Thrips Scarring Research Articles

Classification of Biotic And Abiotic Stresses on Grape Berries using Transfer Learning

Grape farming is one of the most lucrative agricultural enterprises in India. There are several biotic and abiotic stress conditions that may adversely affect the yield if not tackled at the right time. It is crucial that the farmer can correctly identify and monitor the type of stress so that steps can be taken to prevent undesirable outcomes. We have gathered a dataset of these stress conditions on grape berries and categorized them into eight classes, necrosis, shriveling, and honeydew by mealybug, mealybug incidence, spray injury, thrips scarring, pink berry, and powdery mildew. Transfer learning was used to test the performance of six major deep learning image classification architectures (namely MobileNet-v2, Inception-v3, Inception-ResNet-v2, ResNet-v2, NASNet, and PNASNet) with variations in training conditions and hyper parameters. The results were compared to determine the most feasible and accurate deep learning architecture and its hyper parameters for the given problem statement. The experiment shows that Inception-ResNet-v2 obtained maximum classification accuracy of 88.75% when learning rate of 0.035 and minibatch size of 10 were applied using 8000 training steps. This result will act as a pre-requisite for the development of an application for mapping vineyard stress conditions on berries and give automated advisory.

Detection of common defects on mandarins by using visible and near infrared hyperspectral imaging

The presence of surface defects is one of the most influential factors in the quality and price of fresh fruit because consumers usually associate quality with a good appearance and without skin defects. Therefore, one of the main purposes of automatic detection of fruit quality is to differentiate between defective ones from sound fruits. However, the detection of defective fruits has always been a challenging task, especially the simultaneous detection of multiple types of defects. This work focuses on the development of multispectral image classification algorithm for detecting the common defects on mandarins based on the visible-near infrared (Vis-NIR) hyperspectral imaging technique. ‘Nanfeng’ mandarins with sound peel and four types of defects (i.e., anthracnose, scarring, decay and thrips scarring) were studied. Principal component analysis (PCA) was used to reduce hyperspectral data dimensionality with the goal of selecting several wavelengths that could be potentially used in an in-line multispectral imaging system. Two characteristic wavelength images at 680 nm and 715 nm in the visible spectral region were selected, and then the second principal component image (PC-2) and ratio image (Q680/715) based on these two characteristic wavelengths were used for defect detection and stem-end identification, respectively. Finally, the detection algorithm of defects was developed based on PC-2 image and ratio image (Q680/715) coupled with a simple thresholding method. For the investigated 356 independent test samples, classification accuracy of 96.63% indicated that the proposed multispectral image algorithm was effective for distinguishing between sound and defective ‘Nanfeng’ mandarins. Only two wavelength images were used in the algorithm, which was very helpful to develop a fast multispectral imaging system for on-line grading of mandarins.

Differential Impacts of Citrus Thrips Across Sweet Orange and Mandarin Species.

Several domesticated Citrus species are grown as major commercial crops in California. Despite this, farmers currently use a single set of management practices, originally created for sweet oranges (Citrus sinensis (L.) Osbeck [Sapindales: Rutaceae]), for both sweet oranges and all mandarin species. Mandarins, primarily Citrus reticulata Blanco, Citrus clementina hort. ex Tanaka, and Citrus unshiu Marcovitch, comprise almost 25% of California citrus acreage, and little work has been done to assess host-pest interactions for these species. Citrus thrips (Scirtothripscitri Moulton [Thysanoptera: Thripidae]) are one of the main pests in California citrus and are major targets for early spring, "petal fall" insecticide applications. We used mixed species citrus blocks to test the influence of Citrus species, including C. sinensis, C. reticulata, C. clementina, and C. unshiu, on 1) citrus thrips densities following petal fall; 2) citrus thrips-induced scarring on both the calyx and stylar ends of fruit; and 3) fruit deformation. Citrus sinensis and C. unshiu had relatively high citrus thrips densities and scarring levels, whereas C. reticulata had lower densities of citrus thrips and scarring levels. The age structure of citrus thrips populations also varied across Citrus species. Fruit deformity associated with citrus thrips scarring was found on all Citrus species examined. Scarring on the stylar-end of fruit, a previously largely ignored location of citrus thrips scarring, was found to be common in C. reticulata. It is clear from our work that species-specific management guidelines for citrus thrips are needed in sweet oranges and mandarins.

Computer vision detection of surface defect on oranges by means of a sliding comparison window local segmentation algorithm

Automatic detection of defective oranges by computer vision system is not easy because of the uneven lightness distribution on the surface of oranges. It means that the methods onlydirectly using global segmentation provide unsatisfactory results when orange images present faint defect characters or inhomogeneous surface. The contrast between sound and defective regions can be used to produce more accurate segmentation results, which is more capable of detecting pixels lying around the defect boundary on orange surface based on the local segmentation method. In this paper, we study and propose a sliding comparison window local segmentation algorithm and also presents the detailed image processing procedure including removal of background pixels, image binarization using local segmentation, image subtraction, image morphological modification, removal of stem end pixels for detecting surface defect in an orange gray-level image. This method is an original contribution that allows successful segmentation of various types of surface defects (e.g., insect injury, wind scarring, thrips scarring, scale infestation, canker spot, dehiscent fruit, copper burn, phytotoxicity).The image segmentation algorithm was tested with 1191 samples of oranges. The proposed algorithm was able to correctly detect 97% of the defective orange. Future work will be focused on whole surface and fast on-line inspection.

Automatic detection of common surface defects on oranges using combined lighting transform and image ratio methods

Automatic detection of fruit peel defects by a computer vision system is difficult due to the challenges of acquiring images from the surface of spherical fruit and the visual similarity between the stem-ends and the true defects. In this study, oranges with wind scarring, thrips scarring, scale infestation, dehiscent fruit, anthracnose, copper burn, canker spot and normal surface were researched. A lighting transform method based on a low pass Butterworth filter with a cutoff frequency D0=7 was first developed to convert the non-uniform intensity distribution on spherical oranges into a uniform intensity distribution over the whole fruit surface. However, the stem-ends were easily confused with defective areas. In order to solve this problem, different color components (R, G and B) and their combinations were analyzed. It was found that a ratio method and R and G component combination coupled with a big area and elongated region removal algorithm (BER) could be used to differentiate stem-ends from defects effectively. Finally, a processing and classification algorithm based on a simple thresholding method was proposed. The result with 98.9% overall detection rate for the 720 independent sample images indicated that the proposed algorithm was effective in differentiation of normal and defective oranges. The method, however, could not discriminate between different types of defects.

Factors influencing citrus fruit scarring caused by Pezothrips kellyanus

Kelly’s citrus thrips (KCT) Pezothrips kellyanus (Bagnall) (Thysanoptera: Thripidae) is a recently recorded cosmopolitan citrus pest, causing fruit scarring that results in downgrading of fruit. Due to the detrimental effects caused on fruits by KCT, we wanted to study some of the factors influencing fruit scarring. Specifically, the objectives were: (1) to determine the fruit development stage when citrus fruits are damaged by KCT and the population structure of KCT during this period, (2) to study the influence of temperature on intensity of damage, and finally, (3) to identify alternative host plants. KCT populations on flowers and fruitlets and alternate plant hosts were sampled in four citrus orchards from 2008 to 2010. The percentage of damaged fruits was also recorded. The exotic vine Araujia sericifera (Apocynaceae) was recorded as a new host for KCT. Thrips scarring started to increase at 350–650 degree-days (DD) above 10.2 °C, coinciding with a peak abundance of the second instar larval stages over all 3 years of the study. The maximum percentage of larval stages of KCT was observed in the 3 years at about 500 DD, a period which corresponds to the end of May or early June. Variation in the severity of fruit scarring appeared to be related to air temperature. Temperature likely affects the synchronisation between the peak in abundance of KCT larvae, and the period when fruitlets are susceptible to thrips damage. Temperature can also influence the survival and development of KCT populations in citrus and other host plants in the citrus agro-ecosystem.

Detection of common defects on oranges using hyperspectral reflectance imaging

To detect various common defects on oranges, a hyperspectral imaging system has been built for acquiring reflectance images from orange samples in the spectral region between 400 and 1000 nm. Oranges with insect damage, wind scarring, thrips scarring, scale infestation, canker spot, copper burn, phytotoxicity, heterochromatic stripe, and normal surface were studied. Hyperspectral images of samples were evaluated using principal component analysis (PCA) with the goal of selecting several wavelengths that could potentially be used in an in-line multispectral imaging system. The third principal component images using six wavelengths (630, 691, 769, 786, 810 and 875 nm) in the visible spectral (VIS) and near-infrared (NIR) regions, or the second principal component images using two wavelengths (691 and 769 nm) in VIS region gave better identification results under investigation. However, the stem-ends were easily confused with defective areas. In order to solve this problem, representative regions of interest (ROIs) reflectance spectra of samples with different types of skin conditions were visually analyzed. The researches revealed that a two-band ratio (R875/R691) image could be used to differentiate stem-ends from defects effectively. Finally, the detection algorithm of defects was developed based on PCA and band ratio coupled with a simple thresholding method. For the investigated independent test samples, accuracies of 91.5% and 93.7% with no false positives were achieved for both sets of selected wavelengths using proposed method, respectively. The disadvantage of this algorithm is that it could not discriminate between different types of defects.

Speed-Sprayer Trials for Citrus Thrips Control, 1997

Abstract Insecticides were evaluated for control of citrus thrips during spring, 1997 in Field 41-42 (13-year-old ‘Washington’ navel oranges) at the University of California’s Lindcove Research and Extension Center near Exeter, California. Pesticides were applied with an FMC CP-267 speed-sprayer pulled behind a tractor. Five treatments were compared against an untreated control using 200 gpa and outside coverage (achieved by reducing fan speed). The field was divided into 12 plots; treatments were assigned to plots randomly and were replicated twice in each field; each plot was six rows wide and 5-8 trees long. Ten data trees were chosen from the center two rows of each plot, excluding the trees at the end of a row. Citrus thrips infestation due to first- and second-instar immatures was monitored after petal fall by examining 5 fruit randomly selected from each data in each plot (50 fruit per plot, 100 fruit per treatment). Citrus thrips fruit scarring evaluations were taken in September on all fruit on the exterior of data trees from knee to eye level. Typical scarring levels on outside fruit as sampled in this study are approximately twice as high as percent scarring of fruit sampled from the entire tree (inside fruit are less severely scarred). Scarring was rated as: (a) none, (b) slight (any citrus thrips scarring), or (c) severe (complete ring scar or extensive surface scarring at a level that would cause downgrading of fruit in a commercial operation). Economic scarring levels in a normal year are approximately 5% severe scars.

California Citrus Thrips Small Plot Trial, 1997

Abstract Insecticides were evaluated for control of citrus thrips during spring, 1997 in Field 12 (27-year-old ‘Atwood’ navel oranges) at the University of California’s Lindcove Research and Extension Center near Exeter, California. The majority of pesticides were applied to trees with a Bean hand-sprayer at 500 psi, outside coverage, approximately 200 gpa. One treatment was applied to the soil: the Metasystox-R soil treatment was applied by pre-watering trees for 2 hours, applying the chemical in 1 gallon of water to the area between 2 trees wetted by drippers, and post-watering for an additional 4 hours (Bowsmith emitters, 2 under each tree, 10 gallons of water per hour per emitter). Field 12 was divided into 4 contiguous blocks of 96 trees and 24 treatments were applied with one replicate of each treatment assigned randomly to each block; each replicate included four contiguous trees. Citrus thrips fruit scarring evaluations were done early September on all fruit of the exterior of data trees from knee to eye level. Typical scarring levels on outside fruit as sampled in this study are approximately twice as high as percent scarring a fruit sampled from the entire tree (inside fruit are less severely scarred). Scarring was rated as: (a) none, (b) slight (any citrus thrips scarring), or (c) severe (complete ring scar or extensive surface scarring at a level that would cause downgrading of fruit in a commercial operation). Economic scarring levels in a normal year are approximately 5% severe scars.

Estimating the level of fruit scarring by citrus thrips from temperature conditions prior to the end of bloom

In this study, we develop and validate multiple regression models to estimate the degree of fruit scarring by citrus thrips, Scirtothrips citri (Moulton), from heat and chill degree days. Regression coefficients indicate that cool weather during early March (2 March–16 March) and warm weather during bloom are associated with high levels of thrips scarring. The biological mechanisms leading to the temperature-fruit scarring relationships are unknown. An economic analysis suggests that using model predictions may increase the average financial return per hectare and reduce the number of insecticide treatments applied against citrus thrips.

Speed-Sprayer Trials for Citrus Thrips Control, 1996

Abstract Insecticides were evaluated spring, 1996 in Field 41-42 at the University of California’s Lindcove Field Station near Exeter, CA for control of citrus thrips. Pesticides were applied with an FMC CP-267 speed-sprayer pulled behind a tractor. Five treatments were compared against an untreated control using 200 gallons of water per acre and outside coverage (achieved by reducing fan speed). The field was divided into 12 plots; treatments were assigned to plots randomly and were replicated twice in each field; each plot was six rows wide and 5-8 trees long. Ten data trees were chosen from the center two rows of each plot, excluding the trees at the end of a row. Citrus thrips infestation due to first and second instar immatures was monitored after petal fall by examining 10 fruit randomly selected from each data tree (100 fruit per plot, 200 fruit per treatment in each field). Predaceous mite levels were monitored by counting the number of motile mites on 10 leaves picked from 0.5 m inside the canopy. Citrus thrips fruit scarring was evaluated in October, 1995 on all fruit on the exterior of data trees from knee to eye level. Scarring was rated as: (a) none, (b) slight (any citrus thrips scarring), or (c) severe (complete ring scar or extensive surface scarring at a level that would cause downgrading of fruit in a commercial operation). Approximately 5% severe scars are normally regarded as economic scarring levels.

California Citrus Thrips Small Plot Trial, 1996

Abstract Insecticides were evaluated spring, 1996 in Field 12 (26 year-old ‘Atwood’ navel oranges) at the University of California’s Lindcove Field Station near Exeter, CA for control of citrus thrips. Pesticides were applied with a Bean hand-sprayer at 500 psi, outside coverage, approximately 200 gpa. Field 12 was divided into 4 contiguous blocks of 88-92 trees (22-23 replicates) and 22 treatments were applied with one replicate of each treatment assigned randomly to each block except extra replicates were assigned to the untreated check: each replicate consisted of four contiguous trees (except 2 replicates which had only 3 trees). Citrus thrips fruit scarring was evaluated early November. 1995 on all fruit on the exterior of data trees from knee to eye level. Scarring was rated as: (a) none, (b) slight (any citrus thrips scarring), or (c) severe (complete ring scar or extensive surface scarring at a level that would cause downgrading of fruit in a commercial operation). Approximately 5% severe scars are normally taken as economic scarring levels.

Abamectin Grower Cooperator Citrus Thrips Trials, 1994

Abstract Abamectin was compared with a standard pesticide (Baythroid, Carzol, or Veratran D) at ten sites in the San Joaquin Valley during spring, 1994. Treatments were applied to navel oranges except at the Cameo site where ‘Valencia’ oranges were treated. Treatments were replicated once or twice at each site and each replicate plot was at least 6 rows wide (most were larger, 2 acres or more). Citrus thrips fruit scarring was evaluated from Oct 1994-Feb 1995. For this, all fruit from eye to knee level on the exterior of 30 randomly selected trees from the interior of each plot were examined except at Carter where 20 trees per treatment were evaluated. Scarring was rated as: (a) none, (b) slight (any citrus thrips scarring), (c) severe (complete ring scar or extensive surface scarring at a level that would cause downgrading of fruit in ;i commercial operation). In a normal year, approximately 5% severe scars are regarded as the economic scarring levels.

California Citrus Thrips Small Plot Trial, 1995

Abstract Insecticides were evaluated spring, 1995 in Field 12 (25 yr-old Atwood navel oranges) at the University of California’s Lindcove Field Station near Exeter, California for control of citrus thrips. Pesticides were applied with a Bean hand-sprayer at 500 psi, outside coverage, approximately 200 gpa. Field 12 was divided into 4 blocks of 92-96 trees (23-24 replicates) and 22 treatments were applied with one replicate of each treatment assigned randomly to each block except extra replicates were assigned to the untreated control; each replicate was four contiguous trees. Citrus thrips fruit scarring evaluations were taken in Oct, 1995 on all fruit on the exterior of data trees from knee to eye level. Typical scarring levels on outside fruit as sampled in this study are approximately twice as high as percent scarring of fruit sampled from the entire tree (inside fruit are less severely scarred). Scarring was rated as: (a) none, (b) slight (any citrus thrips scarring), or (c) severe (complete ring scar or extensive surface scarring at a level that would cause downgrading of fruit in a commercial operation). Economic scarring levels in a normal year are approximately 5% severe scars.

Field Trials with Abamectin for Control of Citrus Thrips, 1995

Abstract Different rates of abamectin were compared against a standard (Veratran D) at five sites in the San Joaquin Valley during spring 1995 for control of citrus thrips. Treatments were applied to navel oranges with each treatment replicated twice at each site. Each replicate plot was at least 6 rows wide (most were larger, 2 acres or more). Citrus thrips infestation due to first and second instar immatures was monitored after petal fall by examining 10 fruit selected randomly from 10 trees of uniform vigor in each plot (200 fruit/treatment) except that 25 fruit were monitored in one of the two plots for each treatment at S & J 6-9 by Andrea Gjerde. Citrus thrips fruit scarring evaluations were taken in October, 1995, on all fruit from eye to knee level on the exterior of 15 randomly selected trees from each plot (30 trees per treatment). Typical scarring levels on outside fruit as sampled in this study are approximately twice as high as percent scarring of fruit sampled from the entire tree (inside fruit are less severally scarred). Scarring was rated as (a) none, (b) slight (any citrus thrips scarring), (c) severe (complete ring scar or extensive surface scarring at a level that would cause downgrading of fruit in a commercial operation). Economic scarring levels in a normal year are approximately 5% severe scars.

Speed-Sprayer Trials for Citrus Thrips Control, 1995

Abstract Insecticides were evaluated spring, 1995 in Field 4142 at the University of California’s Lindcove Field Station near Exeter, California for control of citrus thrips. Pesticides were applied with an FMC CP-267 speed-sprayer pulled behind a tractor. Five treatments were compared against an untreated control using 200 gpa and outside coverage (achieved by reducing fan speed). The field was divided into 12 plots; treatments were assigned to plots randomly and replicated twice in each field; each plot was six rows wide and 5-8 trees long. Ten data trees were chosen from the center two rows of each plot, excluding the trees at the end of a row. Citrus thrips infestation due to first and second instar immatures was monitored after petal fall by examining 10 fruit randomly selected from each data tree (100 fruit per plot, 200 fruit per treatment in each field). Citrus thrips fruit scarring evaluations were taken in Oct, 1995 on all fruit on the exterior of data trees from knee to eye level. Typical scarring levels on outside fruit as sampled in this study are approximately twice as high as percent scarring of fruit sampled from the entire tree (inside fruit are less severely scarred). Scarring was rated as: (a) none, (b) slight (any citrus thrips scarring), or (c) severe (complete ring scar or extensive surface scarring at a level that would cause downgrading of fruit in a commercial operation). Economic scarring levels in a normal year are approximately 5% severe scars.

California Citrus Thrips Small Plot Trial, 1995

Abstract Insecticides were evaluated spring, 1995 in Field 12 (25 yr-old Atwood navel oranges) at the University of California’s Lindcove Field Station near Exeter, California for control of citrus thrips. Pesticides were applied with a Bean hand-sprayer at 500 psi, outside coverage, approximately 200 gpa. Field 12 was divided into 4 blocks of 92-96 trees (23-24 replicates) and 22 treatments were applied with one replicate of each treatment assigned randomly to each block except extra replicates were assigned to the untreated control; each replicate was four contiguous trees. Citrus thrips fruit scarring evaluations were taken in Oct, 1995 on all fruit on the exterior of data trees from knee to eye level. Typical scarring levels on outside fruit as sampled in this study are approximately twice as high as percent scarring of fruit sampled from the entire tree (inside fruit are less severely scarred). Scarring was rated as: (a) none, (b) slight (any citrus thrips scarring), or (c) severe (complete ring scar or extensive surface scarring at a level that would cause downgrading of fruit in a commercial operation). Economic scarring levels in a normal year are approximately 5% severe scars.

Integrated citrus thrips control reduces secondary pests

Citrus growers are very concerned about scarring of the rind caused by early-season pests such as citrus thrips, katydid and various Lepidopterous larvae because heavily scarred fruit is downgraded in the packing house. Citrus growers who use a broad-spectrum pesticide program for early-season pests experience problems with pest resurgence and pesticide resistance, but generally have low levels of fruit scarring. Growers who use both selective pesticides and natural enemies have fewer secondary pest outbreaks of citrus red mite, but don't always effectively control citrus thrips scarring.

Speed-Sprayer Trials for Citrus Thrips Control, 1994

Abstract Insecticides were evaluated in 2 fields at the University of California’s Lindcove Field Station near Exeter, California for control of citrus ,thrips. Pesticides were applied with an FMC CP-757 speed-sprayer. In Field 23, different rates and timings of Agri-Mek were evaluated using 125 gpa and outside coverage (achieved by reducing fan speed). In Field 41-42, 5 treatments were compared against an untreated control and were applied similarly. Field 23 was divided into 10 plots and Field 41-42 was divided into 12 plots; treatments were assigned to plots randomly and replicated twice in each field. Each plot was 6 rows wide and 5-8 trees long. In each plot, 10 data trees were chosen from the center 2 rows of the plot, excluding the trees at the end of a row. Citrus thrips infestation due to first and second instars was monitored twice a week for 6 wks after petal fall by examining 5 fruit randomly from each data tree (50 fruit per plot, 100 fruit per treatment in each field). Citrus thrips fruit scarring evaluations were taken in Oct 1994 on all fruit on the exterior of data trees from knee to eye level. Typical scarring levels on outside fruit as sampled in this study are approximately twice as high as percent scarring of fruit sampled from the entire tree (inside fruit are less severely scarred). Scarring was rated as: (a) none, (b) slight (any citrus thrips scarring), or (c) severe (complete ring scar or extensive surface scarring at a level that would cause downgrading of fruit in a commercial operation). Economic scarring levels in a normal year are about 5% severe scars.

California Small Plot Citrus Thrips Trials, 1994

Abstract Insecticides were evaluated in 2 fields at the University of California’s Lindcove Field Station near Exeter, California for control of citrus thrips (Field 12, 24 yr old ‘Atwood’ navel oranges; Field 14, 22 yr old Old Line navels). Pesticides were applied with a Bean hand-sprayer at 500 psi, outside coverage, approximately 200 gpa. Field 12 was divided into 4 replicate blocks of 52 trees and 12 treatments were applied with one replicate of each treatment assigned randomly to each block except a second replicate was assigned randomly to the control in 3 of the 4 blocks and the Admire treatment was excluded from one block. Each replicate was 4 contiguous trees. Field 14 was designed similarly with 4 blocks and 33 treatments with one 4-tree replicate assigned randomly to each treatment in each block. Citrus thrips infestation due to first and second instars was monitored in some of the treatments in Field 14 twice a wk for 6 wks after petal fall by examining 5 fruit randomly from each data tree (50 fruit per plot, 100 fruit per treatment in each field). Citrus thrips fruit scarring evaluations were taken in Oct, 1994 on all fruit on the exterior of data trees from knee to eye level. Typical scarring levels on outside fruit as sampled in this study are approximately twice as high as percent scarring of fruit sampled from the entire tree (inside fruit are less severely scarred). Scarring was rated as: (a) none, (b) slight (any citrus thrips scarring), or (c) severe (complete ring scar or extensive surface scarring at a level that would cause downgrading of fruit in a commercial operation). Economic scarring levels in a normal yr are about 5% severe scars. Ctirus cutworm and fruit tree leafroller levels were high in this block just prior to and after petal fall resulting in high levels of fruit drop. After assessing citrus thrips fruit scarring levels in Oct, any trees with less than 30 outside assessed fruit were excluded from the analysis (a total of 13 trees were excluded, 1—3 trees from each of 9 treatments).