Intelligent weighing display terminal recognition system and method based on image recognition

Abstract

The invention discloses an intelligent weighing display terminal recognition system based on image recognition, and the system comprises an image collection module which is used for collecting an image displayed by a display module, and transmitting the collected image to a recognition terminal module through a control module; the recognition terminal module is used for receiving the image, performing optical recognition on the image by adopting a recognition algorithm and an algorithm trained by an improved neural network model, extracting text information and formatting a result, and obtaining a recognition result after recognition is completed; the report generation module is used for generating a data report according to the identification result, storing the data report in a specified directory and informing a user through the interface module; and the user interaction interface module provides a user operation entrance and a feedback interface, is used for displaying the data report generated by the report generation module, and is also used for displaying a task state, a generation result or error information. The method has the advantages that the report can be synchronously generated, and automatic processing and management of data are realized.

Description

Technical Field

[0001] This invention relates to the field of weighing technology, and in particular to an intelligent weighing display terminal identification system and method based on image recognition. Background Technology

[0002] The description in this section provides only background information related to the disclosure of this invention and does not constitute prior art.

[0003] Currently, traditional weighing systems rely heavily on manual operation, which is not only inefficient but also prone to human error. With the development of intelligent technology, electronic scales are indispensable in supermarkets, using weighing sensors to weigh items. However, the combination of image recognition and intelligent weighing cannot yet generate Excel reports simultaneously.

[0004] It should be noted that the above description of the technical background is only for the purpose of providing a clear and complete explanation of the technical solutions of the present invention and facilitating understanding by those skilled in the art. It should not be assumed that the above technical solutions are known to those skilled in the art simply because they have been described in the background section of this invention. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide an intelligent weighing display terminal identification system and method based on image recognition, which addresses the shortcomings of the prior art.

[0006] This application discloses an intelligent weighing display terminal identification system based on image recognition, wherein an item to be weighed is placed on the weighing platform, including:

[0007] A weighing module and a display module, wherein the weighing module is used to acquire item data of the item to be weighed;

[0008] The control module transmits the item data from the weighing module to the display module;

[0009] The image acquisition module is used to acquire the image displayed by the display module and transmit the acquired image to the recognition terminal module through the control module;

[0010] The terminal module is used to receive the image, perform OCR recognition on the image using an OCR recognition algorithm and an algorithm trained with an improved LeNet neural network model, extract text information and format the result, and obtain the recognition result after the recognition is completed.

[0011] The report generation module generates a data report based on the recognition results, saves the data report to a specified directory, and notifies the user through the interface module.

[0012] The user interaction interface module provides user operation entry and feedback interface, which is used to display data reports generated by the report generation module, and also to display task status, generation results or error information.

[0013] Furthermore, in the aforementioned intelligent weighing display terminal recognition system based on image recognition, the recognition terminal module extracts text information from the image, specifically including:

[0014] The image is detected, and text regions containing text are identified within the image;

[0015] The detected text region is classified by direction, and the direction category is output. If direction classification is enabled, the text region will be rotated and corrected.

[0016] Each text region is detected, and the pixel information of the text region is converted into a character sequence;

[0017] The identified character sequence is matched against a character set. If the identified character is not in the character set, it will be filtered or replaced with the closest legal character.

[0018] Multiple text regions can be processed simultaneously using multithreading.

[0019] The recognition results for each text region are arranged in the detection order, and the final recognized text information is output.

[0020] Furthermore, in the aforementioned image recognition-based intelligent weighing display terminal recognition system, the recognition terminal module's process for recognizing custom characters is as follows:

[0021] Input data, which may be an image path, an image string, or an image byte stream;

[0022] Image preprocessing involves converting a color image to a grayscale image, smoothing the image using a Gaussian filter, and then converting the grayscale image back to a black and white image.

[0023] Contour detection and filtering: Find contours in the black and white image, and filter out irrelevant contours based on area and aspect ratio;

[0024] Morphological operations connect adjacent contours through morphological dilation;

[0025] The outline sorting and clipping involves sorting the outlines from left to right and clipping each outline.

[0026] Adjust the cropped digital area to a fixed size and normalize it;

[0027] The ONNX model is used to predict and identify numbers or characters in the processed image.

[0028] Combine all the identified characters into a string and output the final recognition result.

[0029] Furthermore, the improved LeNet neural network model of the aforementioned image recognition-based intelligent weighing display terminal identification system includes a first convolutional layer, a second convolutional layer, a third convolutional layer, a first fully connected layer, a second fully connected layer, and a third fully connected layer.

[0030] Furthermore, in the aforementioned image recognition-based intelligent weighing display terminal identification system, the improved LeNet neural network model uses ReLU as the activation function, with a convolution kernel size of 3x3 and padding of 1.

[0031] Furthermore, in the aforementioned image recognition-based intelligent weighing display terminal identification system, the item data includes the item name, item number, item price, and corresponding weighing time and weight.

[0032] Furthermore, the aforementioned intelligent weighing display terminal identification system based on image recognition also includes a cloud server, and the control module uploads the data report to the cloud server.

[0033] This application embodiment also provides an identification method for the image recognition-based intelligent weighing display terminal identification system as described above, including the following steps:

[0034] The item to be weighed is placed on the weighing platform, and the weighing module obtains the item data.

[0035] The control module transmits the item data from the weighing module to the display module;

[0036] The image acquisition module acquires the image displayed by the display module and transmits the acquired image to the recognition terminal module through the control module;

[0037] The recognition terminal module receives the image, performs OCR recognition on the image using an OCR recognition algorithm and an algorithm trained with an improved LeNet neural network model, extracts text information and formats the result, and obtains the recognition result after the recognition is completed;

[0038] The report generation module generates a data report based on the recognition results, saves the data report to a specified directory, and notifies the user through the user interaction interface module.

[0039] The user interface module provides user operation entry and feedback interface, and displays the data reports generated by the report generation module.

[0040] In summary, the structure adopted in the embodiments of the present invention has the following advantages:

[0041] The intelligent weighing display terminal identification system based on image recognition described in this invention captures information displayed on the LED screen of the electronic scale in real time using a USB camera. Simultaneously, the system can generate Excel reports containing multi-dimensional information such as weighing time, serial number, and accuracy using a custom Excel template. The report data can be synchronized to a cloud data system in real time, facilitating data analysis and decision-making for managers. The system achieves automated data processing and management by simultaneously generating Excel reports. The weighing accuracy reaches over 99%, and the report generation speed is extremely fast, improving the weighing efficiency and data processing capabilities of the production line. With its high weighing accuracy, fast report generation speed, and ease of operation, this system can be widely used in production workshops, warehousing, and other fields, possessing broad market prospects and application value.

[0042] To further understand the features and technical content of the present invention, please refer to the following detailed description and drawings of the present invention. However, the drawings provided are for reference and illustration only and are not intended to limit the present invention. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a schematic diagram of an intelligent weighing display terminal identification system based on image recognition in an embodiment of the present invention;

[0045] Figure 2 This is a schematic diagram of the intelligent weighing display terminal identification method based on image recognition in an embodiment of the present invention. Detailed Implementation

[0046] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0047] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can understand the advantages and effects of the present invention from the content disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the concept of the present invention. Furthermore, the accompanying drawings of the present invention are for simple illustrative purposes only and are not depictions of actual dimensions; this is stated in advance. The following embodiments will further describe the relevant technical content of the present invention in detail, but the disclosed content is not intended to limit the scope of protection of the present invention.

[0048] It should be understood that while terms such as "first," "second," and "third" may be used in this document to describe various components or signals, these components or signals should not be limited by these terms. These terms are primarily used to distinguish one component from another, or one signal from another. Furthermore, the term "or" as used herein should, as appropriate, include any combination of one or more of the related listed items.

[0049] Reference Figures 1 to 2 As shown in the figure, this application discloses an intelligent weighing display terminal identification system based on image recognition, wherein an item to be weighed is placed on the weighing platform, including:

[0050] A weighing module and a display module, wherein the weighing module is used to acquire item data of the item to be weighed;

[0051] The control module transmits the item data from the weighing module to the display module;

[0052] The image acquisition module is used to acquire the image displayed by the display module and transmit the acquired image to the recognition terminal module through the control module;

[0053] The terminal module is used to receive the image, perform OCR recognition on the image using an OCR recognition algorithm and an algorithm trained with an improved LeNet neural network model, extract text information and format the result, and obtain the recognition result after the recognition is completed.

[0054] The report generation module generates a data report based on the recognition results, saves the data report to a specified directory, and notifies the user through the interface module.

[0055] The user interface module provides user access and feedback, displaying data reports generated by the report generation module, as well as task status, generation results, and error messages. The user interface module offers a simple and intuitive interface, facilitating system settings, report export, and other operations. The interface design conforms to ergonomic principles, making it easy and user-friendly.

[0056] Using the above system, items to be weighed are placed on the weighing platform. The weighing module inside the platform acquires the weight information of the items placed on the weighing unit and transmits the acquired weight information to the intelligent analysis module. When an item to be weighed is detected on the weighing unit, the weighing module sends a drive signal to the image acquisition module. The image acquisition module uses a camera module (such as a tilted camera or a USB camera), which does not require high-definition configuration. Based on the received drive signal, the image acquisition module acquires an image of the item to be weighed placed on the weighing platform and transmits the acquired image to the recognition terminal module. The recognition terminal module uses an offline OCR (Optical Character Recognition) algorithm and a recognition algorithm trained by an improved LeNet neural network model. It can quickly read the readings of the display module and determine whether there is a discrepancy, assisting production line personnel in their production work. The report generation module acquires the OCR data and, based on the template type selected by the user, can automatically generate a report containing multi-dimensional information such as weighing time, weight, and identity information, based on the weighing data and recognition results. The system generates report files using the Excel method, saves the files to a specified directory, and notifies the user through the user interface module. The report format is standardized and the data is accurate, facilitating subsequent data analysis and management. The system boasts high weighing accuracy, fast report generation speed, and simple operation, and can be widely used in production workshops, warehousing, and other fields, with broad market prospects and application value.

[0057] Specifically, in this embodiment, the recognition terminal module extracts text information from the image, including:

[0058] The image is detected, and text regions containing text are identified within the image;

[0059] The detected text region is classified by direction, and the direction category is output. If direction classification is enabled, the text region will be rotated and corrected.

[0060] Each text region is detected, and the pixel information of the text region is converted into a character sequence;

[0061] The identified character sequence is matched against a character set. If the identified character is not in the character set, it will be filtered or replaced with the closest legal character.

[0062] Multiple text regions can be processed simultaneously using multithreading.

[0063] The recognition results for each text region are arranged in the detection order, and the final recognized text information is output.

[0064] Specifically, in this embodiment, the process of recognizing custom characters by the recognition terminal module is as follows:

[0065] Input data, which may be an image path, an image string, or an image byte stream;

[0066] Image preprocessing involves converting a color image to a grayscale image, smoothing the image using a Gaussian filter, and then converting the grayscale image back to a black and white image.

[0067] Contour detection and filtering: Find contours in the black and white image, and filter out irrelevant contours based on area and aspect ratio;

[0068] Morphological operations connect adjacent contours through morphological dilation;

[0069] The outline sorting and clipping involves sorting the outlines from left to right and clipping each outline.

[0070] Adjust the cropped digital area to a fixed size and normalize it;

[0071] The ONNX model is used to predict and identify numbers or characters in the processed image.

[0072] Combine all the identified characters into a string and output the final recognition result.

[0073] Specifically, in this embodiment, the improved LeNet neural network model includes a first convolutional layer, a second convolutional layer, a third convolutional layer, a first fully connected layer, a second fully connected layer, and a third fully connected layer.

[0074] Specifically, in this embodiment, the improved LeNet neural network model uses ReLU as the activation function, a 3x3 kernel size, and padding of 1.

[0075] Specifically, in this embodiment, the item data includes the item name, item number, item price, and corresponding weighing time and weight.

[0076] Specifically, in this embodiment, a cloud server is also included, and the control module uploads the data report to the cloud server.

[0077] This embodiment also provides a recognition method for the image recognition-based intelligent weighing display terminal recognition system as described above, including the following steps:

[0078] The item to be weighed is placed on the weighing platform, and the weighing module obtains the item data.

[0079] The control module transmits the item data from the weighing module to the display module;

[0080] The image acquisition module acquires the image displayed by the display module and transmits the acquired image to the recognition terminal module through the control module;

[0081] The recognition terminal module receives the image, performs OCR recognition on the image using an OCR recognition algorithm and an algorithm trained with an improved LeNet neural network model, extracts text information and formats the result, and obtains the recognition result after the recognition is completed;

[0082] The report generation module generates a data report based on the recognition results, saves the data report to a specified directory, and notifies the user through the user interaction interface module.

[0083] The user interface module provides user operation entry and feedback interface, and displays the data reports generated by the report generation module.

[0084] Using the above method, this intelligent weighing display and recognition system captures real-time information from the electronic scale's LED display via a USB camera. Simultaneously, the system can generate Excel reports containing multi-dimensional information such as weighing time, serial number, and accuracy using a custom Excel template. The report data can be synchronized to a cloud data system in real time, facilitating data analysis and decision-making for managers. The system achieves automated data processing and management by simultaneously generating Excel reports. With a weighing accuracy exceeding 99% and extremely fast report generation speed, the system improves the weighing efficiency and data processing capabilities of the production line. This system, characterized by high weighing accuracy, fast report generation, and ease of operation, can be widely used in production workshops, warehousing, and other fields, possessing broad market prospects and application value.

[0085] The content disclosed above is only a preferred and feasible embodiment of the present invention, and is not intended to limit the scope of the patent application of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention specification and drawings are included in the scope of the patent application of the present invention.

[0086] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0087] Although this application has been described by way of examples, those skilled in the art will know that this application has many modifications and variations without departing from the spirit of this application, and it is intended that the appended embodiments include these modifications and variations without departing from this application.

Claims

1. An intelligent weighing display terminal identification system based on image recognition, characterized in that, Items to be weighed are placed on the weighing platform, including: A weighing module and a display module, wherein the weighing module is used to acquire item data of the item to be weighed; The control module transmits the item data from the weighing module to the display module; The image acquisition module is used to acquire the image displayed by the display module and transmit the acquired image to the recognition terminal module through the control module; The terminal module is used to receive the image, perform OCR recognition on the image using an OCR recognition algorithm and an algorithm trained with an improved LeNet neural network model, extract text information and format the result, and obtain the recognition result after the recognition is completed. The report generation module generates a data report based on the recognition results, saves the data report to a specified directory, and notifies the user through the interface module. The user interaction interface module provides user operation entry and feedback interface, which is used to display data reports generated by the report generation module, and also to display task status, generation results or error information.

2. The intelligent weighing display terminal identification system based on image recognition according to claim 1, characterized in that, The recognition terminal module extracts text information from the image, specifically including: The image is detected, and text regions containing text are identified within the image; The detected text region is classified by direction, and the direction category is output. If direction classification is enabled, the text region will be rotated and corrected. Each text region is detected, and the pixel information of the text region is converted into a character sequence; The identified character sequence is matched against a character set. If the identified character is not in the character set, it will be filtered or replaced with the closest legal character. Multiple text regions can be processed simultaneously using multithreading. The recognition results for each text region are arranged in the detection order, and the final recognized text information is output.

3. The intelligent weighing display terminal identification system based on image recognition according to claim 2, characterized in that, The process by which the recognition terminal module recognizes custom characters is as follows: Input data, which may be an image path, an image string, or an image byte stream; Image preprocessing involves converting a color image to a grayscale image, smoothing the image using a Gaussian filter, and then converting the grayscale image back to a black and white image. Contour detection and filtering: Find contours in the black and white image, and filter out irrelevant contours based on area and aspect ratio; Morphological operations connect adjacent contours through morphological dilation; The outline sorting and clipping involves sorting the outlines from left to right and clipping each outline. Adjust the cropped digital area to a fixed size and normalize it; The ONNX model is used to predict and identify numbers or characters in the processed image. Combine all the identified characters into a string and output the final recognition result.

4. The intelligent weighing display terminal identification system based on image recognition according to claim 1, characterized in that, The improved LeNet neural network model includes a first convolutional layer, a second convolutional layer, a third convolutional layer, a first fully connected layer, a second fully connected layer, and a third fully connected layer.

5. The intelligent weighing display terminal identification system based on image recognition according to claim 1, characterized in that, The improved LeNet neural network model uses ReLU as the activation function, with a 3x3 kernel size and padding of 1.

6. The intelligent weighing display terminal identification system based on image recognition according to claim 1, characterized in that, The item data includes the item name, item number, item price, and corresponding weighing time and weight.

7. The intelligent weighing display terminal identification system based on image recognition according to claim 1, characterized in that, It also includes a cloud server, to which the control module uploads the data reports.

8. A recognition method for an intelligent weighing display terminal recognition system based on image recognition as described in any one of claims 1 to 7, characterized in that, Includes the following steps: The item to be weighed is placed on the weighing platform, and the weighing module obtains the item data. The control module transmits the item data from the weighing module to the display module; The image acquisition module acquires the image displayed by the display module and transmits the acquired image to the recognition terminal module through the control module; The recognition terminal module receives the image, performs OCR recognition on the image using an OCR recognition algorithm and an algorithm trained with an improved LeNet neural network model, extracts text information and formats the result, and obtains the recognition result after the recognition is completed; The report generation module generates a data report based on the recognition results, saves the data report to a specified directory, and notifies the user through the user interaction interface module. The user interface module provides user operation entry and feedback interface, and displays the data reports generated by the report generation module.

Images