Abstract: The present system and apparatus uses image processing to recognize object size within a scene. The system includes novel image processing apparatus and methods to segment one or more object images from a background image of the scene. A processed image (that can be used to characterize size features) of the object(s) is then compared to stored reference images. The object size is recognized when a match occurs. The system can recognize object sizes independent of number of objects present and the objects may be touching each other and overlapping. The system can be trained to recognize object sizes that it was not originally programmed to recognize.

Abstract: The computer imaging analysis of bakery products for quality control and other purposes is disclosed. Apparatus and methods useful in such analysis are disclosed. The methods are useful on all types of bakery products. They can be used to analyze for parameters, such as size, shape, area and volume. They can also be used to analyze holes, grain or crust. Viewable images may be provided. The parameters can be compared with prescribed specifications and can be used on a plurality of products to determine substantial uniformity.

Abstract: An image analysis (IA) system for scoring characteristics predictive of palatability and yield of a meat animal carcass or cut. The IA system uses an imaging device, a data processing unit for processing image data, and an output device for output of processed data to the user. Also disclosed is a method for using the IA system in predicting palatability, yield, or defect conditions of a meat animal carcass or cut. The results are identified with a particular piece of meat for further grading, sortation and processing.

Abstract: A device for overloading products from a working machine having a driver's stand to a transporting vehicle has an overloading unit provided in the working machine, and a monitor assembly for monitoring overloading of the product from the working machine to the transporting vehicle, the monitor assembly including an analog monitoring camera associated with the overloading unit and filming an overloading process, an analog control monitor arranged in the driver's cabin of the working machine such that an indication of the monitoring camera is performed by the control monitor, a first microprocessor connected to the monitoring camera and digitalizing a video signal, a second microprocessor to which the video signal is transmitted, and a digitally operating graphic indicator to which the digitalized video signal is transmitted by the second microprocessor for indication.

Abstract: The present invention relates to an apparatus and method for the automated inspection of objects for the presence of visual anomalies. The apparatus includes a first wide angle camera for acquiring an image of the object, a processor for detecting targets and generating target location from the image of the object, a two axis post-objective scanner associated with a high resolution camera for directing target image to the high resolution camera. The scanner provides a mechanism for saccadic emulation in combination with a high resolution video camera, which can be synchronized to the frame rate of the video camera for rapid high resolution examination of an object.

Abstract: The present system and apparatus uses image processing to recognize object size within a scene. The system includes novel image processing apparatus and methods to segment one or more object images from a background image of the scene. A processed image (that can be used to characterize size features) of the object(s) is then compared to stored reference images. The object size is recognized when a match occurs. The system can recognize object sizes independent of number of objects present and the objects may be touching each other and overlapping. The system can be trained to recognize object sizes that it was not originally programmed to recognize.

Abstract: Image processing system using cameras and image processing techniques to identify undesirable objects on roller conveyor lines. The cameras above the conveyor capture images of the passing objects. The roller background information is removed and images of the objects remain. To analyze each individual object accurately, the adjacent objects are isolated and small noisy residue fragments are removed. A spherical optical transform and a defect preservation transform preserve any defect levels on objects even below the roller background and compensate for the non-lambertian gradient reflectance on spherical objects at their curvatures and dimensions. Defect segments are then extracted from the resulting transformed images. The size, level, and pattern of the defect segments indicate the degree of defects in the object. The extracted features are fed into a recognition process and a decision making system for grade rejection decisions.

Abstract: A monitoring system for an agricultural vehicle. The vehicle is provided with a video camera and an associated video monitor. The video monitor is located in a cab of the vehicle and the video camera is oriented facing the rear of the vehicle. When an agricultural implement is connected to the vehicle, the monitor may be used to view the implement without turning away from the direction of travel.

Abstract: An apparatus for monitoring a water quality by raising an aquatic living thing in a monitoring water tank 1. The monitoring water tank 1 is taken through a camera 12 to be displayed on a television 14. A monitoring area E comprising a plurality of sensor points is set on a television scene through a light pen, and a fish sensing device 13 senses variation of the sensor points in luminance level to continuously detect the moving positions of fish F, F' under observation. A personal computer 15 detects, on the basis of the moving positions of the fish under observation, whether or not each of the fish under observation takes any one of a plurality of abnormal action patterns, and conducts an alarm operation if both the two fish F, F' under observation assume any abnormal action pattern.

Abstract: This invention includes an optical characterization method capable of determining various characteristics of samples that preferably include naturally-occurring color deviations. In the preferred embodiment, this method is used in connection with food products and, particularly, potato products such as french fried potatoes. The method of this invention overcomes such disadvantages by generating from the RGB pixel values a sample-based color space that corresponds to the naturally-occurring color deviations of the samples. Preferably, the method includes generating HSI pixel values that correspond to the RGB pixel values and are defined with respect to an HSI color space having hue, saturation, and intensity coordinates. The sample-based representation of the color characteristics of the samples is determined on a pixel-by-pixel basis. As a result, color grades for the samples can be assigned according to the distribution of pixels within the sample-based representation.

Abstract: Evaluation of carcass, or carcass portions, by object image definition processing comprising the steps of: recording a first image of a background taken from a viewing point; positioning the carcass or carcass portion in the background; recording a second image taken from the viewing point of the background with the carcass or carcass portion positioned therein; and analyzing the first and second images to differentiate the carcass or carcass portion image from the background image for providing a defined image of the carcass or carcass portion, thus resolving the location and/or profile of the carcass or carcass portion positioned in the background. The differentiation includes the subtraction of the first or second image from the other, preferably for each color component respectively, so as to provide a number of component difference images which are then recombined to provide an absolute difference image.

Abstract: A machine vision system and method of enhancing the imaging of an article which is comprised of optically translucent or semi-transparent material. Generally, the system includes a vision processor, a video camera, a computer, and an illuminator. The illuminator directs light, in a three dimensional space, at a surface of the material other than a surface to be imaged. The light which enters the translucent material is scattered isotropically within the material and emerges from the surface to be imaged, in effect illuminating the material. The illumination enhances contrast, that can be typically achieved with conventional lighting, between the material and its background or adjoining components permitting the machine vision system to clearly image and detect features of the article.

Abstract: Image processing system using cameras and image processing techniques to identify undesirable objects on roller conveyor lines. The cameras above the conveyor capture images of the passing objects. The roller background information is removed and images of the objects remain. To analyze each individual object accurately, the adjacent objects are isolated and small noisy residue fragments are removed. A spherical optical transform and a defect preservation transform preserve any defect levels on objects even below the roller background and compensate for the non-lambertian gradient reflectance on spherical objects at their curvatures and dimensions. Defect segments are then extracted from the resulting transformed images. The size, level, and pattern of the defect segments indicate the degree of defects in the object. The extracted features are fed into a recognition process and a decision making system for grade rejection decisions.

Abstract: Automated grading of meat (carcasses or cuts, particularly pork legs) employs the steps of: a) obtaining a representative image, or representative images, of a meat cut; e.g. using video cameras; b) processing said representative image or representative images to provide data relatable to the fatness of said meat cut; c) processing data provided at step (b), so as to produce one or more parameters suitable for categorizing the meat cut and/or the carcass from which the meat cut was taken; suitable parameters include the amount of fat or lean tissue, the location of fat tissue and the predicted yield of meat product; and d) comparing said parameter(s) with values stored in a database to determine the overall grading of said carcass or meat cut.

Abstract: At least a representative fraction of the peeled vegetables which have passed through a steam peeler, and abrasive peeler, or both, is presented to a video camera for inspection. The camera output is analyzed by a computer controller to determine the amount of peel remaining on the vegetable and displayed in a visual format to the operator. The controller provides information to the operator on peel fraction remaining so that the operator may manually adjust speed of brush rotation and auger speed or other parameters of the peeling apparatus, or automatically adjusts these parameters to maintain level of peel with varying vegetable attributes. More representative peel fraction data is obtained by analyzing only the central half of the vegetable image captured by the vision system.

Abstract: The present invention is directed to a device and method for analysis of peanut pods in a machine vision system. A method of classification of the pods is based on a maturity class system wherein various colors of the pod determine its maturity and therefore its approximate harvest time. The machine vision system permits quick scanning of the entire surface area of the peanut pod to be scanned and an analysis of its maturity can then be based on the overall view of the pod. The device and process utilize the views of the peanut pod, as determined by the camera imaging system so as to compare the images with maturity classes relating to color of the pod and, therefore, a determination of ripeness and of harvestability of the peanut crop.

Abstract: A system and method for sorting items (16) computes the geometric center ("centroid") (156) of any item containing a defect (26) or multiple defects, and directs an ejection air blast at the centroid of the defective item rather than at the location of the defect. Video data from a scanning camera (24) are transmitted to an "item processor" (32A') and a "defect processor" (32). The item processor builds in memory (108) an image of every acceptable or defective item while the defect processor builds a "defect list" (170) of defect coordinate locations detected only on defective items. The defect processor transmits the defect list to the item processor where the defect list is compared with the stored image of the item. For each item containing at least one defect, the item processor computes a defective item centroid that is added to a defective items list (174) for use by a defect removal process that actuates air blasts directed toward the centers of defective items.

Abstract: A system and method for sorting items (16) computes the geometric center ("centroid") (156) of any item containing a defect (26) or multiple defects, and directs an ejection air blast at the centroid of the defective item rather than at the location of the defect. Video data from a scanning camera (24) are transmitted to an "item processor" (32A') and a "defect processor" (32). The item processor builds in memory (108) an image of every acceptable or defective item while the defect processor builds a "defect list" (170) of defect coordinate locations detected only on defective items. The defect processor transmits the defect list to the item processor where the defect list is compared with the stored image of the item. For each item containing at least one defect, the item processor computes a defective item centroid that is added to a defective items list (174) for use by a defect removal process that actuates air blasts directed toward the centers of defective items.