Plant Diseases and Pests are a major challenge in the agriculture sector. An accurate and a faster detection of diseases and pests in plants could help to develop an early treatment technique while substantially reducing economic losses. Recent developments in Deep Neural Networks have allowed researchers to drastically improve the accuracy of object detection and recognition systems. In this paper, we present a deep-learning-based approach to detect diseases and pests in tomato plants using images captured in-place by camera devices with various resolutions. Our goal is to find the more suitable deep-learning architecture for our task. Therefore, we consider three main families of detectors: Faster Region-based Convolutional Neural Network (Faster R-CNN), Region-based Fully Convolutional Network (R-FCN), and Single Shot Multibox Detector (SSD), which for the purpose of this work are called “deep learning meta-architectures”. We combine each of these meta-architectures with “deep feature extractors” such as VGG net and Residual Network (ResNet). We demonstrate the performance of deep meta-architectures and feature extractors, and additionally propose a method for local and global class annotation and data augmentation to increase the accuracy and reduce the number of false positives during training. We train and test our systems end-to-end on our large Tomato Diseases and Pests Dataset, which contains challenging images with diseases and pests, including several inter- and extra-class variations, such as infection status and location in the plant. Experimental results show that our proposed system can effectively recognize nine different types of diseases and pests, with the ability to deal with complex scenarios from a plant’s surrounding area.

A fundamental problem that confronts deep neural networks is the requirement of a large amount of data for a system to be efficient in complex applications. Promising results of this problem are made possible through the use of techniques such as data augmentation or transfer learning of pre-trained models in large datasets. But the problem still persists when the application provides limited or unbalanced data. In addition, the number of false positives resulting from training a deep model significantly cause a negative impact on the performance of the system. This study aims to address the problem of false positives and class unbalance by implementing a Refinement Filter Bank framework for Tomato Plant Diseases and Pests Recognition. The system consists of three main units: First, a Primary Diagnosis Unit (Bounding Box Generator) generates the bounding boxes that contain the location of the infected area and class. The promising boxes belonging to each class are then used as input to a Secondary Diagnosis Unit (CNN Filter Bank) for verification. In this second unit, misclassified samples are filtered through the training of independent CNN classifiers for each class. The result of the CNN Filter Bank is a decision of whether a target belongs to the category as it was detected (True) or not (False) otherwise. Finally, an integration unit combines the information from the primary and secondary units while keeping the True Positive samples and eliminating the False Positives that were misclassified in the first unit. By this implementation, the proposed approach is able to obtain a recognition rate of approximately 96%, which represents an improvement of 13% compared to our previous work in the complex task of tomato diseases and pest recognition. Furthermore, our system is able to deal with the false positives generated by the bounding box generator, and class unbalances that appear especially on datasets with limited data.

Deep learning shows its advantages and potentials in plant disease recognition and has witnessed a profound development in recent years. To obtain a competing performance with a deep learning algorithm, enough amount of annotated data is requested but in the natural world, scarce or imbalanced data are common, and annotated data is expensive or hard to collect. Data augmentation, aiming to create variations for training data, has shown its power for this issue. But there are still two challenges: creating more desirable variations for scarce and imbalanced data, and designing a data augmentation to ease object detection and instance segmentation. First, current algorithms made variations only inside one specific class, but more desirable variations can further promote performance. To address this issue, we propose a novel data augmentation paradigm that can adapt variations from one class to another. In the novel paradigm, an image in the source domain is translated into the target domain, while the variations unrelated to the domain are maintained. For example, an image with a healthy tomato leaf is translated into a powdery mildew image but the variations of the healthy leaf are maintained and transferred into the powdery mildew class, such as types of tomato leaf, sizes, and viewpoints. Second, current data augmentation is suitable to promote the image classification model but may not be appropriate to alleviate object detection and instance segmentation model, mainly because the necessary annotations can not be obtained. In this study, we leverage a prior mask as input to tell the area we are interested in and reuse the original annotations. In this way, our proposed algorithm can be utilized to do the three tasks simultaneously. Further, We collect 1,258 images of tomato leaves with 1,429 instance segmentation annotations as there is more than one instance in one single image, including five diseases and healthy leaves. Extensive experimental results on the collected images validate that our new data augmentation algorithm makes useful variations and contributes to improving performance for diverse deep learning-based methods.