Food color is an important attribute of food quality. This paper discusses issues in using machine vision for the objective assessment of food color, such as color image segmentation, calibration and statistical parameter design, and their application to pea color assessment. The algorithm first established a 3D histogram on RGB color space based on an octree data structure. From the color space, a statistical index was calculated to measure the major color of an object simulating the characteristics of human color perception. This method was applied to assess the major color of peas. Accuracy and efficiency were achieved in measuring pea seed and its variations.

This system is designed to assist diagnosis of the plant health globally. The system is formed by portable plant health measurement devices connected to a diagnosis and analysis center through a flexible information network. A flexible network is formed so that users from the remote areas as well as internet are able to use the system. The hardware and software is designed in an open technology for easier upgrades. Portable plant health measurement instrument is a networkable leaf flash spectrophotometer capable of measuring Qa, Electrochromy, P700, Fluorescence, S Fluorescence, reflectance spectra, temperature, humidity and image of the leaf with GPS information. The network and intelligent user interface options of the system can be used by any commercially or user designed instrument.

Segmentation is an important step in the early stage of image analysis. Color or multi-spectral image segmentation usually involves search and clustering techniques in a three or higher dimensional spectral space - an exercise which is considered computationally expensive. This paper presents a new color segmentation method for color image analysis with its application to plant leaf area measurement. A 3D histogram for an RGB color image is established basing on an octree data structure. The histogram represents the color distribution of the image in the RGB color space on which a 3D Gaussian filter is applied to smooth out small maxima of this distribution. The color space is then searched to find out al the major maxima. Around each maxima, a covering cube with a controlled side width is established. These maxima and covering cubes are considered to be potential color classes. Each cube may expand according to the value of surrounding neighbors. Once enough modes and their cover cubes have been found, a k-means clustering algorithm is used to classify these maxima into a predetermined number of classes. Then, the classified modes and the color covered by the cubes are used as training samples for a Bayes classifier which can be used to classify all the pixels in the image. A statistical relaxation method is then sued as a find segmentation. This method can either be supervised or unsupervised, depending on the different requirements of specific applications. The octree data structure significantly reduces the color space to be searched and consequently reduces computational cost. An extension of this method can also be applied to multi-spectral image analysis.

A non-invasive method to estimate internal temperature in boneless, skinless chicken meat after cooing is presented. In this work, the internal temperature of chicken breast samples, measured at approximately half the thickness, was correlated with the external temperature of the surface above and the cooling time. For the non-invasive and accurate external temperature measurement a focal planar array IR camera with spectral range of 3.4-5 micrometers was used. At this spectral band, the interference of water vapor originated from the sample is practically eliminated. Neural networks were used to establish a correlation between internal temperature with external temperature and cooling time. To model the internal and external temperature time series a one-hidden layer feed forward layer, with three hidden nodes was used. The network was trained with 60 time series of 20 time points each one, ranging form 0 to 570 seconds. Training was conducted for 400 epochs, with learning rate 0.3. The predictions obtained were compared with a test data set to judge the performance of the network. The method has great potential for the real-time estimation of internal temperature of cooked chicken meat in industrial lines.

We present a conceptual framework for coupling sensing to crop models for closed-loop analysis of plant production for NASA's program in advanced life support. Crop status may be monitored through non-destructive observations, while models may be independently applied to crop production planning and decision support. To achieve coupling, environmental variables and observations are linked to mode inputs and outputs, and monitoring results compared with model predictions of plant growth and development. The information thus provided may be useful in diagnosing problems with the plant growth system, or as a feedback to the model for evaluation of plant scheduling and potential yield. In this paper, we demonstrate this coupling using machine vision sensing of canopy height and top projected canopy area, and the CROPGRO crop growth model. Model simulations and scenarios are used for illustration. We also compare model predictions of the machine vision variables with data from soybean experiments conducted at New Jersey Agriculture Experiment Station Horticulture Greenhouse Facility, Rutgers University. Model simulations produce reasonable agreement with the available data, supporting our illustration.

A multivariate numeric image can be seen as a 3-way data table: two dimensions of this table are of spatial nature whereas the other characterizes the constitutive univariate images. The process of labeling consists in assigning a qualitative group to each pixel of the original multivariate image. A supervised learning method, stepwise discriminant analysis was compared with two unsupervised methods, simple C-means clustering (CMC) and fuzzy C-means. As illustrative example, the methods were applied on multivariate images of sections of maize kernels obtained by fluorescence imaging. CMC requires the utilization of a function assessing the distance between some representative patterns and the pixel vectors. The relative interest of Euclidean distance and Mahalanobis distance was investigated. The best results were obtained by using CMC and simple Euclidean distance. In these conditions, it was possible to identify, with no a priori knowledge, the main tissues of maize.

Segmentation of agricultural products on a conveyor belt is a first step for product inspection. We consider a new algorithm to achieve segmentation. We use x-ray images which provide useful internal information on the state of the product. The product items considered vary in size, shape, gray-scale properties, and lie at random orientations. Many items touch and thus new techniques are necessary to detect each item at any orientation, estimate the number of touching items and their centers, and segment overlapping touching items to provide separate image filters for touching input items. Test results are presented for x-ray film and linescan images of various agricultural products including one extensive database.

Abstract not available.

The fresh produce packing industry represents a large potential market for machine vision inspection systems. Unlike most manufacturing industries, there is no single 'reference product' form which any deviations represent a flaw. The Optigrade II machine was designed to replace human sorters and extensively utilizes neural networks to emulate the human sorting process. The network architecture and design principles are presented with an emphasis on the problems arising in the development of a commercial product.

Fruit and vegetables suffer different manipulations from the field to the final consumer. These are basically oriented towards the cleaning and selection of the product in homogeneous categories. For this reason, several research projects, aimed at fast, adequate produce sorting and quality control are currently under development around the world. Moreover, it is possible to find manual and semi- automatic commercial system capable of reasonably performing these tasks.However, in many cases, their accuracy is incompatible with current European market demands, which are constantly increasing. IVIA, the Valencian Research Institute of Agriculture, located in Spain, has been involved in several European projects related with machine vision for real-time inspection of various agricultural produces. This paper will focus on the work related with two products that have different requirements: fruit and olives. In the case of fruit, the Institute has developed a vision system capable of providing assessment of the external quality of single fruit to a robot that also receives information from other senors. The system use four different views of each fruit and has been tested on peaches, apples and citrus. Processing time of each image is under 500 ms using a conventional PC. The system provides information about primary and secondary color, blemishes and their extension, and stem presence and position, which allows further automatic orientation of the fruit in the final box using a robotic manipulator. Work carried out in olives was devoted to fast sorting of olives for consumption at table. A prototype has been developed to demonstrate the feasibility of a machine vision system capable of automatically sorting 2500 kg/h olives using low-cost conventional hardware.

Pinhole insect damage in natural almonds is very difficult to detect on-line. Further, evidence exists relating insect damage to aflatoxin contamination. Hence, for quality and health reasons, methods to detect and remove such damaged nuts are of great importance in this study, we explored the possibility of using x-ray imaging to detect pinhole damage in almonds by insects. X-ray film images of about 2000 almonds and x-ray linescan images of only 522 pinhole damaged almonds were obtained. The pinhole damaged region appeared slightly darker than non-damaged region in x-ray negative images. A machine recognition algorithm was developed to detect these darker regions. The algorithm used the first order and the second order information to identify the damaged region. To reduce the possibility of false positive results due to germ region in high resolution images, germ detection and removal routines were also included. With film images, the algorithm showed approximately an 81 percent correct recognition ratio with only 1 percent false positives whereas line scan images correctly recognized 65 percent of pinholes with about 9 percent false positives. The algorithms was very fast and efficient requiring only minimal computation time. If implemented on line, theoretical throughput of this recognition system would be 66 nuts/second.

A machine vision system was developed to inspect and estimate the internal damage of rough rice. A modified dark field illumination technique was use to direct light through the rice kernels without saturating the CCD camera. Under modified dark field illumination, the good portions of the rice kernels appeared translucent, while the damaged portions appeared opaque as well as some portions of the hull and the germ of the kernel. A combination of thresholding and morphological operators were used to segment the dark areas and to approximate the actual damaged area. The rice was visually separated into categories of undamaged, spot dammed, and damaged by trained entomologist and plant pathologists. The machine vision system was 91.5 percent successful overall for correctly categorizing a test sample of rice kernels.

Classification of real-time x-ray images of randomly oriented touching pistachio nuts is discussed. The ultimate objective is the development of a system for automated non- invasive detection of defective product items on a conveyor belt. We discuss the extraction of new features that allow better discrimination between damaged and clean items. This feature extraction and classification stage is the new aspect of this paper; our new maximum representation and discrimination between damaged and clean items. This feature extraction and classification stage is the new aspect of this paper; our new maximum representation and discriminating feature (MRDF) extraction method computes nonlinear features that are used as inputs to a new modified k nearest neighbor classifier. In this work the MRDF is applied to standard features. The MRDF is robust to various probability distributions of the input class and is shown to provide good classification and new ROC data.

In marketing channels, bread is sometimes delivered in a frozen sate for distribution. Changes occur in physical dimensions, crumb grain and appearance of slices. Ten loaves, twelve bread slices per loaf were scanned for digital image analysis and then frozen in a commercial refrigerator. The bread slices were stored for four weeks scanned again, permitted to thaw and scanned a third time. Image features were extracted, to determine shape, size and image texture of the slices. Different thresholds of grey levels were set to detect changes that occurred in crumb, images were binarized at these settings. The number of pixels falling into these gray level settings were determined for each slice. Image texture features of subimages of each slice were calculated to quantify slice crumb grain. The image features of the slice size showed shrinking of bread slices, as a results of freezing and storage, although shape of slices did not change markedly. Visible crumb texture changes occurred and these changes were depicted by changes in image texture features. Image texture features showed that slice crumb changed differently at the center of a slice compared to a peripheral area close to the crust. Image texture and slice features were sufficient for discrimination of slices before and after freezing and after thawing.

Networks of NIR transmission spectrometers operating in the range 850 to 1050 nm are used worldwide to determine wheat grain quality parameters such as protein content. These instrumental system often require maintenance of calibrations for each grain class, and updating of calibrations for each crop year. In order to facilitate annual updates nd eliminate the need for multiple wheat class calibration models, this laboratory is pursuing a modeling strategy that uses locally weighted regression (LWR) to access a spectral database. With LWR, the calibration model defines the procedure to access the database and calculate the prediction, and this model can potentially remain the same for all classes and crop years. Incorporation of new sample variation is accomplished by new additions to the spectral database. Details are presented on development of an NIR model for determination of protein in multiple wheat-classes using the LWR approach with Y- distance weighting. This model is compared with a linear partial least-squares regression model spanning the same diverse set of samples. Initial steps were taken to validate these models with spectra measured on seven instruments at two remote locations.

To make malt, barley kernels are moistened to a moisture content of about 0.79, germinated and then kilned. Experienced maltsters control the process parameters to achieve a certain desired quality. Barley malt is commercially dried for a large moisture reduction from 0.79 to 0.02 resulting in its chemical constituents and physical characteristics. This paper addresses attributes of malt measured by machine vision. The paper explains the hardware and software for capturing the visual attributes/morphological features of malt at several moisture contents during drying. The measured data and the source of variations in the data are discussed.

In the present work, a method for the identification of kernel tissue in cross-sections, based on their natural fluorescence properties is presented. The method involved a multivariate fluorescence video imaging system. The system made it possible to record sequences of images by changing the spectral conditions. Each tissue was characterized on the images by varying fluorescence properties. The images were linearly combined and the most discriminant images for the identification of the tissue were selected by stepwise discriminant analysis. Images were labeled according to the nature of the tissues by attributing to each pixel of a sequence of images a qualitative group number corresponding to each tissue. On these segmented images, more than 98.8 percent of the pixels were correctly identified.

A hyperspectral imaging system has been developed to provide the capability of both airborne and ground/laboratory data acquisitions. The system consists of modular front imaging optics with a liquid crystal tunable filter (LCTF), a CCD video camera, a frame grabber and a portable computer system. The spectral range is form 450 nm to 750 nm with a 10 nm bandpass for each band acquired. The system can capture different spectral images at a rate up to 14 images per second. Hyperspectral imaging with an LCTF provides a new method for hyperspectral image acquisition. The system allows the user to define a wavelength sequence of up to thirty-two spectrums specifically required for individual application, and can quickly switch from the current wavelength to the next during automated image acquisition. Hyperspectral images of crop fields, vegetation, fruits, and meat were successfully captured during laboratory experiments and airborne image acquisition. The constructed spectral image cube not only shows the spatial features of the target, but also reveals the individual pixels with unique spectral signatures. The imaging system with LCTF is, therefore, very useful in biological and agricultural assessment for detecting variations in crop fields, or defects in samples and products.

One of the seed characteristics which seems to correlate with the vigor is the speed of growing. An experimental rig was built to measure this speed using image processing and evaluation technique. The system was able to take automatically pictures in regular intervals, to process them and to carry out the necessary calculations. The image taken from the seedings was scanned by horizontal lines from the bottom to the top. The R, G and B values for each pixel of each line were summarized and a curve was drawn of the sums. Each curve was then derived. A pair of peeks - one below and one above the central line show the vertical edges of a seedling stem. The results of examination are shown in seedling high versus time diagram. The slope of the curve - and so the speed of growing - changes during observation at all the three varieties.

Color class of wheat is an important attribute for the identification of cultivars and the marketing of wheat, but is not always easy to measure in the visible spectral range because of variation in vitreosity and surface structure of the kernels. This work examines whether short-wavelength near IR imaging in the range 632-1098 nm can be used to distinguish different cultivars. The spectral characteristics of six hard white winter and hard red spring wheats were first studied by bulk-sample SW-NIR reflectance spectroscopy using regression analysis to select appropriate wavelengths and sets of wavelengths. Prediction of percent red wheat was better if C-H or O-H vibrational overtones were included in the models in addition to the tail from the visible chromophore absorbance, apparently because the vibrational bands make it possible to normalize the color measurement to the dry matter content of the samples. Next, a reflectance spectral image of 640 X 480 spatial pixels and 11 wavelengths was acquired for a mixture of the two contrasting wheat samples using a CCD camera and a liquid crystal tunable filter. The cultivars were distinguished in the image of principal component (PC) score number two that was calculated from the spectral image. The discrimination is due to the tail from the absorbance band that peaks in the visible. PC images 3 and 6 seem to arise mainly from O-H and C-H bands, respectively, and it is speculated that these spectral features will be important for generating multivariate models to predict the color class of grain. It is shown that the contrast between the red-wheat, white- wheat and background can be increased by applying histogram equalization and segmentation of the kernels in the images.

To produce consistent products, graded to predetermined size and inspected for disease and defects such as bruising and common scab is important for the final quality presented to the consumer. A project funded by the British Potato Council, the Ministry of Agriculture Fisheries and Food, and RJ Herbert Engineering is aimed at developing spectrophotometric methods of disease detection previously investigated by SAC through to commercialization.

Abstract not available.

We have designed and built a passive sensor of sunlight- excited chlorophyll fluorescence which provides for the real-time, in situ sensing of photosynthetic activity in plants. This sensor, which operates as a Fraunhofer line discriminator, detects light at the cores of the lines comprising the atmospheric oxygen A-band and B-bands, centered at 760 nm and 688 nm respectively. These bands also correspond to wavelengths in the far red and red chlorophyll fluorescence bands. The sensor operates on the principle that as light collected from the fluorescing plants is passed through a cell containing oxygen at low pressure, the oxygen will absorb the energy and subsequently re-emit photons which can be detected by a photomultiplier tube. Since the oxygen in the cell will absorb light at exactly the wavelengths that have been strongly absorbed by the oxygen in the atmosphere, the response to incident sunlight is minimal. This mode of measurement is limited to target plants that are close enough that the plants' fluorescence is not itself appreciably absorbed by atmospheric oxygen.

The driving by man in a straight line and turning at the end of the row of the plantation demands high concentration which may limit the possible speed of the vehicle. With automatic steering control working speed can be increased and there is no health when working with chemicals. The necessary input information for the automatic steering can be taken from the natural surrounding. In the plantations the stems of the plants are the most characteristic objects, the bottom of the stems appear in a straight line. The equation of such a line is not influenced by the distance between the stems. In the project described in this paper, a CCD camera mounted on the front of a model tractor takes pictures from one side of the plantation row. Evaluating the images in real time the necessary intervention for keeping the vehicle in straight line can be calculated. The basic equations for steering control and the first image processing experiences are presented.

Alfalfa cubes are grade according to many factors, including overall color, appearance, and particle size. The grading process is currently done manually, and particle sizing is an off-line process done by physically breaking apart the cubes and sieving the particles. This paper presents research which may lead to an automated on-line grading system for alfalfa cubes. A machine vision system was used to extract texture and color features of alfalfa cubes. A neural network algorithm was used to discriminate two types of cubes of varying particle sizes by the use of their texture and color features. The network correctly classified all 22 test cubes using all color and texture features, and correctly classified 21 out of 22 test cubes suing only the texture features.

The spectral reflectance of young rice plants was measured in the visible and near-IR region of the spectrum using a commercially available fiber optic contact probe and miniature spectrometer. This work aims to identify an empirical spectral index which changes when rice is exposed to increased levels of chloride anions in the irrigation water and soil. The ratio of near IR reflectance to that of green, R_750/555 is known to be a quantitative measure of chlorophyll content in the leaf but int his study does not show a consistent shift for sample which are exposed to chloride levels equal to or less than 0.1 percent by mass of soil. However, leaf contact spectral reflectance measurements did reveal a significant and consistent increase in R_750/555 along the length of the leaves, and this variation should represent an important factor in modeling remote and proximal sensing data.

Though most herbicide is applied uniformly in agronomic fields, there is strong evidence that weeds are not distributed uniformly within the crop fields. If an effective weed detection system were developed, both economic and environmental benefits would result from its use for site-specific weed management. Past work in this area has focused mainly on either low spatial resolution photo-detectors or off-line machine vision system. This study was undertaken to develop real-time machine vision weed detection for outdoor lighting conditions. The novel environmentally adaptive segmentation algorithm was developed with the objective of real-time operation on an on-board computer-based system. The EASA used cluster analysis to group pixels of homogeneous color regions of the image together which formed the basis for image segmentation. The performance of several variations of this algorithm was measured by comparing segmented field images produced by the EASA, fixed-color HSI region segmentation, and ISODATA clustering with hand-=segmented reference images. The time cost and questionable accuracy of hand- segmented reference images led to exploration of the use of computer-segmented reference images. Sensitivity and background sensitivity were used as performance measured. Significant differences were found between the means of sensitivity, background sensitivity, and overall performance across segmentation schemes. Similar results were obtained with computer-segmented reference images.

For the site-specific application of herbicides, the automatic detection and evaluation of weeds is necessary. Since reflectance of crop, weeds and soil differs in visual and near IR wavelengths, there is a potential for using reflection measurements at different wavelengths to distinguish between them. Diffuse reflectance spectra of crop and weed leaves were used to evaluate the possibilities of weed detection with reflection measurements. Fourteen different weed species and four crops were included in the dataset. Classification of the spectra in crop, weeds and soil is possible, based on 3 to 7 narrow wavelength bands. The spectral analysis was repeated for reflectance measurements of canopies. Sugarbeet and Maize and 7 weed species were included in the measurements. The classification into crop and weeds was still possible, suing a limited number of wavelength band ratios. This suggest that reflection measurements at a limited number of wavelength bands could be used to detect and treat weeds in a field. This is a great environmental benefit, as agrochemicals will only be used where they are needed. The possibilities of using optical reflectance for weed detection and treatment in the field are discussed.

A spectral detection system discriminating the targets for the non target area was tested during spray applications in apple and pear orchards. The objective of the test was to evaluate the accuracy of the system working at different application parameters and to estimate the rate of possible spray savings obtained during applications on the trees of different size and weeds of different density. The system consisted of the spray units equipped with optic sensor and a control unit which could operate up to 16 spray units. Each spray unit had an optic detector and two light sources emitting two beams of light at the wavelengths 670 and 750. The ratio between emitted and reflected light for each wavelength was the basis for discriminating between the presence or the absence of chlorophyll. The information was processed and used to control the electric solenoid valves opening or shutting off the nozzles. The target detection system worked technically properly. It enabled the selective spray application with spray savings adequate to the tree row profile. In intensive apple and pear orchards 16-25 percent reduction of spray volume was obtained. For herbicide applications the detection system discriminated weeds for the bare ground. Both sensitivity of the sensors and weed density had a significant influence on the spray savings. At medium sensitivity, a considerable spray saving amounting 23 percent was obtained only on the plots with very low weed coverage.

To implement spatially variable application of herbicides for weed control in arable corps, information on the distribution of weeds within the field is required. Manual surveying of weed patches is labor-intensive and not economic for production agriculture. As real-time patch spraying is still a difficult process, the overall objective of this research is to study the feasibility of automatically mapping weeds, a few days before the herbicide application.

Optical spectral reflectance and image analysis techniques were investigated as possible solutions to discriminate crop and weed plants. The range of pants included two brassica crop species, a cereal crop and eight weed species. Spectral signatures were obtained form optical reflectance measurement taken with a spectrophotometer in reflectance mode in the region between 700 and 1350 nm. Algorithms were developed based on multivariate statistical analysis of the plant reflectance spectra. By minimizing wavebands of interest for certain crop/weed combinations, better than 95 percent discrimination accuracy was obtained for only two or three waveband measures. Using filters at these wavebands it was possible to easily segregate corp from weed plants in images. Discrimination on the basis of leaf texture was investigated using textural signatures for whole leaves derived from a gray level co-occurrence matrix of nearest- neighbor pixel intensity. Textural features of leaves were expressed in the form of feature vectors comprising nine textural parameters extracted from the co-occurrence matrix. A numerical Bayesian classifier was used to classify leaves based on minimum distance between a mean feature vector determined form a training set and the test feature vector. A mean discrimination accuracy of 90 percent was achieved between al plant species and almost 100 percent separation was achieved between the crop and weeds. The results show that a combination of spectral imaging and texture analysis may provide a robust method of discrimination with potential for real time application.

This work evaluates real-time techniques for a novel concept of identifying weeds, location and extraction of outline features. THE proposed techniques are conducted by electro- optical methods and perform with the speed of light. The optical system is compact, easy to align and uses a small number of inexpensive components. Generating the 'right' filter for a pattern recognition problem is presented as an optimization process for which the filter performance is the function to be maximized. The genetic algorithm is introduce as a search procedure that uses a biologically motivated random choice as a tool to guide a highly exploitative search through the filter space for nonlinear correlation. The features of the genetic algorithm are ideal for a highly efficient and fast learning process. Computer simulations demonstrate very efficient pattern recognition and excellent discrimination.

Machine vision based on classical image processing techniques has the potential to be a useful tool for plant detection and identification. Plant identification is needed for weed detection, herbicide application or other efficient chemical spot spraying operations. The key to successful detection and identification of plants as species types is the segmentation of plants form background pixel regions. In particular, it would be beneficial to segment individual leaves form tops of canopies as well. The segmentation process yields an edge or binary image which contains shape feature information. Results indicate that red-green-blue formats might provide the best segmentation criteria, based on models of human color perception. The binary image can be also used as a template to investigate textural features of the plant pixel region, using gray image co-occurrence matrices. Texture features considers leaf venation, colors, or additional canopy structure that might be used to identify various type of grasses or broadleaf plants.

Consumers demand for natural quality products and concern about the ecological impact of agricultural is growing in all European countries. For the farmers to follow the evolution of the market, new procedures have to be introduced in agriculture to obtain satisfactory production levels, keeping high quality standards, without damaging the environment.

Abstract not available.

This report presents results theoretical and experimental investigation of a new type of the electro-discharge laser which has as a basis the strong rotated supersound flows. It has been shown that heat transfer inside supersound vortex flow can be related to convection-diffusion type and electrical power coupling in discharge can reach the level of 300 W/cm². It is more than tow order higher than in ordinary gas discharge. The relations of similarity and scaling laws for vortex electro-discharge laser has been proposed. This laser and plasmatrons can be used for various biological, agricultural and forestrial processing. By suing this laser we can detect morphological and pathological skin's changing.

A new conception of the scientific problem of information exchange in the system plant-man-environment is developed. The laser-optical methods and the system are described which allow computer automated investigation of bio-objects without damaging their vital function. The results of investigation of optical-physiological features of plants and seeds are presented. The effects of chlorophyll well and IR beg are discovered for plants and also the effects os water pumping and protein transformations are shown for seeds. The perspectives of the use of the optical methods and equipment suggested to solve scientific problems of agriculture are discussed.

Activated various ways water is used in various branches of a food-processing industry, plant cultivation and so on. By means of water the external forces are capable to render influence to many live organisms, in particular, plants. We intend to show research of the process of hydrations in the melted water and water by influence electromagnetic fields have different frequencies with help of molecular probe. The molecular probe was chosen the molecule of 1,4-dioxane.

Topinambour belongs to medicinal pants with unique useful chemical composition which is characterized by a wide range of biological-active substances. This composition stipulates high nutrient value of topinambour. On this basis the researchers of the Ukrainian Sate University of Food Technologies elaborated some technologies of prophylactic- curative food-stuffs. These products promote the strengthening of immune system, therefore they are very useful for all people, particularly for those who live on the region contaminated by radionuclides. The results of medical-biological and clinical investigations have been discussed in this paper.

The results on the modeling of non-linear dynamics of strong continuous and impulse radiation in the laser nephelometry of polydisperse biological systems, important from the viewpoint of applications in biotechnologies, are presented. The processes of nonlinear self-action of the laser radiation by the multiple scattering in the disperse biological agro-media are considered. The simplified algorithms of the calculation of the parameters of the biological media under investigation are indicated and the estimates of the errors of the laser-nephelometric measurements are given. The universal high-informative optical analyzers and the standard etalon specimens of agro- objects make the technological foundation of the considered methods and systems.

The design of robust machine vision algorithms is one of the most difficult parts of developing and integrating automated systems. Historically, most of the techniques have been developed using ad hoc methodologies. This problem is more severe in the area of natural/biological products. In this arena, it has been difficult to capture and model the natural variability to be expected in the products. This present difficulty in performing quality and process control in the meat, fruit and vegetable industries. While some systems have been introduced, they do not adequately address the wide range of needs. This paper will propose an algorithm development technique that utilizes modes of the human visual system. It will address that subset of problems that humans perform well, but have proven difficult to automate with the standard machine vision techniques. The basis of the technique evaluation will be the Georgia Tech Vision model. This approach demonstrates a high level of accuracy in its ability to solve difficult problems. This paper will present the approach, the result, and possibilities for implementation.

The main criteria used to describe the geometry of agricultural objects are volume and axis measurements. Today accuracy of 10-30 percent is common in mechanical size grading system for potatoes. Electronic systems reach about 10 percent. The market standards are increasing and tolerance values are reducing. A system with tighter sizing parameters is definitely required, although it is envisaged that there will never be a need for micron resolution in size and general shape detection. Resolution in the range of about 1-2 mm is adequate. Agricultural products have allow unit value and many of them have to be handled in a short time period. Fast simple sensors are therefore needed including a simple, compact mechanical construction. Known optical methods are limited in respect of the numbers of 'viewpoints' of the object, which has a bearing on the accuracy.

Color is an important factor in Agricultural and the Food Industry. Agricultural or prepared food products are often grade by producers and consumers using color parameters. Color is used to estimate maturity, sort produce for defects, but also perform genetic screenings or make an aesthetic judgement. The task of sorting produce following a color scale is very complex, requires special illumination and training. Also, this task cannot be performed for long durations without fatigue and loss of accuracy. This paper describes a machine vision system designed to perform color classification in real-time. Applications for sorting a variety of agricultural products are included: e.g. seeds, meat, baked goods, plant and wood.FIrst the theory of color classification of agricultural and biological materials is introduced. Then, some tools for classifier development are presented. Finally, the implementation of the algorithm on real-time image processing hardware and example applications for industry is described. This paper also presented an image analysis algorithm and a prototype machine vision system which was developed for industry. This system will automatically locate the surface of some plants using digital camera and predict information such as size, potential value and type of this plant. The algorithm developed will be feasible for real-time identification in an industrial environment.

Frequently, real world data is degraded by under sampling of intrinsic periodicities, or by sampling with unevenly spaced intervals. This results in dropout or missing data, and such data sets are particularly difficult to process using conventional image processing methods. In many cases, one must still extract as much information as possible from a given data set, although available data may be sparse or noisy. In such cases, we suggest algorithms based on wavelet transform will offer a viable alternative as some early work in the area has indicated. An architecture of an image classification software system is suggested to implement an improved scheme for the analysis, representation, processing and classification of images. The scheme is based on considering the segments of images as wavelets so that small details in the images can be exploited. The objective is to implement this scheme automatically and rapidly decompose a 2D image into a combination of elemental images so that an array of processing methods can be applied. Thus, the scheme offers potential utility for analysis of images and compression of image data. Moreover, the elemental images may be considered patterns that the system is required to recognize, so that the scheme offers potential utility for industrial and military applications involving robot vision and/or automatic recognition of targets.