Convolutional Neural Network Architecture for Plant Seedling Classification

Abstract

Weed control is a challenging problem that may face crops productivity. Weeds are perceived as an important problem because they conduce to reduce crop yields due to the expanding competition for nutrients, water, and sunlight besides they serve as hosts for diseases and pests. Thus, it is crucial to identify weeds in early growth in order to avoid their side effects on crops growth. Previous conventional machine learning technologies exploited for discriminating crops and weeding species faced challenges of effectiveness and reliability of weed detection at preliminary stages of growth. This work proposes the application of deep learning technique for plant seedling classification. A new Convolutional Neural Networks (CNN) architecture is designed to classify plant seedlings at their early growth stages. The presented technique is appraised using plant seedlings dataset. Average accuracy, precision, recall, and F1score are utilized as evaluation metrics. The results reveal the capability of the proposed technique in discriminating among 12 species (3 crops and 9 weeds). The system achieved 94.38% average classification accuracy. The proposed system is compared with existing plant seedling systems. The results demonstrate that the proposed method outperforms the existing methods.

Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural Networks

“…ResNet-50 and Xception performed better than VGG16, achieving a performance of 97% and 98%, respectively. Recent publications like dos Santos Ferreira et al [15], Potena et al [18], Tang et al [4], Sharpe et al [39] and Elnemr [19] have also achieved classification results of over 90%. Yet in the majority of these cases, a low number of classes were used (2-4), or the datasets were only sufficient to prove the researched hypothesis but not sufficient to transfer the results into the complexity of the real world.…”

“…They can not be used for weed management applications like, for example, precision spraying or mechanical weed control [6]. The selection of a limited number of classes for classification is mainly due to the fact that the more classes that are considered, the less accurate the result [19]. In our case we managed to achieve quite a high classification accuracy, overpassing 97% in two of our networks, with twelve different classes, representing three summer plants with some of their representative weeds, both grasses, and broadleaved weeds.…”

“…Convolution neural networks (CNNs)-first implemented by LeCun et al [16]-can be used as a tool providing highly-accuracy concerning image classification, object detection, and can even be a valuable candidate for fine-grained classification [17]. Although the use of CNNs is relatively new, recent publications have reached high classification accuracies of 99.50% for classifying segments as crop, soil, grass, and broadleaf weeds [15], 96.10% on a blob-wise crop/weed classification [18], 94.38% between twelve different plant species [19], and 95.70% of eight Australian weed species [20]. CNNs can provide insights into image related datasets that we have not yet understood, achieving identification accuracies that sometimes surpass the human-level performance [21].…”

“…Their dataset underlines the importance of adequate images for each species because if the amount of data is insufficient the recognition rate will significantly decline. Elnemr [19] proposed a new simple self-built CNN architecture to classify twelve classes (three crops and nine weeds) during their early growth stages. The results indicate that the more classes that the training dataset comprises, the more difficult it is to reach a good classification result.…”

Classification of plant seedlings using deep convolutional neural network architectures

“…Authors in [6] have collected the benchmark plant seedlings dataset and made it publically available to ease the work of researchers. Authors in [7] used the same dataset and designed a CNN to classify the plants and weeds. It has achieved an average accuracy of 94.38%.…”