Abstract: In one embodiment, a video analysis service receives video data captured by one or more cameras at a particular location. The service applies a neural network-based model to portions of the video data, to identify objects within the video data. The service maps outputs of the neural network-based model to symbols using a conceptual space. The outputs of the model comprise the identified objects. The service applies a symbolic reasoning engine to the symbols, to generate an alert. The service sends the alert to a user interface in conjunction with the video data.

Abstract: A method of detecting traffic passing a camera overlooking a roadway. The method comprises receiving video frames by a traffic analytics engine from the camera, determining a mask that defines a lane detection region by the traffic analytics engine based on an assumed average length of a vehicle and based on analyzing lane boundary markers in the video frames; determining a background reference frame by the traffic analytics engine by applying the mask to the video frames and by averaging the pixels of the masked video frames; determining that at least some of the masked video frames differ from the background reference frame by more than a detection threshold; and incrementing a traffic count associated with the lane detection region stored in a memory of the computer system based on the masked video frames that differ from the background reference frame by more than the detection threshold.

Abstract: Systems and methods monitor driver behavior for vehicular fleet management in a fleet of vehicles using driver-facing imaging device. The systems and methods herein relate generally to vehicular fleet management for enhancing safety of the fleet and improving the performance of the fleet drivers, and further relate to monitoring the operation of fleet vehicles using one or more driver-facing imaging devices disposed in the fleet vehicles for recording activities of the fleet drivers and their passengers, storing information relating to the monitored activities, selectively generating warnings related to the monitored activities, and reporting the monitored activities to a central fleet management system for use in enhancing the safety of the vehicles of the fleet and for helping to improve the performance of the fleet drivers.

Abstract: A design support system for permitting a design that easily meets desired conditions regarding an entire item group is provided. An automatic estimation system acting as the design support system comprises: an item recognition section that recognizes each of the items included in the item group by individually recognizing elements making up the item; a designated condition recognition section that recognizes a designated condition from the manufacturing conditions; and a recommended-to-be-examined element recognition section that recognizes, with respect to the designated condition recognized, the element corresponding to any of the manufacturing conditions that is recommended to be examined for changes. The recommended-to-be-examined element recognition section displays a model of the item group by highlighting the element for which the manufacturing condition is recommended to be examined for changes.

Abstract: A vision system for determining an identity of an individual animal in a population of animals with known identity is provided. A first image sensor arrangement is configured to capture three-dimensional or thermographic images of the individual animal. A second image sensor arrangement is configured to capture two-dimensional images of the individual animal. Control circuitry is configured to obtain a first image of the individual animal captured by the first image sensor arrangement and to detect a body part in the first image, and in response to detecting the body part, obtain a second image of the individual animal captured using the second image sensor arrangement, and to identify the individual animal by comparing metrics of the second image with the reference data in a data storage.

Abstract: A method for producing security elements in an image which are not visible to the human eye and which cannot be copied, in particular for checking the authenticity of images. The image is imaged by means of a halftone, the halftone consisting of individual image dots arranged adjacent to each other. This is characterized in that at least one field having a random geometric shape or freeform is defined in the image/the halftone. By means of manipulation of image dots in the field and/or by means of manipulation of the entire field, an encrypted information that cannot be copied is stored for comparison with at least one database and the serial number is displayed by means of contours formed in the halftone.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine learning. One of the methods includes receiving an image; providing the image to a neural network model, wherein the neural network model is trained to output predictions of one or more locations within the image and corresponding classifications; extracting text content within one or more of the one or more locations; analyzing the extracted text content using the corresponding classifications to evaluate one or more of external consistency with other data records or internal consistency with content from one or more of the particular locations; and generating one or more outputs based on the analyzing.

Abstract: The present disclosure provides methods and systems for performing licence plate matching. A reference list comprising licence plate identifiers is obtained. At least one transformation rule is applied to the licence plate identifiers of the reference list to generate entries forming at least one augmented reference list, and storing the at least one augmented reference list in at least one database. A search request comprising an input licence plate identifier is obtained. The at least one transformation rule is applied to the input licence plate identifier to generate a search list comprising at least one search term. The at least one database is queried with the search list to identify a match between at least one of the entries of the at least one augmented reference list and the at least one search term of the search list. A signal responsive is output to identifying the match.

Abstract: A system and a method for smart information recognition for user health identification are disclosed. The system and the method comprise a display unit, a color code detection unit, an image filter, an optical character recognition unit, a code detection unit and an elimination unit. The display unit contains a user information. The color code detection unit is associated with the display unit to split at least one of the user information by analyzing at least three colors in an image. The image filter detects at least one of the user's information. Further, the optical character recognition unit recognizes a text of the user information. The code detection unit detects an image code and the elimination unit is used for eliminating a binary object that is close to an image border. The proposed system and method ensure complete security to prevent abuse of an individual's personal information.

Abstract: A method for extracting data from lineless tables includes storing an image including a table in a memory. A processor operably coupled to the memory identifies a plurality of text-based characters in the image, and defines multiple bounding boxes based on the characters. Each of the bounding boxes is uniquely associated with at least one of the text-based characters. A graph including multiple nodes and multiple edges is generated based on the bounding boxes, using a graph construction algorithm. At least one of the edges is identified for removal from the graph, and removed from the graph to produce a reduced graph. The reduced graph can be sent to a neural network to predict row labels and column labels for the table.

Abstract: A computer-implemented method and system for processing a document page is based on text and non-text detections in an image path. An object block is generated for each image content identified within an input page. the blocks are extracted from the input document for downstream processing. Then, the object blocks are classified based on whether the content is text or non-text. The extracted non-text objects—which are specified by their bounding boxes—are processed separately from the rest of the content. The processing is performed on the text content blocks in parallel. However, when error diffusion is employed, the error diffusion is performed sequentially on the non-text content blocks to avoid stitching artifacts between individually error diffused patches in non-text areas.

Abstract: Provided herein are systems, methods and computer readable media for identifying content to represent web pages and creating a representative image from the content. An example method may include retrieving a web document using a uniform resource locator (URL) contained in a dequeued work item, determining, from the web document, candidate images for creation of the representative image including extracting image references, wherein the image references are extracted by identifying image tags with source attributes, values of which are URLs locating images, filtering the URLs using a blacklist of expressions designed to match the URLs of images comprising one or more predefined undesirable characteristics, and retrieving the images which do not match any of the expressions using an HTTP client, and creating the representative image, comprising at least modifying a chosen image selected from among the candidate images.

Abstract: Methods and systems for training a neural network to distinguish between text documents and image documents are described. A corpus of text and image documents is obtained. A page of a text document is scanned by shifting a text window to a plurality of locations. In accordance with a determination that the text in the window at a respective location meets text line criteria, the text in the window is stored as a respective text snippet. A plurality of image windows are superimposed over at least one page of an image document. In accordance with a determination that the content of a respective image window meets image criteria, content of the image window is stored as a respective image snippet. The respective text snippet and the respective image snippet are provided to a classifier.

Abstract: A method for generating training data for hand-printed text recognition includes obtaining a structured document, obtaining a set of hand-printed character images and database metadata from a database, generating a modified document page image, and outputting a training file. The structured document includes a document page image that includes text characters and document metadata that associates each of the text characters to a document character label. The database metadata associates each of the set of hand-printed character images to a database character label. The modified document page image is generated by iteratively processing each of the text characters.

Abstract: Systems and methods for spatial-aware information extraction from electronic source documents are disclosed. Exemplary implementations may: obtain an electronic source document in electronic format, including human-readable information; obtain extracted information that has been extracted from the electronic source document; generate a character-based representation of the electronic source document that uses a grid of character positions; and present a user interface to a user to search and/or select information in the electronic source document based on the character-based representation.

Abstract: A dermatoglyph detector includes a detection circuit and an electronic processor unit. The detection circuit includes an electrically conductive thin film in which there are formed both electrodes that are arranged to come into contact with the skin of a portion of a human body and also conductive tracks connecting the electrodes to the processor unit. The processor unit is arranged to determine electrical characteristics of the body portion extending between each pair of electrodes in contact with the skin, and to execute a computer program for acting on the basis of the determined electrical characteristics to distinguish between an authentic body portion and a fake body portion. The detection circuit includes at least two track segments of different shapes between two calibration terminals so as to present an impedance ratio that is not equal to unity.

Abstract: A display device relating to a method of operating thereof, including: a display panel having a touch sensing unit to sense an external touch and a display unit including a plurality of pixels; a fingerprint sensing panel to sense a fingerprint disposed on one surface of the display unit, the fingerprint sensing panel having a plurality of fingerprint sensing pixels respectively connected to a plurality of fingerprint scan lines and a plurality of fingerprint sensing lines, and a fingerprint scan driving circuit to drive one or more fingerprint scan lines included in a sensing area; and a read-out circuit to output a selection signal for selecting a sensing area of the fingerprint sensing panel.

Abstract: Improving the accuracy of ultrasonic touch sensing and fingerprint imaging using acoustic impedance matching is disclosed. Acoustic impedance mismatches between an ultrasonic transducer array and a sensing plate can be reduced to maximize energy transfer and minimize parasitic reflections. A reduction in acoustic impedance mismatches can be accomplished using (i) a composite epoxy having a higher acoustic impedance than epoxy alone, (ii) one or more matching layers having an acoustic impedance that is approximately the geometric mean of the acoustic impedance of the sensing plate and the acoustic impedance of the transducer array, (iii) pores or perforations in the sensing plate, or (iv) geometric structures formed in the sensing plate. In addition, parasitic reflections can be suppressed using an absorbent layer.

Abstract: A fingerprint sensing apparatus includes a plurality of fingerprint sensors and a fingerprint readout circuit. The fingerprint sensors may be configured to operate in a fingerprint sensing cycle. The fingerprint readout circuit may be coupled to the plurality of fingerprint sensors via a plurality of sensing lines. The fingerprint readout circuit may be configured to control the fingerprint sensors to operate in the fingerprint sensing cycle. The fingerprint sensing cycle includes an initialization period, an exposure period and a readout period. A voltage of a reset node in each fingerprint sensor among the fingerprint sensors is reset to a first voltage in a reset period before the fingerprint sensing cycle starts. The voltage of the reset node in each fingerprint sensor is initialized to an initial voltage in the initialization period. The initial voltage is different from the first voltage.

Abstract: A fingerprint sensing device includes a first substrate, a sensing element layer, a second substrate, a micro-structure layer, and a spacer layer. The sensing element layer is located on the first substrate and includes multiple sensing elements. The second substrate is located on the sensing element layer. The micro-structure layer is located between the second substrate and the sensing element layer, and includes multiple micro-lens structures and multiple dummy structures. Orthogonal projections of the micro-lens structures on the first substrate overlap orthogonal projections of the sensing elements on the first substrate. The spacer layer is located between the second substrate and the sensing element layer, and includes multiple main spacers. Each of the main spacers covers at least one of the dummy structures.

Abstract: A method for extracting a signature of a fingerprint shown on a source image is described. For this purpose, the source image is transformed into the frequency domain. One or more ridge frequencies are next determined by means of a convolutional neural network applied to said transformed image, n being an integer greater than or equal to 1. The source image is normalized in response to said n ridge frequencies determined. One or more signatures of said fingerprint are finally extracted from said n normalized images.

Abstract: A fingerprint verification method includes selecting one or more first fingerprint groups from among a plurality of fingerprint groups based on an input fingerprint image, each fingerprint group of the plurality of fingerprint groups including partial fingerprint images; and determining whether verification is successful based on the input fingerprint image and each of the partial fingerprint images included in the one or more first fingerprint groups.

Abstract: A method for estimating human body temperature includes receiving, via a thermal camera, a thermal image captured of a real-world environment, the thermal image including thermal intensity values for each of a plurality of pixels of the thermal image. A position of a first human face is identified within the thermal image, the first human face corresponding to a first human subject. A skin tone of the first human face is identified. Based on the identified skin tone, a skin tone correction factor is applied to one or more thermal intensity values of one or more pixels corresponding to the first human face to give one or more tone-corrected thermal intensity values. Based on the one or more tone-corrected thermal intensity values an indication of a body temperature of the first human subject is reported.

Abstract: An electronic device includes a first display on a major surface, a second display positioned on another major surface, and optionally at least one imager collocated with the second display. One or more processors identify a predefined event occurring and select whether to present content on the first display or the second display. The one or more processors can cause an imager to capture at least one image. When image matches a first predefined criterion, the one or more processors cause a presentation of content to occur on the first display. When the image matches a second predefined criterion, the one or more processors cause the presentation of the content to occur on the second display. The one or more processors can also compare sizes of the first touch sensitive display portion and the second touch sensitive display portion to select between the first display and the second display.

Abstract: An image processing apparatus, an image processing method, and an image processing program capable of selecting an image having common characteristics with a previously selected image, and a recording medium storing the program are provided. In a case where an image of a child and a father captured together is included in common in a first image selected from a first image group and a second image selected from a second image group, a speech balloon 200 for notifying a user to select such an image IR1 from a target image group is displayed on a display panel 21 of a smartphone. In a case where the user selects the image IR1 of the child and the father captured together, common characteristics with a previously selected image are maintained.

Abstract: Disclosed is a face verification method and apparatus. The method including analyzing a current frame of a verification image, determining a current frame state score of the verification image indicating whether the current frame is in a state predetermined as being appropriate for verification, determining whether the current frame state score satisfies a predetermined validity condition, and selectively, based on a result of the determining of whether the current frame state score satisfies the predetermined validity condition, extracting a feature from the current frame and performing verification by comparing a determined similarity between the extracted feature and a registered feature to a set verification threshold.

Abstract: Disclosed herein are methods and systems for determining whether a user engaged in an interactive video session is a genuine user or a potential impersonator by analyzing a plurality of consecutive images depicting the user while engaged in the video session to identify one or more dynamic facial patterns in the face of the user while his lips are moving. Each such dynamic facial pattern may express a movement of one or more of a plurality of wrinkles and/or other dynamic facial features (e.g., nostrils, distance between nostrils, ear, skin portion, muscle, etc.) in the face of the user. The user may be then determined to be genuine or not based on a comparison between the identified dynamic facial pattern(s) and one or more reference dynamic facial patterns.

Abstract: A disclosed computer-implemented method may include directing a display device included in a head-mounted display worn by a user to illuminate, via a projection of a line at an illumination time, a portion of a cornea of the user. The method may further include detecting, via an image sensor at a detection time, a portion of the projection of the line reflected by the portion of the cornea of the user and identifying a distortion of the projection of the line reflected by the portion of the cornea of the user. The method may also include determining a shape of the cornea of the user based on the illumination time, the detection time, and the distortion of the projection of the line reflected by the portion of the cornea. Various other methods, systems, apparatuses, and computer-readable media are also disclosed.

Abstract: A system for eye-tracking according to an embodiment of the present invention includes a data collection unit that acquires face information of a user and location information of the user from an image captured by a photographing device installed at each of one or more points set within a three-dimensional space and an eye tracking unit that estimates a location of an area gazed at by the user in the three-dimensional space from the face information and the location information, and maps spatial coordinates corresponding to the location of the area to a three-dimensional map corresponding to the three-dimensional space.

Abstract: Related methods are provided for establishing a baseline value to represent an eyelid opening dimension for a person engaged in an activity, where the activity may be driving a vehicle, operating industrial equipment, or performing a monitoring or control function; and for operating a system for monitoring eyelid opening values with real time video data.

Abstract: A computer-implemented method includes: (i) receiving location information that represents a physical location of a user; (ii) receiving a first image that has been captured by the user; (iii) in response to receiving the first image, obtaining a second image that has been captured by a camera and that depicts a particular object in an area around the physical location; (iv) determining whether the first image matches the second image; and (v) in response to determining that the first image matches the second image, determining that the user is authentic.

Abstract: The present disclosure is enclosed in the area of validation of vehicles in road tolls, which may also be designated as tolling systems. The present disclosure includes an automated computational method for the determination of the validity of the passage of a vehicle in a toll which includes two detection modes of a vehicle, through optical means and a mobile device receiving a wireless beacon with unique information associated with the toll and subsequently in connection with a remote backend server. The wireless beacon is a simple type of message which does not require that the mobile device and a fixed wireless device establish a connection. Such feature is one particularly relevant in the applications of the present disclosure, as it highly improves the efficacy of the receipt of the unique information associated with the toll by the mobile device. The present disclosure further includes a corresponding system.

Abstract: The present application discloses a method, system and related device of implementing vehicle automatic inspection and repair. The method includes: obtaining, by a vehicle controller, vehicle self-inspection data, and controlling a vehicle to drive and stop at an inspection and repair position when determining the vehicle malfunctions according to the vehicle self-inspection data; sending, by the vehicle controller, vehicle diagnostic information to an inspection and repair apparatus; and determining, by the inspection and repair apparatus, a corresponding repair advice according to the vehicle diagnostic information, and sending the repair advice to the vehicle controller.

Abstract: A controller diagnostic method includes transmitting a Diagnostic Trouble Code (DTC) request signal to a plurality of controllers; receiving a first frame of the plurality of controllers in response to the DTC request signal; delaying a transmission time of a flow control signal and transmitting the delayed flow control signal to the plurality of controllers; and receiving a DTC information by at least one consecutive frame provided by the plurality of controllers in response to the delayed flow control signal.

Abstract: A plurality of fault conditions are detected on a communication network onboard a vehicle. The detected fault conditions, a fault condition importance, environment conditions, and a vehicle operation mode are input to a neural network that outputs rankings for respective detected fault conditions. The neural network is trained by determining a loss function based on a maximum likelihood principle that determines a probability distribution that ranks the detected fault conditions. The vehicle is operated based on the rankings of the fault conditions.

Abstract: Disclosed herein are various embodiments of an electronic lockbox for storing keys and key cards. The lockbox may include calendar-based entry rules so that the key codes can differ based on the date and time. The lockbox may be controllable by a mobile device such as a mobile phone, tablet, or other mobile device. The lockbox may include functionality so that key codes for the lockbox can be transmitted via websites such as Airbnb, HomeAway, or other rental websites, so that guests automatically receive their unique lockbox codes when they confirm their reservations. The lockbox may also receive a Bluetooth low energy virtual key which may be transmitted directly from a user's mobile phone to the lockbox, so that no manual code entry through the keypad is required by a user. The lockbox may be capable of accepting multiple passcodes enabled at different times and dates, and for different purposes.

Abstract: Embodiments relate to a system comprising a drug storage comprising a container to hold a drug; a communication module; and a cyber security module. The system is operable to log record of access to the drug and maintain a ledger of the record of access to the drug using a blockchain technology. The access to the drug is secured by the cyber security module.

Abstract: Forms of interaction with an electronic system, such as for games of chance, games of skill, and combinations thereof are described herein. A system is provided for effecting defined game play and prizing structure parameters in an electronic entertainment environment. The system may include an input for receiving the parameters, a memory coupled to the input for storing the parameters, a processing system coupled to the storage for generating game play to effect the defined parameters, storage for recording information regarding particular game play events and an interface for at least presenting game play events to users of the electronic entertainment system. In one mode of operation, one or more mandated parameters are externally imposed, and variable parameters are selected such that the mandated parameters are met globally, and such that the user experience is optimized.

Abstract: A camera captures a display of a gaming device and determines information that appears on the display. The camera is mounted on a video gaming device, and the camera continuously or at various intervals captures images of the screen of the video gaming device. Those images are analyzed to determine information displayed on the video gaming device, such as game speed (e.g., time between handle pulls, total time of play, handle pulls during a session, etc.), bet amounts, bet lines, credits, etc. This information may be determined in various ways, such as by using image processing of images captured by the camera. Machine learning algorithms may also be used to infer key information displayed on the screen of the video gaming device to capture and/or analyze. A housing of the camera may also have a secondary display oriented in a similar direction as the screen of the video gaming device.

Abstract: Embodiments of this concept are direct to a game that includes a combination of an entertainment game and a gambling game. This game combination provides an entertainment game that retains the playability and fun of a skill game or other non-traditional gambling game while allowing for wagers to still be placed and awards won. In some embodiments, the wager-based gambling game is tied directly into the entertainment game, which provides additional entertainment and excitement. Other embodiments separate some of the aspects of the gambling game from the entertainment game to retain the feel of well known gaming devices while still providing an entertainment game to the player.

Abstract: A multi-cabinet game build is disclosed. The multi-cabinet game build includes common game play assets and tailored game play assets. The common game play assets are shared by gaming machines across multiple cabinet types. The tailored game play assets are used by gaming machines of a certain cabinet type. A configuration tool is also disclosed which permits a technician to specify a game build configuration for a gaming machine, which configures the gaming machine to present a game of a multi-cabinet game build using the common game play assets and appropriate tailored game play assets for the gaming machine.

Abstract: Systems and methods are provided for using a non-regulated device to generate data objects via a regulated device. A first device can provide interface content items corresponding to one or more events for which to generate a data object, and receive, via a user selection, object information identifying an event of the one or more events, one or more object parameters, and a second device identifier identifying a second device of the user. The first device can generate a request to provide the object information to one or more servers, and transmit the request to provide the object information to one or more servers. The request causes the one or more servers to store an entry including the object information, generate a link to the object information, and transmit a message including the link to the second device of the user using the second device identifier.

Abstract: An inspection system of a chip includes a reading device and a determining unit. The reading device is configured to count a number of chips stored in a storage case, the chips associated with a table game and including a chip having a radio tag, read the radio tag while the chips are stored in the storage case, and acquire chip information. The determining unit is configured to compare the chip information of the chips in the storage case with a physical number of the chips in the storage case, determine that there is an abnormal chips among the chips stored in the storage case based on a determination that the counted number of the chips does not match a physical number of the chips in the storage case, and output a result associated with an indication of the abnormal chip.

Abstract: A system and method for purchasing credits is described. The method includes receiving an electronic transaction request instruction by a mobile electronic transaction terminals. Each electronic transaction terminals includes a display and is in exclusive electronic communication with a secure gateway. The method proceeds to generate an electronic transaction request for an electronic transaction using the electronic transaction request instruction. The method then communicates the electronic transaction request from the secure gateway to a financial account server. At the secure gateway, an electronic transaction approval from the financial account server is received. The secure gateway then generates an authorization to dispense credits. The authorization to dispense credits is communicated from the secure gateway to at least one mobile electronic transaction terminal. Credits are then dispensed, wherein the credits are associated with a credit system located at an activity table.

Abstract: A gaming system compatible with patron-controlled portable electronic devices, such as smart phones or tablet computers, is described. The gaming system can include electronic gaming machines that are compatible to receive both virtual ticket vouchers and printed ticket vouchers that are redeemable for credits on the electronic gaming machines. Information associated with a virtual ticket voucher can be stored on a patron-controlled portable electronic device and then can be wireless transmitted to the electronic gaming machines. The electronic gaming machines can be configured to issue virtual ticket vouchers and printed ticket vouchers that can be redeemed for cash or additional game play on another electronic gaming machine. In one embodiment, the electronic gaming machine can be configured to issue a virtual ticket voucher to a patron-controlled portable electronic device.

Abstract: A bonusing system for gaming devices provides a bonus award eligible to be won via participating gaming devices. A messaging application programming interface (API) receives wagering event messages in a first message format from third-party servers. A message queue receives wagering event messages from the messaging API in a second message format. A bonusing system server manages award determination for the bonus award.

Abstract: A gaming machine comprises a display and an electronic controller for playing a first game. The electronic controller is configured to randomly determine whether to display one or more bonus symbols in the first game, each bonus symbol being associated with a bonus value award. Where a trigger event occurs during the first game, such as the appearance of a predetermined order of bonus symbols, electronic controller is configured to display an array of the bonus symbols on the display or optionally on another display. Where bonus symbols appear in further plays of the first game or plays of a second game, the bonus symbols are added to the array and bonus symbols present on the array are sequentially transferred to a win meter, which increments by the amount of the associated bonus value award of each transferred bonus symbol.

Abstract: An electronic gaming machine includes a game controller configured to (a) determine, during a base game, that a feature game trigger condition is satisfied; (b) activate a feature game within the base game; (c) display, a feature game play area associated with the feature game, the feature game play area including a plurality of zone patterns overlaid on the symbol display positions; (d) convert the symbol display positions into independent feature game reels; (e) generate a first game outcome by (i) holding a first set of feature game reels displaying the prize symbols while (ii) selecting and displaying a symbol for a second set of feature game reels; (f) determine that at least one zone pattern is complete with prize symbols; (g) apply a zone multiplier associated with the zone pattern to credit values within the zone pattern; and (h) award the incremented credit values to the player.

Abstract: A method of displaying a subset of all available wagers on the different possible outcomes for a play inside of a live sporting event that is dependent upon the portion of the game the user is watching so that the user may view available wagers and the live sporting event on the same display.

Abstract: Security flaps for use with cash trays and cash trays including such security flaps are disclosed. An apparatus includes a cash tray having a base and a plurality of walls that extend from the base and define a plurality of paper-currency compartments. A plurality of distal edges of the walls define openings of the paper-currency compartments. A spring-biased security flap is coupled to the cash tray and adapted to engage or be immediately adjacent the distal edges of the walls of at least one of the paper-currency compartments to cover the corresponding opening.