Segmentation of tomato leaf images based on adaptive clustering number of K-means algorithm

Tian, Kai; Li, Jiuhao; Zeng, Jiefeng; Asenso, Evans; Zhang, Lina

doi:10.1016/j.compag.2019.104962

Cited by 140 publications

(58 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An online citrus dataset [ 126 ] is available that contains 759 sample images of healthy fruits, healthy leaves, non-healthy leaves (black spot, canker, greening, melanoses), and non-healthy fruits (black spot, canker, greening, scab). Another dataset that has recently been made available [ 21 ] contains 1000 images of tomato leaves, with a mix of healthy leaves and infected samples (yellow leaf curl, mosaic virus). This dataset includes 200 images with white backgrounds for training purposes and 800 images with natural backgrounds for testing purposes.…”

Section: Realistic Datasetsmentioning

confidence: 99%

“…One of the current problems with unsupervised disease detection models is time complexity. However, the high achieved accuracy of k-mean clustering algorithms [ 21 ] is still in need of more computational time concerning the index validity term. Another key problem is the segmentation sensitivity towards the region of interest (ROI) determination [ 22 , 23 , 24 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Review of the State of the Art of Deep Learning for Plant Diseases: A Broad Analysis and Discussion

Hasan

Yusuf

Alzubaidi

2020

Plants

145

View full text Add to dashboard Cite

Deep learning (DL) represents the golden era in the machine learning (ML) domain, and it has gradually become the leading approach in many fields. It is currently playing a vital role in the early detection and classification of plant diseases. The use of ML techniques in this field is viewed as having brought considerable improvement in cultivation productivity sectors, particularly with the recent emergence of DL, which seems to have increased accuracy levels. Recently, many DL architectures have been implemented accompanying visualisation techniques that are essential for determining symptoms and classifying plant diseases. This review investigates and analyses the most recent methods, developed over three years leading up to 2020, for training, augmentation, feature fusion and extraction, recognising and counting crops, and detecting plant diseases, including how these methods can be harnessed to feed deep classifiers and their effects on classifier accuracy.

show abstract

Section: Realistic Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Review of the State of the Art of Deep Learning for Plant Diseases: A Broad Analysis and Discussion

Hasan

Yusuf

Alzubaidi

2020

Plants

145

View full text Add to dashboard Cite

show abstract

“…After image segmentation, each bounding box includes the segmentation of the corresponding object and the unwanted background. The general extraction methods distinguish object and background based on a single index, such as size, or contour [17] [23]. In this paper, the size difference and connected domain analysis are both used to determine the "most probable" region for the detected object.…”

Section: Object Extractionmentioning

confidence: 99%

“…Hou et al utilized the Gaussian Mixture Model (GMM) and the Expectation-Maximization (EM) algorithm to address the problem of image color extraction [15]. Sun et al [16] and Tian et al [17] employed the K-means algorithm to realize the quantization of depth images and the extraction of tomato leaf images, respectively. The fast convergence speed and straightforward logic structure make the K-means algorithm widely used in the color quantization, and image segmentation areas [18].…”

Section: Introductionmentioning

confidence: 99%

Image Object Extraction Based on Semantic Detection and Improved K-Means Algorithm

et al. 2020

View full text Add to dashboard Cite

Object extraction is an important tool in many applications within the image processing and computer vision communities. You Only Look Once version 3 (YOLOv3) has been extensively applied to many fields as a state-of-the-art technique for object semantic detection. Despite its numerous characteristics, YOLOv3 has to be combined with appropriate image segmentation technologies to achieve effective 2D object extraction in real-time monitoring, robot navigation, and target search. In this paper, the K-means algorithm is applied to the segmentation of depth images. Considering the inherent sensitivity to the randomness of the initial cluster center and the uncertainty of cluster number K in the initialization phase of the K-means algorithm, this paper proposes a new method that combines the semantic image information with the image depth information. Specifically, this method proposed to pre-classify the center depth of the object to determine the appropriate value of K required in the K-means algorithm. At the same time, the proposed algorithm improves the selection of the initial center via the maximin method. This paper introduces a multi-parameter extraction method to enable to correctly identify the object of interest after image segmentation. The technique considers three parameters to achieve this: i) the elements of size, ii) the connected domain, and iii) the diagonal detection. Experiments using open-source datasets demonstrate that the average processing time and the segmentation accuracy of the improved K-means algorithm are 20.36% faster and 3.12% higher than the conventional K-means algorithm, respectively. The extraction accuracy of the proposed method is 6.69% higher than that of the SuperCut extraction method.

show abstract

“…As the pillar of wine industry, grape is receiving increasingly interest and now has genome sequence from thousands of germplasm [2][3][4]. Conventionally, different germplasm (genotypes) were classified according to their working phenotypes by designated biologists, where "manual" images were used in terms of canopy architecture, leaf area, and other functions [5][6][7]. These functions can be calculated manually or through a customized image processing algorithm.…”

Section: Introductionmentioning

confidence: 99%

Identification of grapevine(Vitis vinifera L.)cultivars by vine leaf image via deep learning and mobile devices

Liu

Guo-qian

et al. 2020

Preprint

View full text Add to dashboard Cite

Background Traditional vine variety identification methods usually rely on destructive sampling of vine leaves followed by physical, physiological, biochemical and molecular measurement, which is destructive, time-consuming, labor-intensive and requires experienced grape phenotype analysts. To mitigate these problems, this study aims to develop an application (App) running on Android client to identify wine grape automatically and in real time, which can help the growers to quickly obtain the variety information. Results Experimental results show that all Convolutional Neural Network (CNN) classification algorithms can achieve an accuracy of over 94% for 21 categories on validation data, which proves the feasibility of using transfer learning to identify grape species in field environments. In particular, the classification model with the highest average accuracy is Googlenet (97.4%) with learning rate (0.001), mini-batch size (32) and maximum number of epochs (80). Testing results of the App on Android device also confirms these results. Conclusions An App running on Android client is developed to identify the wine grape in real time and field condition, which can help the growers to quickly obtain the variety information of wine grape. A total of 4200 leaf images were first collected in the field environment, which contain 21 types of typical grapes. Then both image complement preprocessing and data augmentation are adopted to enhance image features and augment the training dataset. On this basis, a number of typical CNN models (including VGG-16, DenseNet, ResNet101, ResNet18, and GoogLeNet) are compared in transfer learning training to identify the suitable one while with model parameter tuning. It is shown that GoogLeNet model outperformed other models in terms of accuracy, model complexity, and robustness with a fine-tuned accuracy of 99.91%. The effect of image complement preprocessing is also assessed by using Grad-CAM algorithm. The developed App is also shown to be feasible for real-life applications with a processing time of less than 1 second.

show abstract

Segmentation of tomato leaf images based on adaptive clustering number of K-means algorithm

Cited by 140 publications

References 19 publications

Review of the State of the Art of Deep Learning for Plant Diseases: A Broad Analysis and Discussion

Review of the State of the Art of Deep Learning for Plant Diseases: A Broad Analysis and Discussion

Image Object Extraction Based on Semantic Detection and Improved K-Means Algorithm

Identification of grapevine(Vitis vinifera L.)cultivars by vine leaf image via deep learning and mobile devices

Contact Info

Product

Resources

About