• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.265-271
• /
• 2015

This study proposes an algorithm for recognizing apple trees in images and detecting apples to measure the number of apples on the trees. The proposed algorithm explores whether there are apple trees or not based on the number of image block-unit edges, and then it detects apple areas. In order to extract colors appropriate for apple areas, the CIE $L^*a^*b^*$ color space is used. In order to extract apple characteristics strong against illumination changes, modified census transform (MCT) is used. Then, using the AdaBoost learning algorithm, characteristics data on the apples are learned and generated. With the generated data, the detection of apple areas is made. The proposed algorithm has a higher detection rate than existing pixel-based image processing algorithms and minimizes false detection.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.324-330
• /
• 2021

Agriculture is one of the essential needs of human life on planet Earth. It is the source of food and earnings for many individuals around the world. The economy of many countries is associated with the agriculture sector. Lots of diseases exist that attack various fruits and crops. Apple Tree Leaves also suffer different types of pathological conditions that affect their production. These pathological conditions include apple scab, cedar apple rust, or multiple diseases, etc. In this paper, an automatic detection framework based on deep learning is investigated for apple leaves disease classification. Different pre-trained models, VGG16, ResNetV2, InceptionV3, and MobileNetV2, are considered for transfer learning. A combination of parameters like learning rate, batch size, and optimizer is analyzed, and the best combination of ResNetV2 with Adam optimizer provided the best classification accuracy of 94%.

• Journal of IKEEE
• /
• v.28 no.2
• /
• pp.150-157
• /
• 2024

In this paper, we propose a novel algorithm for predicting the number of apples on an apple tree using a deep learning-based object detection model and a polynomial regression model. Measuring the number of apples on an apple tree can be used to predict apple yield and to assess losses for determining agricultural disaster insurance payouts. To measure apple fruit load, we photographed the front and back sides of apple trees. We manually labeled the apples in the captured images to construct a dataset, which was then used to train a one-stage object detection CNN model. However, when apples on an apple tree are obscured by leaves, branches, or other parts of the tree, they may not be captured in images. Consequently, it becomes difficult for image recognition-based deep learning models to detect or infer the presence of these apples. To address this issue, we propose a two-stage inference process. In the first stage, we utilize an image-based deep learning model to count the number of apples in photos taken from both sides of the apple tree. In the second stage, we conduct a polynomial regression analysis, using the total apple count from the deep learning model as the independent variable, and the actual number of apples manually counted during an on-site visit to the orchard as the dependent variable. The performance evaluation of the two-stage inference system proposed in this paper showed an average accuracy of 90.98% in counting the number of apples on each apple tree. Therefore, the proposed method can significantly reduce the time and cost associated with manually counting apples. Furthermore, this approach has the potential to be widely adopted as a new foundational technology for fruit load estimation in related fields using deep learning.

• Journal of agriculture & life science
• /
• v.43 no.6
• /
• pp.105-109
• /
• 2009

Kyungsan nursery complex which has a vast area for the production of various species of fruit tree stocks is in a high demand of virus-free saplings. Apple tree stocks, the most important products, urgently need more rapid and reliable viral diagnosis. In this study, a bead beater was tested because of convenience in dealing with large number of samples. Also, industrial glass bead abrasive (0.4 mm in diameter) at very low cost was used in a disposable way. For bead beater-aided RNA extraction from apple stem tissues, the guanidine thiocyanate method was confirmed to be very reliable. Silca membrane filter tube in connection to vacuum filtering device was strongly suggested for simplifying RNA capture and washing steps. Apple virus detection was confirmed by RT-PCR.

• The Plant Pathology Journal
• /
• v.35 no.2
• /
• pp.164-171
• /
• 2019

An assay for detecting Apple scar skin viroid (ASSVd) was developed based on nucleic acid sequence based amplification (NASBA) in combination with realtime detection during the amplification process using molecular beacon. The ASSVd specific primers for amplification of the viroid RNA and molecular beacon for detecting the viroid were designed based on highly conserved regions of several ASSVd sequences including Korean isolate. The assay had a detection range of $1{\times}10^4$ to $1{\times}10^{12}$ ASSVd RNA $copies/{\mu}l$ with reproducibility and precision. Following the construction of standard curves based on time to positive (TTP) value for the serial dilutions ranging from $1{\times}10^7$ to $1{\times}10^{12}$ copies of the recombinant plasmid, a standard regression line was constructed by plotting the TTP values versus the logarithm of the starting ASSVd RNA copy number of 10-fold dilutions each. Compared to the established RT-PCR methods, our method was more sensitive for detecting ASSVd. The real-time quantitative NASBA method will be fast, sensitive, and reliable for routine diagnosis and selection of viroid-free stock materials. Furthermore, real-time quantitative NASBA may be especially useful for detecting low levels in apple trees with early viroid-infection stage and for monitoring the influence on tree growth.

• Proceedings of the Korean Society of Plant Pathology Conference
• /
• 2002.11a
• /
• pp.126-126
• /
• 2002

• The Plant Pathology Journal
• /
• v.22 no.1
• /
• pp.63-67
• /
• 2006

Apple scar skin, one of the most destructive diseases affecting apple, is caused by Apple scar skin viroid (ASSV d). Fruit dappling appeared on several cultivars in Korea and has been distributed to major cultivated areas since 2001. ASSVd was identified from infected fruits by using nucleic acid sequence-based amplification with electrochemiluminescence (NASBA-ECL). NASBA-ECL method was faster and hundredfold more sensitive than reverse transcription-polymerase chain reaction (RT-PCR) for ASSVd detection in apple leaves/ stems. ASSVd was rapidly transmitted to the entire tree in the second year after artificial inoculation. The ASSVd could be transmitted efficiently by using contaminated pruning scissors to both lignified stems (60 to $70\%$) and green shoots (20 to $40\%$) of apple tree and young plants. Dipping of contaminated scissors in $2\%$ sodium hypochlorite solution effectively prevented viroid transmission. In the ASSV d-infected fruits, the viroid was easily detected from fruit skin, seed coat, and embryo. Moreover, embryo and endosperm separately excised from the ASSVd-infected seeds were ASSVd positive in NASBA-ECL assay. Seedlings germinated from ASSVd-positive seeds showed $7.7\%$ infection rate., which indicated that ASSVd is seed-borne.

• Journal of Biosystems Engineering
• /
• v.41 no.3
• /
• pp.255-262
• /
• 2016

Purpose: Fuji apples are one of the top selling exports for South Korea bringing in over $233.4 million in 2013. However, during the last few decades, about half of the Fuji apple orchards have been infected by Apple Marssonina Blotch disease (AMB), a fungal disease caused by Diplocarpon mali., which takes about 40 days to exhibit obvious visible symptoms. Infected leaves turn yellow and begin growing brown lesions. AMB promotes early defoliation and reduces the quality and quantity of apples an infected tree can produce. Currently, there is no prediction model for AMB on the market. Methods: The Precision Agriculture Laboratory (PAL) at the University of Florida (UF) has been working with the National Academy of Agricultural Science, Rural Development Administration, South Korea to investigate the use of hyperspectral data in creating an early detection method for AMB. The RDA has been researching hyperspectral techniques for disease detection at their Apple Research Station in Gunwi since 2012 and disseminates its findings to the local farmers. These farmers were surveyed to assess the state of knowledge of AMB in the area. Out of a population of about 750 growers, 111 surveys were completed (confidence interval of +/- 8.59%, confidence level of 95%, p-value of 0.05). Results: The survey revealed 32% of the farmers did not know what AMB was, but 45% of farmers have had their orchards infected by AMB. Twenty-five percent could not distinguish AMB from other symptoms. Overwhelmingly, 80% of farmers strongly believed an early detection method for AMB was necessary. Conclusions: The results of the survey will help to evaluate the outreach programs of the RDA so they can more effectively educate farmers on the identifying, treating, and mediating AMB.

• 한국균학회소식:학술대회논문집
• /
• 2014.10a
• /
• pp.36-36
• /
• 2014

Apple blotch, caused by Marssonina coronaria, induce early defoliation in apple and leading to critical economic losses in apple orchards in Korea. Since M. coronaria is difficult to culture, we developed isolation and cultural method. We collected M. coronaria isolates from Gyeongbuk Province and then constructed phylogentic tree based on ITS regions. As the results, phylogenetic relationship indicated that all Korean isolates formed a same cluster and closely related to Chinese isolates [1]. Ecological characteristic of M. coronaria have been observed in apple orchards which located in Gyeongbuk Province from 2011 to present. As the results, the typical apple blotch symptoms were observed from July, and then the infected leaves were discolored and formed acervuli on the leaves. After rainfall, severe infection of symptoms such as discoloration and early defoliation were continuously observed until October. Also overwintered conidia were observed in next March on the fallen diseased leaves [2]. In the last 5 years, ascopores of M. coronaria were not observed in apple orchards which were severely infected by M. coronaria in Korea. Thus, it is assumed that overwintered conidia could be a primary inoculum of M. coronaria. Meanwhile, apple blotch has long latent periods compare to other apple disease. During the latent period, early diagnosis of apple blotch is the most important to control the disease by spray fungicide. In this reason, we developed novel diagnostic method to detect M. coronaria during latent period using optical coherence tomography (OCT) and Loop-mediated isothermal amplification (LAMP) method [2, 3]. In this presentation, it will introduce ecological characterization of M. coronaria in Korea and unique detection technique of M. coronaria in apple. It will be helpful to develop new strategies to control apple blotch in Korea.

• The Plant Pathology Journal
• /
• v.20 no.2
• /
• pp.147-154
• /
• 2004

A simple and reliable procedure for RT-PCR detection of Apple stem pitting virus (ASPV), Cherry rasp leaf virus (CRLV), and Cherry necrotic rusty mottle virus (CNRMV) was developed. Two virus specific primer sets for each virus were found to specifically detect each virus among fourteen sets of designed oligonucleotide primers. Total RNAs extracted from healthy and from ASPV-,CRLV- and CNRMV-infected plant tissues were used to synthesize cDNA using oligo dT primer and then amplified by virus-specific primers for each virus. Each primer specifically amplified DNA fragments of 578 bp and 306 bp products for ASPV (prAS CP-C and prAS CP-N primers, respectively); 697 bp and 429 bp products for CRLV (prCR4 and prCR5-JQ3D3 primers, respectively); and 370 bp and 257 bp products for CNRMV (prCN4 and prCN6-NEG 1 primers, respec-tively) by RT-PCR. DNA sequencing of amplified DNA fragments confirmed the nature of each amplified DNA. Altogether, these results suggest that these virus specific primer sets can specifically amplify viral sequences in infected tissues and thus indicate that they can be used for specific detection of each virus.