Search Results (19)

China is the world’s largest producer of chili peppers, which occupy particularly important economic and social values in various fields such as medicine, food, and industry. However, during its production process, chili peppers are affected by pests and diseases, resulting in significant yield reduction due to the temperature and environment. In this study, a lightweight pepper disease identification method, DD-YOLO, based on the YOLOv8n model, is proposed. First, the deformable convolutional module DCNv2 (Deformable ConvNetsv2) and the inverted residual mobile block iRMB (Inverted Residual Mobile Block) are introduced into the C2F module to improve the accuracy of the sampling range and reduce the computational amount. Secondly, the DySample sampling operator (Dynamic Sample) is integrated into the head network to reduce the amount of data and the complexity of computation. Finally, we use Large Separable Kernel Attention (LSKA) to improve the SPPF module (Spatial Pyramid Pooling Fast) to enhance the performance of multi-scale feature fusion. The experimental results show that the accuracy, recall, and average precision of the DD-YOLO model are 91.6%, 88.9%, and 94.4%, respectively. Compared with the base network YOLOv8n, it improves 6.2, 2.3, and 2.8 percentage points, respectively. The model weight is reduced by 22.6%, and the number of floating-point operations per second is improved by 11.1%. This method provides a technical basis for intensive cultivation and management of chili peppers, as well as efficiently and cost-effectively accomplishing the task of identifying chili pepper pests and diseases. Full article

In response to the challenges of low accuracy in traditional pepper blight identification under natural complex conditions, particularly in detecting subtle infections on early-stage leaves, stems, and fruits. This study proposes a multi-site pepper blight disease image recognition algorithm based on YOLOv8, named MSPB-YOLO. This algorithm effectively locates different infection sites on peppers. By incorporating the RVB-EMA module into the model, we can significantly reduce interference from shallow noise in high-resolution depth layers. Additionally, the introduction of the RepGFPN network structure enhances the model’s capability for multi-scale feature fusion, resulting in a marked improvement in multi-target detection accuracy. Furthermore, we optimized CIOU to DIOU by integrating the center distance of bounding boxes into the loss function; as a result, the model achieved an impressive mAP@0.5 score of 96.4%. This represents an enhancement of 2.2% over the original algorithm’s mAP@0.5. Overall, this model provides effective technical support for promoting intelligent management and disease prevention strategies for peppers. Full article

Pepper Phytophthora blight caused by Phytophthora capsici results in substantial losses in global pepper cultivation. The use of biocontrol agents with the dual functions of disease suppression and crop growth promotion is a green and sustainable way of managing this pathogen. In this study, six biocontrol strains of Trichoderma with high antagonistic activity against P. capsici were isolated and screened from the rhizosphere soil of healthy peppers undergoing long-term continuous cultivation. Morphological identification and molecular biological identification revealed that strains 2213 and 2221 were T. harzianum, strains 5111, 6311, and 6321 were T. brevicompactum, and strain 7111 was T. virens. The results showed that T. brevicompactum 6311 had the greatest inhibitory effect against P. capsici. The inhibition rate of 6311 on the mycelial growth of P. capsici was 82.22% in a double-culture test, whereas it reached 100% in a fermentation liquid culture test. Meanwhile, the pepper fruit tests showed that 6311 was 29% effective against P. capsici on pepper, and a potting test demonstrated that the preventive and controlling effect of 6311 on pepper epidemics triggered by P. capsici was 55.56%. The growth-promoting effect, germination potential, germination rate, radicle-embryonic axis length, germination index, and fresh weight of peppers cultured in the 6311 fermentation broth were significantly increased compared with the results for the control group. Scanning electron microscopy revealed that 6311 achieved the parasitism of P. capsici, producing siderophores and the growth hormone indoleacetic acid (IAA) to achieve disease-suppressive and growth-promoting functions. Transcriptomic results indicated that genes encoding proteins involved in plant disease resistance, namely flavanone 3-hydroxylase (F3H) and growth transcription factor (AUX22), were generally upregulated after the application of 6311. This study demonstrated that 6311 exhibits significant bioprotective and growth-promoting functions. Full article

Timely and accurate detection of diseases in vegetables is crucial for effective management and mitigation strategies before they take a harmful turn. In recent years, convolutional neural networks (CNNs) have emerged as powerful tools for automated disease detection in crops due to their ability to learn intricate patterns from large-scale image datasets and make predictions of samples that are given. The use of CNN algorithms for disease detection in important vegetable crops like potatoes, tomatoes, peppers, cucumbers, bitter gourd, carrot, cabbage, and cauliflower is critically examined in this review paper. This review examines the most recent state-of-the-art techniques, datasets, and difficulties related to these crops’ CNN-based disease detection systems. Firstly, we present a summary of CNN architecture and its applicability to classify tasks based on images. Subsequently, we explore CNN applications in the identification of diseases in vegetable crops, emphasizing relevant research, datasets, and performance measures. Also, the benefits and drawbacks of CNN-based methods, covering problems with computational complexity, model generalization, and dataset size, are discussed. This review concludes by highlighting the revolutionary potential of CNN algorithms in transforming crop disease diagnosis and management strategies. Finally, this study provides insights into the current limitations regarding the usage of computer algorithms in the field of vegetable disease detection. Full article

Pepper is a high-economic-value agricultural crop that faces diverse disease challenges such as blight and anthracnose. These diseases not only reduce the yield of pepper but, in severe cases, can also cause significant economic losses and threaten food security. The timely and accurate identification of pepper diseases is crucial. Image recognition technology plays a key role in this aspect by automating and efficiently identifying pepper diseases, helping agricultural workers to adopt and implement effective control strategies, alleviating the impact of diseases, and being of great importance for improving agricultural production efficiency and promoting sustainable agricultural development. In response to issues such as edge-blurring and the extraction of minute features in pepper disease image recognition, as well as the difficulty in determining the optimal learning rate during the training process of traditional pepper disease identification networks, a new pepper disease recognition model based on the TPSAO-AMWNet is proposed. First, an Adaptive Residual Pyramid Convolution (ARPC) structure combined with a Squeeze-and-Excitation (SE) module is proposed to solve the problem of edge-blurring by utilizing adaptivity and channel attention; secondly, to address the issue of micro-feature extraction, Minor Triplet Disease Focus Attention (MTDFA) is proposed to enhance the capture of local details of pepper leaf disease features while maintaining attention to global features, reducing interference from irrelevant regions; then, a mixed loss function combining Weighted Focal Loss and L2 regularization (WfrLoss) is introduced to refine the learning strategy during dataset processing, enhancing the model’s performance and generalization capabilities while preventing overfitting. Subsequently, to tackle the challenge of determining the optimal learning rate, the tent particle snow ablation optimizer (TPSAO) is developed to accurately identify the most effective learning rate. The TPSAO-AMWNet model, trained on our custom datasets, is evaluated against other existing methods. The model attains an average accuracy of 93.52% and an F1 score of 93.15%, demonstrating robust effectiveness and practicality in classifying pepper diseases. These results also offer valuable insights for disease detection in various other crops. Full article

Viral diseases pose a significant threat to tomato crops (Solanum lycopersicum L.), one of the world’s most economically important vegetable crops. The limited genetic diversity of cultivated tomatoes contributes to their high susceptibility to viral infections. To address this challenge, tomato breeding programs must harness the genetic resources found in native populations and wild relatives. Breeding efforts may aim to develop broad-spectrum resistance against the virome. To identify the viruses naturally infecting 19 advanced lines, derived from native tomatoes, high-throughput sequencing (HTS) of small RNAs and confirmation with PCR and RT-PCR were used. Single and mixed infections with tomato mosaic virus (ToMV), tomato golden mosaic virus (ToGMoV), and pepper huasteco yellow vein virus (PHYVV) were detected. The complete consensus genomes of three variants of Mexican ToMV isolates were reconstructed, potentially forming a new ToMV clade with a distinct 3’ UTR. The absence of reported mutations associated with resistance-breaking to ToMV suggests that the Tm-1, Tm-2, and Tm-2² genes could theoretically be used to confer resistance. However, the high mutation rates and a 63 nucleotide insertion in the 3’ UTR, as well as amino acid mutations in the ORFs encoding 126 KDa, 183 KDa, and MP of Mexican ToMV isolates, suggest that it is necessary to evaluate the capacity of these variants to overcome Tm-1, Tm-2, and Tm-2² resistance genes. This evaluation, along with the characterization of advanced lines using molecular markers linked to these resistant genes, will be addressed in future studies as part of the breeding strategy. This study emphasizes the importance of using HTS for accurate identification and characterization of plant viruses that naturally infect tomato germplasm based on the consensus genome sequences. This study provides crucial insights to select appropriate disease management strategies and resistance genes and guide breeding efforts toward the development of virus-resistant tomato varieties. Full article

In this paper, we propose a new Modified Laplacian Vector Median Filter (MLVMF) for real-time denoising complex images corrupted by “salt and pepper” impulsive noise. The method consists of two rounds with three steps each: the first round starts with the identification of pixels that may be contaminated by noise using a Modified Laplacian Filter. Then, corrupted pixels pass a neighborhood-based validation test. Finally, the Vector Median Filter is used to replace noisy pixels. The MLVMF uses a 5 × 5 window to observe the intensity variations around each pixel of the image with a rotation step of π/8 while the classic Laplacian filters often use rotation steps of π/2 or π/4. We see better identification of noise-corrupted pixels thanks to this rotation step refinement. Despite this advantage, a high percentage of the impulsive noise may cause two or more corrupted pixels (with the same intensity) to collide, preventing the identification of noise-corrupted pixels. A second round is then necessary using a second set of filters, still based on the Laplacian operator, but allowing focusing only on the collision phenomenon. To validate our method, MLVMF is firstly tested on standard images, with a noise percentage varying from 3% to 30%. Obtained performances in terms of processing time, as well as image restoration quality through the PSNR (Peak Signal to Noise Ratio) and the NCD (Normalized Color Difference) metrics, are compared to the performances of VMF (Vector Median Filter), VMRHF (Vector Median-Rational Hybrid Filter), and MSMF (Modified Switching Median Filter). A second test is performed on several noisy chest x-ray images used in cardiovascular disease diagnosis as well as COVID-19 diagnosis. The proposed method shows a very good quality of restoration on this type of image, particularly when the percentage of noise is high. The MLVMF provides a high PSNR value of 5.5% and a low NCD value of 18.2%. Finally, an optimized Field-Programmable Gate Array (FPGA) design is proposed to implement the proposed method for real-time processing. The proposed hardware implementation allows an execution time equal to 9 ms per 256 × 256 color image. Full article

Colletotrichum species are among the most devastating plant pathogens in a wide range of hosts. Their accurate identification requires a polyphasic approach, including geographical, ecological, morphological, and genetic data. Solanaceous crops are of significant economic importance for Bulgarian agriculture. Colletotrichum-associated diseases pose a serious threat to the yield and quality of production but are still largely unexplored. The aim of this study was to identify and characterize 26 pathogenic Colletotrichum isolates that threaten solanaceous crops based on morphological, pathogenic, and molecular data. DNA barcodes enabled the discrimination of three main taxonomic groups: C. acutatum, C. gloeosporioides, and C. coccodes. Three different species of acutatum complex (C. nymphaeae, C. godetiae, and C. salicis) and C. cigarro of the gloeosporioides complex were associated with fruit anthracnose in peppers and tomatoes. The C. coccodes group was divided in two clades: C. nigrum, isolated predominantly from fruits, and C. coccodes, isolated mainly from roots. Only C. salicis and C. cigarro produced sexual morphs. The species C. godetiae, C. salicis, and C. cigarro have not previously been reported in Bulgaria. Our results enrich the knowledge of the biodiversity and specific features of Colletotrichum species, which are pathogenic to solanaceous hosts, and may serve as a scientific platform for efficient disease control and resistance breeding. Full article

Dirigent proteins (DIR) play important roles in the biosynthesis of lignins and lignans, defensive responses, secondary metabolism, and disease resistance in plants. The DIR gene family has been identified and studied in many plants. However, the identification of DIR gene family in eggplant has not been conducted yet. Therefore, in this study, based on the available genome information of eggplant, the DIR family genes in eggplant were identified with bioinformatics methods. The expression pattern analyses of eggplant DIR family genes in different organs and stresses were also conducted to understand their biological functions. The results showed that a total of 24 DIR genes were identified in the eggplant, which were divided into three subfamilies (DIR-a, DIR-b/d, and DIR-e). Synteny analysis of DIR genes among eggplant, Arabidopsis, and rice showed that 15 eggplant DIR genes were colinear with 18 Arabidopsis DIR genes, and 16 eggplant DIR genes were colinear with 15 rice DIR genes. Phylogenetic tree analysis showed that 19 pairs of orthologous genes were identified between eggplant and pepper. The cis-acting elements analysis implied that the eggplant DIR genes contained a lot of cis-elements associated with stress and hormone response. The organ-specific expression analysis of eggplant DIR family genes revealed that only the SmDIR3 gene was highly expressed in all the 19 organs of eggplant. Some SmDIR genes, including SmDIR7, SmDIR8, SmDIR11, SmDIR14, SmDIR18, SmDIR19, SmDIR20, and SmDIR23, were not or were lowly expressed in the eggplant organs, while the other eggplant DIR family genes showed an organ-specific expression pattern. Furthermore, 19 of 24 SmDIR genes were differentially expressed in response to abiotic and biotic stresses. 5 SmDIR genes, including SmDIR3, SmDIR5, SmDIR6, SmDIR12, and SmDIR22, were differentially expressed under multiple types of abiotic and biotic stresses. Especially notable, the SmDIR22 gene was differentially expressed under three types of abiotic stresses and two types of biotic stresses, which indicated that the SmDIR22 gene plays an important role in the response to abiotic and biotic stresses. These results provide valuable evidence for a better understanding of the biological role of DIR genes in eggplant. Full article

In Myanmar, yellow mosaic and leaf curl diseases caused by whitefly-transmitted begomoviruses are serious problems for vegetables such as tomatoes and peppers. To investigate the incidence of begomoviruses in Myanmar between 2017 and 2019, a field survey of tomato and pepper plants with virus-like symptoms was conducted in the Naypyitaw, Tatkon, and Mohnyin areas of Myanmar. Among the 59 samples subjected to begomovirus detection using polymerase chain reaction, 59.3% were infected with begomoviruses. Complete genome sequences using rolling circle amplification identified five begomovirus species: tomato yellow leaf curl Thailand virus (TYLCTHV), tomato yellow leaf curl Kanchanaburi virus (TYLCKaV), tobacco leaf curl Yunnan virus (TbLCYnV), chili leaf curl Pakistan virus (ChiLCV/PK), and tobacco curly shoot Myanmar virus (TbCSV-[Myanmar]). Excluding the previously reported TYLCTHV, three begomoviruses (ChiLCV/PK, TYLCKaV, and TbLCYnV) were identified in Myanmar for the first time. Based on the 91% demarcation threshold of begomovirus species, TbCSV-[Myanmar] was identified as a new species in this study. Among these, ChiLCV/PK and TbCSV-[Myanmar] were the most predominant in tomato and pepper fields in Myanmar. Identification of begomovirus species may be helpful for predicting the origin of viruses and preventing their spread. Full article

Bacterial wilt (BW) disease, which is caused by Ralstonia solanacearum, is one globally prevalent plant disease leading to significant losses of crop production and yield with the involvement of a diverse variety of monocot and dicot host plants. In particular, the BW of the soil-borne disease seriously influences solanaceous crops, including peppers (sweet and chili peppers), paprika, tomatoes, potatoes, and eggplants. Recent studies have explored genetic regions that are associated with BW resistance for pepper crops. However, owing to the complexity of BW resistance, the identification of the genomic regions controlling BW resistance is poorly understood and still remains to be unraveled in the pepper cultivars. In this study, we performed the quantitative trait loci (QTL) analysis to identify genomic loci and alleles, which play a critical role in the resistance to BW in pepper plants. The disease symptoms and resistance levels for BW were assessed by inoculation with R. solanacearum. Genotyping-by-sequencing (GBS) was utilized in 94 F₂ segregating populations originated from a cross between a resistant line, KC352, and a susceptible line, 14F6002-14. A total of 628,437 single-nucleotide polymorphism (SNP) was obtained, and a pepper genetic linkage map was constructed with putative 1550 SNP markers via the filtering criteria. The linkage map exhibited 16 linkage groups (LG) with a total linkage distance of 828.449 cM. Notably, QTL analysis with CIM (composite interval mapping) method uncovered pBWR-1 QTL underlying on chromosome 01 and explained 20.13 to 25.16% by R² (proportion of explained phenotyphic variance by the QTL) values. These results will be valuable for developing SNP markers associated with BW-resistant QTLs as well as for developing elite BW-resistant cultivars in pepper breeding programs. Full article

In response to the difficulty of plant leaf disease detection and classification, this study proposes a novel plant leaf disease detection method called deep block attention SSD (DBA_SSD) for disease identification and disease degree classification of plant leaves. We propose three plant leaf detection methods, namely, squeeze-and-excitation SSD (Se_SSD), deep block SSD (DB_SSD), and DBA_SSD. Se_SSD fuses SSD feature extraction network and attention mechanism channel, DB_SSD improves VGG feature extraction network, and DBA_SSD fuses the improved VGG network and channel attention mechanism. To reduce the training time and accelerate the training process, the convolutional layers trained in the Image Net image dataset by the VGG model are migrated to this model, whereas the collected plant leaves disease image dataset is randomly divided into training set, validation set, and test set in the ratio of 8:1:1. We chose the PlantVillage dataset after careful consideration because it contains images related to the domain of interest. This dataset consists of images of 14 plants, including images of apples, tomatoes, strawberries, peppers, and potatoes, as well as the leaves of other plants. In addition, data enhancement methods, such as histogram equalization and horizontal flip were used to expand the image data. The performance of the three improved algorithms is compared and analyzed in the same environment and with the classical target detection algorithms YOLOv4, YOLOv3, Faster RCNN, and YOLOv4 tiny. Experiments show that DBA_SSD outperforms the two other improved algorithms, and its performance in comparative analysis is superior to other target detection algorithms. Full article

Recently, deep-learning techniques have become the foundations for many breakthroughs in the automated identification of plant diseases. In the agricultural sector, many recent visual-computer approaches use deep-learning models. In this approach, a novel predictive analytics methodology to identify Tobacco Mosaic Virus (TMV) and Pepper Huasteco Yellow Vein Virus (PHYVV) visual symptoms on Jalapeño pepper (Capsicum annuum L.) leaves by using image-processing and deep-learning classification models is presented. The proposed image-processing approach is based on the utilization of Normalized Red-Blue Vegetation Index (NRBVI) and Normalized Green-Blue Vegetation Index (NGBVI) as new RGB-based vegetation indices, and its subsequent Jet pallet colored version NRBVI-Jet NGBVI-Jet as pre-processing algorithms. Furthermore, four standard pre-trained deep-learning architectures, Visual Geometry Group-16 (VGG-16), Xception, Inception v3, and MobileNet v2, were implemented for classification purposes. The objective of this methodology was to find the most accurate combination of vegetation index pre-processing algorithms and pre-trained deep- learning classification models. Transfer learning was applied to fine tune the pre-trained deep- learning models and data augmentation was also applied to prevent the models from overfitting. The performance of the models was evaluated using Top-1 accuracy, precision, recall, and F1-score using test data. The results showed that the best model was an Xception-based model that uses the NGBVI dataset. This model reached an average Top-1 test accuracy of 98.3%. A complete analysis of the different vegetation index representations using models based on deep-learning architectures is presented along with the study of the learning curves of these deep-learning models during the training phase. Full article

Bacterial spot (BS), caused by Xanthomonas campestris pv. Vesicatoria (Xcv), severely affects the quality and yield of pepper. Thus, breeding new pepper cultivars with enhanced resistance to BS can improve economic benefits for pepper production. Identification of BS resistance genes is an essential step to achieve this goal. However, very few BS resistance genes have been well characterized in pepper so far. In this study, we reanalyzed public multiple time points related to RNA-seq data sets from two pepper cultivars, the Xcv-susceptible cultivar ECW and the Xcv-resistant cultivar VI037601, post Xcv infection. We identified a total of 3568 differentially expressed genes (DEGs) between two cultivars post Xcv infection, which were mainly involved in some biological processes, such as Gene Ontology (GO) terms related to defense response to bacterium, immune system process, and regulation of defense response, etc. Through weighted gene co-expression network analysis (WGCNA), we identified 15 hub (Hub) transcription factor (TF) candidates in response to Xcv infection. We further selected 20 TFs from the gene regulatory network (GRN) potentially involved in Xcv resistance response. Finally, we predicted 4 TFs, C3H (p-coumarate 3-hydroxylase), ERF (ethylene-responsive element binding factor), TALE (three-amino-acid-loop-extension), and HSF (heat shock transcription factor), as key factors responsible for BS disease resistance in pepper. In conclusion, our study provides valuable resources for dissecting the underlying molecular mechanism responsible for Xcv resistance in pepper. Additionally, it also provides valuable references for mining transcriptomic data to identify key candidates for disease resistance in horticulture crops. Full article

Red pepper (Capsicum annuum, L.), is one of the most important spice plants in Korea. Overwintering pepper fruits are a reservoir of various microbial pepper diseases. Here, we conducted metagenomics (DNA sequencing) and metatranscriptomics (RNA sequencing) using samples collected from three different fields. We compared two different library types and three different analytical methods for the identification of microbiomes in overwintering pepper fruits. Our results demonstrated that DNA sequencing might be useful for the identification of bacteria and DNA viruses such as bacteriophages, while mRNA sequencing might be beneficial for the identification of fungi and RNA viruses. Among three analytical methods, KRAKEN2 with raw data reads (KRAKEN2_R) might be superior for the identification of microbial species to other analytical methods. However, some microbial species with a low number of reads were wrongly assigned at the species level by KRAKEN2_R. Moreover, we found that the databases for bacteria and viruses were better established as compared to the fungal database with limited genome data. In summary, we carefully suggest that different library types and analytical methods with proper databases should be applied for the purpose of microbiome study. Full article