In this paper, we present a new idea to analyze facial expression by exploring some common and specific information among different expressions. Inspired by the observation that only a few facial parts are active in expression disclosure (e.g. around mouth, eye), we try to discover the common and specific patches which are important to discriminate all the expressions and only a particular expression, respectively. A two-stage multi-task sparse learning (MTSL) framework is proposed to efficiently locate those discriminative patches. In the first stage MTSL, expression recognition tasks, each of which aims to find dominant patches for each expression, are combined to located common patches. Second, two related tasks, facial expression recognition and face verification tasks, are coupled to learn specific facial patches for individual expression. Extensive experiments validate the existence and significance of common and specific patches. Utilizing these learned patches, we achieve superior performances on expression recognition compared to the state-of-the-arts.
SummaryFusarium head blight (FHB) and Fusarium seedling blight (FSB) of wheat, caused by Fusarium pathogens, are devastating diseases worldwide. We report the expression of RNA interference (RNAi) sequences derived from an essential Fusarium graminearum (Fg) virulence gene, chitin synthase (Chs) 3b, as a method to enhance resistance of wheat plants to fungal pathogens. Deletion of Chs3b was lethal to Fg; disruption of the other Chs gene family members generated knockout mutants with diverse impacts on Fg. Comparative expression analyses revealed that among the Chs gene family members, Chs3b had the highest expression levels during Fg colonization of wheat. Three hairpin RNAi constructs corresponding to the different regions of Chs3b were found to silence Chs3b in transgenic Fg strains. Co-expression of these three RNAi constructs in two independent elite wheat cultivar transgenic lines conferred high levels of stable, consistent resistance (combined type I and II resistance) to both FHB and FSB throughout the T 3 to T 5 generations. Confocal microscopy revealed profoundly restricted mycelia in Fginfected transgenic wheat plants. Presence of the three specific short interfering RNAs in transgenic wheat plants was confirmed by Northern blotting, and these RNAs efficiently downregulated Chs3b in the colonizing Fusarium pathogens on wheat seedlings and spikes. Our results demonstrate that host-induced gene silencing of an essential fungal chitin synthase gene is an effective strategy for enhancing resistance in crop plants under field test conditions.
Understanding how plants respond to drought can benefit drought resistance (DR) breeding. Using a non-destructive phenotyping facility, 51 image-based traits (i-traits) for 507 rice accessions were extracted. These i-traits can be used to monitor drought responses and evaluate DR. High heritability and large variation of these traits was observed under drought stress in the natural population. A genome-wide association study (GWAS) of i-traits and traditional DR traits identified 470 association loci, some containing known DR-related genes. Of these 470 loci, 443 loci (94%) were identified using i-traits, 437 loci (93%) co-localized with previously reported DR-related quantitative trait loci, and 313 loci (66.6%) were reproducibly identified by GWAS in different years. Association networks, established based on GWAS results, revealed hub i-traits and hub loci. This demonstrates the feasibility and necessity of dissecting the complex DR trait into heritable and simple i-traits. As proof of principle, we illustrated the power of this integrated approach to identify previously unreported DR-related genes. OsPP15 was associated with a hub i-trait, and its role in DR was confirmed by genetic transformation experiments. Furthermore, i-traits can be used for DR linkage analyses, and 69 i-trait locus associations were identified by both GWAS and linkage analysis of a recombinant inbred line population. Finally, we confirmed the relevance of i-traits to DR in the field. Our study provides a promising novel approach for the genetic dissection and discovery of causal genes for DR.
BackgroundRice panicle phenotyping is important in rice breeding, and rice panicle segmentation is the first and key step for image-based panicle phenotyping. Because of the challenge of illumination differentials, panicle shape deformations, rice accession variations, different reproductive stages and the field’s complex background, rice panicle segmentation in the field is a very large challenge.ResultsIn this paper, we propose a rice panicle segmentation algorithm called Panicle-SEG, which is based on simple linear iterative clustering superpixel regions generation, convolutional neural network classification and entropy rate superpixel optimization. To build the Panicle-SEG-CNN model and test the segmentation effects, 684 training images and 48 testing images were randomly selected, respectively. Six indicators, including Qseg, Sr, SSIM, Precision, Recall and F-measure, are employed to evaluate the segmentation effects, and the average segmentation results for the 48 testing samples are 0.626, 0.730, 0.891, 0.821, 0.730, and 76.73%, respectively. Compared with other segmentation approaches, including HSeg, i2 hysteresis thresholding and jointSeg, the proposed Panicle-SEG algorithm has better performance on segmentation accuracy. Meanwhile, the executing speed is also improved when combined with multithreading and CUDA parallel acceleration. Moreover, Panicle-SEG was demonstrated to be a robust segmentation algorithm, which can be expanded for different rice accessions, different field environments, different camera angles, different reproductive stages, and indoor rice images. The testing dataset and segmentation software are available online.ConclusionsIn conclusion, the results demonstrate that Panicle-SEG is a robust method for panicle segmentation, and it creates a new opportunity for nondestructive yield estimation.Electronic supplementary materialThe online version of this article (10.1186/s13007-017-0254-7) contains supplementary material, which is available to authorized users.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.