摘要:
A neural network based optical character recognition technique is presented for identifying characters in a moving web. Image acquisition means defines an imaging window through which the moving web passes such that the characters printed thereon can be imaged. Classification data is extracted and accumulated for each printed web character passing through the imaging window. A light source provides transmissive illumination of the web as it is being imaged. A neural network accelerator is coupled to the image acquisition means for intelligent processing of the accumulated classification data to produce therefrom printed character classification information indicative of each corresponding character imaged. A processor is coupled to the accelerator for converting the classification information into the appropriate ASCII character code. The technique is particularly useful for reading dot-matrix-type characters on a noisy, semi-transparent background at fast real-time rates. A neural network algorithm based recognition method is also described.
摘要:
A method and computer software program for publishing images at an accessible website and for ordering goods and/or services to be provided by a fulfillment provider. A high resolution digital image is forwarded from a user to a fulfillment provider that stores the high resolution digital image and associates a unique ID with the high resolution image. The unique ID identifies the storage location of where the high resolution image is stored and the internet address of the fulfillment provider. The user receives the unique ID that is associated with the high resolution image. The user then forwards to an accessible website a low resolution image copy of the high resolution image and the unique ID. The website publishes the low resolution image on the accessible website along with an action button that is associated with the unique ID. Selection of the action button by a viewer causes the viewer being forwarded to the fulfillment provider so that the viewer will to be able to access the high resolution image stored by the fulfillment provider.
摘要:
A method and computer software program for publishing images at an accessible website and for ordering goods and/or services to be provided by a fulfillment provider. A high resolution digital image is forwarded from a user to a fulfillment provider that stores the high resolution digital image and associates a unique ID with the high resolution image. The unique ID identifies the storage location of where the high resolution image is stored and the internet address of the fulfillment provider. The user receives the unique ID that is associated with the high resolution image. The user then forwards to an accessible website a low resolution image copy of the high resolution image and the unique ID. The website publishes the low resolution image on the accessible website along with an action button that is associated with the unique ID. Selection of the action button by a viewer causes the viewer being forwarded to the fulfillment provider so that the viewer will to be able to access the high resolution image stored by the fulfillment provider.
摘要:
A bar code reader particularly useful in a photographic film scanner of the type employing a light source and CCD array for sensing the bar code elements. Lateral location of the bar code pattern is established by analyzing the output of the CCD array within a bar code detection window to determine the location of a longitudinal edge transition of the line of clock elements in the bar code pattern and then to use clock and data element detection windows at spaced locations from the line of clock edge transition to read the encoded values of the bar code. In one embodiment, the line of transition between the clock and data elements is used as the line of longitudinal edge transition of the line of clock elements. In another embodiment, the longitudinal clock edge transition remote from the data elements and adjacent the central image frame region is used.
摘要:
A dual speed film drive apparatus to achieve high speed and low speed film drive employs a limited speed range stepper motor with pinion input drive gear, and an output driven gear connected to a film advance mechanism. High and low speed drive is achieved by use of a pivoted intermediate gear drive module having high speed and low speed gear set positions to interconnect the stepper motor input drive gear to the output driven gear. Shifting of the gear module between gear set positions is accomplished by a DC motor operated cam drive mechanism which pivots the gear module selectively between the high speed and low speed gear set positions. The cam drive mechanism includes a camming slot having dwell segments at each end of the slot. An open loop control gear mesh procedure includes is also described for meshing the high speed and low speed intermediate gear drives with the input drive gear and output driven gear. In this procedure, the cam drive mechanism initially drives the gears toward mesh and then reverses the cam drive by a limited amount. If the input drive gear properly meshed with the intermediate gear drive, the dwell segment prevents the gear from being unmeshed. If stubbing occurred, the cam drive is still in the drive segment of the cam and backs the intermediate gear drive away while the stepper is activated by a partial tooth pitch. The cam drive is then driven forward again to engage the intermediate gear with the input gear. The stepper motor is then driven forward and back by equal amounts to clear any stub condition that might still exist between the intermediate gear and output driven gear interface. The open loop control routine avoids the need for complex and costly active feedback mechanisms to detect and clear a gear stubbing condition during gear shifting.
摘要:
A solder paste brick inspection and physical quality scoring system 10 employs a neural network 70 trained with a fuzzified output vector. An image of solder paste bricks 64 on a printed circuit board 12 is acquired by a CCD camera 30. Values of a predetermined set of brick metrics are extracted from the image by a computer 28 and used as a crisp input vector to trained neural network 70. A defuzzifier 76 converts a fuzzy output vector from neural network 70 into a crisp quality score output which can be used for monitoring and process control.
摘要:
A web of photographic film or the like having an optical property to be inspected and measured (such as exposure density or reflectance) is transported through a flasher chamber at a predetermined nominal speed and is exposed to radiation in the flasher to produce a series of longitudinally spaced, transversely oriented exposure bands separated by unexposed bands on the web. The transport speed of the web through the exposure chamber is selected for a given exposure period for each band such that the web moves only a minor fraction of the longitudinal width of each band during exposure of the band. Subsequent inspection of the web, for example, in a densitometer, produces a pulsed output signal waveform in which the peak amplitudes of the pulses are proportional to the optical property being measured independent of any perturbations in transport speed of the web through the exposure chamber.
摘要:
An imaging method and system enables the use of available images to form a pictorial type border around a specific image that a user has selected to be printed. With the method and system of the invention, images from an order or from an electronic storage mechanism can be analyzed to determine which of the images are to be border images for a selected image. These images are then resized to form border images for the selected image.
摘要:
A method and computer software program for publishing images at an accessible website and for ordering goods and/or services to be provided by a fulfillment provider. A high resolution digital image is forwarded from a user to a fulfillment provider that stores the high resolution digital image and associates a unique ID with the high resolution image. The unique ID identifies the storage location of where the high resolution image is stored and the internet address of the fulfillment provider. The user receives the unique ID that is associated with the high resolution image. The user then forwards to an accessible website a low resolution image copy of the high resolution image and the unique ID. The website publishes the low resolution image on the accessible website along with an action button that is associated with the unique ID. Selection of the action button by a viewer causes the viewer being forwarded to the fulfillment provider so that the viewer will to be able to access the high resolution image stored by the fulfillment provider.
摘要:
A printer dock for use with a digital data terminal, has a housing having a paper inlet portal, a first tray receiver, and a second tray receiver. The first tray receiver adjoins the paper inlet portal. The second tray receiver is disposed in spaced relation to the paper inlet portal. A printer engine is disposed in the housing. The printer engine has a paper path extending from an entrance facing the paper inlet portal. A device interface is operatively connectable to the data terminal and the printer engine. A paper tray is alternately mountable in a use position and a storage position. The paper tray, in the use position, is located in the first tray receiver and is disposed in operative relation to the printer engine. The paper tray, in the storage position, is located within the second tray receiver.