Litcius/Paper detail

Rice Diseases Recognition Using Effective Deep Learning Models

Seksan Mathulaprangsan, Kitsana Lanthong, Duangpen Jetpipattanapong, Siwadol Sateanpattanakul, Sujin Patarapuwadol

202040 citationsDOI

Abstract

Rice is the most important grain in Thailand for both consuming and exporting. One of the critical problems in rice cultivation is rice diseases, which affects directly to the yield. Disease recognition by a human is hard and the performance depends on the farmer's experience. To overcome this problem, we did two folds of contributions. First, an infield rice disease image dataset was created. Second, a number of deep learning models including ResNets and DenseNets were applied to classify such rice diseases. The experimental results reveal that the proposed framework can achieve high accuracy, more than 95% in average, and has potential to be implemented and provide to Thai farmers in the future.

Topics & Concepts

Deep learningComputer scienceArtificial intelligenceGrain yieldYield (engineering)Agricultural engineeringMachine learningRice plantImage (mathematics)Pattern recognition (psychology)AgronomyEngineeringBiologyMaterials scienceMetallurgySmart Agriculture and AISpectroscopy and Chemometric AnalysesGABA and Rice Research