66 results about "Visual discrimination" patented technology

A system and method for retraining the visual system of a subject with damage to the striate and / or extrastriate visual cortex includes displaying a visual stimulus within a first location of an impaired visual field of the subject; and detecting the subject's perception of an attribute of the visual stimulus. The system and method are believed to effectively recruit undamaged higher level structures in the visual system to assume the functions of the damaged structures.

A system and method for retraining the visual system of a subject with damage to the striate and / or extrastriate visual cortex includes displaying a visual stimulus within a first location of an impaired visual field of the subject; and detecting the subject's perception of an attribute of the visual stimulus. The system and method are believed to effectively recruit undamaged higher level structures in the visual system to assume the functions of the damaged structures.

The invention relates to a 49S / SMD automatic crystal test and detection packaging machine which includes an industrial control computer; the invention also includes a working platform, a vibration loading device, a material-screening testing device, a visual discrimination A device, a crystal shift-loading and orienting device, a carrier tape supply device, a carrier tape guiding device, a visual discrimination B device, a heat sealing membrane-loading material-supplying device, a carrier tape heat sealing mechanism, a carrier tape driving device, a carrier tape material-receiving device and a rack. The invention is characterized in that the bulk of 49S / SMD crystals can be effectively screened by a material-screening mechanism; the 'qualified products' and 'unqualified products' can be tested and distinguished; later, the placing direction and the surface condition can be judged by a visual system; the real qualified products are packaged and the unqualified products are placed in a recovery device for the unqualified products with rapid speed, high accuracy and high degree of automation, so the manual operation is completely replaced.

The present invention discloses a polygon contour similarity detection method. The method comprises: removing an irregular part in figures; establishing a mathematical model of two figures, a complete vector set that describes the figures establishing a feature matrix corresponding to the figures, and calculating an included angle between two adjacent edges; calculating the shortest distance between the two figures; and performing enhanced processing on a calculating result. The polygon contour similarity detection method improves the visual discrimination effect of a machine on figure similarity, and is especially helpful in solving the problem that it is not easy for people to discriminate high-similarity figures; the figure detection effect has relatively high stability and reliability; and the detection time is short, the operation is efficient, and the effect implementation cost is low. According to the polygon contour similarity detection method, only the edges of the figures are inquired, thereby reducing data processing amount. According to the polygon contour similarity detection method, the feature matrix of the figures is constructed, appropriate determination criteria are selected, multi-time enhancement nonlinear transformation is performed on feature matrix elements, and a similarity standard is established by using a multi-value and multi-standard weighted average, so that an algorithm is efficient and has relatively high stability.

A non-contact strain measuring method based on visual discrimination is provided, which relates to the strain measuring method of miniature device. The invention overcomes the defect that using the traditional contact extensometer or strain foil is unable to measure the tensile property of miniature device and is easy to damage the test piece. Firstly, use CCD camera, optical lens set and data collecting card to collect the image of the mark on the tested piece during tension test process; secondly, conduct quickness processing to the edge of the collected image; thirdly, fix the distance between two points according to the quantity of pixels in the furthest edge in the direction of tension force; fourthly, utilize the change of the distance in the furthest edge in the direction of tension force to count the strain value and build corresponding relationship with the received tension. The invention can precisely measure the strain in the single-direction tension test of miniature device or micro-forming material, which has the advantages of no abrasion, strong anti-interference performance and high precision.

A framework and methodology providing for navigation of the connectedness of selected entities of a plurality of entities adapted for display on a user interface. The system and method can comprise a receipt module for receiving a first search request for determining a secondary entity of said plurality of entities in relation to a primary entity of said plurality of entities. The first search request includes at least one search parameter associated with the primary entity for use in determining the secondary entity from said plurality of entities. The system and method can further comprise a search module for determining the secondary entity as matching the first search request according to a predefined inclusion threshold and a generation module for generating a primary connection view including a domain having a plurality of sectors. The connection view can be used in providing a visual discernment by a user of a degree of relatedness between the primary entity and the secondary entity and a relationship between the secondary entity and each of the plurality of sectors, such that the secondary entity is positioned in the domain in one of the plurality of sectors and the primary entity is positioned in the domain in a position related to said each of the plurality of sectors. The system and method can further comprise a matching module for modifying the first search request as a second search request by substituting the determined secondary entity as a revised primary entity for the second search request, wherein a secondary connection view is generated as a navigation of the primary connection view such that the secondary connection view has the revised primary entity and at least one further secondary entity of said plurality of entities matching the second search request according to a corresponding predefined inclusion threshold.

A currency genuineness detection system with visual discrimination complemented by automatic discrimination using plurality of opto-electronic sensors with reflective and fluorescence properties of security documents is developed. The detection sensing strategy utilizes integrated response of the wide optical band sensed under UV visible along with optional near infra red light illumination. A security document is examined under static condition. A window signalsignature is thus possible from the photodetectors responses for various kinds of documents of different denominations, kinds and country of origin. A programmable technique for checking the genuineness of a security document is possible by feeding a unique code of the currency under examination.

An identification system distinguishes among a set of individual containers. The identification system has an identifier member associated with each of the containers in the set for facilitating visual discrimination of each of the containers from the others of the set. The identifier member of each container in the set has distinct and visibly different printed identifying indicia positioned over a surface portion of the container, and an opaque covering material covering the printed identifying indicia. The opaque covering material is removable to selectively expose a preselected one of the printed identifying indicia so that during consumption of the contents of the container a user may readily distinguish his container from the other containers in the set by visual inspection of the exposed printed identifying indicia.

A game engine is configured to accept human intelligence tasks as in-game content and present the in-game content to the game player. A method performed by the game engine enables performance of human intelligence tasks, such as visual discrimination, in a video game context. The game engine may receive a definition of human intelligence tasks from one or more remote sources. The game engine may present the human intelligence tasks to multiple video game participants as in-game content. The game engine defines and enables game play rules for the in-game content. The game play rules set parameters for the multiple video game participants to perform the human intelligence tasks to achieve desired results. The game engine may award each of the multiple video game participants an improved game score upon successful performance of the human intelligence tasks in accordance with the game play rules. The game engine may measure success by consistency in responses between different participants or trials.

A game engine is configured to accept human intelligence tasks as in-game content and present the in-game content to the game player. A method performed by the game engine enables performance of human intelligence tasks, such as visual discrimination, in a video game context. The game engine may receive a definition of human intelligence tasks from one or more remote sources. The game engine may present the human intelligence tasks to multiple video game participants as in-game content. The game engine defines and enables game play rules for the in-game content. The game play rules set parameters for the multiple video game participants to perform the human intelligence tasks to achieve desired results. The game engine may award each of the multiple video game participants an improved game score upon successful performance of the human intelligence tasks in accordance with the game play rules. The game engine may measure success by consistency in responses between different participants or trials.

A wireless IC tag attached to the object in the tangential direction to open up a space between the two, the structure of the tag 41 is such that wireless IC tag 1 is sandwiched between thin rectangular strips of plastic etc., which even when bent in the lengthwise direction, will return to their original shape. Tag area 42, where wireless IC tag 1 is sandwiched, is of a different color than support area 43 to allow for clear visual discrimination of its position. Support area 43 is designed to secure distance between object 2 and wireless IC tag 1. The end opposite the foregoing thin slip tag area 42 is attachment area 45 which is supported in a manner that allows it to freely rotate around pin 44. Attachment area 45 can retain the tag area 42 and support area 43 at any desired angle. Attachment area 45 is attached to object 2 by paste, glue, clips, pins, etc., or, it may be inserted into the object. The present invention relates to non-contact communication system.

The invention provides an intelligent forest land and building extraction method for cultivated land protection, and belongs to the technical field of identification. The method is characterized by matching homonymous points with multi-modal remote sensing images; extracting rough land class boundaries of the forest land and the building by utilizing an attention enhancement semantic segmentationmethod; and performing polygon boundary optimization on the building and forest land elements by utilizing an image morphological filtering method and a probability graph model respectively to obtainaccurate land boundaries. According to the method, accurate registration is carried out on the multi-modal remote sensing images so that a problem of information loss of a single-source remote sensingimage due to cloud shielding is solved, and the problem of difficult registration caused by significant nonlinear geometric distortion and radiation difference among the multi-modal remote sensing images is solved too; based on a forest land and building semantic segmentation method based on attention enhancement, the problem of low land utilization efficiency of visual discrimination is solved;and based on a ground class boundary accurate extraction method of an image form and a vector topology rule, the boundary of a ground object is optimized, and the problem of accurate and intelligent extraction of forest land and buildings is solved.

A method and an apparatus for preoperative identification of a perforator vessel for plastic and / or reconstructive surgery using ICG fluorescence angiography imaging are disclosed. Time-resolved image processing is used to highlight perforator locations and to enable visual discrimination among candidate perforators by various computed metrics. Based on these metrics, the surgeon is able to interactively locate and select perforator vessels suitable for plastic and reconstructive surgery.

A method and an apparatus for preoperative identification of a perforator vessel for plastic and / or reconstructive surgery using ICG fluorescence angiography imaging are disclosed. Time-resolved image processing is used to highlight perforator locations and to enable visual discrimination among candidate perforators by various computed metrics. Based on these metrics, the surgeon is able to interactively locate and select perforator vessels suitable for plastic and reconstructive surgery.

The invention discloses a video playing method and device, a computing device and a storage medium. The video playing method comprises the steps of determining a type of dyschromatopsia, wherein the type of dyschromatopsia corresponds to one or multiple color adjustment strategies; when a to-be-played image frame is obtained, performing color adjustment on the image frame by adopting the one or multiple color adjustment strategies so as to improve the visual discrimination degree of an area corresponding to one or multiple colors in the image frame; and playing the image frame after being subjected to the color adjustment.

The invention provides a psycholinguistic evaluation method and system for Chinese aphasia. The method comprises performing auditory analysis testing, speech input buffer testing, speech input dictionary testing and lexical semantic testing on a patient in sequence; performing visual discrimination testing, concept semantic testing, lexical semantic testing, speech output dictionary testing and speech motion planning testing on the patient in sequence; sequentially performing glyph visual recognition testing, glyph input dictionary testing, and lexical semantic testing on the patient in sequence; and evaluating and judging evaluation test results. The system includes a main server, a client and a human-computer interaction terminal. The main server includes a database and a listening comprehension evaluation process subsystem, a graph naming evaluation process subsystem, a reading evaluation process subsystem and a test evaluation module. According to the psycholinguistic evaluation method and system for Chinese aphasia, the damage of different properties in aphasia can be determine by evaluation testing, and a therapist can be assisted to accurately locate the damaged part of thebrain region, thereby achieving targeted treatment of aphasia and improving the treatment efficiency.

The invention discloses a radar video multistage multicolor hierarchical display system structure, which comprises a display and control console, wherein the display and control console is connected with a radar front end; bilateral signal transmission is performed between the display and control console and the radar front end; the radar front end is used for transmitting analog signals, including video signals, triggering signals, bow signals and direction signals to the display and control console; the display and control console is used for transmitting a corresponding control command to the radar front end, and is connected with an isolating transformer; the isolating transformer is connected with an onboard power supply module. By adopting a multistage multicolor hierarchical display technology, radar images are clearer and more real, and targets are easier to identify. A well-designed color scheme is adopted, so that the brightness difference presented by strong-weak echoes can be reduced as much as possible, and the visual fatigue of an operator is relieved. Radar echoes of different amplitudes are presented by means of color difference, the display contrast effects of the targets and clutters are enhanced, the visual discrimination between the targets and the clutters is enhanced, and the capability of finding small targets under a clutter background is increased.

The present invention discloses a method and an apparatus for preoperative identification of a perforator vessel for plastic and / or reconstructive surgery using ICG fluorescence angiography imaging. Time-resolved image processing is used to highlight perforator locations and to enable visual discrimination among candidate perforators by various computed metrics Based on these metrics, the surgeon is able to interactively locate and select perforator vessels suitable for plastic and reconstructive surgery.

The invention relates to an ecological vulnerability evaluation method suitable for an expressway road domain. The method comprises the steps of providing grade division of regional ecological vulnerability evaluation and division of an ecological vulnerability range corresponding to each grade; collecting corresponding ground objects conforming to each grading characteristic of ecological vulnerability evaluation on the remote sensing image to serve as sample points to participate in modeling analysis, and adding the ecological vulnerability EFD of each sample point into attributes of the sample points in geographic information software; extracting a remote sensing index and a terrain index corresponding to each influence factor influencing the ground environment change and causing ecological vulnerability, performing normalization processing, and extracting the remote sensing index and the terrain index into the attributes of the sample points so as to enable the influence factors tobe comparable with each other; coupling the indexes, constructing an ecological vulnerability evaluation model, and obtaining a spatial distribution diagram of ecological vulnerability grading zoningof the research area through model calculation. The precision verification mode of the model is visual, accurate, simple and convenient, and both subjective visual discrimination and objective data analysis can achieve the effect.

The invention discloses a strawberry external quality lossless grading device based on machine vision. The strawberry external quality lossless grading device comprises a lifting mechanism, a conveying mechanism, a visual discrimination mechanism, a screening mechanism and a control mechanism. The lifting mechanism is arranged at the leftmost end. The conveying mechanism is installed at the right end of the lifting mechanism. The visual discrimination mechanism and the screening mechanism are fixedly installed above the conveying mechanism left and right. The control mechanism is in electric signal connection with the lifting mechanism, the conveying mechanism, the visual discrimination mechanism and the screening mechanism. According to the strawberry external quality lossless grading device based on machine vision, on the premise that the requirement for convenient use is met, the effects of being simple in structure and convenient to operate are achieved, lossless grading can be conducted on the size, the shape, the appearance and other external qualities of strawberries, the safe using performance is good, and the practical using requirement is met.

The invention discloses a method for generating a target gamma curve of a display based on a visual discrimination requirement. A just-noticeable difference (JND) is subjected to segment and distributed calculation according to a calculation formula and an inverse operation formula of an index relationship between brightness and the JND by combining the native gamma curve of the display on the basis of a display requirement, a JND index value is calculated, the target gamma curve is finally obtained, and all or part of gray scales of the generated target gamma curve can completely accord with equal-difference discrimination of human vision on the basis of the display requirement after the generated target gamma curve passes the verification of the display. The method is simple and effective, can be suitable for effectively generating the target gamma curves of various displays and is also suitable for other application of the curve, and data is simply and conveniently calculated and accurately and reliably corrected.

Provided is a device for inspecting a film carrier tape for electronic component mounting which can efficiently discriminate true and pseudo failures, and also a method for confirming a pattern failure. This inspection device comprises a failure confirming unit. The confirming unit takes an image of one of image pickup zones etc. set as piece divisions in which a failure part of a wiring pattern detected by an image processor is positioned; displays the image pickup zone; and performs selective input operation to determine a visual discrimination result of whether at least one failure included in the displayed one image pickup zone is a true failure or all failure parts are pseudo failures. The images of the image pickup zones etc. including the failure parts are displayed in the decreasing order of sizes of the failure parts included in the image pickup zones.

The invention belongs to the technical field of forest fire monitoring and early warning, and discloses a forest fire monitoring and early warning system and method, a storage medium and computer equipment. The method comprises steps of using L1-level data information of a scanning radiometer carried by a wind cloud meteorological satellite; extracting fire points at different moments by using a fixed threshold method; dynamically tracking and monitoring a fire process by using a visual discrimination method to realize the positioning of an ignition point; normalizing vegetation index data byusing a scanning radiometer carried by a wind cloud meteorological satellite, correcting a forest fire risk index formula, making a forest fire risk weather grade relative to the first three days of afire hazard by combining local meteorological data, and analyzing a corresponding relationship between the fire risk weather grade and the forest fire hazard. The forest fire hazard early warning system has great significance in forest fire hazard monitoring and forest fire hazard early warning, effective information is provided for forest fire extinguishing command decision making, and scientific reference is provided for related decision making or service departments.

The invention discloses a coal dressing system and method based on artificial intelligence image recognition. A conveying belt is arranged, coal materials move along with the conveying belt in a single-row mode, in the moving process, coal ash on the coal materials is washed by a spray gun, part of the solid surface is exposed, a camera device shoots and sends shot images to a control module in real time, gangue and coal briquettes are recognized in real time through an artificial intelligence image recognition technology, then a flow guide sorting mechanism on the downstream of the conveyingbelt is controlled to act, and the gangue and the coal briquettes are separated. The coal ash on the coal materials is washed by arranging the spray gun, so that the visual discrimination degree of the coal and the gangue is increased; then the gangue and the coal briquettes are recognized by applying the artificial intelligence visual image recognition technology of deep learning, so that the accuracy of machine vision recognition can be greatly improved, the sorting precision is high, the equipment cost is low, the processing particle size is wide, the processing capacity is high, most of manual work can be replaced, the labor cost is saved, the coal mine pollution and water consumption are reduced, and the coal loss is reduced; and the system and method are beneficial to being deployedunderground, the gangue well outlet amount is effectively reduced, and environmental protection is facilitated.

The present invention discloses a single-polarization synthetic aperture radar image pseudo colorization method. The method includes the following steps that: 1, the amplitude data of a single-view SAR image are obtained, negative exponential transformation is performed on the amplitude data, the transformed amplitude data are normalized to an interval of [0, 1]; 2, the grayscale u of the interval of [0,1] is corresponding to the grayscale U of an interval of [0,255]; 3, the grayscale of the interval of [0,255] is divided into 4 layers, and each layer of pixel grayscale is transformed differently, so that RGB data can be obtained; and 4, the RGB-channel data obtained in the step 3 are synthetized into a pseudo-color image. With the method of the invention adopted, the obtained pseudo-color image has a unique noctilucent effect; an artificial target with strong scattering and a natural region with weak scattering can be well differentiated, in specific, the weak scattering region embodies deep blue, the strong scattering target embodies orange; and since evident visual discrimination can be realized, target judgment and interpretation can be benefitted.

The invention discloses a method for efficiently and visually discriminating the authenticity of Tetrastigma hemsleyanum Diels et Gilg by using DNA mimic enzyme. The method comprises the following steps: 1, obtaining the authenticity difference sequence of Tetrastigma hemsleyanum Diels et Gilg, and obtaining an object-to-be-detected PCR product; and 2, carrying out strand displacement cycle signal amplification technology colorimetric visualization on the object-to-be-detected PCR product to discriminate the authenticity of Tetrastigma hemsleyanum Diels et Gilg: carrying out an enzyme digestion strand displacement cycle reaction to generate a large amount of G-rich sequences for forming G-quadruplexes in a system, and forming a G-quadruplex-hemin DNA mimic enzyme in the presence of K<+> and Hemin in order to realize visual discrimination of the authenticity of Tetrastigma hemsleyanum Diels et Gilg, wherein the enzyme has horseradish peroxidase-like activity and can catalyze color development of an ABTS<2->-H2O2 system. The method has the advantages of low cost, simple DNA cultivation technology, good reappearance and good stability, avoids gel electrophoresis analysis to save a lot of time and realize direct use of the method in rapid and visual discrimination of the authenticity of Tetrastigma hemsleyanum Diels et Gilg, and is hopeful to be widely applied in the medicinal material market and the food safety field.

There is provided a travel time display device for an industrial robot which can display travel time on the screen such that time taken for moving a work from any designated starting point to any other point can be seen at a glance. The travel time display device includes: a display for displaying on the screen the location of the industrial robot and an area in which the industrial robot can transport the work; a position designator for designating a travel starting point of the industrial robot at an arbitrary position on the display screen; a calculator for setting a plurality of time intervals with respect to necessary travel time from the travel starting point and calculating a travelable area, to be displayed on the display screen; and a display for depicting the travelable areas with a visual discrimination between the travelable areas.

Methods for determining the probability of a human observer correctly performing a visual discrimination task of a target with a dynamic image stream, movie, are based on the V50 criterion, or the number of resolvable cycles needed by the human observer for a fifty percent probability of discrimination task completion, for performing the same visual discrimination task of the same targets in static scenes given an infinite amount of time. Once the V50 value is determined for the target set using static images, this value is used with the resolvable cycles V of the target set from the movie in an empirical Target Transfer Probability Function TTPF defined by P∞(t)=(V(t) / V50(t))1.5 / (1+(V(t) / V50(t))1.5). The TTPF calculates the probability of correctly performing the visual discrimination task of a target at a given instance in time within the movie. These P∞ values are then modified by a time limited search equation.