A method of detecting apple leaf diseases based on improved convolutional neural network

Abstract

Apple tree diseases have perplexed orchard farmers for several years. At present, numerous studies have investigated deep learning for fruit and vegetable crop disease detection. Because of the complexity and variety of apple leaf veins and the difficulty in judging similar diseases, a new target detection model of apple leaf diseases DF-Tiny-YOLO, based on deep learning, is proposed to realize faster and more effective automatic detection of apple leaf diseases. Four common apple leaf diseases, including 1,404 images, were selected for data modeling and method evaluation, and made three main improvements. Feature reuse was combined with the DenseNet densely connected network and further realized to reduce the disappearance of the deep gradient, thus strengthening feature propagation and improving detection accuracy. We introduced Resize and Re-organization (Reorg) and conducted convolution kernel compression to reduce the calculation parameters of the model, improve the operating detection speed, and allow feature stacking to achieve feature fusion. The network terminal uses convolution kernels of 1 × 1, 1 × 1, and 3 × 3, in turn, to realize the dimensionality reduction of features and increase network depth without increasing computational complexity, thus further improving the detection accuracy. The results showed that the mean average precision (mAP) and average intersection over union (IoU) of the DF-Tiny-YOLO model were 99.99% and 90.88%, respectively, and the detection speed reached 280 FPS. Compared with the Tiny-YOLO and YOLOv2 network models, the new method proposed in this paper significantly improves the detection performance. It can also detect apple leaf diseases quickly and effectively.

YOLO-Based Phenotyping of Apple Blotch Disease (Diplocarpon coronariae) in Genetic Resources after Artificial Inoculation

“…In addition, new approaches such as transfer learning offer a way to overcome the typical challenges of training a deep learning algorithm (e.g., high variance, low accuracy or bias) and allow an easy adaption of pretrained models to a specific dataset [14]. This makes it quick and easy to establish models for a customised dataset that achieve a high level of precision as demonstrated in studies on rice leaf diseases [15,16], grape leaf lesions [17] and apple leaf diseases [18][19][20][21][22][23][24].…”

Deep reinforcement learning enables adaptive-image augmentation for automated optical inspection of plant rust

“…The classification and detection of plant diseases are only possible to judge whether the disease occurs in certain locations (Di and Li, 2022;Khan et al, 2022;Yan et al, 2022;Deng et al, 2023;. Using computer vision segmentation algorithms, the size and shape of plant rust spots can be obtained (Wang et al, 2021;Ban et al, 2022;Shoaib et al, 2022;Dang et al, 2023;, and the severity of rust occurrence can be quantitatively evaluated.…”

“…However, image augmentation and image segmentation were previously trained in separate ways (Di and Li, 2022). The image segmentation results cannot provide feedback to the DRL-based image augmentation model.…”

Dilated convolution capsule network for apple leaf disease identification

“…The qualitative results validated that the proposed system can efficiently and accurately identify leaf disease symptoms and can be used as a practical tool by farmers and apple growers to aid them in the diagnosis, quantification, and follow-up of infections. Di et al (Di and Li, 2022) proposed an apple disease detection approach based on improved CNN, namely, DF-Tiny-YOLO. Feature reuse is combined with DenseNet dense connection network to reduce the disappearance of depth gradient, so as to strengthen feature propagation and improve detection accuracy.…”

“…Di et al. ( Di and Li, 2022 ) proposed an apple disease detection approach based on improved CNN, namely, DF-Tiny-YOLO. Feature reuse is combined with DenseNet dense connection network to reduce the disappearance of depth gradient, so as to strengthen feature propagation and improve detection accuracy.…”