References of "Leemans, Vincent"
     in
Bookmark and Share    
Full Text
See detailQuality evaluation of Apples
Leemans, Vincent ULg; Kleynen, Olivier

in Sun, Da-Wen (Ed.) Computer Vision Technology for Food Quality Evaluation (2008)

The chapter describe how to asses apple quality by using machine vision. The concept of quality of an apple is detailed. The manipulation of the fruits, the lighting and the acquisition techniques are ... [more ▼]

The chapter describe how to asses apple quality by using machine vision. The concept of quality of an apple is detailed. The manipulation of the fruits, the lighting and the acquisition techniques are reviewed. The shape and colour assessment are summarised. The evaluation of the surface defects is [less ▲]

Detailed reference viewed: 45 (3 ULg)
Full Text
Peer Reviewed
See detailOn-the-go georeferenced measurements of soil mechanical strength and differenciation of soil structure.
Destain, Marie-France ULg; Sirjacobs, Damien ULg; Hanquet, Bernard et al

in Geophysical Research Abstracts (2008)

Soil strength is defined as the resistance which as to be overcome to obtain a given soil deformation. Amongst the numerous methods developed to measure soil strength, two are classically used. On one ... [more ▼]

Soil strength is defined as the resistance which as to be overcome to obtain a given soil deformation. Amongst the numerous methods developed to measure soil strength, two are classically used. On one hand, a laboratory method based on triaxial tests of undisturbed soil samples allows the estimation of cohesion and internal friction angle by the Mohr-Coulomb equation. On the other hand, measuring soil penetration resistance by pushing a cone into a soil is a widely used technique. Both techniques deliver discontinuous field information and are not suited to produce digital soil mapping. The objectives of this paper are to present a sensor able to continuously measure soil strength variations. The sensor was constituted of a thin blade pulled in the soil at a constant depth and speed and a beam which transferred the soil-blade forces to a transducer fixed on a vehicle. The transducer measures the draft force Fx, the vertical force Fz and the moment My thanks to an octagonal ring dynamometer. A measurement chain was developed to acquire simultaneously the signals provides by the soil strength sensor and those of a DGPS. Signal processing was notably based on geostatistics and allows soil mapping [1]. Four fields representative of the soils used in silty areas for arable production in Belgium were selected. The measurements were repeated several times during 1999-2003. Targeted test plots were chosen in each field to perform reference measurements, namely granulometry, cohesion, friction angle, pF, water content, dry bulk density, and cone index. The within-field studies revealed high variability caused by texture, history, traffic, etc., and showed a correlation between the sensor signals and physical parameters, such as cone index and soil moisture, as long as no over-consolidation of the soil occurred [2]. To assess the similarity of soil strength between the fields, the data Fx, Fz and My were classified by using canonical variates (CV). The two first CV represented 95.9 % of the variability, which means that two main variables contain the essential part of the information. In a plane (Fz, Fx), three clusters could be distinguished. The first one (trials 1 and 5), characterized by a low draft and a high Fz, corresponded to trials performed in March on soils ploughed during the winter, naked or covered with small vegetation, and characterized by small values of cone index. The second one (trials 2, 3, 4, 7) with high values of Fx and Fz grouped measurements done just after wheat harvest in August. The third cluster (trials 6) corresponded to measurements performed during wheat growth. It may be concluded that the signals from the sensor treated by suited statistical analysis have the potential to differentiate soil structures at a field scale. REFERENCES [1] Sirjacobs D., Hanquet B., Lebeau F., Destain M.-F. (2002). On-line mechanical resistance mapping and correlation with soil physical properties for precision agriculture. Soil and Tillage Research 64, 231-242. [2] Hanquet B., Sirjacobs D., Destain M.-F., Frankinet M., Verbrugge J.-C. (2004). Analysis of soil variability measured with a soil strength sensor. Precision Agriculture, 5, 227-246. [less ▲]

Detailed reference viewed: 36 (9 ULg)
Full Text
Peer Reviewed
See detailDetermination of plant height for weed detection in stereoscopic images
Piron, Alexis ULg; Leemans, Vincent ULg; Kleynen, Olivier et al

in AGENG 2008 Conference - Agricultural & Biosystems Engineering for a Sustainable World (2008)

The aim of this study was twofold. The first goal was to acquire high accuracy stereoscopic images of small-scale field scenes, the second to examine the potential of plant height as a discriminant factor ... [more ▼]

The aim of this study was twofold. The first goal was to acquire high accuracy stereoscopic images of small-scale field scenes, the second to examine the potential of plant height as a discriminant factor between crop and weed, within carrot rows. Emphasis was put on how to determine actual plant height taking into account the variable distance from camera to ground and ground irregularities for in-field measurements. Multispectral stereoscopic images were taken over a period of 19 days starting one week after crop emergence and seven weed species were considered. Images were acquired with a mobile vision system consisting in a filter wheel based multispectral camera and a video projector. The stereoscopy technique used belonged to the coded structured light family. The stereoscopic acquisition method yielded good results despite the numerous stereoscopic difficulties exhibited by the scenes. A plant height parameter as opposed to distance from camera to plant pixels gave better results for classification (classification accuracy of up [less ▲]

Detailed reference viewed: 74 (29 ULg)
Full Text
Peer Reviewed
See detailA Computer-Vision Based Precision Seed Drill Guidance Assistance
Leemans, Vincent ULg; Destain, Marie-France ULg

in Computers and Electronics In Agriculture (2007), 59(1-2),

This paper presents a control mechanism aiming to position seed drills relative to the previous lines, while sowing. The position was measured by a machine vision system and used in a feedback control ... [more ▼]

This paper presents a control mechanism aiming to position seed drills relative to the previous lines, while sowing. The position was measured by a machine vision system and used in a feedback control loop. An articulated mechanism was used to ensure the lateral displacement of the drill relative to the tractor. The behaviour of the whole outfit was studied during several field tests. The standard deviation of the error, measured as the difference between the observed inter-row distance and its set value, was 23 mm and its range was less than 100 mm, which was sufficient to fulfil the requirements of the application. Sources of systematic errors were also identified as linked to the geometric considerations. Their correction requires an accurate mounting of the camera, which may be possible for a serial montage. [less ▲]

Detailed reference viewed: 65 (17 ULg)
Full Text
Peer Reviewed
See detailÉtude des paramètres opératoires de pressage mécanique des amandes de Vitellaria paradoxa Gaertn C.F. (karité)
Yé, S.; Lebeau, Frédéric ULg; Wathelet, Jean-Paul ULg et al

in Biotechnologie, Agronomie, Société et Environnement = Biotechnology, Agronomy, Society and Environment [=BASE] (2007), 11(4), 267-273

Study of the operational parameters of mechanical pressing of almonds of Vitellaria paradoxa Gaertn C.F. (shea tree). Sheabutter is one of the most diffi cult oleaginous resources to extract by ... [more ▼]

Study of the operational parameters of mechanical pressing of almonds of Vitellaria paradoxa Gaertn C.F. (shea tree). Sheabutter is one of the most diffi cult oleaginous resources to extract by traditional way. In Burkina Faso, where production of sheanuts is estimated at 70 000 tons per year, presses manufactured locally are used to improve the production. In order to optimize the handcraft process of sheabutter production, extraction parameters of Vitellaria paradoxa Gaertn C.F. were studied under laboratory controlled conditions on 3 g samples of ground almonds using a uni-axial compression test machine specifi cally instrumented for this purpose. The studied operational parameters were the grinding (unsieved sample 0.5 mm<Ø<5 mm ; sieved samples 0.5 mm<Ø<1 mm ; 1 mm<Ø<2 mm ; 2 mm<Ø<4 mm ; 4 mm<Ø<5 mm), the heating temperature (30; 50; 70; 90; 110; 130; 150°C) and the extraction pressure (7; 10; 13.4; 15; 16.17; 17.44; 20; 22.43 and 25 MPa). The grinding has favourably infl uenced the extraction rate. The fi nest sieved fraction (0.5 mm<Ø<1 mm) presented the highest extraction rate, 84%. When using unsieved samples, the best results were obtained with a heating temperature of 90°C and an extraction pressure of 20 MPa. In these conditions, the extraction rate reached 78% and the chemical characteristics of the sheabutter were not altered. As a result, a signifi cant increase of the handcrafted presses effi ciency could be reached by simple and inexpensive modifi cations as an increase of the pressure applied to the product, by a decrease of the pressing chamber diameter. [less ▲]

Detailed reference viewed: 50 (10 ULg)
Full Text
Peer Reviewed
See detailAgricultural tools guidance assistance by using machine vision
Leemans, Vincent ULg; Destain, Marie-France ULg

in Proceedings of the NCTAM 2006 7th National Congress on Theoretical and Applied Mechanics (2006, May 30)

This paper presents a regulation mechanism aiming to position agricultural tools relatively to the previous lines, while sowing or harvesting. The sowing rows were revealed by a background correction, the ... [more ▼]

This paper presents a regulation mechanism aiming to position agricultural tools relatively to the previous lines, while sowing or harvesting. The sowing rows were revealed by a background correction, the background being obtained thanks to a median rank filter. The method was found efficient in eliminating the shadows. For the crop rows (chicory rows), a neural network was used to localise the plants. While the petiole and the leaves were easily separated from the soil, the chicory root and the soil having about the same colour and the lighting condition varying widely, it was more difficult to obtain a good contrast between those parts, which leaves place for some improvements. The adapted Hough transform consisted in computing one transform for each line in the cluster with, for reference, the position and direction of the theoretical position of the row. The different transforms were then added. The position was used in a feedback regulation loop. An articulated mechanism was used to ensure the lateral displacement of the tool relatively to the tractor. The behaviour of the whole outfit was studied during several field tests. The standard deviation of the error, measured as the difference between the observed inter-row distance and its theoretica value, was of 23 mm for sowing and 31 mm for harvesting and its amplitude was less than 100 mm for sowing and less than 115 mm during the harvest, which was sufficient to fulfil the requirements of the application. Sources of systematic errors were also identified as linked to the geometric considerations. Their correction requires an accurate mounting of the camera, which may be possible for a serial montage. [less ▲]

Detailed reference viewed: 24 (1 ULg)
Full Text
Peer Reviewed
See detailApplication Of The Hough Transform For Seed Row Localisation Using Machine Vision
Leemans, Vincent ULg; Destain, Marie-France ULg

in Biosystems Engineering (2006), 94(3),

This paper compares two methods based on machine vision to provide driver assistance in seed drill guidance in order to improve spacing accuracy during contiguous passages. The first case consisted of ... [more ▼]

This paper compares two methods based on machine vision to provide driver assistance in seed drill guidance in order to improve spacing accuracy during contiguous passages. The first case consisted of following the furrow created at the preceding passage by a special marker disc attached to the seed drill. A camera was located on the tractor and detected this furrow. In the second case, the seed rows themselves were detected by the camera without making use of the marker disc. In both cases, several video sequences were acquired in various situations, including different soil textures and various illumination conditions (375 sequences were acquired during three years). A pre-treatment of these sequences was performed and included a background subtraction in order to remove shadows and other wide unevenness. In the first case, the best results were obtained by using an image treatment based on the Hough transform coupled to a recursive filter. The search of the maximum of the Hough transform was performed using a mean shift algorithm. In the second case, where several parallel rows were simultaneously present on the images, an adapted Hough transform was proposed which took into account the a priori knowledge of the rows spacing. The trueness and precision in row detection were superior in the second case. The results are compatible with the application, since the trueness was smaller than 30 mm. This suggested that it can be possible to assist the manual guidance of a seed drill by an automatic system consisting in a camera detecting the seed rows. [less ▲]

Detailed reference viewed: 44 (13 ULg)
Full Text
Peer Reviewed
See detailLine Cluster Detection Using A Variant Of The Hough Transform For Culture Row Localisation
Leemans, Vincent ULg; Destain, Marie-France ULg

in Image and Vision Computing (2006), 24(5),

An adaptation of the Hough transform was proposed for the detection of line clusters of known geometry. This method was applied in agriculture for the detection of sowing furrows created by a driller and ... [more ▼]

An adaptation of the Hough transform was proposed for the detection of line clusters of known geometry. This method was applied in agriculture for the detection of sowing furrows created by a driller and of chicory plant rows during harvesting process. The sowing rows were revealed by a background correction, the background being obtained thanks to a median rank filter. The method was found efficient in eliminating the shadows. For the crop rows, a neural network was used to localise the plants. While the petiole and the leaves were easily separated from the soil, the chicory root and the soil having about the same colour and the lighting condition varying widely, it was more difficult to obtain a good contrast between those parts, which leaves place for some improvements. The adapted Hough transform consisted in computing one transform for each line in the cluster with, for reference, the position and direction of the theoretical position of the row. The different transforms were then added. It was found effective for both the sowing rows and the chicory rows. Results remained good even in very noisy conditions, when the rows were incomplete or when artefacts would lead its classical counter part to show several alignments other than the expected ones. The culture rows were localised with a precision of a few centimetres which was compatible with the proposed applications. [less ▲]

Detailed reference viewed: 64 (30 ULg)
Full Text
Peer Reviewed
See detailDevelopment of a multi-spectral vision system for the detection of defects on apples
Kleynen, Olivier; Leemans, Vincent ULg; Destain, Marie-France ULg

in Journal of Food Engineering (2005), 69(1), 41-49

A method to sort 'Jonagold' apples based on the presence of defects was proposed. A multi-spectral vision system including four wavelength bands in the visible/NIR range was developed. Multi-spectral ... [more ▼]

A method to sort 'Jonagold' apples based on the presence of defects was proposed. A multi-spectral vision system including four wavelength bands in the visible/NIR range was developed. Multi-spectral images of sound and defective fruits were acquired tending to cover the whole colour variability of this bicolour apple variety. Defects were grouped into four categories: slight defects, more serious defects, defects leading to the rejection of the fruit and recent bruises. Stem-ends/calyxes were detected using a correlation pattern matching algorithm. The efficiency of this method depended on the orientation of the stem-end/calyx according to the optical axis of the camera. Defect segmentation consisted in a pixel classification procedure based on the Bayes' theorem and non-parametric models of the sound and defective tissue. Fruit classification tests were performed in order to evaluate the efficiency of the proposed method. No error was made on rejected fruits and high classification rates were reached for apples presenting serious defects and recent bruises. Fruits with slight defects presented a more important misclassification rate but those errors fitted however the quality tolerances of the European standard. Considering an actual ratio of sound fruits of 90%, less than 2% of defective fruits were classified into the sound ones. (c) 2004 Elsevier Ltd. All rights reserved. [less ▲]

Detailed reference viewed: 63 (7 ULg)
Full Text
Peer Reviewed
See detailA guidance assistance method for precision sugar beet sowing using machine vision.
Leemans, Vincent ULg; Destain, Marie-France ULg

in Pr. Josse De Baerdemaeker (Ed.) AgEng 2004 Conference - Engineering the future - Book of abstracts (2004, September)

This paper presents a method for seed drill guidance by using machine vision

Detailed reference viewed: 29 (1 ULg)
Full Text
Peer Reviewed
See detailA Real-Time Grading Method Of Apples Based On Features Extracted From Defects
Leemans, Vincent ULg; Destain, Marie-France ULg

in Journal of Food Engineering (2004), 61(1),

This paper presents a hierarchical grading method applied to Jonagold apples. Several images covering the whole surface of the fruits were acquired thanks to a prototype grading machine. These images were ... [more ▼]

This paper presents a hierarchical grading method applied to Jonagold apples. Several images covering the whole surface of the fruits were acquired thanks to a prototype grading machine. These images were then segmented and the features of the defects were extracted. During a learning procedure, the objects were classified into clusters by k-mean clustering. The classification probabilities of the objects were summarised and on this basis the fruits were graded using quadratic discriminant analysis. The fruits were correctly graded with a rate of 73 %. The errors were found having origins in the segmentation of the defects or for a particular wound, in a confusion with the calyx end. [less ▲]

Detailed reference viewed: 49 (1 ULg)
Full Text
Peer Reviewed
See detailSelection of the most efficient wavelength bands for 'Jonagold' apple sorting
Kleynen, O.; Leemans, Vincent ULg; Destain, Marie-France ULg

in Postharvest Biology & Technology (2003), 30(3), 221-232

This paper presents a method based on quadratic discriminant analysis to select the best filters for detecting a wide range of defects in 'Jonagold' apple fruit using a multi-spectral vision system ... [more ▼]

This paper presents a method based on quadratic discriminant analysis to select the best filters for detecting a wide range of defects in 'Jonagold' apple fruit using a multi-spectral vision system. Reflectance spectra of damaged and sound tissue were recorded using a visible/NIR spectrometer. Analysed defects consisted of scald, hail damage (with and without skin perforation), limb rubs, russets, scab tissue, frost damage, rot, visible flesh damage and recent bruises. Camera filter effects were approximated by summing the reflectances of all the wavelengths within the filter bandwidth. Combinations of three and four filters were tested and evaluated for discriminating damaged tissues from healthy ones. If a three-filter combination appeared sufficient to detect most of the damaged tissue, a four-filter combination should be considered for the complete sorting automation of this bicolour apple variety. A fourth filter was necessary to quantify the ratio between the blush and ground colours. Regarding recent bruise defects which represented the major difficulty, an image segmentation algorithm based on local contrast variations can enhance their detection. (C) 2003 Elsevier B.V. All rights reserved. [less ▲]

Detailed reference viewed: 42 (5 ULg)
Peer Reviewed
See detailExternal quality grading of Jonagold apples using a multi-spectral vision system
Kleynen, Olivier; Leemans, Vincent ULg; Destain, Marie-France ULg

in Balsa-Canto E., Mora J.; Onate E. (Eds.) II International Workshop - Information Technologies and Computing Techniques for the Agro-Food Sector (2003)

This paper presents a method to sort Jonagold apples using a four bands multi-spectral image acquisition device. Multi-spectral images of sound tissue and various defects were acquired. Defects could be ... [more ▼]

This paper presents a method to sort Jonagold apples using a four bands multi-spectral image acquisition device. Multi-spectral images of sound tissue and various defects were acquired. Defects could be divided into four classes: slight defects (e.g. small russet), more serious defects (scar tissue), defects leading to the rejection of the fruit (e.g. rot) and recent bruises (between one hour and two hours old). Image segmentation was based on the Bayes' theorem. Each pixel of the fruit was classified into 'healthy' or 'defect' classes according to the probability distribution of the spectral components of each class. Once segmented, the fruit was graded by linear discriminant analysis on the basis of the relative area of the defect and statistical parameters computed on the spectral components of the two tissues classes. Results (cross validation) showed 94% and 84% if the sound and defective fruits respectively well classified. Most of the misclassified defective fruits (89%) belonged to the slight defect category. [less ▲]

Detailed reference viewed: 24 (1 ULg)
See detailContrôle des produits agroalimentaires par analyse d'images
Leemans, Vincent ULg; Kleynen, Olivier; Destain, Marie-France ULg

in Nouveaux capteurs pour la maîtrise de la qualité des produits agroalimentaires - Etat de la recherche européenne (2002, November 22)

Présentation de méthodes utilisées dans un processus de contrôle de qualité basé sur l'analyse d'image, en se focalisant sur la couleur et la forme des produits et leur classification

Detailed reference viewed: 36 (3 ULg)
Full Text
Peer Reviewed
See detailOn-line fruit grading according to their external quality using machine vision
Leemans, Vincent ULg; Magein, Hugo ULg; Destain, Marie-France ULg

in Biosystems Engineering (2002), 83(4), 397-404

This paper presents apple grading into four classes according to European standards. Two varieties were tested: Golden Delicious and Jonagold. The image database included more than a 1000 images of fruits ... [more ▼]

This paper presents apple grading into four classes according to European standards. Two varieties were tested: Golden Delicious and Jonagold. The image database included more than a 1000 images of fruits (528 Golden Delicious, 642 Jonagold) belonging to the three acceptable categories-Extra, I and II-and the reject (each class represents, respectively, about 60, 10 and 20% of the sample size). The image grading was achieved in six steps: image acquisition; ground colour classification; defect segmentation; calyx and stem recognition; defects characterisation and finally the fruit classification into quality classes. The proposed method for apple external quality grading showed correct classification rates of 78 and 72%, for Golden Delicious and Jonagold apples, respectively. Taking into account that the healthy fruit were far better graded and considering that this class was under represented in the sample compared with the fruit population, the results of the proposed method (an error rate which drops to 5 and 10%, respectively) are compatible with the requirements of European standards. (C) 2002 Silsoe Research Institute. Published by Elsevier Science Ltd. All rights reserved. [less ▲]

Detailed reference viewed: 54 (4 ULg)
Full Text
Peer Reviewed
See detailApplication of image analysis to the identification and rating of road surface distress
Rasse, Catherine; Leemans, Vincent ULg; Destain, Marie-France ULg et al

in Correia; Branco (Eds.) Bearing Capacity of Roads, Railways and Airfields (2002)

Numerical image analysis is used to detect narrow cracks on bituminous pavement. This problem is complicated because of the variable road aspect, which depends on coarseness textures, changing ambient ... [more ▼]

Numerical image analysis is used to detect narrow cracks on bituminous pavement. This problem is complicated because of the variable road aspect, which depends on coarseness textures, changing ambient lighting, presence of humidity and because of the poor contrast of the cracks with regard to road texture. The paper presents algorithms suited to detect random cracks edges in a noisy environment in three stages. The pre-treatment consisted mainly in applying a background correction to eliminate the heterogeneity due to humidity, shade, ... In the treatment, a threshold value was applied to segment the 'object' from the rest of the image. As these objects may be cracks, part cracks, or some noise erroneously segmented as defect, a post-treatment was applied to appreciate more accurately if a pixel belonged to an object or to the background. It aimed also to assembly parts of the cracks in continuous structure. When compared to visual detection, efficient detection of cracks is obtained. Further work needs to be done to get an automatic detection of the cracks whatever the road texture. [less ▲]

Detailed reference viewed: 19 (0 ULg)
Full Text
Peer Reviewed
See detailEvaluation of tactile sensors in apple firmness measurement
Petit, Catherine; Leemans, Vincent ULg; Kleynen, Olivier et al

in Proceedings of the Conference 'Physical Methods in Agriculture, Appoach to precision and quality' (2001)

The objective of the work consists to develop a non-destructive fruit firmness measurement. The tactile sensor technology was chosen. The force measurement acting between the fruit-sensor as well as the ... [more ▼]

The objective of the work consists to develop a non-destructive fruit firmness measurement. The tactile sensor technology was chosen. The force measurement acting between the fruit-sensor as well as the contact area are coupled with other meaqsurements, like the color of the fruit. The results of the measurements are compared with the firmness reference values (Magness-Taylor test) and also with the acoustic impulse response technique. Several parameters correlated with firmness are proposed. [less ▲]

Detailed reference viewed: 43 (4 ULg)
See detailDéveloppement de méthodes pour apprécier 'en ligne' la qualité externe de pommes par vision artificielle
Leemans, Vincent ULg; Destain, Marie-France ULg; Magein, Hugo ULg

Book published by Ministère des Classes moyennes et de l'Agriculture - DG6 -Service Recherche subventionnée (2001)

L'ouvrage présente les résultats des recherches effectuées pour mettre au point un système de tri automatisé pour pommes, en fonction des critères de qualité externe, la couleur, la forme et la présence ... [more ▼]

L'ouvrage présente les résultats des recherches effectuées pour mettre au point un système de tri automatisé pour pommes, en fonction des critères de qualité externe, la couleur, la forme et la présence de défauts. [less ▲]

Detailed reference viewed: 26 (4 ULg)
Peer Reviewed
See detailOn-line fruit grading according to external quality using machine vision.
Leemans, Vincent ULg; Magein, Hugo ULg; Destain, Marie-France ULg

in AgEng Warwick 2000 - Abstract part 1 - Agricultural engineering into the third millennium (2000, July)

This paper presents apple grading into four classes according to European standards. Two varieties were tested, the Golden delicious and the Jonagold. The image database included more than thousand images ... [more ▼]

This paper presents apple grading into four classes according to European standards. Two varieties were tested, the Golden delicious and the Jonagold. The image database included more than thousand images of fruits (528 Golden, 642 Jonagold) belonging to three categories Extra, I, II and to reject. The image grading was achieved in six steps : the image acquisition, the ground colour classification, the defect segmentation, the calyx and stem recognition, the defects characterisation and finally the fruit classification in quality classes. The proposed method for apple external quality grading showed correct classification rates of 78 and 72% respectively for Golden delicious and for Jonagold apples. Taking into account that the healthy fruits were far better graded and considering that this class was under represented, the results of the proposed method (an error rate reaching respectively 5 and 10%) are compatible with the requirements of the European standards. [less ▲]

Detailed reference viewed: 57 (2 ULg)
See detailContribution au classement des fruits par analyse d'images numériques. Application au tri en ligne des pommes Golden delicious et Jonagold.
Leemans, Vincent ULg

Doctoral thesis (2000)

This work aims to set up an automatic quality fruit grading method based on external characteristics. Special attention is drawn to various defects such as wounds, bruises, physiological diseases, fungi ... [more ▼]

This work aims to set up an automatic quality fruit grading method based on external characteristics. Special attention is drawn to various defects such as wounds, bruises, physiological diseases, fungi attack, etc. Two 3-CCD cameras mounted on a test rig were used for the image acquisition. Golden delicious apples are characterised by their uniform colour. This later was modelled by a multivariate Gaussian distribution and the defect detection was carried out by computing the Mahalanobis distance separating a pixel's colour and the mean colour of the fruit. For Jonagold apples, having a multimodal colour frequency distribution, the defect location was based on a non-parametric model of the fruit colour and on Bayes' theorem. In both cases, the development of an algorithm, taking into account local information, enhanced the segmentation precision. The calyx and stem ends, which appear as defects on the image, were detected by a pattern correlation technique. The segmented areas (poles, defects and over-segmentation zones) were characterised with shape, colour and texture descriptors. The fruit grading into four classes (Extra, A, B and cull) according to European standards is obtained by using a cluster analysis on the segmented regions. The results obtained are favourable and make it possible to envisage the transfer of developed algorithms onto a commercial sorting machine. [less ▲]

Detailed reference viewed: 37 (2 ULg)