (MLP) Neural

Network with one hidden layer, whose output reveals if

thesampleisinfectedbythediseaseofinterestornot.

Thresholding

The method proposed by S ena Jr et al. (2003) aims

to discriminate between maize plants affected by fall

armyworm from healthy ones using digit al images. They

divided their algorithm into two main stages: image pro-

cessing and image analysis. In the image processing stage,

the image is transformed to a grey sc ale, thresholded and

filtered to remove spurious artifac ts. In the image anal-

ysis stage, the whole image i s divided into 12 blocks.

Blocks whose leaf area is less than 5% of the total area

are discarded. For each remaining block, the number of

connected objects, representing the diseased regions, is

counted. The plant is considered diseased if this number is

above a threshold, which, after empirical evaluation, was

set to ten.

Dual-segmented regression analysis

Story et al. (2010) proposed a method for monitoring and

early detection of c alcium deficiency in lettuce. The first

step of the algorithm is the plant segmentation by thresh-

olding, so the c anopy region is isolated. The outlines of the

region of interest are applied back to the original image,

in such a way only the area of interest is considered. From

that, a number of color features (RGB and HSL) and tex-

ture features (from the gray-level co-occurrence matrix)

are extracted. After that, the separation point identify-

ing the onset of stress due to the calcium deficiency is

calculated by identifying the me an difference between

the treatment and control containers at each measured

time for all features. Dual-segmented regression analy-

sis is performed to identify where in time a change point

was present between the nutrient-deficit group of plants

and the healthy group of plants. The authors concluded

Barbedo SpringerPlus 2013, 2:660 Page 3 of 12

http://www.springerplus.com/content/2/1/660

arguing that their system can be used to monitor plants

in greenhouse s dur ing the night, but more research is

nee ded for its use during the day, when lighting conditions

vary more intensely.

Quantification

The methods presented in this section aim to quantify the

severity of a given disease. Such a severity may be inferred

either by the area of the leaves that are affected by the

disease, or by how deeply rooted is the affection, which

can be estimated by means of color and texture features.

Most quantification algorithms include a segmentation

step to isolate the symptoms, f rom which features can be

extracted and properly processed in order to provide an

estimate for the severity of the disease.

It is worth noting that the problem of determining the

severity of a disease by analyzing and measuring its symp-

toms is dif ficult even if performed manually by one or

more specialists, which have to pair the diagnosis guide-

lines with the symptoms as accurately as possible. As

a result, the manual measurements will always contain

some degree of subjectivity, which in turn means that ref-

erences used to validate the automatic methods are not

exactly “ground truth ”. It is important to take this into

consideration when assessing the performance of those

methods.

The methods presented in the following are grouped

according to the main strategies they employ to estimate

the se verity of the diseas es.

Thresholding

One of the first methods to us e digital image processing

was proposed by Lindow and Webb (1983). The images

were captured using an analog video camera, under a red

light illumination to highlight the necrotic areas. Those

images were later digitized and stored in a computer. The

tests were per formed using leaves from tomatoes, bracken

fern, sycamore and California buckeye. The identification

of the necrotic regions is done by a simple thresholding.

The algorithm then apply a correction factor to compen-

sate for pixel variations in the healthy parts of the leaves,

so at least s ome of the pixels from healthy regions that

were misclassified a s part of the diseased areas can be

reassigned to the correct set.

Price et al. (1993) compared visual and digital image-

processing methods in quantifying the severity of coffee

leaf rust. They tested two different imaging systems. In the

first one, the image s were captured by a black and white

charge coupled device (CCD) camera , and in the second

one, the images were captured with a color CCD cam-

era. In both cases, the segmentation was performed by a

simple thresholding. According to the authors, the image

processing-based systems had better performance than

visual evaluations, e specially for ca ses with more severe

symptoms. They also observed that the color imaging had

greater potential in discriminating betwe en rusted and

non-rusted foliage.

The method proposed by Tucker and Chakraborty

(1997) aims to quantify and identify diseas es in sunflower

and oat leaves. The first step of the algorithm is a seg-

mentation whose threshold varies according to the disease

being considered (blight or rust). The resulting pixels are

connected into clusters representing the diseas ed regions.

Depending on the characteristics of the lesions, they are

classified into the appropriate category (type a or b in case

of blight and by size in case of rust). The authors reported

goo d results, but observed some errors due to inappropri-

ate illumination during the capture of the images.

Martin and Rybicki (1998) proposed a method to quan-

tify the sy mptoms caused by the maize streak virus. The

thresholding scheme adopted by the authors was based on

the strateg y des cribed by Lindow and Webb (1983) and

briefly explained in the previous paragraph. The authors

compared the results obtained by visual assessment, by

using a commercial software package and by employing

a custom system implemented by themselves. They con-

cluded that the commercial and custom software packages

had approximately the same performance, and that both

computer-based methods achieved better accuracy a nd

precision than the visual approach.

The method proposed by Skaloudova et al. (2006) mea-

sures the damage caused in leaves by spider mites. The

algorithm is based on a two-stage thresholding. The first

stage discriminates the leaf from the background, and the

second stage separates damaged regions from healthy sur-

face. The final estimate is given by the ratio betwe en the

number of pixels in damage regions divided by the total

number of pixels of the leaf. The authors compared the

results with two other methods based on the leaf dam-

age index and chlorophyll fluorescence. The y concluded

that their method and the leaf damage index provided

superior results when compared with the chlorophyll

fluore scence.

In their work, Weizheng et al. (2008) presented a strat-

eg y to quantify lesions in soybe an leaves. The algorithm is

basically composed by a two-step thresholding. The first

threshold aims to separate leaf from background. After

that, the image containing only the leaf is converted to the

HSI color space, and the Sobel operator is applied to iden-

tify the lesion edges. A second threshold is applied to the

resulting Sobel gradient image. Finally, small objects in the

binary image are disc arded and holes enclo sed by white

pixels are filled. The resulting objec ts reveal the diseased

regions.

Camargo and Smith (2009a) proposed a method to

identify reg ions of leaves containing lesions caused by

disea ses. The tests were performed using leaves from a

variety of plants, like bananas , maize, alfalfa, cotton and

剩余11页未读，继续阅读

评论收藏

内容反馈

qq_39790565

粉丝: 0
资源: 1

Digital image processing techniques for detecting, quantifying

Digital image processing

Digital_image_processing

Digital_image_processing.rar_消噪 图像

digital_image_processing.rar_Digital Gradient

Digital-image-processing.zip_图形图像处理_Others_

Machine Learning for OpenCV_Intelligent image processing with Python(2017).epub

Fast radial symmetry for detecting points of interest论文的代码

Exposing digital forgeries by detecting inconsistencies in lighting

Fast Radial Symmetry forDetecting Points of Interest

Digital-image-processing.rar_processing_图像合成

Digital-image-processing.rar_image processing_pre

Digital-image-processing.rar_图形图像处理_matlab_

The-experiment-of-Digital-image-processing:NJU原理编译器

Digital_Image_Processing.zip_image_processing

A new generalized CUSUM control chart for detecting a range of mean shifts

Theory and Applications of Image Registration

3D GAN for Detecting Temporal Irregularities in Videos

Machine Learning for OpenCV_ Intelligent image processing with Python.pdf

TextSnake - A Flexible Representation for Detecting Text of Arbitrary Shapes.pdf

Digital image processing(2rd edition)-Gonzales-part 3

Digital-image-processing.zip_4 3 2 1

Lab 3_ Digital imagery and image processing.docx

Digital-image-processing.rar_human

Digital-image-.rar_image processing_processing

Spatially Conditioned Graphs for Detecting Human-Object.pdf

Detecting and Classifying Low Probability of Intercept Radar

a copy detection mechanism for digital documents

Evaluation of Open-Source IDE Plugins for Detecting Security Vul

Evaluation of Open-Source IDE Plugins for Detecting Security Vu

最新资源

Digital_image_processing.rar_消噪图像