Abstract: An adhered substance detection apparatus includes an obtaining portion configured to obtain captured image data outputted from an imaging portion, a detection portion configured to detect presence or absence of an adhered substance of each of plural regions of an imaging surface of the imaging portion on the basis of the captured image data, and a judgement portion configured to distinguish a reliable region and an unreliable region from each other, a reliability property of predetermined arithmetic processing performed by a processing apparatus with the use of the captured image data is kept to be equal to or greater than a predetermined value in the reliable region, and the reliability property is less than the predetermined value in the unreliable region.

Abstract: Disclosed is a machine for acquiring images (1) including: a support (10) for optical lens, on one side of the support, a light source (20), on the other side of the support, an image sensor (30) suitable for capturing at least two images of the optical lens illuminated by the light source, viewed from two different angles.

Abstract: A defect detecting method, a defect detecting system, and a non-transitory computer-readable medium are provided. The defect detecting method includes applying a rank filter to multiple scan images of consecutive dies of a reference wafer scanned by a wafer inspection tool to obtain multiple reference die images; collecting multiple target die images of a target die of a target wafer scanned by the wafer inspection tool; comparing the target die images with the reference die images to detect multiple defects according to differences of pixel values of corresponding pixels in the target die images and the reference die images; and excluding multiple common defects from the detected defects to detect at least one mask defect printed on the target wafer, where the common defects are obtained by the wafer inspection tool performing a wafer inspection on the target wafer.

Abstract: An intermediate image generating unit 81 generates a plurality of intermediate images from a good product image representing a good product and a faulty product image representing a faulty product. An intermediate image display unit 82 arranges the plurality of intermediate images between the good product image and the faulty product image and displays the same on a display device. A boundary acceptance unit 83 accepts, as a boundary between the good product image and the faulty product image, a designation by a user of a boundary between the intermediate images. A teaching image identification unit 84 identifies the images of the good product image and the faulty product image on the basis of the designated boundary.

Abstract: A non-transitory computer-readable medium for monitoring a semiconductor fabrication process includes an image conversion model having an artificial neural network. The image conversion model, when executed, causes the processor to receive a first image and a second image of a semiconductor wafer. The artificial neural network is trained by inputting a dataset representing the first image and the second image, generating a conversion image of the semiconductor wafer and calibrating weights and biases of the artificial neural network to match the conversion image to the second image. A third image of the semiconductor wafer is generated based on the calibrated weights and biases of the artificial neural network. The image conversion model with the trained artificial neural network may be transmitted to another device for image conversion of low resolution images.

Abstract: A detection method for a display panel motherboard and a display panel motherboard. The detection method for the display panel motherboard including a plurality of display panels arranged in a matrix includes: dividing the display panel motherboard into a plurality of detection regions, at least one detection region corresponding to at least a portion of each display panel in a same string of display panels; performing a defect detection on patterns in all the display panels in the at least one detection region.

Abstract: An appearance inspection system enabling a route to be easily set when a target is imaged while causing a relative position of an imaging device with respect to the target to be different is provided. A decision part decides a plurality of relative position candidates of the imaging device with respect to the target at which focus of a lens module is possible on the inspection target position with regard to each of a plurality of the inspection target positions on the target. A selection part selects relative positions one by one from corresponding plurality of relative position candidates for each of the plurality of inspection target positions and selects a route candidate satisfying a preset requirement from a plurality of route candidates generated by sequentially connecting the plurality of selected relative positions as a designation route.

Abstract: A method of scanning a 3D object includes: receiving a user's input to perform a scanning operation via a user interface, and in response using a light projector, projecting structured light onto the surface of a physical object about target positions on the surface of the physical object; and recording a sequence of first images of at least a portion of the surface of the physical object including a light scatter region illuminated by the structured light being projected about the target positions on the surface of the physical object using a camera. A trained image processing network configured during training to output data comprising a representation of positions being estimates of the target positions on the surface of the physical object in response to receiving one or more first images can be used.

Abstract: An integrity monitoring system for a first image sensor includes an electronic processor configured to receive sensor data for the provision of image data associated with an environment of the avionic sensor. The electronic processor is configured to monitor the avionic sensor for integrity. The electronic processor is configured to perform at least one of: determining a presence of an optical feature associated with optics of the first image sensor, comparing overlap information derived from the sensor data and other sensor data, comparing characteristics of a digital output stream of the sensor data to expected characteristics, or comparing a first motion derived from the image data and a second motion derived from avionic position equipment.

Abstract: Method and system for confirming the integrity of a tamper-evident seal based on a comparison of the value of at least one parameter describing the physical structure of a predetermined breaking point provided in the seal, which value is determined from at least one captured image of the seal, with a pre-determined reference parameter value.

Abstract: A method for detecting network anomalies includes receiving a control message from a cellular network and extracting one or more features from the control message. The method also includes predicting a potential label for the control message using a predictive model configured to receive the one or more extracted features from the control message as feature inputs. Here, the predictive model is trained on a set of training control messages where each training control message includes one or more corresponding features and an actual label. The method further includes determining that a probability of the potential label satisfies a confidence threshold. The method also includes analyzing the control message to determine whether the control message corresponds to a respective network performance issue. When the control message impacts network performance, the method includes communicating the network performance issue to a network entity responsible for the network performance issue.

Abstract: A substrate working system includes a component mounter that mounts a component on a substrate, and an inspection unit provided in the component mounter or a device downstream of the component mounter and that performs a substrate inspection different from a normal substrate inspection when an abnormality related to a mounting operation is detected in the component mounter.

Abstract: A technique relates to a manufacturing process. A computer system receives a material identification of a resource being manufactured, and receives images captured of units of the resource, the resource having been cut into the units. Features are determined for each of the units from the images. Feature vectors are created on a one-to-one basis for each of the units. A blockchain is formed using the feature vectors associated with each of the units, the blockchain having the material identification of the resource and a certificate identifying the units. A feasibility of the certificate for the units of the resource is validated via the blockchain.

Abstract: A system comprising a multifunctional peripheral device in which the multifunctional peripheral device comprises a processor and a display device, in which the processor detects signature lines in an electronic document, and in which the display device of the multifunctional peripheral device displays the detected signature lines one at a time.

Abstract: A method of detecting defects in a composite structure includes applying heat to a surface of a composite structure. Thermographic images or frames captured by a moving camera may be utilized to form temporally aligned images that include temperature data (pixels) from a plurality of frames, wherein the (pixels) comprise data captured at a simple (uniform) time delay from the time at which heat was applied. The temporally aligned thermographic data for the surface region may include variations due to differences in thermal transients caused by defects in the composite structure. The variations in the thermographic data may be utilized to detect one or more defects in the composite structure.

Abstract: In a method and system for estimating an operating state of a facility, an imaging sensor (or camera) is positioned to acquire image data from a facility of interest. Image data received from the imaging sensor is stored and then processed by a computer to identify one or more regions of interest within each image. A model is then created that relates data from the pixels (i.e., pixel values) from one or more of the identified regions of interest in the image data to the operating state for the facility. As new image data is received, that image data is input into the model to estimate the operating state of the facility, and the estimated operating state is then reported to market participants.

Abstract: A powder application arrangement for use in an apparatus for manufacturing work pieces by irradiating powder layers with electromagnetic radiation or particle radiation, the powder application arrangement comprises a carrier adapted to receive layers of a raw material powder and a work piece made of the raw material powder by a generative layer construction method. The powder application arrangement further includes a powder application device configured to deposit the raw material powder onto the carrier At least one camera is attached to the powder application device in such a position that it is capable of acquiring images of at least one of a surface of a raw material powder layer applied onto the carrier by means of the powder application device and a surface of the work piece made of the raw material powder by a generative layer construction method while the powder application device is moved across the carrier.

Abstract: In an example, a method includes determining, by a processor, a cumulative indication of defects present in linear sub-portions located in a common position of each of a plurality of substrate sheets bearing a printed image. The method may further comprise identifying, by the processor, a linear defect based on the cumulative indication of defects.

Abstract: Large scale instance recognition is provided that can take advantage of channel-wise pooling. A received query image is processed to extract a set of features that can be used to generate a set of region proposals. The proposed regions of image data are processed using a trained classifier to classify the regions as object or non-object regions. Extracted features for the object regions are processed using feature correlation against extracted features for a set of object images, each representing a classified object. Matching tensors generated from the comparison are processed using a spatial verification network to determine match scores for the various object images with respect to a specific object region. The match scores are used to determine which objects, or types of objects, are represented in the query image. Information or content associated with the matching objects can be provided as part of a response.

Abstract: An inspection device for inspecting an inspection object of a PTP sheet including a pocket portion formed in a container film, and a cover film mounted to the container film to close the pocket portion, or a portion of a PTP film forming the PTP sheet, includes: an irradiator that irradiates the inspection object with a predetermined light; an imaging device that takes an inspection image of the irradiated inspection object and a peripheral portion of the inspection object; and a processor that: determines whether the inspection object is defective or non-defective based on inspection image data of the inspection object taken from the inspection image. The inspection image data includes data of respective pixels corresponding to an inspection target area subjected to the defective/non-defective determination, and data of respective pixels corresponding to a non-inspection target area that excludes the inspection target area.

Abstract: Method for obtaining information from short-fibre-reinforced plastic components sequentially produced by an X-ray computed tomography. A learning phase includes: generating CT data sets for a random sample of plastic components from a production process; extracting at least one defect-free region of the plastic components; determining characteristic feature(s) in the extracted regions, relevance of individual features, and regions which are characteristic of the plastic component type and production process thereof, over a predetermined period of the plastic components productions, which exhibit considerable characteristic differences between good parts and reject parts; and defining the feature(s) with its characteristic as trained classifier.

Abstract: A method is disclosed which includes illuminating one or more objects when they enter a field of view (FOV). The method includes capturing an image of one or more objects once they enter the FOV, and performing an iterative analysis of the image based on a plurality of detection operations and according to one or more sequential operational relationships and one or more logical operational relationships. The iterative analysis comprises analyzing the image according to a first detection operation, modifying one or more geometrical operational relationships, and modifying a second detection operation based on the one or more sequential operational relationships, the one or more logical operational relationships, and the one or more geometrical operational relationships. The method further includes repeating the iterative analysis until a final detection operation is completed, and sending a signal to an exterior component to perform an action corresponding to the one or more objects.

Abstract: A computer-implemented method for processing images may include obtaining at least one image for analyzing; inputting the at least one image to at least one of a plurality of image plugins; analyzing the at least one image via the at least one of the plurality of image plugins; determining metadata related to the at least one image based on the at least one of the plurality of image plugins; filtering the at least one image based on one or more rule sets to generate at least one filtered image; sorting the at least one filtered image to generate at least one sorted image; displaying the at least one sorted image based on an organizational sequence of a webpage; displaying navigation controls via the webpage; and displaying the at least one sorted image according to a user interaction with the navigation controls on the webpage.

Abstract: An x-ray inspection apparatus may comprise an x-ray source, an x-ray detector, and a drive assembly. The drive assembly may be configured to lift a part carrier such that the part carrier is disengaged from a feed assembly and an object mounted on the part carrier is positioned between the x-ray source and the x-ray detector. The feed assembly may be configured to feed part carriers into and out of the x-ray inspection apparatus. The drive assembly may be further configured to subsequently lower the part carrier such that the part carrier is reengaged with the feed assembly.

Abstract: A method for inspecting an end face, comprising: an arrangement step of arranging a honeycomb structure having a partition wall extending from a first end face to a second end face, at a predetermined position using the second end face as a placement face; a first image data for processing acquisition step of acquiring first image data for processing while irradiating the first end face with light having an angle of 40° or more, the angle being an angle formed between the light and an axis being perpendicular to the placement face of the honeycomb structure; a second image data for processing acquisition step of acquiring second image data for processing while irradiating the first end face with light having an angle of less than 40°; and a crack detection step of detecting a crack by comparing the first image data for processing with the second image data for processing.

Abstract: The subject matter disclosed herein relates generally to industrial automation systems, and, more particularly, to collecting video streams from a variety of video devices in an industrial environment, identifying and analyzing potential problems in the industrial environment using the video streams, and presenting the video streams and data associated with the potential problem to appropriate recipients.

Abstract: Apparatus for determining height, width, weight or body mass index (BMI) of a subject or distance along an object. For BMI, the apparatus includes a digital camera; an application; a processing unit for storing the vertical and horizontal dimensions of known substantially rectangular reference objects. A user interface prompts and receives the type of reference object held by the user or its dimensions. For each of the vertical and horizontal dimensions, a magnitude in pixels and in distance of the reference object to form a ratio and a pixel magnitude of the vertical and horizontal dimensions of the subject in the image(s), is used to derive an estimated height and width of the subject from the pixel magnitude of the vertical and horizontal dimensions of the subject in the image(s). In some embodiments, the number of pixels occupied by the subject in the image(s) is used with a look-up table.

Abstract: Footprint data of an item that is representative of a boundary of the item and where that boundary is located is obtained using occlusion of a projected line. Line projectors are arranged at opposite sides of a conveyor belt and at an angle that is acute with respect to a plane of the conveyor belt and produce lines on the conveyor belt within a measurement area. As an item moves past the measurement area, the sides of the item occlude a portion of the projected lines. Cameras acquire a series of images as the object moves with respect to the measurement area. The images are processed to determine where the projected lines were occluded. An edge point is then determined representative of that location. One or more lines may be fitted to a plurality of edge points to determine the boundary of the item.

Abstract: Methods, systems, and computer-readable storage media for generation of a vehicle repair plan. Implementations include actions of receiving vehicle damage data including an image of a damaged vehicle. The vehicle damage data is processed to determine a component region. The component region is processed to determine a damaged area and a damage type of a portion of the damaged vehicle. A maintenance plan is generated for the damaged vehicle based on the damaged area and the damage type. The maintenance plan is initiated for the damaged vehicle.

Abstract: Techniques for adjusting a brightness of a field of view of a stereo-optical sensor device (e.g., of a system used to count individuals) are disclosed. According to an embodiment, the stereo-optical sensor device obtains, from a light sensor of the stereo-optical sensor device, a luminosity value of the field of view of the stereo-optical camera. The stereo-optical sensor device determines, as a function of the luminosity value, whether to adjust a brightness of one or more light sources. The stereo-optical sensor device adjusts, in response to the determination, the brightness of the one or more light sources.

Abstract: A shape evaluation method includes a shape error calculation step that calculates a shape error, which is an error between a designed shape and a shape to be evaluated, and a visible error detection step that detects visible shape errors on the basis of the shape error and predetermined visual characteristic data.

Abstract: An adaptable sorter unit includes an attachment mechanism, a sorting device that is capable of deflecting a sample, a data port that is capable of receiving information, and a power port that is connectable to a power source. The attachment mechanism, the sorting device, the data port, and the power port are physically connected together. The adaptable sorter unit also includes a memory circuit and a processor circuit configured to read information received via the data port and control the sorting device. The sorting device is a vacuum system, a mechanical pedal system, or an air jet system. The attachment mechanism is a mounting bracket, a mounting bracket receptacle, a weldable material, a clamp, a bolt, or a screw. The attachment mechanism connects the adaptable sorter unit to a processing line such that the adaptable sorter unit is capable of deflecting a sample traveling along the processing line.

Abstract: A measurement device that can improve measurement accuracy and increase the number of times of service of a measurement jig. The measurement device includes a movement control section that positions the measurement jig at an instructed position in the transfer direction, an imaging control section that images the positioned measurement jig by the measurement camera and acquires an image data, an image processing section that calculates an actual position of the measurement jig based on multiple measurement marks which are included in the image data, and an error measurement section that measures a positioning error in the transfer direction due to the driving device based on the instructed position and the actual position.

Abstract: The present invention relates to a testing method and a corresponding testing system, for example for testing workpieces (2), which are provided for producing containers, in particular beverage bottles, and which can consist of a basic body and a barrier layer that is at least partially applied to the basic body, whereby the workpieces (2) are transported into a receiving vessel (4) by means of a transport device (3), and whereby an image of the workpieces (2) is generated by means of a capturing device (6) and is transmitted to a processing device for testing, wherein the workpieces (2) are led into the receiving vessel (4) upon leaving the transport device (3), whereby the image is generated between the departure from the transport device (3) and the receiving vessel (4) and wherein the image is processed by the processing device in such a way that the quality of the basic body and/or the quality of the barrier layer of the workpieces (2) is tested in order to detect defective workpieces (2).

Abstract: A picture filtering method performed by an encoding device, according to the present invention, comprises the steps of: deriving, from a current picture, regions for adaptive loop filtering (ALF); deciding ALF coefficients by picture unit or region unit; on the basis of the ALF coefficients, determining, by region unit, whether ALF is usable; re-deciding ALF coefficients for an ALF-usable first region; deriving a filter shape for the first region; on the basis of the re-decided ALF coefficients, determining, by unit of coding units (CUs) in the first region, whether ALF is usable; performing filtering for ALF-usable CUs on the basis of the derived filter shape and the re-decided ALF coefficients; and transmitting at least one among information on the ALF-usable first region and information on the ALF-usable CUs. According to the present invention, efficient filtering appropriate for image properties per region may be applied.

Abstract: A component inspecting device inspects presence or absence of an abnormal state of two linear wires based on changes in the amount of received light of a first light ray and a second light ray received by a first light receiver and a second light receiver, respectively when a component is moved such that the two linear wires in the normal state block the first light ray and the second light ray in a posture wherein an arrangement direction of the two linear wires crosses optical axes of the first light ray of the first light projector and the second light ray of the second light projector. This device can detect an abnormality such as a bend or the like of linear wires by a simple configuration and a simple operation in a component having two linear wires which have axis directions parallel to each other and have different lengths.

Abstract: A system can host APIs for a plurality of different tenants and receive requests from many different client devices. As requests are received, an associated tenant can be identified, and a router can determine if a container instance is available to service the request. A container instance may be an empty container instance including an internal endpoint, a Web server, and a runtime environment. An empty container instance can be unassociated with a particular tenant. To associate a container instance with a tenant, a data store, such as a key-value data store can retrieve configuration files that turn the agnostic container instance into a container instance that is associated with particular tenant and includes configuration code to perform the requisite API functions. The pool of empty and populated containers can be managed efficiently.

Abstract: A method of performing automated object inspection includes obtaining a plurality of test images. For each of the plurality of test images, the method includes quantitatively determining a respective transformation from a predefined contour of the reference marker in the predefined common layout to a respective anchor contour corresponding to the reference marker as captured in the test image; and applying an inverse of the respective transformation to at least a portion of the test image to obtain a respective regularized version of the test image, such that the reference markers captured in the respective regularized versions of the plurality of test images share an image-independent location and orientation. The method further includes performing independent automated inspection on each of two or more sub-portions of the respective regularized versions of the test images.

Abstract: A method of qualifying physical components using computed tomography (CT) includes obtaining qualified CT data from a CT scanner for at least one qualified physical component. Qualification data is generated based on the qualified CT data, where the qualification data defines a qualification envelope. Candidate CT data is obtained from the CT scanner for a candidate physical component. Comparison data is then generated based on the candidate CT data and the qualification data, where the comparison data indicates whether the candidate CT data is within the qualification envelope defined by the qualification data. An acceptance signal is generated if the comparison data meets acceptance criteria.

Abstract: An image processing apparatus includes: an image acquisition part that obtains an image including a captured target object; a first recognition part that extracts a feature related to the target object in the image and discriminates a category related to the target object based on a result of the feature extraction; a reliability acquisition part that obtains reliability of a discrimination result of the first recognition part with reference to data indicating reliability of the discrimination result stored in association with a candidate category classified by the first recognition part; a second recognition part that executes discrimination processing in accordance with the discrimination result of the first recognition part, extracts a feature related to the target object in the image, and discriminates the category related to the target object based on the result of the feature extraction and the reliability of the discrimination result of the first recognition part.

Abstract: A PLC system includes a displacement sensor, drives, and a PLC. When an unmeasurable condition is detected at a data obtaining position, the PLC system moves the displacement sensor back to the position at which the unmeasurable condition is detected, and again performs measurement. When an unmeasurable condition is detected again in the measurement, the PLC system SYS moves the stage to the next data obtaining position, and again performs measurement.

Abstract: An ingredient data system that ingests text and graphics of product labels associated with consumer products generally includes a memory having instructions stored thereon; and at least one processor to execute the instructions to transmit via a network a representation of a label view to a user interface on a client computing device that displays one or more of the master attributes associated with the first request, at least a portion of each of the images of one or more of the product labels of the consumer products having the one or more master attributes associated with the first request and at least a portion of the sales history, and at least a portion of each of the images of one or more of the product labels associated with the related consumer products and at least a portion of a sales history.

Abstract: An ingredient data system that ingests text and graphics of product labels associated with consumer products generally includes a memory having instructions stored thereon; and at least one processor to execute the instructions to transmit via a network a representation of a label view to a user interface on a client computing device that displays one or more of the master attributes associated with the first request, at least a portion of each of the images of one or more of the product labels of the consumer products having one or more of the master attributes associated with the first request, and at least a portion of each of the images of one or more of the product labels associated with the related consumer products having the at least one master attribute different from one or more of the master attributes associated with the first request.

Abstract: A system for identification of items and products is provided, comprising an optical identification mark associated physically and in a database with a specific item or product, wherein the optical identification mark comprises an optical element with unique refractive properties and a laser beam source and said optical identification mark is configured to transmit a laser beam emitted by the laser beam source through said optical element and surrounding medium to create a light beam with unique light and shape properties that is utilized as a token for identification of the specific optical identification mark and subsequent identification of the associated specific item or product.

Abstract: A method and apparatus for reading unique identifiers of an integrated circuit. The unique identifiers may be physically unclonable functions (PUFs), formed by high energy ions implanted into semiconductor material of the integrated circuit. The method may include electrically or optically stimulating each of the PUFs and sensing with an optical sensor optical characteristics of resulting light emitted from the PUFs. Then the method may include comparing values associated with the optical characteristics of the PUFs with groups of stored values in a circuit database. Each of the groups of stored values may be associated with optical characteristics of PUFs of a known authentic circuit. The method may then include the controller providing verification of authenticity of the integrated circuit when each of the values associated with the optical characteristics of the PUFs match the stored values of at least one of the groups in the circuit database.

Abstract: A defect in an image of a semiconductor wafer can be classified as an initial defect type based on the pixels in the image. Critical dimension uniformity parameters associated with the defect type can be retrieved from an electronic data storage unit. A level of defectivity of the defect can be quantified based on the critical dimension uniformity parameters. Defects also can be classified based on critical dimension attributes, topography attributes, or contrast attributes to determine a final defect type.

Abstract: A device may receive video of a facility from an image capture system. The video may show an individual within the facility, an object within the facility, or an activity being performed within the facility. The device may process the video using a technique to identify the individual within the facility, the object within the facility, or the activity being performed within the facility. The device may track the individual, the object, or the activity through the facility to facilitate an analysis of the individual, the object, or the activity. The device may perform the analysis of the individual, the object, or the activity using information related to tracking the individual, the object, or the activity. The device may perform an action related to the individual, the object, or the activity based on a result of the analysis. The action may positively impact operations of the facility.

Abstract: There are provided a system and method of vehicle image comparison, the method including: obtaining an input image capturing at least part of a vehicle; segmenting the input image into one or more input segments corresponding to one or more mechanical components; retrieving a set of reference images, thereby obtaining a respective set of corresponding reference segments for each input segment; and generating at least one difference map corresponding to at least one input segment, comprising, for each input segment: comparing the input segment with each corresponding reference segment thereof using a comparison model, giving rise to a set of difference map candidates each indicating probability of presence of DOI between the given input segment and the corresponding reference segment; and providing a difference map corresponding to the given input segment according to probability of each difference map candidate in the set of difference map candidates.

Abstract: A method for configuring an electronic housing mounted on a wheel of a motor vehicle for the purposes of transmitting signals intended for a central unit incorporated into the motor vehicle, involving dividing one turn of the wheel into a predetermined number n of referenced sectors, commanding the emission of a sequence of n successive signals, referred to as configuration signals, which are synchronized with the n referenced sectors and of emission duration tem?T/n, where T is the period of rotation of the wheel, identifying and memorizing the referenced sectors corresponding to the configuration signals received by the central unit, and configuring the electronic housing by selecting at least one of the identified referenced sectors for the subsequent emission of the signals intended for the central unit.

Abstract: There are provided a system and method of vehicle image comparison, the method including: obtaining an input image comprising a plurality of image portions; retrieving a set of reference images; for each image portion, searching for a best matching reference portion in the set of reference images, comprising: i) for each given reference image: identifying a reference region; using a similarity model on the given image portion and the reference region to obtain a similarity map indicating a similarity between the image portion and a respective reference image portion; and selecting a reference image portion with the best similarity as a reference portion candidate; and ii) selecting the best matching reference portion; and comparing each given image portion with the best matching reference portion using a comparison model, giving rise to a difference map indicating probability of presence of DOI in the given image portion.