Abstract: A method for determining the boundary between abutting food product in a food processing system uses scan data of the food product to identify a perimeter of the abutting food product. Optionally, data from scanning the food product is first tested to determine or predict if more than one article is present. A perimeter of the abutting food product is generated from the scan data, and the perimeter information is manipulated to identify or estimate the boundary between the product. For example, the boundary may be eroded until it separates into two portions. The two portions are then expanded, constrained by the original perimeter, such that a region of interest includes overlapping portion that includes the boundary. The region of interest is analyzed to locate the boundary. In another method, a parametric shape is fit to the image to identify the individual articles. In another method, a shortest line or surface separating the perimeter into two substantial portions is found.

Abstract: The present invention provides a complete artificial intelligence system for the acquisition and analysis of nucleic acid array hybridization information. The system includes a central data processing facility and one or more user facilities, linked by encrypted connections. Each user facility may include an optical scanning system to collect hybridization signals from a nucleic acid array, an image processing system to convert the optical data into a set of hybridization parameters, a connection to a data network, and a user interface to display, manipulate, search, and analyze hybridization information. This system reads data from a nucleic acid microarray, analyzes test results, evaluates patient risk for various ailments, and recommends methods of treatment. The automated artificial intelligence system is a real time, dynamic decision making tool that can be used in conjunction with a clinical analysis system, and with the information obtained in a research and development environment.

Abstract: The method is for forest inventory and for determination of stand attributes. Stand information of trees, sample plots, stands and larger forest areas can be determined by measuring or deriving the most important attributes for individual trees. The method uses a laser scanner and overlapping images. A densification of the laser point clouds is performed and the achieved denser point clouds are used to identify individual trees and groups of trees. A computer program is used for performing the method.

Abstract: Disclosed are methods of and systems for producing vegetation information for an area of interest using at least two comparison index values. The comparison index values can be generated based on specific reflectivity characteristics of vegetation relative to non-vegetation.

Abstract: A fluorescence observation apparatus includes an image storage unit for storing a plurality of pairs of bright-field images and fluorescence images of a small laboratory animal in such a manner that relative positions thereof are aligned; a display unit for displaying the plurality of fluorescence images stored in the image storage unit so as to be arrayed in at least one direction; an outline extracting unit for extracting an outline shape of the small laboratory animal in each bright-field image; and an image-position adjusting unit for adjusting a display position of each associated fluorescence image so that the outline shapes of the small laboratory animal extracted by the outline extracting unit are aligned with each other in a direction orthogonal to the arrayed direction.

Abstract: The present invention relates to a volume-of-interest segmentation system for use with molecular imaging quantization, which includes: a set of template for segmentation of organ/anatomical region-of-interest, an animal size/weight/location calculator, an animal spine position calculator, and a texture analyzer. It can be used for saving time and reducing cost for segmentation of interested regions and increasing the precision of molecular image quantization.

Abstract: There are described methods and apparatus for assessing sediments generated in liquid-based systems. The methods involve optically obtaining information to enable height and, thus, volume data relating to sediments to be measured. Although single samples of liquid-based systems may be processed the methods are particularly suited to processing multiple samples to obtain data relating to sediments at a high rate. The apparatus includes automated handling equipment to enable samples to be moved between workstations and relative to associated optical equipment that is used to obtain information relating to the sediments.

Abstract: The present invention provides systems and methods to automatically analyze Landsat satellite data of forests. The present invention can easily be used to monitor any type of forest disturbance such as from selective logging, agriculture, cattle ranching, natural hazards (fire, wind events, storms), etc. The present invention provides a large-scale, high-resolution, automated remote sensing analysis of such disturbances.

Abstract: An apparatus and method for non-invasive lean recovery from a sparse lean product, where the method can include conveying ground sparse lean product through a conveyance channel where the conveyance channel extends along a path that extends through a scanning position adjacent a scanner. The process includes scanning along a predetermined length with the scanner the ground sparse lean product traveling through the conveyance channel and further analyzing the scan and determining the percent fat content for each ground sparse lean product segment which is defined by the predetermined length of the ground sparse lean product within the volume of the conveyance channel and the cross section areas of the conveyance channel. The process can further include directing each ground sparse lean product segment down one of a plurality of processing paths corresponding to the one defined fat content range in which the corresponding percent fat content falls.

Abstract: In various embodiments, the present disclosure provides a method of generating crop biometric information in field conditions that includes scanning top surfaces of various plant crown structures of a plurality of plants in one or more rows of plants within a field to collect scan data of the crown structures. Additionally, the method includes converting the scan data into a high spatial resolution 3-dimensional field contour map that illustrates an aggregate 3-dimensional field contour of the scanned plants. The method further includes extracting, from the high spatial resolution 3-dimensional field contour map, biometric information relating to the plants in each of one or more selected rows of the scanned rows of plants.

Abstract: A system and method for computing an amount of timber that can be harvested from a plurality of trees is provided. An image related to a plurality of trees in a region may be obtained. A digital representation of the image may be analyzed to determine at least one of a presence, a location and/or a height of at least some of the trees. An inventory report related to an amount of timber that may be harvested may be generated based on at least one of the presence, location and/or a height of trees in the region.

Abstract: The system for uniquely identifying subjects from a target population operates to acquire, process and analyze images to create data which contains indicia sufficient to uniquely identify an individual in a population of interest. This system implements an automated, image-based process that captures data indicative of a selected set of external characteristics for subjects that are members of a target population of a predetermined species.

Abstract: The present invention refers to a system for the diagnosis of plant anomalies which comprises at least: an acquisition device (1) capable of capturing images in real time of at least one sample of a plant to be diagnosed; a storage unit (2) comprised by a database of digitalized images (7) of samples of plants affected by anomalies and also comprised by a database of technical information (8) related to said anomalies; a human interface device (3) capable of displaying digitalized images of the plant samples; a human control device (4) capable of allowing for an active interaction between a user and the human interface device; and a processing unit (5) operatively associated to the acquisition device (1), to the storage unit (2), to the human interface device (3) and to the human control device (4).

Abstract: A nondestructive system and method for aflatoxin detection based on red-orange fluorescence is described. A sorting plane is illuminated with a wide band black light source. At least one image of unsorted produce on said sorting plane is obtained. A red component of the at least one image is evaluated. Contaminated produce is determined based on the red component.

Abstract: A produce recognition method which uses hierarchical Bayesian learning and kernel combination, and which offers classification-oriented synergistic data integration from diverse sources. An example method includes providing a classifier having a plurality of inputs, each input being adapted to receive produce data of a different modality; mapping the produce data to the respective input of the classifier by a computer; for each input, independently operating on the data relating to that input to create a feature set by the computer; comparing each feature in the feature set to respective pre-trained data for that feature to produce a similarity description set; combining all similarity description sets using a dedicated weighting function to produce a composite similarity description by the computer; and deriving a plurality of class values from the composite similarity description to create a recognition result for the produce item by the computer.

Abstract: Indicating a precise geographic extent and a precise geographic location of a dig area at a work site at which excavation is planned, to facilitate detection and/or marking of a presence or an absence of an underground facility in the dig area. A graphical user interface includes an aerial image of a geographic area proximate to and including the work site and the dig area, and a drawing tool to facilitate placement of one or more dig area indicators on the aerial image. A user uses the drawing tool to delimit the precise geographic extent and the precise geographic location of the dig area(s) on the displayed aerial image so as to form the dig area indicator(s), representing unbuffered dig areas, and thereby generate a marked-up aerial image. Geographic coordinates are determined corresponding to the unbuffered dig area(s) represented by the dig area indicator(s).

Abstract: A biometric kit and method of using the same that includes the collection and verification of photographs, an animal nose print and DNA profile of a pet or animal along with a specific animal information profile. The collected and verified data is converted to a digital format and stored.

Abstract: A method of discriminating between kernel and chaff particles, in crop, using a crop viewing apparatus that includes an image-capturing device that is capable of capturing one or more images of crop in the crop viewing apparatus. The image capturing device connected to a processing device for processing one or more resulting images. The crop viewing apparatus also includes one or more lamps for illuminating crop in the crop viewing apparatus. The lamp illuminates the crop in a range of illumination levels up to a maximal level equal to or above a reflectivity saturation level at which increasing illumination causes no further reflectivity change. The crop viewing apparatus further includes one or more control devices for controlling the level of illumination provided by each lamp.

Abstract: Methods, systems and devices are implemented in connection with measuring subcutaneous fat and loin depth in a portion of muscle tissue. Consistent with one such method a probe is presented to the portion of muscle tissue. The probe produces a response-provoking signal in the muscle tissue used to determine the fat and loin depth in the portion of muscle tissue.

Abstract: A method of processing vegetation data including the steps of identifying data relating to an agricultural field, segregating areas of predetermined development patterns and prescribing application rates of an agricultural compound. The identifying step includes identifying data relating to an agricultural field representative of areas of predetermined development patterns of vegetation in the field. The segregating step includes segregating the areas of the predetermined development patterns thereby defining segregated areas, other areas in the field being non-segregated areas. The prescribing step including prescribing application rates of an agricultural compound to the non-segregated areas dependent on at least one attribute determined from the data.

Abstract: A new application of machine vision for process industries is proposed. The invention consists of: (1) estimation of visual quality of products, (2) modeling causal relationship between estimated quality and process variables, and (3) optimization of visual quality using the causal model. This invention can handle the stochastic nature in visual appearance of products that process industries provide, which has been a main obstacle for the success of machine vision in process industries. Also, it opens new tasks in machine vision such as modeling and optimization of visual quality of products.

Abstract: An imaging system containing an electron-multiplying charge-coupled device detector and line-scan spectrograph is used for identifying wholesome and unwholesome freshly slaughtered chicken carcasses on high-speed commercial chicken processing lines. Multispectral imaging algorithms allow for real-time online identification of wholesome and unwholesome chicken carcasses.

Abstract: Systems and techniques for product identification using terahertz radiation detection. An area of interest is illuminated with radiation in the terahertz frequency range and terahertz radiation reflected from objects within the area of interest is detected and a detector signal based on the detected radiation is processed to generate identifying information for the objects. The generated identifying information may be compared against stored identifying information for products and the result of the comparison is used to select a product or group of products for which the comparison produces a match. Processing of the detector signal may generate a spectral signature characteristic of reflective and absorptive properties of an object under illumination, and the spectral signature may be compared with stored spectral signature information for products.

Abstract: Systems and methods are described that provide a fast and simple way of administering a drug program related to an animal. Specifically, systems are provided that can receive, compile and analyze information regarding the condition of an organ in a form that is readily readable, transferable to others, and associated with, or linked to, other information such as the presence or absence of an administered drug, combination of drugs, or drug program.

Abstract: In one embodiment, a method includes capturing an image of a first organic polarized object using an image capture device. The method also includes collecting a first image data of the first organic polarized object. The method further includes algorithmically calculating a first dimension data based on the first image data. The method further includes generating a first data table of the first dimension data. The method also includes forming a training data set using the first data table. The method also includes computing high vote count data for second organic polarized object using the training data and second dimension data sets to identify precise shape, size, location and orientation. The method further includes calibrating coordinate systems of a robotic end effector with an image capture device and commanding the robotic end effector to pick up and place the second organic polarized object in a precise location and orientation.

Abstract: An imaging system containing an electron-multiplying charge-coupled device detector and line-scan spectrograph is used for identifying wholesome and unwholesome freshly slaughtered chicken carcasses on high-speed commercial chicken processing lines. Multispectral imaging algorithms allow for real-time online identification of wholesome and unwholesome chicken carcasses.

Abstract: An apparatus for recognizing and determining the position of at least one teat of a milking animal includes a scanning head comprising a light source and a camera. The light source emits light into a region which is expected to contain a teat or teats and the camera captures images formed by the light. In a first scanning mode, the scanning head is moved from a low initial position upwards in a circular coil until the position of at least a first teat has been established. Thereafter, in a second scanning mode, the scanning head is moved upwards in a to circular coil until the positions of all teats have been established, or a predetermined time limit has elapsed during the scanning procedure. The coil traversed during the first scanning mode is wider than the coil traversed during the second scanning mode.

Abstract: The present invention is directed to a method and system utilizing novel computer software for determining the antler, horn, and pronghorn size of an animal by calculating, measuring, analyzing, comparing, scoring, presenting, and comparing the antler and horn sizes of animals such as deer, bovids, and pronghorns from digital data and/or photographs.

Abstract: The invention relates to a method for computer-aided segmentation of an environment into individual objects, in particular of a wood into individual trees, in which signals (SIG_R) backscattered by the objects are recorded by measurement technology, wherein the backscattered signals (SIG_R) result from the irradiation of the environment to be segmented with electromagnetic radiation. Furthermore, in the method according to the invention, spatial co-ordinates (x, y, z) of points which cause the backscattering and represent the object parts (X1, X2, . . . , Xs) are determined from the backscattered signals (SIG_R), and a feature vector (f) is assigned to each of the points (P; P1, P2), which feature vector comprises at least the spatial co-ordinates (x, y, z) of the point in question (P; P1, P2). Then a distance measure (d) is determined for each of the feature vectors (f), which represents a similarity between the feature vectors (f) of two points (P; P1, P2).

Abstract: A system and method of determining nitrogen levels from a digital image. In particular, a method of determining leaf nitrogen concentration and yield from a digital photograph of a fully developed leaf (collared leaf) of a crop of nonlegumes, such as corn, rice, wheat, cotton, potatoes or sugarcane. The digital image is processed to determine a dark green color index (“DGCI”), which is closely related to leaf nitrogen concentration and yield. Standardized color disks having known DGCI values are included in the digital photograph and serve as an internal standard. The internal standard allows correction of DGCI of samples when using different cameras and/or when lighting conditions change.

Abstract: Method for assigning a stonefruit to a predetermined class, in which the stonefruit is transported along at least one source of high-energy electromagnetic radiation such that at least a part of the radiation penetrates through the stonefruit to at least one camera thereto provided and is there captured by the camera to form a contrast image using the captured radiation after which the contrast image is processed by a processing unit which is provided to evaluate a pattern in the contrast image caused by a variation in the density or thickness of a material of the stonefruit corresponding to at least one predetermined feature of the stonefruit and to assign, based on the evaluation of the feature, the stonefruit to a predetermined class, characterised in that the feature mainly corresponds to the presence or absence of a slit in a pit of the stonefruit.

Abstract: A false color composite image is created by assigning mid infrared data from three time-spaced images of an area of interest to corresponding RGB color components for the false color composite image. The RGB color components for the false color composite image are then converted into color space data and classified into a number of color classes. An age is assigned to the color classes to create a classified image of age classes of the area of interest.

Abstract: An apparatus for recognizing and determining the position of at least one teat of a milking animal includes a scanning head comprising a light source and a camera. The light source emits light into a region which is expected to contain a teat or teats and the camera captures images formed by the light. In a first scanning mode, the scanning head is moved from a low initial position upwards in a circular coil until the position of at least a first teat has been established. Thereafter, in a second scanning mode, the scanning head is moved upwards in a circular coil until the positions of all teats have been established, or a predetermined time limit has elapsed during the scanning procedure. The coil traversed during the first scanning mode is wider than the coil traversed during the second scanning mode.

Abstract: A method of creating a segmentation of a volume of interest in an object data set is described, which object data set is formatted into object data slices, in which at least two object data slices each contain a contour line defining the portion of the volume of interest present in that object data slice as a region of interest. The method comprises the steps of calculating at least one surface which cuts through each of the at least two regions of interest, defining two curves on each surface which intersect with the contour lines, arranging for those curves to define the portion of the volume of interest present in the surface, calculating on each of the remaining object data slices a contour line which includes those points on the curves which intersect with that object data slice. A computer program and work station are also described.

Abstract: Systems and methods are described that provide a fast and simple way of administering a drug program related to an animal. Specifically, systems are provided that can receive, compile and analyze information regarding the condition of an organ in a form that is readily readable, transferable to others, and associated with, or linked to, other information such as the presence or absence of an administered drug, combination of drugs, or drug program.

Abstract: An apparatus (10) for recognizing and determining the position of at least one teat cup (401, 402, 403, 404) of at least one teat cup magazine (42, 421, 422). The apparatus (10) emits waves (20) into a region (A) which is expected to contain a teat cup or teat cups (401, 402, 403, 404). The apparatus (10) also includes a detector (260) for detecting reflections of the waves (20). The apparatus (10) also includes a unit (24) for evaluating the reflections in order to determine if the reflections originate from the teat cup or cups (401, 402, 403, 404). Furthermore, the apparatus (10) also includes a unit (26) for determining the position of the teat cup or cups (401, 402, 403, 404) if it is established that the reflections originate from the teat cup (401, 402, 403, 404).

Abstract: A system and method for measuring an animal includes a light source and an optical source. The light source, which is preferably an array of monochromatic light emitting diodes, at least partially backlights one or more of the animal's legs. The optical sensor or device, which is preferably a single dimension camera or charged-coupled device, opposes the light source and obtains an image that includes silhouettes of one or more legs of the animal. A processor, such as a computer with software and data storage, determines measurements, such as the approximate skeletal trunk length of the animal, from the silhouetted legs in the image. One or more first ultrasound transducers can be arranged to determine an approximate height of the pelvic region, and one or more second ultrasound transducers can be arranged to determine an approximate width of the pelvic region.

Abstract: An apparatus, method and computer program storage device cooperate to acquire an image of at least a part of a meal. An analysis is then done on the image to determine a substance in the image. The analysis also considers caloric intake and exercise data and compares the same with a health management model to arrive at a recommendation for a user who consumed the meal. Various optional features include using wireless communications to receive exercise data from sensors, as well as communication related images such as the menu of a restaurant or the location of the restaurant.

Abstract: The present invention relates generally to an apparatus for and a method of measuring and selecting grain for use in milling, or seed for use in plant breeding. Said method is adapted to optically analyze seeds/grains to qualitatively and quantitatively characterize the seed/grain, and more particularly, to analyze the gradation of color, whiteness, and hard endosperm of the seed/grain. This method and apparatus perform color image analysis of seed/grain sample(s) to characterize multiple quality traits.

Abstract: It is aimed to enable analyzing vegetation growth conditions at multiple times of a year accurately using radar images obtainable from a flying body such as artificial satellites, etc. A plurality of radar images of a ground surface of a same target area, which have been taken at multiple times of a year by a radar device mounted on a flying body, are acquired. The acquired plurality of radar images is stored in a map database. While using as a criterion image a radar image of the plurality of radar images stored in the map database, taken at a predetermined time in the multiple times of a year, other radar images than the criterion image of the plurality of radar images, taken at other times than the predetermined time in the multiple times of a year, are aligned with the criterion image, respectively. Then, backscatter coefficients of specified areas in the plurality of radar images are extracted.

Abstract: Disclosed is a method and an apparatus for measuring the growth of leaf disks. The method comprises the following steps: a) Calibrating the capture system, b) capturing at least 2 images of a leaf disk, c) processing the image data, comprising i) segmenting the leaf disks by threshold segmentation, ii) multiple morphological erosion steps, iii) edge cleaning to remove the edge of the storage vessel, d) 3D reconstruction: generating a disparity map by means of a stereo algorithm, calculating a 3D surface model based on the previously determined calibration parameters from the disparity map, e) smoothing the previously obtained surface model, f) determining the growth rates from the time series of the areas. The apparatus comprises at least one camera, a lighting unit, a translation table in the X/Y plane for the camera and (infrared) lighting, storage vessels for leaf disks, and electronic evaluation and control units.

Abstract: A living animals conveying device for sorting animals with respect to a characteristic such as color, size, gender, or weight. In the case of chicks, an embodiment of the invention includes a section for conveying chicks with chicks positioned in buckets with their wings spread out, and an automatic chicks sexing system. A first endless bucket conveyor comprising pre-positioning buckets able to individually receive and transport a living animal, is oriented with respect to a second endless bucket conveyor, comprising sorting buckets able to individually receive and transport a living animal, the first conveyor and the second conveyor being arranged in such a way that each pre-positioned living animal in a pre-positioning bucket falls from the pre-positioning bucket into a sorting bucket arranged below the pre-positioning bucket.

Abstract: A method and an apparatus for noninvasively and quantitatively determining spatially resolved absorption and reduced scattering coefficients over a wide field-of-view of a food object, including fruit or produce, uses spatial-frequency-domain imaging (SFDI). A single modulated imaging platform is employed. It includes a broadband light source, a digital micromirror optically coupled to the light source to control a modulated light pattern directed onto the food object at a plurality of selected spatial frequencies, a multispectral camera for taking a spectral image of a reflected modulated light pattern from the food object, a spectrally variable filter optically coupled between the food object and the multispectral camera to select a discrete number of wavelengths for image capture, and a computer coupled to the digital micromirror, camera and variable filter to enable acquisition of the reflected modulated light pattern at the selected spatial frequencies.

Abstract: A thinning or weeding apparatus includes an image processing apparatus. The image processing apparatus includes an automated visual detection system which includes a visual sensor system and an image processing system capable of receiving an image from the visual sensor system. The image processing apparatus then processes the image in the image processing system to determine where plants are located and to determine which plants will be thinned or weeded and which will not.

Abstract: An apparatus and method of quantitatively obtaining a measurement of pollen of a plant. One method of counting comprises imaging the sample with the pollen well-distributed in the focal plane of the imager. Image evaluation software can identify and count objects in the image that are consistent with pollen. Total pollen count for the plant can be derived from the count of pollen of the sample, proportionality of the sample volume to the starting volume, and proportionality of area of sample imaged to total area of sample. Pollen quantification can be used for research or commercial production decisions relative to the plant or its seed.

Abstract: A process for using a hand-held infrared inspection system incorporating on-board training, on-board validation, on-board operator certification, on-board reporting information, or on-board survey instructions. Improved methods for automating area surveys are provided through exception-driven surveillance practices. Imbedded information enables less experienced operators to use more sophisticated devices more effectively. Validation or certification assures operator knowledge or ability. Multilevel classification of anomalies aids in automated analysis and report generation.

Abstract: A computer-implemented method for estimating a volume of at least one food item on a food plate is disclosed. A first and second plurality of images are received from different positions above a food plate, wherein angular spacing between the positions of the first plurality of images is greater than angular spacing between the positions of the second plurality of images. A first set of poses of each of the first plurality of images is estimated. A second set of poses of each of the second plurality of images is estimated based on at least the first set of poses. A pair of images taken from each of the first and second plurality of images is rectified based on at least the first and second set of poses. A 3D point cloud is reconstructed based on at least the rectified pair of images. At least one surface of the at least one food item above the food plate is estimated based on at least the reconstructed 3D point cloud. The volume of the at least one food item is estimated based on the at least one surface.

Abstract: The invention refers to a method of selecting stem segments with desired characteristics and more specifically the invention refers to a method of selecting stem segments of graminaceous plants (from the Gramineae/Poaceae family), such as plants of the Saccharum spp, including sugar cane. According to an embodiment of the invention, the method of selecting stem segments, comprises the steps of identifying at least one characteristic of each stem segment by a sensor; and separating the stem segments comprising the said characteristic from those which do not comprise the said characteristic, depending on the response of said identification means; characterized in that the sensor is selected from the group consisting of a pressure transducer sensor, a capacitive sensor, an ultrasound sensor, an x-ray sensor, a magnetic sensor, and a microwave sensor.

Abstract: The invention relates generally to an improved plant breeding system. More particularly, this invention relates to a method for automated, high throughput analysis of plant phenotype and plant genotype in a breeding program.

Abstract: A grain images obtained by CCD line sensors are processed by binarization processing to obtain contour images of grains and images of colored portions in the grains. The images are displayed on a monitor screen of an operating panel 30. The contour images and the images of the colored portions are displayed in a superposed state. Box frames generated by a highlight display circuit in control means 12 are simultaneously displayed by being superposed on the contour images having defective portions, thus producing a highlight display of defective grains. The defective grains include a grain having a light colored portion and a grain having a dark colored portion.