“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Reliable, automatic, multifunctional, and high-throughput phenotypic technologies are increasingly considered important tools for rapid advancement of genetic gain in breeding programs. With the rapid development in high-throughput phenotyping technologies, research in this area is entering a new era called 'phenomics.' The crop phenotyping community not only needs to build a multi-domain, multi-level, and multi-scale crop phenotyping big database, but also to research technical systems for phenotypic traits identification and develop bioinformatics technologies for information extraction from the overwhelming amounts of omics data. Here, we provide an overview of crop phenomics research, focusing on two parts, from phenotypic data collection through various sensors to phenomics analysis. Finally, we discussed the challenges and prospective of crop phenomics in order to provide suggestions to develop new methods of mining genes associated with important agronomic traits, and propose new intelligent solutions for precision breeding.

/pdf/crop-phenomics-current-status-and-perspectives-ox8gp5q121.pdf

Crop Phenomics: Current Status and Perspectives.

Crop yields need to be improved in a sustainable manner to meet the expected worldwide increase in population over the coming decades as well as the effects of anticipated climate change Recently, genomics-assisted breeding has become a popular approach to food security; in this regard, the crop breeding community must better link the relationships between the phenotype and the genotype While high-throughput genotyping is feasible at a low cost, high-throughput crop phenotyping methods and data analytical capacities need to be improved

/pdf/high-throughput-estimation-of-crop-traits-a-review-of-ground-4ej5it3p3y.pdf

High-Throughput Estimation of Crop Traits: A Review of Ground and Aerial Phenotyping Platforms

Yield potential is a commonly used term but its definition and measurement are quite vague. The absence of agreement in its definition and measurement can lead to misunderstanding and to misleading claims. Considering concepts in literature, this paper has adopted a clear definition and distinction between yield potential and potential yield. Yield potential is the yield of a cultivar when grown in environments to which it is adapted; with nutrients and water nonlimiting and with pests, diseases, weeds, lodging, and other stresses effectively controlled. Potential yield is the maximum yield that could be reached by a crop in given environments such as those determined by simulation models with reasonable physiological and agronomic assumptions. Direct and indirect measurements of progress in yield potential among crops have been discussed in this paper with care for complications arising from cultivar by environment interaction.

Yield potential: its definition, measurement, and significance

Phenotyping of crops is important due to increasing pressure on food production. Therefore, an accurate estimation of biomass during the growing season can be important to optimize the yield. The potential of data acquisition by UAV-LiDAR to estimate fresh biomass and crop height was investigated for three different crops (potato, sugar beet, and winter wheat) grown in Wageningen (The Netherlands) from June to August 2018. Biomass was estimated using the 3DPI algorithm, while crop height was estimated using the mean height of a variable number of highest points for each m2. The 3DPI algorithm proved to estimate biomass well for sugar beet (R2 = 0.68, RMSE = 17.47 g/m2) and winter wheat (R2 = 0.82, RMSE = 13.94 g/m2). Also, the height estimates worked well for sugar beet (R2 = 0.70, RMSE = 7.4 cm) and wheat (R2 = 0.78, RMSE = 3.4 cm). However, for potato both plant height (R2 = 0.50, RMSE = 12 cm) and biomass estimation (R2 = 0.24, RMSE = 22.09 g/m2), it proved to be less reliable due to the complex canopy structure and the ridges on which potatoes are grown. In general, for accurate biomass and crop height estimates using those algorithms, the flight conditions (altitude, speed, location of flight lines) should be comparable to the settings for which the models are calibrated since changing conditions do influence the estimated biomass and crop height strongly.

/pdf/biomass-and-crop-height-estimation-of-different-crops-using-3f2v4rpdx2.pdf

Biomass and Crop Height Estimation of Different Crops Using UAV-Based Lidar

Digital watermarking has been widely used to protect the copyright and integrity of multimedia data. Previous studies mainly focus on designing watermarking techniques that are robust to attacks of destroying the embedded watermarks. However, the emerging deep learning based image generation technology raises new open issues that whether it is possible to generate fake watermarked images for circumvention. In this paper, we make the first attempt to develop digital image watermark fakers by using generative adversarial learning. Suppose that a set of paired images of original and watermarked images generated by the targeted watermarker are available, we use them to train a watermark faker with U-Net as the backbone, whose input is an original image, and after a domain-specific preprocessing, it outputs a fake watermarked image. Our experiments show that the proposed watermark faker can effectively crack digital image watermarkers in both spatial and frequency domains, suggesting the risk of such forgery attacks.

Watermark Faker: Towards Forgery of Digital Image Watermarking

In an increasingly information-based modern society, online shopping has gradually become the first choice for people to buy goods. Therefore, more and more e-commerce platforms have emerged, such as Tmall, JD, etc., and e-commerce economy has gradually become an important part of promoting social progress. Since most e-commerce reviews are short texts, it takes a lot of time for consumers to search for useful information for themselves. Therefore, this paper clusters short texts for the first time, and takes the user's review text as the input of the model to get the clustering results. The review text with similar views will be grouped into the same cluster, At the same time, we can get the topic words in each cluster, that is, where consumers pay most attention in the consumption process. Due to the large number of comment texts, we use Dirichlet and multinomial mixed model as the first clustering model, because this model does not need to set the clusters number in advance, and has good performance on large-scale data sets. For the results of the first clustering, although consumers' concerns can be analysed, it is difficult to judge consumers' attitudes, so we take the subject words in the clustering results as input to form a new short text, use TF-IDF to extract the features of the short text constructed by the subject words, then use K-means method to judge the emotional polarity, and then use homogeneity, integrity NMI effectively evaluates the clustering results. Through the experimental results of two clusters, we can clearly find out where consumers pay most attention after purchasing a certain commodity. For example, after purchasing clothes, most consumers focus on the materials and brands of clothes. After clustering, we can get the clustering results of all consumers and the clustering subject words, that is, consumers in the same cluster have similar concerns about goods. After the second clustering, the emotional polarity of consumers can be analyzed, which is of positive significance to consumers' purchase decisions.

Feiyu Zhu

Papers

Watermark Faker: Towards Forgery of Digital Image Watermarking

Research on multimodal clustering method for E-commerce review