A shrimp processing system conveys raw peeled shrimps to an imaging chamber in which shrimp bits and shrimps with residual shell are detected and diverted from the stream of acceptable shrimps allowed to pass on to downstream processing. An ultraviolet (UV) light source in the imaging chamber is constantly on. A visual inspection system takes images of the passing stream of shrimp when a white-light source is turned on to illuminate an exposure region to detect bits, clumps of shrimps, and acceptable individual shrimps. The visual inspection system takes images of the passing stream when the white-light source is turned off and the exposure region is subjected only to ultraviolet radiation. The visual inspection system detects shrimps with residual shell in the V images. Shrimp bits and shrimps with residual shell are diverted from the stream of shrimps by air jet nozzles to corresponding reject destinations.

Devices, systems and methods for sorting and labeling food products are provided. Respective spectra of food products for a plurality of segments of a line are received at a controller from at least one line-scan dispersive spectrometer configured to acquire respective spectra of the food products for the plurality of segments of the line. The controller applies one or more machine learning algorithms to the respective spectra to classify the plurality of segments according to at least one of one or more food parameters. The controller controls one or more of a sorting device and a labeling device according to classifying the plurality of segments to cause the food products to be one or more of sorted and labeled according to the at least one of the one or more food parameters.

Methods and systems for using multiple hyperspectral cameras sensitive to different wavelengths to predict characteristics of objects for further processing, including recycling, are described. The multiple hyperspectral images can be used to predict higher resolution spectra by using a trained machine learning model. The higher resolution spectra may be more easily analyzed to sort plastics into a recyclability category. The hyperspectral images may also be used to identify and analyze dark or black plastics, which are challenging for SWIR, MWIR, and other wavelengths. The machine learning model may also predict the base polymers and contaminants of plastic objects for recycling. The hyperspectral images may be used to predict recyclability and other characteristics using a trained machine learning model.

The present disclosure relates to a method, device, system and computer-program product for setting a lighting condition when an object is checked and a storage medium. The method includes that: the object is lighted by light sources capable of changing lighting parameters, and the object is captured by an image sensor in such lighting parameters to obtain captured images, wherein the object has known label data; and a part of or all of the captured images and the corresponding label data of the object are applied to learning of a machine learning model, and the lighting condition and the check algorithm parameters of the machine learning model is set simultaneously by optimizing both the lighting parameters and the check algorithm parameters, on the basis of a comparison result between an estimation result of the machine learning model and the label data. Therefore, operations are simplified.

Provided is a grain gloss measurement apparatus capable of accurately measuring gloss of grain. A grain gloss measurement apparatus includes a light source to emit light to a measurement region for grain in an oblique direction, a light receiver to receive the light reflected from the measurement region, and a gloss value calculation device to calculate a gloss value of the grain based on the reflected light received by the light receiver. The light source includes a first light source to emit light to the measurement region from one side and a second light source to emit light from another side that is opposite to the first light source across the measurement region. The light emitted from the first light source and the light emitted from the second light source have different wavelengths. The light receiver is disposed on the same side as the second light source, and the gloss value calculation device includes an image processing unit to identify a grain zone in the measurement region based on the light of the second light source that is reflected off the grain and received by the light receiver.

An automatic inspection process for detecting visible defects on a manufactured item, the process including a set up mode in which images of same-type defect free items, but not images of same-type defected items, are obtained, and an inspection mode in which images of both same-type defect free items and same-type defected items, are obtained and defects are detected, where images of the same-type defect free items are analyzed and based on the analysis the process switches to the inspection mode.

A method is provided for measuring optical characteristics of a glass sheet as the glass sheet is conveyed in a system for fabricating glass sheets including one or more processing stations and one or more conveyors for conveying the glass sheet during processing. The method comprises providing a background screen including contrasting elements arranged in a pre-defined pattern and a camera for acquiring an image of the background screen; acquiring data associated with a shape of a glass sheet travelling on a conveyor upstream from the background screen; removing the glass sheet from the conveyor; and positioning the glass sheet between the camera and the screen and thereafter acquiring an image of the background screen; re-positioning the glass sheet for continued movement of the glass sheet on the conveyor; and performing one or more processing operations using the acquired image data to analyze the optical characteristics of the glass sheet.

An apparatus for inspecting containers and in particular cans, having an illumination device which illuminates the can to be inspected and radiates radiation onto an inner base wall of the container, and having an image recording device which records at least one spatially resolved image of the inner base wall illuminated by the illumination device is provided. The apparatus has a first polarization device in a beam path between a light source of the illumination device and the inner base wall in such a way that the radiation reaching the inner base wall is polarized, wherein the illumination device being designed in such a way that a predominant proportion of the radiation irradiated into the container by the illumination device reaches the inner base wall.

Composite resin containing cellulose is irradiated with infrared light, reflected light from the composite resin irradiated with the light is received, normalization is performed at a peak position maximized in a peak at 2800 cm.sup.−1 or more and 3000 cm.sup.−1 or less, which is a C—H stretching peak caused by the composite resin, in a reflection or absorption spectrum obtained by the reflected light, and a reflection or absorption spectrum for determination is obtained. The spectrum is used to acquire a ratio value of a spectral intensity (background intensity) at a position of 1000 cm.sup.−1 or less according to a determined resin type and different from a wave number at which a peak derived from resin of the determined resin type is expressed, and a ratio of the spectral intensity (background intensity) is used so that a composite of cellulose combined in composite resin can be determined with high accuracy.

An apparatus (1) for inspecting an object, where the object is made up of a first layer of plastic material and a second layer of EVO or EVOH and has a base wall (A) and a side wall (B) which is inclined relative to the base wall (A), comprises: an inspection zone (10) in which the object can be placed for inspection; a conveyor (12) for feeding the object to the inspection zone (10) along a feed plane (P); an imaging device (14) configured to view the object positioned in the inspection zone (10) and to generate an image (143) of the object; a processor (151), configured to process the image (143), to inspect the second layer. The conveyor (12) is configured to dispose the object in the inspection zone (10) with the base wall (A) positioned according to a predetermined orientation relative to the feed plane (P).