Implementation of RGB and Grayscale Images in Plant Leaves Disease Detection – Comparative Study

Kora, Padmavathi; Thangadurai, K.

doi:10.17485/ijst/2016/v9i6/77739

Cited by 89 publications

(43 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…using Fuzzy C-Means. To convert RGB to binary image, firstly get the values of three primary colours which are Red, Green and Blue [14]. After that, encodes this linear intensity values using the gamma expansion.…”

Section: Resultsmentioning

confidence: 99%

Simple Screening Method of Maize Disease using Machine Learning

Afendi¹

2019

IJITEE

View full text Add to dashboard Cite

Plant leaf diseases are significant issue in agriculture field. Some of the common plant leaf diseases are powdery mildew, dark spot and rust. They are a noteworthy wellspring of an immense number of dollar worth of setbacks to farmers on a yearly premise. Plant breeders frequently need to screen countless number of plant leaves to find the stage of diseases of their crops to perform an early treatments. Therefore, a robust method for field screening is needed in order to spare the farmers and the environment as well. Inappropriate used of treatments such as impulsive pesticides can imperil the environment. Hence, this paper present a simple and efficient machine learning method which is Fuzzy C-Means algorithm to screen leaf disease severity in maize. Fuzzy C-Means is a new algorithm and very efficient to be used in object detection. Therefore, it is applicable to detect disease spot in plant leaf and measure the diseases severity. This field screening method help the farmer to identify the progression of the diseases in their crops quicker and easier than the other field screening techniques.

show abstract

Section: Resultsmentioning

confidence: 99%

Simple Screening Method of Maize Disease using Machine Learning

Afendi¹

2019

IJITEE

View full text Add to dashboard Cite

show abstract

“…According to Gupta, et al [29], the main types of imaging techniques are photometric feature-based (also called RGB), fluorescence, hyperspectral and thermal. Padmavathi and Thangadurai [30] describe an RGB image as representing three color component intensities (red, green and blue), and RGB-based methods have been broadening their applications in several areas of agronomic sciences because of their fitness to analyze color discrepancies between distinct biological samples [13,29,30].…”

Section: Rgb Imaging In Plant Pathologymentioning

confidence: 99%

Why RGB Imaging Should be Used to Analyze Fusarium Graminearum Growth and Estimate Deoxynivalenol Contamination

Cambaza

Koseki

Kawamura

2019

MPs

View full text Add to dashboard Cite

Size-based fungal growth studies are limited because they do not provide information about the mold’s state of maturity, and measurements such as radius and diameter are not practical if the fungus grows irregularly. Furthermore, the current methods used to detect diseases such as Fusarium head blight (FHB) or mycotoxin contamination are labor-intensive and time consuming. FHB is frequently detected through visual examination and the results can be subjective, depending on the skills and experience of the analyzer. For toxin determination (e.g., deoxynivalenol (DON), the best methods are expensive, not practical for routine. RGB (red, green and blue) imaging analysis is a viable alternative that is inexpensive, easy to use and seemingly better if enhanced with statistical methods. This short communication explains why RGB imaging analysis should be used instead of size-based variables as a tool to measure growth of Fusarium graminearum and DON concentration.

show abstract

“…Grey scale image is a neutral colour image that contains only brightness information and no contain other colour information. In short, grey scale image is a colour independent image that contain 8 bit/pixel allows the image to represent 0-255 different brightness colour image (Padmavathi and Thangadurai, 2016). After select the cluster image, we convert the segmented colour image of digitised maize leaf image into grey scale image.…”

Section: Grey Scale Conversationmentioning

confidence: 99%

“…Binary image is the simplest type of image and has two values, black and white or '0' and '1'. The binary image is referred to as a 1 bit/pixel image because it takes only one binary digit to represent each pixel (Padmavathi and Thangadurai, 2016). It is used to separate the pixel values of the input grey scale image into foreground (1) and background (0); each and every pixel could be compared with the calculated threshold value.…”

Section: Image Binarisationmentioning

confidence: 99%

Ethiopian Maize Diseases Recognition and Classification using: Support Vector Machine

Alehegn

2019

IJCVR

View full text Add to dashboard Cite

Currently, more than 72 maize diseases found in Ethiopia that attacked different part of maize. There are different traditional mechanisms to identify and classify maize leaf diseases by chemical analysis or visual observation. But, the traditional mechanisms have their own drawbacks take more time and require professional staff. Therefore, many researchers have been doing a lot in identifying and classifying the different types of diseases that attack maize using image processing. However, as far as the researcher's knowledge no attempt has been done for Ethiopian maize diseases dataset. In this study an attempt has been made to develop maize leaf diseases recognition and classification using both support vector machine model and image processing. To evaluate the recognition and classification accuracy from the total dataset of 800 images, 80% used for training and the remaining 20% for testing the model. Based on the experiment result using combined (texture, colour and morphology) features with support vector machine an average accuracy of 95.63% achieved.

show abstract

Implementation of RGB and Grayscale Images in Plant Leaves Disease Detection – Comparative Study

Cited by 89 publications

References 24 publications

Simple Screening Method of Maize Disease using Machine Learning

Simple Screening Method of Maize Disease using Machine Learning

Why RGB Imaging Should be Used to Analyze Fusarium Graminearum Growth and Estimate Deoxynivalenol Contamination

Ethiopian Maize Diseases Recognition and Classification using: Support Vector Machine

Contact Info

Product

Resources

About