Segmentation of Crop Disease Images with an Improved K-means Clustering Algorithm

2018 ◽  
Vol 34 (2) ◽  
pp. 277-289 ◽  
Author(s):  
Zhibin Wang ◽  
Kaiyi Wang ◽  
Shouhui Pan ◽  
Yanyun Han
Keyword(s):  
Clustering Algorithm ◽  
Color Space ◽  
Entropy Method ◽  
Adaptive Segmentation ◽  
Segmentation Method ◽  
Threshold Method ◽  
Initial Cluster ◽  
Crop Disease ◽  
Color Clustering ◽  
Spot Image

Abstract. Disease spot segmentation from crop leaf images is a key prerequisite for disease early warning and diagnosis. To improve the accuracy and stability of disease spot segmentation, an adaptive segmentation method for crop disease images based on K-means clustering is proposed. The approach is based on three stages. First, the excess green feature and the a* component of the CIE (L*a*b*) color space were combined to adaptively learn the initial cluster centers. Second, iterative color clustering of two clusters was conducted using the squared Euclidian distance as the similarity distance. Finally, the distance of a* components between two clusters as the clustering criterion function was used to correct the clustering results. To verify the effectiveness of the proposed method, segmentation experiments were performed on images of three kinds of cucumber diseases and one kind of soybean disease. The results of the experiments were compared with the results obtained using a fixed threshold method, the Otsu method, the traditional K-means clustering method, and the Renyi entropy method, which showed that our adaptive segmentation method was accurate and robust for segmentation of crop disease images. Keywords: Adaptive, CIE L*a*b*, Disease spot, Image segmentation, K-means clustering.

Research on the Segmentation Method of Rice Leaf Disease Image

2012 ◽  
Vol 220-223 ◽  
pp. 1339-1344 ◽  
Author(s):  
Li Bo Liu
Keyword(s):  
Clustering Algorithm ◽  
Segmentation Method ◽  
Threshold Method ◽  
Fuzzy C Means ◽  
Rice Leaf ◽  
Leaf Disease ◽  
Otsu Method ◽  
Rice Disease ◽  
Fuzzy C Means Clustering ◽  
Iterative Threshold

In Order to Improve the Segmentation Effect of the Rice Leaf Disease Images, we Take Optimal Iterative Threshold Method,OTSU Method and Fuzzy C-means Clustering Algorithm to Make Adaptive Segmentation of Rice Disease Images which Were Collected under Different Circumstances. through Comparative Analysis, Experimental Results Show that: Three Methods All Can Effective Separate Spot from the Leaves; in Comparison, the Effect of the Fuzzy C-means Clustering Algorithm Is the Best, but the Number of Iterations Is too many and the Time Spent on it Is the Most; the Effect of OTSU Method Is Lesser, Optimal Iterative Threshold Method Is the Worst. Comprehensive Considering the Segmentation Accuracy and Efficiency, the Paper Chooses OTSU as the Segmentation Method of the Rice Leaf Disease Images.

scholarly journals Automatic measurement of traditional Chinese costume from its silhouette through Fuzzy c-means clustering method

2020 ◽  
Vol 15 ◽  
pp. 155892502097832
Author(s):  
Jiaqin Zhang ◽  
Jingan Wang ◽  
Le Xing ◽  
Hui’e Liang
Keyword(s):  
Industrial Application ◽  
Clustering Algorithm ◽  
Color Space ◽  
Automatic Measurement ◽  
Feature Point ◽  
Feature Points ◽  
Point Location ◽  
Fuzzy C Means ◽  
Fuzzy C Means Clustering ◽  
Environmental Robustness

As the precious cultural heritage of the Chinese nation, traditional costumes are in urgent need of scientific research and protection. In particular, there are scanty studies on costume silhouettes, due to the reasons of the need for cultural relic protection, and the strong subjectivity of manual measurement, which limit the accuracy of quantitative research. This paper presents an automatic measurement method for traditional Chinese costume dimensions based on fuzzy C-means clustering and silhouette feature point location. The method is consisted of six steps: (1) costume image acquisition; (2) costume image preprocessing; (3) color space transformation; (4) object clustering segmentation; (5) costume silhouette feature point location; and (6) costume measurement. First, the relative total variation model was used to obtain the environmental robustness and costume color adaptability. Second, the FCM clustering algorithm was used to implement image segmentation to extract the outer silhouette of the costume. Finally, automatic measurement of costume silhouette was achieved by locating its feature points. The experimental results demonstrated that the proposed method could effectively segment the outer silhouette of a costume image and locate the feature points of the silhouette. The measurement accuracy could meet the requirements of industrial application, thus providing the dual value of costume culture research and industrial application.

An Image Segmentation Method Based on Adaptability Threshold

2013 ◽  
Vol 734-737 ◽  
pp. 2912-2916
Author(s):  
Hui Li ◽  
Ping He
Keyword(s):  
Image Segmentation ◽  
Strain Measurement ◽  
Maximum Entropy Method ◽  
Entropy Method ◽  
Important Application ◽  
Original Image ◽  
Segmentation Method ◽  
One Dimensional ◽  
The One ◽  
Application Fields

Automation strain measurement of the sheet metal deforming becomes one of the important application fields of computer vision. The algorithm of image segmentation based on adaptability threshold was presented for image segmentation of metal steel. In order to validate the proposed method, it is tested and compared with Ostu method and the one-dimensional maximum entropy method. Experiment results indicate that the method is simple and effective, and has an advantage of reservation of the main features of the original image.

scholarly journals Aplikasi Machine Vision pada Hexacopter untuk Deteksi Survival Kits di Bidang Mitigasi Bencana

2020 ◽  
Vol 12 (2) ◽  
pp. 72-79
Author(s):  
Ismawan Noor Ikhsan ◽  
Son Ali Akbar
Keyword(s):  
Machine Vision ◽  
Color Space ◽  
Region Of Interest ◽  
Contour Detection ◽  
Segmentation Method ◽  
Smart System ◽  
Hsv Color Space ◽  
Aerial Vehicle ◽  
Detection Evaluation ◽  
Flying Robots

Hexacopter belongs to one of flying robots that is used to carry out a special mission such as retrieving and delivering survival kits object. Thus, it should be built by smart system to determine the object accurately. However, there was an interference from other object that made it difficult to recognize the survival kits object. Therefore, the development of machine vision with the integration of the hexacopter control system is expected to improve the object recognition process. This study intends to develop a survival kit detection using the image processing method, which involved 1) segmentation on the Hue, Saturation, Value (HSV) color space, 2) contour detection, and 3) Region of Interest (ROI) selected detection. The evaluation of the segmentation method performances was done through the three-part experiments (i.e., the similar shape, variety of a color object, and an object shape). The result of survival kits object detection evaluation obtained an accuracy of 90.33%, precision of 99.63%, and recall of 91.24%. According to the performances obtained in this study, the development of machine vision systems on Unmanned Aerial Vehicle (UAV) has a high accuracy for the object survival kits detection even with another object interference.

scholarly journals Hybrid K Mean Clustering Algorithm for Crop Production Analysis in Agriculture

2019 ◽  
Vol 9 (2S) ◽  
pp. 9-13
Keyword(s):  
Cluster Analysis ◽  
Precision Agriculture ◽  
Crop Production ◽  
Clustering Algorithm ◽  
Research Work ◽  
K Value ◽  
Clustering Technique ◽  
Production Analysis ◽  
Initial Cluster ◽  
The Stability

The proposed research work aims to perform the cluster analysis in the field of Precision Agriculture. The k-means technique is implemented to cluster the agriculture data. Selecting K value plays a major role in k-mean algorithm. Different techniques are used to identify the number of cluster value (k-value). Identification of suitable initial centroid has an important role in k-means algorithm. In general it will be selected randomly. In the proposed work to get the stability in the result Hybrid K-Mean clustering is used to identify the initial centroids. Since initial cluster centers are well defined Hybrid K-Means acts as a stable clustering technique.

scholarly journals Research on the Method of Coke Optical Tissue Segmentation Based on Adaptive Clustering

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Huaiguang Liu ◽  
Liheng Zhang ◽  
Shiyang Zhou ◽  
Li Fang
Keyword(s):  
Mahalanobis Distance ◽  
Euclidean Distance ◽  
Clustering Algorithm ◽  
Adaptive Threshold ◽  
Segmentation Method ◽  
Tissue Segmentation ◽  
Adaptive Clustering ◽  
Morphological Filtering ◽  
Key Factor ◽  
The Relationship

The microstructure is the key factor for quality discriminate of coke. In view of the characteristics of coke optical tissue (COT), a segmentation method of coke microstructures based on adaptive clustering was proposed. According to the strategy of multiresolution, adaptive threshold binarization and morphological filtering were carried out on COT images with lower resolution. The contour of the COT body was detected through the relationship checking between contours in the binary image, and hence, COT pixels were picked out to cluster for tissue segmentation. In order to get the optimum segmentation for each tissue, an advanced K -means method with adaptive clustering centers was provided according to the Calinski-Harabasz score. Meanwhile, Euclidean distance was substituted with Mahalanobis distance between each pixel in HSV space to improve the accuracy. The experimental results show that compared with the traditional K -means algorithm, FCM algorithm, and Meanshift algorithm, the adaptive clustering algorithm proposed in this paper is more accurate in the segmentation of various tissue components in COT images, and the accuracy of tissue segmentation reaches 94.3500%.

A Method to Enhance the Fog Image Based on Dark Object Subtraction

2014 ◽  
Vol 543-547 ◽  
pp. 2484-2487
Author(s):  
Jing Zhang ◽  
Wei Dong ◽  
Jian Xin Wang ◽  
Xu Ning Liu
Keyword(s):  
Dynamic Range ◽  
Color Space ◽  
Threshold Value ◽  
Entropy Method ◽  
Image Contrast ◽  
Dark Object ◽  
Image Contrast Enhancement ◽  
Degraded Image ◽  
Enhancement Method ◽  
Rgb Color Space

Aiming at the problem of poor image contrast and low visibility, a single image contrast enhancement method is put forward in this paper. The method is based on Dark-object subtraction technique, translating the fog degraded image from RGB color space to YIQ color space, and taking out the Y component. Then using the maximum entropy method to get the threshold value of image segmentation, we can put different portion of the image according to the different formula for image restoration. The processed image must be converted from YIQ color space to RGB color space In the back of the steps. Finally, the image needs a linear dynamic range adjustment to enhance the contrast and brightness. Experiments show that the method can effectively remove haze effect on the image. The dehazing effect of the processed image is obvious. The image becomes clear and bright, and the details is outstanding, which is convenient for observation and analysis.

Sign in / Sign up

Export Citation Format

Share Document