• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.4
• /
• pp.1-8
• /
• 2019

Plant phenomics is a technique for observing and analyzing morphological features in order to select plant varieties of excellent traits. The conventional methods is difficult to apply to the phenomics system. because the color threshold value must be manually changed according to the detection target. In this paper, we propose the convolution neural network (CNN) structure that can automatically segment plants from the background for the phenomics system. The LeafNet consists of nine convolution layers and a sigmoid activation function for determining the presence of plants. As a result of the learning using the LeafNet, we obtained a precision of 98.0% and a recall rate of 90.3% for the plant seedlings images. This confirms the applicability of the phenomics system.

• Korean Journal of Breeding Science
• /
• v.43 no.4
• /
• pp.233-240
• /
• 2011

Food security has been a main global issue due to climate changes and growing world population expected to 9 billion by 2050. While biodiversity is becoming more highlight, breeders are confronting shortage of various genetic materials needed for new variety to tackle food shortage challenge. Though biotechnology is still under debate on potential risk to human and environment, it is considered as one of alternative tools to address food supply issue for its potential to create a number of variations in genetic resource. The new technology, phenomics, is developing to improve efficiency of crop improvement. Phenomics is concerned with the measurement of phenomes which are the physical, morphological, physiological and/or biochemical traits of organisms as they change in response to genetic mutation and environmental influences. It can be served to provide better understanding of phenotypes at whole plant. For last decades, high-throughput screening (HTS) systems have been developed to measure phenomes, rapidly and quantitatively. Imaging technology such as thermal and chlorophyll fluorescence imaging systems is an area of HTS which has been used in agriculture. In this article, we review the current statues of high-throughput screening system in phenomics and its application for crop improvement.

• Journal of Plant Biotechnology
• /
• v.43 no.1
• /
• pp.21-29
• /
• 2016

Remote Sensing (RS) is a technique to obtain necessary information in a non-contact and non-destructive method by using various sensors on the surface, water or atmospheric phenomena. These techniques combine elements such as sensors, and platform and information communication technology (ICT) for mounting the sensor. ICT has contributed significantly to the success of smart agriculture through quantification and measurement of environmental factors and information such as weather, crop and soil management to distribution and consumption stage, as well as the production stage by the cloud computer. Remote sensing techniques, including non-destructive non-contact bioimaging (remote imaging) is required to measure the plant function. In addition, bioimaging study in plant science is performed at the gene, cellular and individual plant level. Recently, bioimaging technology is considered the latest phenomics that identifies the relationship between the genotype and environment for distinguishing phenotypes. In this review, trends in remote sensing in plants, plants diagnostics and response to environment and status of plants phonemics research were presented.

• Korean Journal of Agricultural Science
• /
• v.47 no.1
• /
• pp.119-130
• /
• 2020

With the current rapid growth and increase in the world's population, the demand for nutritious food and fibers and fuel will increase. Therefore, there is a serious need for the use of breeding programs with the full potential to produce high-yielding crops. However, existing breeding techniques are unable to meet the demand criteria even though genotyping techniques have significantly progressed with the discovery of molecular markers and next-generation sequencing tools, and conventional phenotyping techniques lag behind. Well-organized high-throughput plant phenotyping platforms have been established recently and developed in different parts of the world to address this problem. These platforms use several imaging techniques and technologies to acquire data for quantitative studies related to plant growth, yield, and adaptation to various types of abiotic or biotic stresses (drought, nutrient, disease, salinity, etc.). Phenotyping has become an impediment in genomics studies of plant breeding. In recent years, phenomics, an emerging domain that entails characterizing the full set of phenotypes in a given species, has appeared as a novel approach to enhance genomics data in breeding programs. Imaging techniques are of substantial importance in phenomics. In this study, the importance of current imaging technologies and their applications in plant phenotyping are reviewed, and their advantages and limitations in phenomics are highlighted.

• Korean Journal of Agricultural Science
• /
• v.45 no.3
• /
• pp.317-323
• /
• 2018

The demand for crop production is increasingly becoming steeper due to the rapid population growth. As a result, breeding cycles should be faster than ever before. However, the current breeding methods cannot meet this requirement because traditional phenotyping methods lag far behind even though genotyping methods have been drastically developed with the advent of next-generation sequencing technology over a short period of time. Consequently, phenotyping has become a bottleneck in large-scale genomics-based plant breeding studies. Recently, however, phenomics, a new discipline involving the characterization of a full set of phenotypes in a given species, has emerged as an alternative technology to come up with exponentially increasing genomic data in plant breeding programs. There are many advantages for using new technologies in phenomics. Yet, the necessity of diverse man power and huge funding for cutting-edge equipment prevent many researchers who are interested in this area from adopting this new technique in their research programs. Currently, only a limited number of groups mostly in developed countries have initiated phenomic studies using high throughput methods. In this short article, we describe the strategies to compete with those advanced groups using limited resources in developing countries, followed by a brief introduction of high throughput phenotyping.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2020.11a
• /
• pp.32-32
• /
• 2020

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.923-935
• /
• 2022

This paper deals with detection and classification of leaf diseases for phenomics systems. As the smart farm systems of plants are increased, It is important to determine quickly the abnormal growth of plants without supervisors. This paper considers the color distribution and shape information of leaf diseases, and designs two deep leaning networks in training the leaf diseases. In the first step, color distribution of input image is analyzed for possible diseases. In the second step, the image is first partitioned into small segments using mean shift clustering, and the color information of each segment is inspected by the proposed Color Network. When a segment is determined as disease, the shape parameters of the segment are extracted and inspected by proposed Shape Network to classify the leaf disease types in the third step. According to the experiments with two types of diseases (frogeye/rust and tipburn) for apple leaves and iceberg, the leaf diseases are detected with 92.3% recall for a segment and with 99.3% recall for an input image where there are usually more than two disease segments. The proposed method is useful for detecting leaf diseases quickly in the smart farm environment, and is extendible to various types of new plants and leaf diseases without additional learning.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.186-189
• /
• 2022

스마트팜 피노믹스 시스템은 재배하는 식물의 성장조건에 맞게 생육 환경을 일정하게 유지하고 관리하는 장치이지만, 그럼에도 불구하고 식물의 질병은 여러 가지 이유로 발생할 수 있다. 본 논문에서는 스마트팜 피노믹스 시스템에서 Mean Shift Segmentation 을 통한 식물의 질병을 자동으로 검출하는 식물 질병 검출 알고리즘을 제안한다. 식물의 질병 정도가 임의의 임계값을 넘을 경우, 해당 식물을 질병의 정도가 심한 식물로 판별하고, 적절한 수확시기를 결정하여 더 나은 상품성을 가진 식물을 재배할 수 있는 방법을 제시한다. 또한 식물의 질병이 급격하게 심해지는 기간을 확인하여 인간의 개입 없이 완전히 자동화된 시스템으로 더욱 세심하고 효율적인 식물 재배를 가능하게 함을 제시한다. 본 논문에서는 아이스버그(양상추)에 대한 재배 환경을 구축하여 생장 기간에 아이스버그에 발생하는 질병인 팁번 현상을 검출하는 실험을 진행하였다. 본 논문에서 제안한 방법은 다른 종류의 다양한 식물에서도 질병 검출이 가능하며, 스마트팜 피노믹스 시스템에서 질병 검출의 자동화를 위한 한 가지 방법으로 활용될 수 있을 것으로 기대된다.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1101-1107
• /
• 2022

The leaf temperature is principally regulated by the opening and closing of stomata that is sensitive to various kinds of plant physiological stress. Thus, the analysis of thermal imagery, one of remote sensing technique, will be useful to detect crop physiological condition on smart farm system and phenomics platform. However, there are few case studies using a thermal imaging camera on the agricultural application. In this study, three cases are presented: the effect of lime fertilizer on the rice, the different physiological properties of soybean under shading condition, and the screening of soybean breeds for salinity tolerance characteristic. The leaf temperature measured by thermal imaging camera on the three cases was used effectively to the physiological change and characteristics. However, the thermal imagery analysis requires considering the accuracy of measured temperature and the weather conditions that affects to the leaf temperature.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.66 no.4
• /
• pp.350-357
• /
• 2021

In the present study, the seed color of 200 common bean genetic resources was analyzed and located on the HTML color chart to classify these resources according to color characteristics. This classification method predicts the components of seed and may serve as a new method for efficiently using secured genetic resources. The imagary data of common bean exhibiting various seed colors were expressed using the HTML color chart. According to the proposed classification method, the seed color was distributed in seven categories: yellow-green, yellow, brown, red, white, gray, and indigo. In addition, the distribution of each seed color was according to its concentration. The distribution by concentration was the highest for red, whereas the distribution of gray and yellow-green was not concentration-dependent. As the dominant pigments based on color distribution, chlorophylls in yellow-green; carotenoids in yellow; and anthocyanins in brown, red, white, gray, and indigo significantly affected seed color. When expressed objectively, seed colors can be applied to the systematic management, breeding, and cultivation of genetic resources and can be useful for marketing or developing products of desired colors. This method can also be applied to other crops.