CN111553430A - Foreign currency identification method and device - Google Patents
Foreign currency identification method and device Download PDFInfo
- Publication number
- CN111553430A CN111553430A CN202010360620.1A CN202010360620A CN111553430A CN 111553430 A CN111553430 A CN 111553430A CN 202010360620 A CN202010360620 A CN 202010360620A CN 111553430 A CN111553430 A CN 111553430A
- Authority
- CN
- China
- Prior art keywords
- image
- foreign currency
- model
- layer
- identified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The invention provides a foreign currency identification method and a device, wherein the method comprises the following steps: the method comprises the steps of obtaining a to-be-identified coin image, inputting the to-be-identified coin image into an input layer of an external coin identification model, and obtaining the currency type, version and face value of the to-be-identified coin image through characteristic classification processing of a full connection layer after multi-round preset processing of the image output by the input layer. The foreign currency recognition model is obtained by training the improved VGG-16 model, the total number of the convolution layers of the foreign currency recognition model is smaller than that of the VGG-16 model, the number of the extracted features of each convolution layer is smaller than that of the extracted features of the corresponding convolution layer in the VGG-16 model, excessive feature extraction cannot be carried out on a coin image to be recognized, so that the features input to the full connection layer are low-layer features representing detailed textures and the like, analysis of the high-layer semantic features of the image by the model is reduced, the occurrence of an overfitting phenomenon is avoided, and the accuracy of the foreign currency recognition model for recognizing the foreign currency image is improved.
Description
Technical Field
The invention relates to the technical field of paper money identification, in particular to a foreign currency identification method and device.
Background
With the economic globalization, foreign currency exchange is more and more common. At present, in the process of currency exchange of foreign currencies, a plurality of foreign currency types are involved, at least ten types of common foreign currencies are involved, and each type of foreign currency also comprises paper currencies with different denominations and different versions. However, in actual life, most people cannot accurately identify various foreign currencies unless sufficient knowledge is reserved, and the accuracy of identifying foreign currencies by manpower is low, so that great transaction risk exists.
In recent years, with the development of image recognition technology, the recognition of foreign currency by using image recognition technology becomes a research trend in the field, and at present, many mature models such as VGG (Visual Geometry Group) and the like exist in the field of image recognition.
Disclosure of Invention
In view of this, the invention provides a foreign currency identification method and device, which improve the accuracy of foreign currency identification.
In order to achieve the above purpose, the invention provides the following specific technical scheme:
a foreign currency identification method comprising:
acquiring a money image to be identified;
the method comprises the steps of inputting a money image to be recognized into an input layer in a foreign money recognition model, obtaining currency, version and face value of the money image to be recognized through multi-round preset processing and feature classification processing of a full connection layer, wherein the size of the input image corresponding to the input layer of the foreign money recognition model is matched with the size of a foreign money, the preset processing comprises feature extraction processing of a convolution layer group, feature reduction processing of a pooling layer and feature normalization processing of a normalization layer, the total number of convolution layers in the foreign money recognition model is smaller than that of a VGG-16 model, and the number of extracted features of each convolution layer in the foreign money recognition model is smaller than that of the corresponding convolution layer in the VGG-16 model.
Optionally, the acquiring the image of the coin to be recognized includes:
acquiring an original image;
preprocessing the original image to obtain a plurality of images to be identified which accord with a preset format;
and respectively inputting each image to be recognized into a coin recognition model for processing, and determining whether each image to be recognized is a coin image to be recognized according to a recognition result.
Optionally, the preprocessing the original image to obtain a plurality of images to be recognized conforming to a preset format includes:
randomly rotating the angle of the original image for multiple times to obtain multiple images;
and respectively adjusting the brightness of each image to a preset brightness value, and converting the color space of each image into HSV (hue, saturation, value) to obtain a plurality of images to be identified.
Optionally, the training method of the foreign currency recognition model includes:
acquiring images of various foreign currencies;
adjusting the brightness of each type of foreign currency image to a preset brightness value, and converting the color space of each type of foreign currency image into HSV (hue, saturation and value) to obtain each type of preprocessed foreign currency image;
carrying out classification labeling and data enhancement on various preprocessed foreign currency images to obtain a training sample set;
and training a preset neural network model by using the training sample set to obtain the foreign currency recognition model, wherein the total number of the convolutional layers in the preset neural network is less than that of the convolutional layers in the VGG-16 model, and the number of the extracted features of each convolutional layer in the preset neural network model is less than that of the extracted features of the corresponding convolutional layer in the VGG-16 model.
Optionally, after obtaining the currency type, the layout and the face value of the money image to be recognized, the method further includes:
inquiring the foreign currency price corresponding to the currency type of the money image to be identified;
calculating the RMB value corresponding to the money image to be identified according to the face value and the foreign currency price of the money image to be identified;
and displaying the standard coin image corresponding to the coin image to be identified and the corresponding RMB value in a front-end display page.
Optionally, after obtaining the currency type, the layout and the face value of the money image to be recognized, the method further includes:
acquiring the positioning information of the mobile terminal for acquiring the coin image to be identified;
calling an electronic map, and inquiring exchange site position information in a preset area corresponding to the positioning information, wherein the exchange site is an exchange site of the currency of the money image to be identified;
and displaying the position information of the exchange points on a front-end display interface.
A foreign currency identification apparatus comprising:
the coin image acquisition unit is used for acquiring a coin image to be identified;
the foreign currency recognition unit is used for inputting the money image to be recognized into an input layer in a foreign currency recognition model, the image output by the input layer is subjected to multi-round preset processing and then subjected to feature classification processing of a full connection layer to obtain the currency type, version and face value of the money image to be recognized, wherein the size of the input image corresponding to the input layer of the foreign currency recognition model is matched with the size of the foreign currency, the preset processing comprises feature extraction processing of a convolution layer, feature reduction processing of a pooling layer and feature normalization processing of a normalization layer, the total number of the convolution layers in the foreign currency recognition model is smaller than that of the convolution layers in the VGG-16 model, and the number of the extracted features of each convolution layer in the foreign currency recognition model is smaller than that of the corresponding convolution layer in the VGG-16 model.
Optionally, the coin image acquiring unit includes:
an original image acquisition subunit, configured to acquire an original image;
the image preprocessing subunit is used for preprocessing the original image to obtain a plurality of images to be identified which accord with a preset format;
and the coin identification subunit is used for respectively inputting each image to be identified into a coin identification model for processing, and determining whether each image to be identified is a coin image to be identified according to an identification result.
Optionally, the image preprocessing subunit is specifically configured to:
randomly rotating the angle of the original image for multiple times to obtain multiple images;
and respectively adjusting the brightness of each image to a preset brightness value, and converting the color space of each image into HSV (hue, saturation, value) to obtain a plurality of images to be identified.
Optionally, the apparatus further includes a model training unit, specifically configured to:
acquiring images of various foreign currencies;
adjusting the brightness of each type of foreign currency image to a preset brightness value, and converting the color space of each type of foreign currency image into HSV (hue, saturation and value) to obtain each type of preprocessed foreign currency image;
carrying out classification labeling and data enhancement on various preprocessed foreign currency images to obtain a training sample set;
and training a preset neural network model by using the training sample set to obtain the foreign currency recognition model, wherein the total number of the convolutional layers in the preset neural network is less than that of the convolutional layers in the VGG-16 model, and the number of the extracted features of each convolutional layer in the preset neural network model is less than that of the extracted features of the corresponding convolutional layer in the VGG-16 model.
Optionally, the apparatus further includes a foreign currency value calculating unit, specifically configured to:
inquiring the foreign currency price corresponding to the currency type of the money image to be identified;
calculating the RMB value corresponding to the money image to be identified according to the face value and the foreign currency price of the money image to be identified;
and displaying the standard coin image corresponding to the coin image to be identified and the corresponding RMB value in a front-end display page.
Optionally, the apparatus further includes a website recommending unit, specifically configured to:
acquiring the positioning information of the mobile terminal for acquiring the coin image to be identified;
calling an electronic map, and inquiring exchange site position information in a preset area corresponding to the positioning information, wherein the exchange site is an exchange site of the currency of the money image to be identified;
and displaying the position information of the exchange points on a front-end display interface.
Compared with the prior art, the invention has the following beneficial effects:
the foreign currency recognition method provided by the invention has the advantages that the foreign currency recognition model is obtained by training an improved VGG-16 model, the size of an input image of an input layer of the foreign currency recognition model is matched with the size of a foreign currency, the image of the foreign currency to be recognized does not need to be stretched or intercepted, the model is more suitable for recognizing the foreign currency, the total number of the convolution layers of the foreign currency recognition model is less than that of the VGG-16 model, the number of extracted features of each convolution layer is less than that of extracted features of the corresponding convolution layer in the VGG-16 model, excessive feature extraction cannot be carried out on the image of the foreign currency to be recognized, so that the features input to a full connection layer are low-layer features representing detailed textures and the like, the analysis of the model on the high-layer semantic features of the image is reduced, the occurrence of an overfitting layer is avoided to a certain extent, and a normalization layer is added after a pool, the characteristics are normalized, the phenomenon of overfitting is avoided to a certain extent, the influence of overfitting on a model processing result is further avoided, and therefore the accuracy of the foreign currency recognition model in recognizing the foreign currency images is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a foreign currency identification method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a method for obtaining an image of a coin to be recognized according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a method for training a foreign currency recognition model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a VGG-16 model and an improved model according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a foreign currency recognition apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention discloses a foreign currency identification method.A user acquires a foreign currency image to be identified through a mobile terminal, such as a smart phone, a tablet personal computer and the like, and then uploads the foreign currency image to a server, and the server inputs the image uploaded by the mobile terminal into a foreign currency identification model obtained by pre-training for processing after preprocessing, so as to obtain the currency type, version and face value of the foreign currency image to be identified. Wherein, the foreign currency recognition model is obtained by training the improved VGG-16 model, the size of an input image of an input layer of the foreign currency recognition model is matched with the size of the foreign currency, the image of the coin to be recognized does not need to be stretched or intercepted, the model is more suitable for recognizing the foreign currency, the total number of the rolling layers of the foreign currency recognition model is less than that of the VGG-16 model, the number of the extracted features of each rolling layer is less than that of the corresponding rolling layer in the VGG-16 model, excessive feature extraction cannot be carried out on the image of the coin to be recognized, so that the features input to the full connection layer are low-layer features representing detailed textures and the like, the analysis of the model on the high-layer semantic features of the image is reduced, the occurrence of over-fitting phenomenon is avoided to a certain degree, a normalization layer is added after the pooling layer for normalization processing of the features, the occurrence of the phenomenon of over-fitting is avoided to a certain extent, and then the influence of the over-fitting on the model processing result is avoided, so that the accuracy of the foreign currency recognition model for recognizing the foreign currency image is improved.
Specifically, referring to fig. 1, the method for identifying a foreign currency disclosed in this embodiment is applied to a server, and specifically includes the following steps:
s101: acquiring a money image to be identified;
the coin image to be recognized can be an original image uploaded by the mobile terminal, wherein the original image is obtained by calling a photographing device by the mobile terminal to photograph at a fixed resolution and then encoding the coin image by BASE 64.
In order to improve the efficiency of image recognition, the money image to be recognized can be obtained by preprocessing an original image uploaded by the mobile terminal, and the preprocessing can include processing such as rotating a random angle, adjusting brightness, converting a color space and the like.
Referring to fig. 2, a preferred method of obtaining an image of a money item to be recognized includes the steps of:
s201: acquiring an original image;
the original image is an image obtained by calling a photographing device by the mobile terminal to photograph at a fixed resolution and then encoding the image by BASE 64.
S202: preprocessing an original image to obtain a plurality of images to be identified which accord with a preset format;
because the original image may be obtained by photographing at any angle, and the images obtained by photographing at different angles have different influences on the identification accuracy, in order to identify the images as accurately as possible, the present embodiment performs random rotation on the angles of the original image for multiple times, respectively, to obtain multiple images, and the multiple images are subjected to brightness adjustment, color space conversion, and the like, so as to correspondingly obtain multiple images to be identified.
The brightness adjustment is to adjust the brightness of the image to a preset brightness value, and the preset brightness value is a preset brightness value, so that the influence of over-brightness or over-darkness of the image acquired by the mobile device on the identification accuracy is avoided.
The color space is converted into a single-channel image by converting the RGB image of the 3 channels into HSV, so that the characteristics extracted by the model are more concentrated during subsequent image processing, and the identification accuracy is improved.
S203: and respectively inputting each image to be recognized into the coin recognition model for processing, and determining whether each image to be recognized is a coin image to be recognized according to the recognition result.
The coin identification model is a classifier obtained by pre-training.
The user probably is arbitrary scene when in actual use, and the image that user's mobile terminal uploaded probably is books, mentality barrier, wrapping bag etc. causes the misidentification of model very easily, in order to avoid this type of condition as far as possible, treats through coin identification model and discerns the discernment image, can filter non-coin image, reduces the misidentification rate, and then improves final discernment rate of accuracy.
S102: and inputting the coin image to be identified into an input layer in the foreign currency identification model, and after the image output by the input layer is subjected to multiple rounds of preset processing, performing characteristic classification processing on a full connection layer to obtain the currency type, version and face value of the coin image to be identified.
When a plurality of to-be-recognized coin images are obtained after images uploaded by the mobile terminal are randomly rotated, each to-be-recognized coin image is respectively input into the foreign coin recognition model to be processed, the recognition result with the highest confidence level is taken as the final recognition result, and the situation that recognition is inaccurate due to the fact that the inclination angle is too large during photographing is avoided.
The foreign currency identification model is obtained by training the improved VGG-16 model in advance, the size of an input image corresponding to an input layer of the foreign currency identification model is matched with the size of a foreign currency, for example, the size 224 of the input image of the VGG-16 input layer is modified into 256 × 192 matched with the size of most foreign currencies.
The preset processing of the foreign currency identification model comprises feature extraction processing of a convolution layer group, feature reduction processing of a pooling layer and feature normalization processing of a normalization layer, wherein the convolution layer group comprises at least one convolution layer, the number of the convolution layers corresponding to each convolution layer group can be different, the total number of the convolution layers in the foreign currency identification model is smaller than that of the convolution layers in the VGG-16 model, and the number of the extraction features of each convolution layer in the foreign currency identification model is smaller than that of the extraction features of the corresponding convolution layer in the VGG-16 model.
The shapes of various foreign currencies are very similar, high-level semantic information is also very similar, and overfitting is easy to perform when the model is actually trained. In order to improve the generalization capability of the foreign currency identification model, the training data of the foreign currency identification model needs to be preprocessed and data enhanced, wherein the preprocessing comprises definition adjustment, brightness adjustment, size scaling, random angle rotation and the like, the training data can be greatly expanded, and the identification accuracy of the model is improved. Referring to fig. 3, the method for training the foreign currency recognition model is as follows:
s301: acquiring images of various foreign currencies;
s302: adjusting the brightness of each type of foreign currency image to a preset brightness value, and converting the color space of each type of foreign currency image into HSV (hue, saturation and value) to obtain each type of preprocessed foreign currency image;
s303: carrying out classification labeling and data enhancement on various preprocessed foreign currency images to obtain a training sample set;
s304: and training the preset neural network model by using the training sample set to obtain a foreign currency recognition model, wherein the total number of the convolutional layers in the preset neural network is less than that of the convolutional layers in the VGG-16 model, and the number of the extracted features of each convolutional layer in the preset neural network model is less than that of the extracted features of the corresponding convolutional layer in the VGG-16 model.
Referring to fig. 4, fig. 4 is a schematic diagram illustrating a comparison between the VGG-16 model and the improved model, wherein the structure of the improved model is merely an example, and the invention is not limited thereto.
It can be seen that, compared with the VGG-16 model, the size of the Input image of the Input layer (Input) of the foreign currency recognition model in this embodiment is matched with the size of the foreign currency, and the extension or interception processing is not required to be performed on the image of the foreign currency to be recognized, so that the model is more suitable for recognizing the foreign currency, and the total number of convolution layers (conv) of the foreign currency recognition model is smaller than that of the VGG-16 model, the number of extracted features of each convolution layer is smaller than that of extracted features of the corresponding convolution layer in the VGG-16 model, and excessive feature extraction is not performed on the image of the foreign currency to be recognized, so that the features Input to the full connection layer are low-layer features representing textures and the like, the analysis of the model on the high-layer semantic features of the image is reduced, the occurrence of the over-fitting phenomenon is avoided to a certain extent, and a normalization layer (BatchNormal) is added after the pooling layer (metamoling) to normalize the features, the occurrence of the phenomenon of over-fitting is avoided to a certain extent, and then the influence of the over-fitting on the model processing result is avoided, so that the accuracy of the foreign currency recognition model for recognizing the foreign currency image is improved.
After the foreign currency image recognition is completed, the recognition result can be returned to the front-end display page, and in order to improve the user experience while the recognition result is displayed, a standard foreign currency image, foreign currency introduction, exchangeable RMB, a foreign currency reservation recommending function, exchange site recommendation and the like can be displayed for the user.
Specifically, the calculation method for exchangeable RMB comprises the following steps:
inquiring the foreign currency price corresponding to the currency type of the money image to be identified;
calculating the RMB value corresponding to the money image to be identified according to the face value and the foreign currency price of the money image to be identified;
and displaying the standard coin image corresponding to the coin image to be identified and the corresponding RMB value in a front-end display page.
The redeemable website recommending method comprises the following steps:
acquiring the positioning information of the mobile terminal for acquiring the coin image to be identified;
calling an electronic map, and inquiring exchange site position information in a preset area corresponding to the positioning information, such as exchange sites within a range of 2 kilometers away from the mobile terminal, wherein the exchange sites are exchange sites of currency types of the money images to be identified;
and displaying the position information of the exchange points on a front-end display interface in an unlimited display mode, such as displaying in a map mode, displaying in a list mode and the like.
In conclusion, by combining foreign currency introduction and foreign currency price quotation, foreign currency knowledge can be popularized for users, various foreign currency functions can be recommended, the network node is guided, the network node traffic is improved, and the user viscosity is increased.
Based on the method for identifying foreign currency disclosed in the above embodiments, the present embodiment correspondingly discloses a foreign currency identification apparatus, please refer to fig. 5, which includes:
a coin image acquiring unit 501, configured to acquire a coin image to be identified;
the foreign currency recognition unit 502 is configured to input the money image to be recognized into an input layer of a foreign currency recognition model, the image output by the input layer is subjected to multiple rounds of preset processing, and then subjected to feature classification processing of a full connection layer to obtain a currency type, a version and a face value of the money image to be recognized, wherein the size of the input image corresponding to the input layer of the foreign currency recognition model is matched with the size of the foreign currency, the preset processing includes feature extraction processing of convolution, feature reduction processing of a pooling layer and feature normalization processing of a normalization layer, the total number of convolution layers in the foreign currency recognition model is smaller than that of the convolution layers in the VGG-16 model, and the number of extracted features of each convolution layer in the foreign currency recognition model is smaller than that of the corresponding convolution layer in the VGG-16 model.
Optionally, the coin image obtaining unit 501 includes:
an original image acquisition subunit, configured to acquire an original image;
the image preprocessing subunit is used for preprocessing the original image to obtain a plurality of images to be identified which accord with a preset format;
and the coin identification subunit is used for respectively inputting each image to be identified into a coin identification model for processing, and determining whether each image to be identified is a coin image to be identified according to an identification result.
Optionally, the image preprocessing subunit is specifically configured to:
randomly rotating the angle of the original image for multiple times to obtain multiple images;
and respectively adjusting the brightness of each image to a preset brightness value, and converting the color space of each image into HSV (hue, saturation, value) to obtain a plurality of images to be identified.
Optionally, the apparatus further includes a model training unit, specifically configured to:
acquiring images of various foreign currencies;
adjusting the brightness of each type of foreign currency image to a preset brightness value, and converting the color space of each type of foreign currency image into HSV (hue, saturation and value) to obtain each type of preprocessed foreign currency image;
carrying out classification labeling and data enhancement on various preprocessed foreign currency images to obtain a training sample set;
and training a preset neural network model by using the training sample set to obtain the foreign currency recognition model, wherein the total number of the convolutional layers in the preset neural network is less than that of the convolutional layers in the VGG-16 model, and the number of the extracted features of each convolutional layer in the preset neural network model is less than that of the extracted features of the corresponding convolutional layer in the VGG-16 model.
Optionally, the apparatus further includes a foreign currency value calculating unit, specifically configured to:
inquiring the foreign currency price corresponding to the currency type of the money image to be identified;
calculating the RMB value corresponding to the money image to be identified according to the face value and the foreign currency price of the money image to be identified;
and displaying the standard coin image corresponding to the coin image to be identified and the corresponding RMB value in a front-end display page.
Optionally, the apparatus further includes a website recommending unit, specifically configured to:
acquiring the positioning information of the mobile terminal for acquiring the coin image to be identified;
calling an electronic map, and inquiring exchange site position information in a preset area corresponding to the positioning information, wherein the exchange site is an exchange site of the currency of the money image to be identified;
and displaying the position information of the exchange points on a front-end display interface.
In the foreign currency recognition device provided by this embodiment, the foreign currency recognition model is obtained by training the improved VGG-16 model, the size of the input image of the input layer of the foreign currency recognition model matches with the size of the foreign currency, the image of the foreign currency to be recognized does not need to be stretched or intercepted, so that the model is more suitable for recognizing the foreign currency, the total number of the convolution layers of the foreign currency recognition model is smaller than that of the VGG-16 model, the number of the extracted features of each convolution layer is smaller than that of the corresponding convolution layer in the VGG-16 model, excessive feature extraction cannot be performed on the image of the foreign currency to be recognized, so that the features input to the full connection layer are low-layer features representing detailed textures and the like, the analysis of the model on the high-layer semantic features of the image is reduced, the occurrence of the over-layer phenomenon is avoided to a certain extent, and the normalization layer is added after the pool, the characteristics are normalized, the phenomenon of overfitting is avoided to a certain extent, the influence of overfitting on a model processing result is further avoided, and therefore the accuracy of the foreign currency recognition model in recognizing the foreign currency images is improved.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A foreign currency identification method, comprising:
acquiring a money image to be identified;
the method comprises the steps of inputting a money image to be recognized into an input layer in a foreign money recognition model, obtaining currency, version and face value of the money image to be recognized through multi-round preset processing and feature classification processing of a full connection layer, wherein the size of the input image corresponding to the input layer of the foreign money recognition model is matched with the size of a foreign money, the preset processing comprises feature extraction processing of a convolution layer group, feature reduction processing of a pooling layer and feature normalization processing of a normalization layer, the total number of convolution layers in the foreign money recognition model is smaller than that of a VGG-16 model, and the number of extracted features of each convolution layer in the foreign money recognition model is smaller than that of the corresponding convolution layer in the VGG-16 model.
2. The method of claim 1, wherein the acquiring of the image of the money item to be recognized comprises:
acquiring an original image;
preprocessing the original image to obtain a plurality of images to be identified which accord with a preset format;
and respectively inputting each image to be recognized into a coin recognition model for processing, and determining whether each image to be recognized is a coin image to be recognized according to a recognition result.
3. The method according to claim 2, wherein the preprocessing the original image to obtain a plurality of images to be recognized conforming to a preset format comprises:
randomly rotating the angle of the original image for multiple times to obtain multiple images;
and respectively adjusting the brightness of each image to a preset brightness value, and converting the color space of each image into HSV (hue, saturation, value) to obtain a plurality of images to be identified.
4. The method of claim 1, wherein the training method of the foreign currency recognition model comprises:
acquiring images of various foreign currencies;
adjusting the brightness of each type of foreign currency image to a preset brightness value, and converting the color space of each type of foreign currency image into HSV (hue, saturation and value) to obtain each type of preprocessed foreign currency image;
carrying out classification labeling and data enhancement on various preprocessed foreign currency images to obtain a training sample set;
and training a preset neural network model by using the training sample set to obtain the foreign currency recognition model, wherein the total number of the convolutional layers in the preset neural network is less than that of the convolutional layers in the VGG-16 model, and the number of the extracted features of each convolutional layer in the preset neural network model is less than that of the extracted features of the corresponding convolutional layer in the VGG-16 model.
5. The method of claim 1, wherein after obtaining the denomination, layout and face value of the money item image to be recognized, the method further comprises:
inquiring the foreign currency price corresponding to the currency type of the money image to be identified;
calculating the RMB value corresponding to the money image to be identified according to the face value and the foreign currency price of the money image to be identified;
and displaying the standard coin image corresponding to the coin image to be identified and the corresponding RMB value in a front-end display page.
6. The method of claim 1, wherein after obtaining the denomination, layout and face value of the money item image to be recognized, the method further comprises:
acquiring the positioning information of the mobile terminal for acquiring the coin image to be identified;
calling an electronic map, and inquiring exchange site position information in a preset area corresponding to the positioning information, wherein the exchange site is an exchange site of the currency of the money image to be identified;
and displaying the position information of the exchange points on a front-end display interface.
7. A foreign currency identification apparatus, comprising:
the coin image acquisition unit is used for acquiring a coin image to be identified;
the foreign currency recognition unit is used for inputting the money image to be recognized into an input layer in a foreign currency recognition model, the image output by the input layer is subjected to multi-round preset processing and then subjected to feature classification processing of a full connection layer to obtain the currency type, version and face value of the money image to be recognized, wherein the size of the input image corresponding to the input layer of the foreign currency recognition model is matched with the size of the foreign currency, the preset processing comprises feature extraction processing of a convolution layer, feature reduction processing of a pooling layer and feature normalization processing of a normalization layer, the total number of the convolution layers in the foreign currency recognition model is smaller than that of the convolution layers in the VGG-16 model, and the number of the extracted features of each convolution layer in the foreign currency recognition model is smaller than that of the corresponding convolution layer in the VGG-16 model.
8. The apparatus of claim 7, wherein the money item image obtaining unit comprises:
an original image acquisition subunit, configured to acquire an original image;
the image preprocessing subunit is used for preprocessing the original image to obtain a plurality of images to be identified which accord with a preset format;
and the coin identification subunit is used for respectively inputting each image to be identified into a coin identification model for processing, and determining whether each image to be identified is a coin image to be identified according to an identification result.
9. The apparatus according to claim 8, wherein the image preprocessing subunit is specifically configured to:
randomly rotating the angle of the original image for multiple times to obtain multiple images;
and respectively adjusting the brightness of each image to a preset brightness value, and converting the color space of each image into HSV (hue, saturation, value) to obtain a plurality of images to be identified.
10. The apparatus according to claim 7, further comprising a model training unit, in particular for:
acquiring images of various foreign currencies;
adjusting the brightness of each type of foreign currency image to a preset brightness value, and converting the color space of each type of foreign currency image into HSV (hue, saturation and value) to obtain each type of preprocessed foreign currency image;
carrying out classification labeling and data enhancement on various preprocessed foreign currency images to obtain a training sample set;
and training a preset neural network model by using the training sample set to obtain the foreign currency recognition model, wherein the total number of the convolutional layers in the preset neural network is less than that of the convolutional layers in the VGG-16 model, and the number of the extracted features of each convolutional layer in the preset neural network model is less than that of the extracted features of the corresponding convolutional layer in the VGG-16 model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010360620.1A CN111553430B (en) | 2020-04-30 | 2020-04-30 | Foreign currency identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010360620.1A CN111553430B (en) | 2020-04-30 | 2020-04-30 | Foreign currency identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111553430A true CN111553430A (en) | 2020-08-18 |
| CN111553430B CN111553430B (en) | 2023-08-18 |
Family
ID=72007971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010360620.1A Active CN111553430B (en) | 2020-04-30 | 2020-04-30 | Foreign currency identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111553430B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112132073A (en) * | 2020-09-28 | 2020-12-25 | 中国银行股份有限公司 | Garbage classification method and device, storage medium and electronic equipment |
| CN116912721A (en) * | 2023-09-14 | 2023-10-20 | 众芯汉创(江苏)科技有限公司 | Power distribution network equipment body identification method and system based on monocular stereoscopic vision |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160121370A1 (en) * | 2013-07-11 | 2016-05-05 | Grg Banking Equipment Co., Ltd. | Banknote recognition and classification method and system |
| CN107341916A (en) * | 2017-07-12 | 2017-11-10 | 深圳怡化电脑股份有限公司 | A kind of discrimination method and identification device |
| CN108734850A (en) * | 2018-04-27 | 2018-11-02 | 深圳怡化电脑股份有限公司 | Paper Currency Identification, paper money identifier and terminal device |
| CN109753978A (en) * | 2017-11-01 | 2019-05-14 | 腾讯科技（深圳）有限公司 | Image classification method, device and computer readable storage medium |
-
2020
- 2020-04-30 CN CN202010360620.1A patent/CN111553430B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160121370A1 (en) * | 2013-07-11 | 2016-05-05 | Grg Banking Equipment Co., Ltd. | Banknote recognition and classification method and system |
| CN107341916A (en) * | 2017-07-12 | 2017-11-10 | 深圳怡化电脑股份有限公司 | A kind of discrimination method and identification device |
| CN109753978A (en) * | 2017-11-01 | 2019-05-14 | 腾讯科技（深圳）有限公司 | Image classification method, device and computer readable storage medium |
| CN108734850A (en) * | 2018-04-27 | 2018-11-02 | 深圳怡化电脑股份有限公司 | Paper Currency Identification, paper money identifier and terminal device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112132073A (en) * | 2020-09-28 | 2020-12-25 | 中国银行股份有限公司 | Garbage classification method and device, storage medium and electronic equipment |
| CN112132073B (en) * | 2020-09-28 | 2024-03-29 | 中国银行股份有限公司 | Garbage classification method and device, storage medium and electronic equipment |
| CN116912721A (en) * | 2023-09-14 | 2023-10-20 | 众芯汉创(江苏)科技有限公司 | Power distribution network equipment body identification method and system based on monocular stereoscopic vision |
| CN116912721B (en) * | 2023-09-14 | 2023-12-05 | 众芯汉创(江苏)科技有限公司 | Power distribution network equipment body identification method and system based on monocular stereoscopic vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111553430B (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105118048B (en) | The recognition methods of reproduction certificate picture and device | |
| WO2020056980A1 (en) | Service guiding method and apparatus based on human facial recognition, and storage medium | |
| JP5427859B2 (en) | System for image capture and identification | |
| CN110166438B (en) | Account information login method and device, computer equipment and computer storage medium | |
| US20160086019A1 (en) | Method, system and computer program for identification and sharing of digital images with face signatures | |
| WO2019148729A1 (en) | Luxury goods identification method, electronic device, and storage medium | |
| WO2016131083A1 (en) | Identity verification. method and system for online users | |
| CN111696080B (en) | Face fraud detection method, system and storage medium based on static texture | |
| CN111553430B (en) | Foreign currency identification method and device | |
| CN110796054B (en) | Certificate verification method and device | |
| CN112464803A (en) | Image comparison method and device | |
| KR102441562B1 (en) | Smart vending machine with AI-based adult authentication function | |
| CN113111880A (en) | Certificate image correction method and device, electronic equipment and storage medium | |
| CN113642639B (en) | Living body detection method, living body detection device, living body detection equipment and storage medium | |
| CN108090728B (en) | Express information input method and system based on intelligent terminal | |
| CN111339884B (en) | Image recognition method, related device and apparatus | |
| CN115983873B (en) | User data analysis management system and method based on big data | |
| CN111402027B (en) | Identity recognition method, commodity loan auditing method, device and terminal equipment | |
| CN116798041A (en) | Image recognition method and device and electronic equipment | |
| CN114612995A (en) | Face feature recognition method and device | |
| WO2022006829A1 (en) | Bill image recognition method and system, electronic device, and storage medium | |
| CN112215076B (en) | Deep handwriting identification method and device based on double-tower network | |
| CN116171462A (en) | Object sequence identification method, network training method, device, equipment and medium | |
| CN111213157A (en) | Express information input method and system based on intelligent terminal | |
| CN114358943A (en) | Online bill processing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |