• Journal of Biosystems Engineering
• /
• v.40 no.1
• /
• pp.89-93
• /
• 2015

Purpose: Machine vision-based image processing methods can be useful for estimating the fresh weight of plants. This study analyzes the ability of two different image processing methods, i.e., morphological and pixel-value analysis methods, to measure the fresh weight of lettuce grown in a closed hydroponic system. Methods: Polynomial calibration models are developed to relate the number of pixels in images of leaf areas determined by the image processing methods to actual fresh weights of lettuce measured with a digital scale. The study analyzes the ability of the machine vision- based calibration models to predict the fresh weights of lettuce. Results: The coefficients of determination (> 0.93) and standard error of prediction (SEP) values (< 5 g) generated by the two developed models imply that the image processing methods could accurately estimate the fresh weight of each lettuce plant during its growing stage. Conclusions: The results demonstrate that the growing status of a lettuce plant can be estimated using leaf images and regression equations. This shows that a machine vision system installed on a plant growing bed can potentially be used to determine optimal harvest timings for efficient plant growth management.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.5
• /
• pp.959-968
• /
• 2019

In the agricultural industry, wireless sensor network technology has being applied by utilizing various sensors and embedded systems. In particular, a lot of researches are being conducted to diagnose diseases of crops early by using sensor network. There are some difficulties on traditional research how to diagnose crop diseases is not practical for agriculture. This paper proposes the algorithm which enables to investigate and analyze the crop leaf image taken by image camera and detect the infected area within the image. We applied the enhanced k-means clustering method to the images captured at horticulture facility and categorized the areas in the image. Then we used the edge detection and edge tracking scheme to decide whether the extracted areas are located in inside of leaf or not. The performance was evaluated using the images capturing tomato leaves. The results of performance evaluation shows that the proposed algorithm outperforms the traditional algorithms in terms of classification capability.

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.149-158
• /
• 2024

Traditional manual identification of crop leaf diseases is challenging. Owing to the limitations in manpower and resources, it is challenging to explore crop diseases on a large scale. The emergence of artificial intelligence technologies, particularly the extensive application of deep learning technologies, is expected to overcome these challenges and greatly improve the accuracy and efficiency of crop disease identification. Crop leaf disease identification models have been designed and trained using large-scale training data, enabling them to predict different categories of diseases from unlabeled crop leaves. However, these models, which possess strong feature representation capabilities, require substantial training data, and there is often a shortage of such datasets in practical farming scenarios. To address this issue and improve the feature learning abilities of models, this study proposes a deep transfer learning adaptation strategy. The novel proposed method aims to transfer the weights and parameters from pre-trained models in similar large-scale training datasets, such as ImageNet. ImageNet pre-trained weights are adopted and fine-tuned with the features of crop leaf diseases to improve prediction ability. In this study, we collected 16,060 crop leaf disease images, spanning 12 categories, for training. The experimental results demonstrate that an impressive accuracy of 98% is achieved using the proposed method on the transferred ResNet-50 model, thereby confirming the effectiveness of our transfer learning approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3708-3728
• /
• 2021

Indian herbal plants are used in agriculture and in the food, cosmetics, and pharmaceutical industries. Laboratory-based tests are routinely used to identify and classify similar herb species by analyzing their internal cell structures. In this paper, we have applied computer vision techniques to do the same. The original leaf image was preprocessed using the Chan-Vese active contour segmentation algorithm to efface the background from the image by setting the contraction bias as (v) -1 and smoothing factor (µ) as 0.5, and bringing the initial contour close to the image boundary. Thereafter the segmented grayscale image was fed to a leaky capacitance fired neuron model (LCFN), which differentiates between similar herbs by combining different groups of pixels in the leaf image. The LFCN's decay constant (f), decay constant (g) and threshold (h) parameters were empirically assigned as 0.7, 0.6 and h=18 to generate the 1D feature vector. The LCFN time sequence identified the internal leaf structure at different iterations. Our proposed framework was tested against newly collected herbal species of natural images, geometrically variant images in terms of size, orientation and position. The 1D sequence and shape features of aloe, betel, Indian borage, bittergourd, grape, insulin herb, guava, mango, nilavembu, nithiyakalyani, sweet basil and pomegranate were fed into the 5-fold Bayesian regularization neural network (BRNN), K-nearest neighbors (KNN), support vector machine (SVM), and ensemble classifier to obtain the highest classification accuracy of 91.19%.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.2
• /
• pp.95-114
• /
• 2022

This study presented the possibility of automatic frost observation and the related image data acquisition through the design and installation of a Multiple-sensor based Frost Observation System (MFOS). The MFOS is composed of an RGB camera, a thermal camera and a leaf wetness sensor, and each device performs complementary roles. Through the test operation of the equipment before the occurrence of frost, the voltage value of the leaf wetness sensor increased when maintaining high relative humidity in the case of no precipitation. In the case of Gapyeong- gun, the high relative humidity was maintained due to the surrounding agricultural waterways, so the voltage value increased significantly. In the RGB camera image, leaf wetness sensor and the surface were not observed before sunrise and after sunset, but were observed for the rest of the time. In the case of precipitation, the voltage value of the leaf wetness sensor rapidly increased during the precipitation period and decreased after the precipitation was terminated. In the RGB camera image, the leaf wetness sensor and surface were observed regardless of the precipitation phenomenon, but the thermal camera image was taken due to the precipitation phenomenon, but the leaf wetness sensor and surface were not observed. Through, where actual frost occurred, it was confirmed that the voltage value of leaf wetness sensor was higher than the range corresponding to frost, but frost was observed on the surface and equipment surface by the RGB camera.

• Journal of Ecology and Environment
• /
• v.32 no.1
• /
• pp.61-65
• /
• 2009

We compared two nondestructive methods for leaf area estimation using leaves of 16 common plant species classified into six types depending on leaf shape. Relatively good linear relationships between actual leaf area (LA) and leaf length (L), width (W), or the product of length and width (LW) were found for ordinary leaves with lanceolate, oblanceolate, linear and sagitttate shapes with entire margins, serrate margins, mixed margins with a entire form and shallow lobes, and ordinary incised margins. LA was better correlated with LW than L or W, with $R^2$ > 0.91. However, for deeply incised lobes, LA estimation using LW showed low correlation coefficient values, indicating low accuracy. On the other hand, a method using photographic paper showed a good correlation between estimates of area based on the mass of a cut-out leaf image on a photographic sheet (PW) and actual leaf area for all types of leaf shape. Thus, the PW method for LA estimation can be applied to all shapes of leaf with high accuracy. The PW method takes a little more time and has a higher cost than leaf estimation methods using LW based on leaf dimensions. These results indicate that researchers should choose their nondestructive LA estimation method according to their research goals.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.11 no.1
• /
• pp.55-60
• /
• 1993

Forest occupied a part of natural ecosystem carries out a role of purifying air, preserving water resource, prevention of the breeding and extermination, recreation areas and etc that preserve and for me one's living environment. In this study, the classification for management of this forest is performed with Landsat TM Image. The classes are decided needle-leaf trees, broad-leaf trees, farming land and grass land, and water. When the TM digital images are classified on computer, water is represented in 7∼13 D.N. of 4th band. But the others is appeared similar mostly specific values so that must be done image processing. When the images compounded 2ed band and 3ed band are processed with ratio of enhancement. Needle-leaf treas is represented in l18∼136 D.N. of 1st band, broad-leaf trees in 72∼91 D.N. of 3ed band, farm land and glass land in 96∼120 of 3ed band. Forest Information is classified with M.L.C, an image classification method. The errors of needle-leaf trees, broad-leaf trees, farm land and grass land, and water are appeared each －7.43, ＋1.89,＋7.58 and －2.04 as compared the digital image with investigation on the scene. Finally, these results are useful for classification of forest vegetation with Landsat TM Image.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.25 no.3
• /
• pp.101-110
• /
• 1997

The purpose of this study was on suggesting what is the image and image formation factor of interior landscaping plants. For this purpose, the sixty interior landscaping plants were selected. Selected plants were classified into 9 groups by similar characteristics of plants, for example, leaf color and leaf pattern. Data analysis were performed by semantic differential scale method, mean score and multiple regression algorithm. The results are as follows, 1. Comparing with image assessment, group 9 got the highest score in all aspects. 2. Comparing with the image assessment of interior landscaping plants, the "impressive" image was obtained the highest score and "bright", "cool", "beautiful" and "fresh" were followed. 3. Multiple regression analysis was performed to clarify influence degree of the adjectives related to the beauty. The next adjectives were significant check points on assessing the beauty of interior landscaping plants. Also, Guzmania magnifical was investigated to have the most beautiful image with the results of preference analysis. Vriesea splendens, Cordyline terminalis Kunth 'Lilliput' and Peperomia sandersii were identified as considerably preferred plants. were identified as considerably preferred plants.

• 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 KSRS Conference
• /
• 2005.10a
• /
• pp.7-10
• /
• 2005

Plant water deficiency during drought season causes physiological stress and can be a critical indicator of forest fire vulnerability. In this study, we attempt to analyze the spectral characteristics of water stressed vegetation by using the laboratory measurement on leaf samples and the canopy reflectance spectra extracted from satellite hyperspectral image data. Leaf-level reflectance spectra were measured by varying moisture content using a portable spectro-radiometer. Canopy reflectance spectra of sample forest stands of two primary species (pine and oak) located in central part of the Korean peninsula were extracted from EO-l Hyperion imaging spectrometer data obtained during the drought season in 2001 and the normal precipitation year in 2002. The preliminary analysis on the reflectance spectra shows that the spectral characteristics of leaf samples are not compatible with the ones obtained from canopy level. Although moisture content of vegetation can be influential to the radiant flux reflected from leaf-level, it may not be very straightforward to obtain the spectral characteristics that are directly related to the level of canopy moisture content. Canopy spectra form forest stands can be varied by structural variables (such as LAt, percent coverage, and biomass) other than canopy moisture content.