Abstract: A method and a device for adaptively recognizing a value document are provided. The method includes: acquiring a collection parameter, and collecting a photoelectric signal of the value document; acquiring a photoelectric signal correction amount, and performing digital compensation on the photoelectric signal; performing feature extraction on the photoelectric signal subjected to the digital compensation to obtain a feature vector; inputting the feature vector to a preset classifier for recognition, to obtain a recognition result of the value document; acquiring a specific region on the value document; acquiring feature information of the photoelectric signal of the value document; calculating an accumulation component and a differential error of the value document; calculating a total correction amount of the photoelectric signal; updating the photoelectric signal correction amount and the collection parameter; and outputting the recognition result.

Abstract: A method and a device for adaptively recognizing a value document are provided. The method includes: acquiring a collection parameter, and collecting a photoelectric signal of the value document; acquiring a photoelectric signal correction amount, and performing digital compensation on the photoelectric signal; performing feature extraction on the photoelectric signal subjected to the digital compensation to obtain a feature vector; inputting the feature vector to a preset classifier for recognition, to obtain a recognition result of the value document; acquiring a specific region on the value document; acquiring feature information of the photoelectric signal of the value document; calculating an accumulation component and a differential error of the value document; calculating a total correction amount of the photoelectric signal; updating the photoelectric signal correction amount and the collection parameter; and outputting the recognition result.

Abstract: A self-correction recognition method and device for a valuable document recognition device is provided. The method includes: extracting a feature of a valuable document; determining whether the feature falls in a discriminant library of any preset category, and obtaining a substitutive centroid according to a feature centroid and the feature in a case that the feature falls in a discriminant library of any preset category; and updating the discriminant library of the category by replacing the feature centroid of the category with the substitutive centroid. The discriminant library is pre-constructed according to the feature centroid of the category, and the feature centroid is calculated from a feature of the category.

Abstract: A Hall detection device for a thickness of a sheet medium is provided, including a mounting rack, a reference shaft and a floating wheel assembly, wherein the floating wheel assembly includes a bracket and at least one floating wheel, one end of the bracket being mounted on the mounting rack via a floating wheel rotary shaft and the other end thereof being rotationally fitted with the floating wheel so as to form a free end, a torsional spring is provided between the floating wheel rotary shaft and the bracket so that the floating wheel elastically bears against the reference shaft, and the bracket is fixedly mounted with a detection block and a sensor for detecting a displacement amount of the detection block.

Abstract: A Hall detection device for a thickness of a sheet medium is provided, including a mounting rack, a reference shaft and a floating wheel assembly, wherein the floating wheel assembly includes a bracket and at least one floating wheel, one end of the bracket being mounted on the mounting rack via a floating wheel rotary shaft and the other end thereof being rotationally fitted with the floating wheel so as to form a free end, a torsional spring is provided between the floating wheel rotary shaft and the bracket so that the floating wheel elastically bears against the reference shaft, and the bracket is fixedly mounted with a detection block and a sensor for detecting a displacement amount of the detection block.

Abstract: A self-correction recognition method and device for a valuable document recognition device is provided. The method includes: extracting a feature of a valuable document; determining whether the feature falls in a discriminant library of any preset category, and obtaining a substitutive centroid according to a feature centroid and the feature in a case that the feature falls in a discriminant library of any preset category; and updating the discriminant library of the category by replacing the feature centroid of the category with the substitutive centroid. The discriminant library is pre-constructed according to the feature centroid of the category, and the feature centroid is calculated from a feature of the category.

Abstract: An overlapping bill detection method and apparatus are provided.

Abstract: A self-correction recognition method and device for a valuable document recognition device is provided. The method includes: extracting a feature of a valuable document; determining whether the feature falls in a discriminant library of any preset category, and obtaining a substitutive centroid according to a feature centroid and the feature in a case that the feature falls in a discriminant library of any preset category; and updating the discriminant library of the category by replacing the feature centroid of the category with the substitutive centroid. The discriminant library is pre-constructed according to the feature centroid of the category, and the feature centroid is calculated from a feature of the category.

Abstract: An image calibration method and device. A deviation compensation coefficient of each pixel is calculated according to image data generated by strong and weak lighting parameters, and the deviation compensation coefficient is used to calibrate data of each image pixel collected and output by an image sensing unit. Therefore, the influence of inconsistency of each photosensitive element of the image sensing unit on the image greyscale can be eliminated, so that the effect of document medium image recognition is increased. The method in the embodiments of the present invention comprises: S1, acquiring a strong lighting parameter of each photosensitive element within a long exposure time and a weak lighting parameter thereof within a short exposure time; S2, acquiring image data of a sheet medium; and S3, according to the strong lighting parameter, the weak lighting parameter and the image data, calculating the calibrated image data of the sheet medium.

Abstract: An image identification system for conducting image identification of a valuable file in an automatic teller machine and a corresponding image storage control method are provided. The system comprises: an image sensor; an image memory; an image identification module; an image storage area controller; and a main control unit, wherein the image storage area controller comprises a storage area index link table which is divided into N nodes, N being a natural number greater than 1, each node corresponding to each of the image storage areas divided by the image storage area controller in a one to one relationship, and each node storing the storage locations of a previous image and a next image which are linked with the node, and being provided with an acquired image write pointer, an identified image read pointer, an unidentifiable image head pointer, and an unidentifiable image tail pointer.

Abstract: A paper currency number recognition apparatus and method. The apparatus comprises: a contact-type sensor (10) for acquiring paper currency image data; a white-light LED transmission light source board (20); an image acquisition processing board (40) which is integrated with an FPGA and a DSP, the FPGA being used for controlling ON/OFF of the white-light LED transmission light source board (20) and driving the contact-type sensor (10) to acquire an image, and the DSP being used for processing and recognizing the paper currency image data; and two pairs of position sensors (30) for detecting whether there is a paper currency entering the paper currency number recognition apparatus, wherein the white-light LED transmission light source board (20) has two light source modes which are strong and weak, and the two light source modes alternately provide a transmission light source for the contact-type sensor (10) to acquire the paper currency image data.

Abstract: An image compensation correction method and a banknote recognition and detection device. The image compensation correction method is applied to the banknote recognition and detection device. The banknote recognition and detection device comprises: a micro controller; a programmable logic device which is connected to the micro controller; an AD chip, a drive circuit and a static random access memory which are connected to the programmable logic device respectively; and a contact image sensor which is connected to the AD chip and the drive circuit respectively. A compensation correction lookup table is pre-stored in the static random access memory, and the programmable logic device can acquire banknote compensation correction data corresponding to a banknote image pixel point by accessing the static random access memory, and send same to the micro controller.

Abstract: A recognition module comprises a detection unit for real-time detection and control of a banknote moving state, wherein at least one group of the through-beam sensors comprises a first sensor and two second sensors, the first sensor whereof is arranged on a midline of a banknote transmission channel, and the two second sensors are arranged at the upstream position of the banknote moving direction relative to the first sensor and are symmetrically distributed on the two sides of the midline of the banknote transmission channel. The condition for judging whether a start signal of an image data acquisition unit is effective is whether a banknote-triggered insertion event is detected by the first sensor; and the condition for judging whether an end signal of the acquisition unit is effective is whether a banknote-exit completion event is detected by three through-beam sensors.

Abstract: An image calibration method and device. A deviation compensation coefficient of each pixel is calculated according to image data generated by strong and weak lighting parameters, and the deviation compensation coefficient is used to calibrate data of each image pixel collected and output by an image sensing unit. Therefore, the influence of inconsistency of each photosensitive element of the image sensing unit on the image greyscale can be eliminated, so that the effect of document medium image recognition is increased. The method in the embodiments of the present invention comprises: S1, acquiring a strong lighting parameter of each photosensitive element within a long exposure time and a weak lighting parameter thereof within a short exposure time; S2, acquiring image data of a sheet medium; and S3, according to the strong lighting parameter, the weak lighting parameter and the image data, calculating the calibrated image data of the sheet medium.

Abstract: An image compensation correction method and a banknote recognition and detection device. The image compensation correction method is applied to the banknote recognition and detection device. The banknote recognition and detection device comprises: a micro controller; a programmable logic device which is connected to the micro controller; an AD chip, a drive circuit and a static random access memory which are connected to the programmable logic device respectively; and a contact image sensor which is connected to the AD chip and the drive circuit respectively. A compensation correction lookup table is pre-stored in the static random access memory, and the programmable logic device can acquire banknote compensation correction data corresponding to a banknote image pixel point by accessing the static random access memory, and send same to the micro controller.

Abstract: A paper currency number recognition apparatus and method. The apparatus comprises: a contact-type sensor (10) for acquiring paper currency image data; a white-light LED transmission light source board (20); an image acquisition processing board (40) which is integrated with an FPGA and a DSP, the FPGA being used for controlling ON/OFF of the white-light LED transmission light source board (20) and driving the contact-type sensor (10) to acquire an image, and the DSP being used for processing and recognizing the paper currency image data; and two pairs of position sensors (30) for detecting whether there is a paper currency entering the paper currency number recognition apparatus, wherein the white-light LED transmission light source board (20) has two light source modes which are strong and weak, and the two light source modes alternately provide a transmission light source for the contact-type sensor (10) to acquire the paper currency image data.

Abstract: An image identification system for conducting image identification of a valuable file in an automatic teller machine and a corresponding image storage control method are provided. The system comprises: an image sensor; an image memory; an image identification module; an image storage area controller; and a main control unit, wherein the image storage area controller comprises a storage area index link table which is divided into N nodes, N being a natural number greater than 1, each node corresponding to each of the image storage areas divided by the image storage area controller in a one to one relationship, and each node storing the storage locations of a previous image and a next image which are linked with the node, and being provided with an acquired image write pointer, an identified image read pointer, an unidentifiable image head pointer, and an unidentifiable image tail pointer.

Abstract: A recognition module comprises a detection unit for real-time detection and control of a banknote moving state, wherein at least one group of the through-beam sensors comprises a first sensor and two second sensors, the first sensor whereof is arranged on a midline of a banknote transmission channel, and the two second sensors are arranged at the upstream position of the banknote moving direction relative to the first sensor and are symmetrically distributed on the two sides of the midline of the banknote transmission channel. The condition for judging whether a start signal of an image data acquisition unit is effective is whether a banknote-triggered insertion event is detected by the first sensor; and the condition for judging whether an end signal of the acquisition unit is effective is whether a banknote-exit completion event is detected by three through-beam sensors.

Abstract: An identification method for a valuable file and an identification device thereof. The method includes the following steps: (1) acquiring an original infrared image, type, denomination and orientation data of a current valuable file; (2) obtaining size data and infrared characteristic data of a corresponding standard valuable file; (3) applying an image projection conversion technology, and correcting the original infrared image to form a second infrared image matched with the size of the standard valuable file; (4) obtaining the infrared characteristic data of the current valuable file from the second infrared image and comparing same with that of the standard valuable file to identify whether the current valuable file is true or false; and (5) outputting the identification result.

Abstract: An identification method for a valuable file and an identification device thereof. The method includes the following steps: (1) acquiring an original infrared image, type, denomination and orientation data of a current valuable file; (2) obtaining size data and infrared characteristic data of a corresponding standard valuable file; (3) applying an image projection conversion technology, and correcting the original infrared image to form a second infrared image matched with the size of the standard valuable file; (4) obtaining the infrared characteristic data of the current valuable file from the second infrared image and comparing same with that of the standard valuable file to identify whether the current valuable file is true or false; and (5) outputting the identification result.