Image Processing Techniques for Diagnosing Rice Plant Disease: A Survey

Sethy, Prabira Kumar; Barpanda, Nalini Kanta; Rath, Amiya Kumar; Behera, Santi Kumari

doi:10.1016/j.procs.2020.03.308

Cited by 96 publications

(32 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This includes applying a Fastie color map to visualize the NDVI values in the image. The pre-processed frame(s) is passed through our CNN model (custom trained CPD detection model using transfer learning with Faster RCNN for prototype 2, SSD MobileNet V2 [1] COCO for prototype 3, and YOLO v4 for prototype 4) for CPD detection and quantification based on the TensorFlow object detection API. The real-time CPD detection is displayed on the system preview window with an overlaid running count of CPD detected.…”

Section: Development and Testing Of The Real-time Cpd Detection And Quantification Monitoring Systemmentioning

confidence: 99%

See 1 more Smart Citation

A Recognition Method for Cassava Phytoplasma Disease (CPD) Real-Time Detection based on Transfer Learning Neural Networks

Plata¹,

Panganiban²,

Alado³

et al. 2021

IJACSA

View full text Add to dashboard Cite

Object detection technology aims to detect the target objects with the theories and methods of image processing and pattern recognition, determine the semantic categories of these objects, and mark the specific position of the target object in the image. This study generally aims to establish a recognition method for Cassava Phytoplasma Disease (CPD) real-time detection based on transfer learning neural networks. Several methods and procedures were conducted, such as the testing of two methods in transmitting long-distance high definition (HD) video capture; establishment of a compact setup for a long-range wireless video transmission system; the development, testing of the real-time CPD detection and quantification monitoring system, providing the comparative performance analysis of the three models used. We have successfully custom-trained three artificial neural networks using transfer learning: Faster Regions with Convolutional Neural Networks (R-CNN) Inception v2, Single Shot Detector (SSD) Mobilenet v2, and You Only Look Once (YOLO) v4. These deep learning models can detect and recognize CPD in actual environment settings. Overall, the developed real-time CPD detection and quantification monitoring system was successfully integrated into the wireless video receiver and seamlessly visualized all the incoming data using the three different CNN models. If the consideration is the image processing speed, YOLOv4 is better compared to other models. But, if accuracy is the priority, Faster R-CNN inception v2 performs better. However, since CPD detection is the main purpose of this study, the Faster R-CNN model is recommended for adoption to detect CPD in a real-time environment.

show abstract

Section: Development and Testing Of The Real-time Cpd Detection And Quantification Monitoring Systemmentioning

confidence: 99%

“…The major challenges of sustainable development include reducing pesticide use, the expense of preserving the environment, and the cost of building quality. Exact, exact, and timely decisions may reduce pesticide use [1]. Cassava is a key crop that has been produced in the Philippines.…”

Section: Introductionmentioning

confidence: 99%

A Recognition Method for Cassava Phytoplasma Disease (CPD) Real-Time Detection based on Transfer Learning Neural Networks

Plata¹,

Panganiban²,

Alado³

et al. 2021

IJACSA

View full text Add to dashboard Cite

show abstract

“…The key for successful disease control is a correct and fast diagnosis of diseases, so that pesticide control measures can be applied timely. Currently, the most widely used method to diagnose rice crop diseases is manual judgment based on the appearance of diseases (Sethy et al, 2020 ). There are not enough people across the region with skills to perform such tasks in a timely manner.…”

Section: Introductionmentioning

confidence: 99%

Automatic Diagnosis of Rice Diseases Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

Rice disease has serious negative effects on crop yield, and the correct diagnosis of rice diseases is the key to avoid these effects. However, the existing disease diagnosis methods for rice are neither accurate nor efficient, and special equipment is often required. In this study, an automatic diagnosis method was developed and implemented in a smartphone app. The method was developed using deep learning based on a large dataset that contained 33,026 images of six types of rice diseases: leaf blast, false smut, neck blast, sheath blight, bacterial stripe disease, and brown spot. The core of the method was the Ensemble Model in which submodels were integrated. Finally, the Ensemble Model was validated using a separate set of images. Results showed that the three best submodels were DenseNet-121, SE-ResNet-50, and ResNeSt-50, in terms of several attributes, such as, learning rate, precision, recall, and disease recognition accuracy. Therefore, these three submodels were selected and integrated in the Ensemble Model. The Ensemble Model minimized confusion among the different types of disease, reducing misdiagnosis of the disease. Using the Ensemble Model to diagnose six types of rice diseases, an overall accuracy of 91% was achieved, which is considered to be reasonably good, considering the appearance similarities in some types of rice disease. The smartphone app allowed the client to use the Ensemble Model on the web server through a network, which was convenient and efficient for the field diagnosis of rice leaf blast, false smut, neck blast, sheath blight, bacterial stripe disease, and brown spot.

show abstract

“…The expected result is the diagnosis of disease of rice, which is obtained based on the symptoms that attack on rice plant. The goal is that when achieved diagnostics diseases of the rice plant in order to quickly given handling is appropriate in order to prevent the occurrence of crop failure (Sethy et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Web-Based Rice Disease Diagnosis Expert System Using Fuzzy Tsukamoto Method and K-Nearest Neighbor Algorithm

Tawarai

Fauziah

Andrianingsih

2021

CNAHPC

View full text Add to dashboard Cite

Technology today is growing rapidly from year to year, not least started to spread to the agricultural sector. With the information technology making society more easily in search of information via the internet from your smart device. The goal of this study was made to facilitate the community, especially farmers in helping to diagnose diseases and pests in rice plants. Rice plants can be attacked by a wide variety of diseases and pests with a wide variety of symptoms experienced in rice plants. To know the kind of disease on rice plants in the era of technology, it takes an expert system that can help detect the disease in rice plants. In this study, Expert System-Based Website using Tsukamoto Fuzzy method and the Algorithm of K-Nearest Neighbor whose purpose is to help people, especially farmers in diagnosing diseases and pests in rice plants by looking at the symptoms of the attack on the rice plant. Data was obtained from the Research and the Ministry of Agriculture then taken some sample data for testing done. The results of the testing data of this expert system is the result of late diagnosis in diseases of the rice with the symptoms that already exist based on the data that have been obtained with an accuracy rate of 92,88%.

show abstract

Image Processing Techniques for Diagnosing Rice Plant Disease: A Survey

Cited by 96 publications

References 37 publications

A Recognition Method for Cassava Phytoplasma Disease (CPD) Real-Time Detection based on Transfer Learning Neural Networks

A Recognition Method for Cassava Phytoplasma Disease (CPD) Real-Time Detection based on Transfer Learning Neural Networks

Automatic Diagnosis of Rice Diseases Using Deep Learning

Web-Based Rice Disease Diagnosis Expert System Using Fuzzy Tsukamoto Method and K-Nearest Neighbor Algorithm

Contact Info

Product

Resources

About