Deep learning for plant identification using vein morphological patterns

Grinblat, Guillermo L.; Uzal, Lucas C.; Larese, Mónica G.; Granitto, Pablo M.

doi:10.1016/j.compag.2016.07.003

Cited by 530 publications

(236 citation statements)

References 20 publications

Supporting

Mentioning

232

Contrasting

Unclassified

Order By: Relevance

“…In this study, based on our discovery that CNN trained on different input data formats provides variants of contextual features of leaf, we design a new hybrid global-local feature extraction model for leaf data based on CNN approach. Instead of relying on either whole leaf data [31,45,46,47] or solely venation [30,31] for species classification, we propose to combine information from two CNN networks, one global network trained upon the whole leaf data and another local network trained upon its corresponding leaf patches. We integrate them via different feature fusion strategies as illustrated in Fig.…”

Section: Hybrid Global-local Leaf Feature Extractionmentioning

confidence: 99%

“…They first segmented the vein pattern using Hit or Miss Transform (UHMT), then used LEAF GUI measures to extract a set of features for veins and areoles. The latest study [30] attempted deep learning in plant identification using vein morphological patterns. They first extracted the vein patterns using UHMT, and then trained a CNN to recognise them using a central patch of leaf images.…”

Section: Related Studiesmentioning

confidence: 99%

See 1 more Smart Citation

How deep learning extracts and learns leaf features for plant classification

Lee

Chan

Mayo

et al. 2017

Pattern Recognition

459

172

View full text Add to dashboard Cite

Highlights• A deep learning approach to quantify discriminatory leaf is proposed.• Shape is not a dominant feature for leaf but rather the different orders of venation.• Deep learning reveals transformation of leaf features from general to specific types.• Findings archived fit with the hierarchical botanical definitions of leaf characters• Features learned using deep learning can improve plant recognition performance. AbstractPlant identification systems developed by computer vision researchers have helped botanists to recognize and identify unknown plant species more rapidly. Hitherto, numerous studies have focused on procedures or algorithms that maximize the use of leaf databases for plant predictive modeling, but this results in leaf features which are liable to change with different leaf data and feature extraction techniques. In this paper, we learn useful leaf features directly from the raw representations of input data using Convolutional Neural Networks (CNN), and gain intuition of the chosen features based on a Deconvolutional Network (DN) approach. We report somewhat unexpected results: (1) different orders of venation are the best representative features compared to those of outline shape, and (2) we observe multi-level representation in leaf data, demonstrating the hierarchical transformation of features from lower-level to higher-level abstraction, corresponding to species classes. We show that these findings fit with the hierarchical botanical definitions of leaf characters. Through these findings, we gained insights into the design of new hybrid feature extraction models which are able to further improve the discriminative power of plant classification systems. The source code and models are available at: https://github.com/cs-chan/Deep-Plant.

show abstract

Section: Hybrid Global-local Leaf Feature Extractionmentioning

confidence: 99%

Section: Related Studiesmentioning

confidence: 99%

How deep learning extracts and learns leaf features for plant classification

Lee

Chan

Mayo

et al. 2017

Pattern Recognition

459

172

View full text Add to dashboard Cite

show abstract

“…State-of-the-art convolutional neural networks have been shown to perform well on a wide variety of phenotyping tasks. The applications of CNNs in plant phenotyping include image classification tasks such as plant species identification [1], stress identification [2], object detection arXiv:1910.01789v2 [cs.CV] 15 Oct 2019 and counting tasks such as panicle or spike detection [3,4,5,6], leaf counting [7], fruit detection [8]; as well as pixel-wise segmentation based tasks such as panicle segmentation [9,10] and crop-weed segmentation [11]. We refer the reader to [12] and [13] for a full treatment of deep learning in agriculture and plant phenotyping tasks.…”

Section: Introductionmentioning

confidence: 99%

Active learning with point supervision for cost-effective panicle detection in cereal crops

et al. 2020

View full text Add to dashboard Cite

Background: Panicle density of cereal crops such as wheat and sorghum is one of the main components for plant breeders and agronomists in understanding the yield of their crops. To phenotype the panicle density effectively, researchers agree there is a significant need for computer vision-based object detection techniques. Especially in recent times, research in deep learning-based object detection shows promising results in various agricultural studies. However, training such systems usually requires a lot of bounding-box labeled data. Since crops vary by both environmental and genetic conditions, acquisition of huge amount of labeled image datasets for each crop is expensive and time-consuming. Thus, to catalyze the widespread usage of automatic object detection for crop phenotyping, a cost-effective method to develop such automated systems is essential.Results: We propose a weak supervision based active learning approach for panicle detection in cereal crops. In our approach, the model constantly interacts with a human annotator by iteratively querying the labels for only the most informative images, as opposed to all images in a dataset. Our query method is specifically designed for cereal crops which usually tend to have panicles with low variance in appearance. Our method reduces labeling costs by intelligently leveraging low-cost weak labels (object centers) for picking the most informative images for which strong labels (bounding boxes) are required. We show promising results on two publicly available cereal crop datasets -Sorghum and Wheat. On Sorghum, 6 variants of our proposed method outperform the best baseline method with more than 55% savings in labeling time. Similarly, on Wheat, 3 variants of our proposed methods outperform the best baseline method with more than 50% of savings in labeling time. Conclusion:We proposed a cost effective method to train reliable panicle detectors for cereal crops. A low cost panicle detection method for cereal crops is highly beneficial to both breeders and agronomists. Plant breeders can obtain quick crop yield estimates to make important crop management decisions. Similarly, obtaining real time visual crop analysis is valuable for researchers to analyze the crop's response to various experimental conditions.

show abstract

“…More recently, deep learning architectures such as convolutional neural network have been found capable of creating and extracting features from raw representations of input data without many human interactions. They were found effective in plant classification as well . But as pointed out by Slaughter et al., most of the 2D image‐based plant recognition systems only worked under ideal conditions, where there were no substantial leaf occlusion and leaf damage problems.…”

Section: Introductionmentioning

confidence: 99%

Crop recognition under weedy conditions based on 3D imaging for robotic weed control

Tang

2017

Journal of Field Robotics

View full text Add to dashboard Cite

A 3D time‐of‐flight camera was applied to develop a crop plant recognition system for broccoli and green bean plants under weedy conditions. The developed system overcame the previously unsolved problems caused by occluded canopy and illumination variation. An efficient noise filter was developed to remove the sparse noise points in 3D point cloud space. Both 2D and 3D features including the gradient of amplitude and depth image, surface curvature, amplitude percentile index, normal direction, and neighbor point count in 3D space were extracted and found effective for recognizing these two types of plants. Separate segmentation algorithms were developed for each of the broccoli and green bean plant in accordance with their 3D geometry and 2D amplitude characteristics. Under the experimental condition where the crops were heavily infested by various types of weed plants, detection rates over 88.3% and 91.2% were achieved for broccoli and green bean plant leaves, respectively. Additionally, the crop plants were segmented out with nearly complete shape. Moreover, the algorithms were computationally optimized, resulting in an image processing speed of over 30 frames per second.

show abstract

Deep learning for plant identification using vein morphological patterns

Cited by 530 publications

References 20 publications

How deep learning extracts and learns leaf features for plant classification

How deep learning extracts and learns leaf features for plant classification

Active learning with point supervision for cost-effective panicle detection in cereal crops

Crop recognition under weedy conditions based on 3D imaging for robotic weed control

Contact Info

Product

Resources

About