Data analysis system using image processing mode of file format

Abstract

The present invention relates to a data analysis system using an image processing mode in a file format, comprising: an information judgment mechanism, which uses a deep feedforward network model to intelligently judge multiple processing sequence numbers based on multiple processing names corresponding to multiple known image processing, the number of pixel rows of the processed image, the number of pixel columns of the processed image, the data stream in the BMP image file format corresponding to the unprocessed image, and the data stream in the BMP image file format corresponding to the processed image; and a mode publishing mechanism, which sends the multiple processing sequence numbers to a cloud computing server. The data analysis system using an image processing mode in a file format of the present invention has compact logic and wide application. Since a deep feedforward network model can be used to intelligently judge multiple processing sequence numbers corresponding to multiple image processing according to each basic information, it helps the image processing end to clarify the image processing sequence when multiple image processing is known but the specific processing sequence is unknown.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to a data analysis system using an image processing mode in a file format. Background Art

[0002] Extracting some useful measurements, data or information from an image is called image analysis. The basic steps of image analysis are to divide the image into some non-overlapping regions, each of which is a continuous set of pixels, measure their properties and relationships, and finally compare the obtained image relationship structure with the model describing the classification of scenes to determine its type. The basis of recognition or classification is the similarity of images. A simple similarity can be defined by the distance in the regional feature space. Another similarity measure based on pixel values ​​is the correlation of image functions. The last similarity defined on the relationship structure is called structural similarity.

[0003] However, the current technical problem encountered in image processing is that when the image signal undergoes multiple known image processing steps, it is impossible to use technical means to obtain the specific processing order of the multiple image processing steps, and thus it is impossible to help the image processing end clarify the image processing order, making it difficult to provide effective information for the prediction and analysis of the subsequent image processing effects. Summary of the invention

[0004] In order to overcome the technical problems in the prior art, the present invention proposes a data parsing system using an image processing mode in a file format, which uses a deep feedforward network model to intelligently determine multiple processing sequence numbers corresponding to multiple image processings based on multiple processing names corresponding to multiple known image processings, the number of pixel rows of the processed image, the number of pixel columns of the processed image, the data stream in the BMP image file format corresponding to the unprocessed image, and the data stream in the BMP image file format corresponding to the processed image. In this way, when multiple image processings are known but the specific processing sequence is unknown, the image processing end is helped to clarify the image processing sequence, so as to predict the effect of subsequent image processing. The invention provides effective information for judgment and analysis, wherein the adopted deep feedforward network model is a purposefully designed structure, wherein the deep feedforward network is subjected to training processing for each time to obtain the deep feedforward network after each training processing and used as the deep feedforward network model, the number of training processing of the deep feedforward network is positively correlated with the data volume of the unprocessed image, and the unprocessed image is converted into a data stream in the BMP image file format, and the processed image is converted into a data stream in the BMP image file format, and the unprocessed image is subjected to multiple known image processing types to obtain the processed image, thereby providing reliable basic data for intelligent judgment of the processing order of executing multiple known image processing types.

[0005] According to the present invention, there is provided a data parsing system using an image processing mode in a file format, the system comprising:

[0006] A data conversion device, used to convert an unprocessed image into a data stream in a BMP image file format, and to convert a processed image into a data stream in a BMP image file format, wherein the unprocessed image is subjected to a plurality of known image processing types to obtain the processed image;

[0007] Establishing devices one by one, for performing training processing on the deep feedforward network for each time, obtaining the deep feedforward network after each training processing and outputting it as a deep feedforward network model, wherein the number of training processing of the deep feedforward network is positively correlated with the amount of data of the unprocessed image;

[0008] An information judgment mechanism is connected to the successive establishment device and the data conversion device, respectively, and is used to use a deep feedforward network model to intelligently judge multiple processing sequence numbers corresponding to multiple image processings based on multiple processing names corresponding to the known multiple image processings, the number of pixel rows of the processed image, the number of pixel columns of the processed image, the data stream in the BMP image file format corresponding to the unprocessed image, and the data stream in the BMP image file format corresponding to the processed image;

[0009] Wherein, a deep feedforward network model is used to intelligently determine the multiple processing sequence numbers corresponding to the multiple image processings based on the multiple processing names corresponding to the multiple image processings, the number of pixel rows of the processed image, the number of pixel columns of the processed image, the data stream in the BMP image file format corresponding to the unprocessed image, and the data stream in the BMP image file format corresponding to the processed image. The multiple processing sequence numbers include: the larger the value of the processing sequence number, the later the processing order of the corresponding image processing;

[0010] The steps of converting the unprocessed image into a data stream in a BMP image file format, converting the processed image into a data stream in a BMP image file format, and obtaining the processed image by subjecting the unprocessed image to a plurality of known image processing types include: the resolution of the unprocessed image and the processed image are equal;

[0011] Wherein, establishing devices one by one for performing training processing on the deep feedforward network for each time to obtain the deep feedforward network after each training processing and outputting it as the deep feedforward network model, wherein the number of training processing of the deep feedforward network is positively correlated with the data amount of the unprocessed image, comprises: using an information mapping formula to represent the information mapping relationship of the positive correlation between the number of training processing of the deep feedforward network and the data amount of the unprocessed image;

[0012] Among them, the information mapping relationship that uses the information mapping formula to express the positive correlation between the number of times the deep feedforward network is trained and the amount of data of the unprocessed image includes: in the information mapping formula, the amount of data of the unprocessed image is the input parameter of the information mapping formula, and the number of times the deep feedforward network is trained is the output parameter of the information mapping formula.

[0013] It can be seen that the present invention has at least the following three important inventive features:

[0014] First: A deep feedforward network model is used to intelligently determine the multiple processing sequence numbers corresponding to the multiple image processings based on the multiple processing names corresponding to the known multiple image processings, the number of pixel rows of the processed image, the number of pixel columns of the processed image, the data stream in the BMP image file format corresponding to the unprocessed image, and the data stream in the BMP image file format corresponding to the processed image. In this way, when the multiple image processings are known but the specific processing sequence is unknown, the image processing end is helped to clarify the image processing sequence, providing effective information for the prediction and analysis of the subsequent image processing effects.

[0015] Second: the deep feedforward network model used is a purposefully designed structure, wherein the deep feedforward network is trained for each time to obtain a deep feedforward network after each training process and used as a deep feedforward network model, and the number of times the deep feedforward network is trained is positively correlated with the amount of data of the unprocessed image;

[0016] The third one: converting the unprocessed image into a data stream in the BMP image file format, converting the processed image into a data stream in the BMP image file format, and obtaining the processed image by subjecting the unprocessed image to multiple known image processing types, thereby providing reliable basic data for intelligent judgment of the processing order of executing multiple known image processing types.

[0017] The data analysis system of the image processing mode using the file format of the present invention has compact logic and wide application. Since a deep feedforward network model can be used to intelligently determine the multiple processing sequence numbers corresponding to multiple image processings according to each basic information, it helps the image processing end to clarify the image processing sequence when multiple image processings are known but the specific processing sequence is unknown. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0019] Figure 1 This is a block diagram of the internal structure of a data analysis system using an image processing mode in a file format according to Embodiment 1 of the present invention.

[0020] Figure 2This is a block diagram of the internal structure of a data analysis system using an image processing mode in a file format according to Embodiment 2 of the present invention.

[0021] Figure 3 This is a block diagram of the internal structure of a data analysis system using an image processing mode in a file format according to Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0022] The following will describe in detail an implementation scheme of a data analysis system using an image processing mode in a file format according to the present invention with reference to the accompanying drawings.

[0023] Figure 1 The internal structure block diagram of the data analysis system using the image processing mode of the file format according to the first embodiment of the present invention is shown, and the system includes:

[0024] A data conversion device, used to convert an unprocessed image into a data stream in a BMP image file format, and to convert a processed image into a data stream in a BMP image file format, wherein the unprocessed image is subjected to a plurality of known image processing types to obtain the processed image;

[0025] For example, a data conversion device is used to convert an unprocessed image into a data stream in a BMP image file format, and to convert a processed image into a data stream in a BMP image file format, wherein the unprocessed image is subjected to a plurality of known image processing types to obtain the processed image, including: using a data simulation mode to implement simulation and testing of a data conversion process of converting the unprocessed image into a data stream in a BMP image file format, and converting the processed image into a data stream in a BMP image file format;

[0026] Establishing devices one by one, for performing training processing on the deep feedforward network for each time, obtaining the deep feedforward network after each training processing and outputting it as a deep feedforward network model, wherein the number of training processing of the deep feedforward network is positively correlated with the amount of data of the unprocessed image;

[0027] An information judgment mechanism is connected to the successive establishment device and the data conversion device, respectively, and is used to use a deep feedforward network model to intelligently judge multiple processing sequence numbers corresponding to multiple image processings based on multiple processing names corresponding to the known multiple image processings, the number of pixel rows of the processed image, the number of pixel columns of the processed image, the data stream in the BMP image file format corresponding to the unprocessed image, and the data stream in the BMP image file format corresponding to the processed image;

[0028] A mode issuing mechanism, connected to the information judging mechanism, for sending a plurality of processing sequence numbers corresponding to the received plurality of image processings to a remote cloud computing server via a mobile communication link;

[0029] Wherein, a deep feedforward network model is used to intelligently determine the multiple processing sequence numbers corresponding to the multiple image processings based on the multiple processing names corresponding to the multiple image processings, the number of pixel rows of the processed image, the number of pixel columns of the processed image, the data stream in the BMP image file format corresponding to the unprocessed image, and the data stream in the BMP image file format corresponding to the processed image. The multiple processing sequence numbers include: the larger the value of the processing sequence number, the later the processing order of the corresponding image processing;

[0030] The steps of converting the unprocessed image into a data stream in a BMP image file format, converting the processed image into a data stream in a BMP image file format, and obtaining the processed image by subjecting the unprocessed image to a plurality of known image processing types include: the resolution of the unprocessed image and the processed image are equal;

[0031] Wherein, establishing devices one by one for performing training processing on the deep feedforward network for each time to obtain the deep feedforward network after each training processing and outputting it as the deep feedforward network model, wherein the number of training processing of the deep feedforward network is positively correlated with the data amount of the unprocessed image, comprises: using an information mapping formula to represent the information mapping relationship of the positive correlation between the number of training processing of the deep feedforward network and the data amount of the unprocessed image;

[0032] Among them, the information mapping relationship that uses the information mapping formula to express the positive correlation between the number of times the deep feedforward network is trained and the amount of data of the unprocessed image includes: in the information mapping formula, the amount of data of the unprocessed image is the input parameter of the information mapping formula, and the number of times the deep feedforward network is trained is the output parameter of the information mapping formula.

[0033] Figure 2 This is a block diagram of the internal structure of a data analysis system using an image processing mode in a file format according to Embodiment 2 of the present invention.

[0034] Compared to Figure 1 , Figure 2 The data parsing system using the image processing mode of the file format may also include the following components:

[0035] A humidity measuring mechanism, comprising a plurality of humidity measuring units, for respectively measuring current surface humidity values ​​of the information judging mechanism, the mode issuing mechanism, the successive establishing device and the data converting device;

[0036] Wherein, the humidity measuring mechanism comprises a plurality of humidity measuring units, which are used to respectively measure the current surface humidity values ​​of the information judging mechanism, the mode issuing mechanism, the successive establishing device and the data converting device, including: the plurality of humidity measuring units respectively used by the information judging mechanism, the mode issuing mechanism, the successive establishing device and the data converting device are a plurality of non-contact humidity sensors;

[0037] Wherein, the humidity measuring mechanism comprises a plurality of humidity measuring units for respectively measuring the current surface humidity values ​​of the information judging mechanism, the mode issuing mechanism, the successive establishing device and the data converting device, and further comprises: the internal structures of a plurality of non-contact humidity sensors respectively used by the information judging mechanism, the mode issuing mechanism, the successive establishing device and the data converting device are the same;

[0038] And wherein, the humidity measuring mechanism comprises a plurality of humidity measuring units for respectively measuring the current surface humidity values ​​of the information judging mechanism, the mode issuing mechanism, the successive establishing device and the data converting device, further comprising: a plurality of non-contact humidity sensors respectively used by the information judging mechanism, the mode issuing mechanism, the successive establishing device and the data converting device have the same humidity measurement upper limit threshold and humidity measurement lower limit threshold;

[0039] And wherein, the humidity measuring mechanism includes multiple humidity measuring units, which are used to respectively measure the current surface humidity values ​​of the information judgment mechanism, the mode publishing mechanism, the successive establishment device and the data conversion device. It also includes: multiple non-contact humidity sensors respectively used by the information judgment mechanism, the mode publishing mechanism, the successive establishment device and the data conversion device are at equal distances from the information judgment mechanism, the mode publishing mechanism, the successive establishment device and the data conversion device.

[0040] Figure 3 This is a block diagram of the internal structure of a data analysis system using an image processing mode in a file format according to Embodiment 3 of the present invention.

[0041] Compared to Figure 1 , Figure 3 The data parsing system using the image processing mode of the file format may also include the following components:

[0042] An immediate notification mechanism, connected to the plurality of non-contact humidity sensors respectively used by the information judgment mechanism, the mode issuing mechanism, the sequential establishment device and the data conversion device, for executing corresponding humidity alarm actions based on humidity measurement results of the plurality of non-contact humidity sensors respectively used by the information judgment mechanism, the mode issuing mechanism, the sequential establishment device and the data conversion device;

[0043] Wherein, the instant notification mechanism is respectively connected to a plurality of non-contact humidity sensors respectively used by the information judgment mechanism, the mode issuing mechanism, the sequential establishment device and the data conversion device, and is used to perform corresponding humidity alarm actions based on humidity measurement results of the plurality of non-contact humidity sensors respectively used by the information judgment mechanism, the mode issuing mechanism, the sequential establishment device and the data conversion device, including: the instant notification mechanism has a built-in humidity receiving unit, a humidity judgment unit and a notification execution unit;

[0044] And wherein, the instant notification mechanism is respectively connected to multiple non-contact humidity sensors respectively used by the information judgment mechanism, the pattern publishing mechanism, the successive establishment device and the data conversion device, and is used to perform corresponding humidity alarm actions based on the humidity measurement results of the multiple non-contact humidity sensors respectively used by the information judgment mechanism, the pattern publishing mechanism, the successive establishment device and the data conversion device. It also includes: within the instant notification mechanism, the humidity receiving unit, the humidity judgment unit and the notification execution unit are connected in sequence.

[0045] In addition, in the data analysis system of the image processing mode using the file format, a deep feedforward network model is used to intelligently determine the multiple processing sequence numbers corresponding to the multiple image processings based on the multiple processing names corresponding to the known multiple image processings, the number of pixel rows of the processed image, the number of pixel columns of the processed image, the data stream in BMP image file format corresponding to the unprocessed image, and the data stream in BMP image file format corresponding to the processed image, including: using a parallel control interface to implement the parallel input of the multiple processing names corresponding to the known multiple image processings, the number of pixel rows of the processed image, the number of pixel columns of the processed image, the data stream in BMP image file format corresponding to the unprocessed image, and the data stream in BMP image file format corresponding to the processed image to the deep feedforward network model.

[0046] Various embodiments of the display system according to the present invention have been described above, and those skilled in the art can easily make modifications and changes based on the above teachings. Therefore, it should be understood that within the scope of the claims, the present invention can be implemented in a manner different from that specifically described herein.

Claims

1. A data analysis system using an image processing mode in a file format, characterized in that: The system comprises: A data conversion device, used to convert an unprocessed image into a data stream in a BMP image file format, and to convert a processed image into a data stream in a BMP image file format, wherein the unprocessed image is subjected to a plurality of known image processing types to obtain the processed image; Establishing devices one by one, for performing training processing on the deep feedforward network for each time, obtaining the deep feedforward network after each training processing and outputting it as a deep feedforward network model, wherein the number of training processing of the deep feedforward network is positively correlated with the amount of data of the unprocessed image; An information judgment mechanism is connected to the successive establishment device and the data conversion device, respectively, and is used to use a deep feedforward network model to intelligently judge multiple processing sequence numbers corresponding to multiple image processings based on multiple processing names corresponding to the known multiple image processings, the number of pixel rows of the processed image, the number of pixel columns of the processed image, the data stream in the BMP image file format corresponding to the unprocessed image, and the data stream in the BMP image file format corresponding to the processed image; A mode issuing mechanism, connected to the information judging mechanism, for sending a plurality of processing sequence numbers corresponding to the received plurality of image processings to a remote cloud computing server via a mobile communication link; Wherein, a deep feedforward network model is used to intelligently determine the multiple processing sequence numbers corresponding to the multiple image processings based on the multiple processing names corresponding to the multiple image processings, the number of pixel rows of the processed image, the number of pixel columns of the processed image, the data stream in the BMP image file format corresponding to the unprocessed image, and the data stream in the BMP image file format corresponding to the processed image. The multiple processing sequence numbers include: the larger the value of the processing sequence number, the later the processing order of the corresponding image processing; The steps of converting the unprocessed image into a data stream in a BMP image file format, converting the processed image into a data stream in a BMP image file format, and obtaining the processed image by subjecting the unprocessed image to a plurality of known image processing types include: the resolution of the unprocessed image and the processed image are equal; Among them, equipment is established one by one to perform training processing on the deep feedforward network for each time to obtain the deep feedforward network after each training processing and output it as a deep feedforward network model, and the number of training processing of the deep feedforward network is positively correlated with the data amount of the unprocessed image, including: using an information mapping formula to represent the information mapping relationship between the number of training processing of the deep feedforward network and the data amount of the unprocessed image.

2. The data analysis system using the image processing mode of the file format as claimed in claim 1, characterized in that: The information mapping relationship that uses the information mapping formula to represent the positive correlation between the number of times the deep feedforward network is trained and the amount of data of the unprocessed image includes: in the information mapping formula, the amount of data of the unprocessed image is the input parameter of the information mapping formula, and the number of times the deep feedforward network is trained is the output parameter of the information mapping formula.

3. The data analysis system using the image processing mode of the file format as claimed in claim 2, characterized in that: The system further comprises: A humidity measuring mechanism, comprising a plurality of humidity measuring units, for respectively measuring current surface humidity values ​​of the information judging mechanism, the mode issuing mechanism, the successive establishing device and the data converting device; Among them, the humidity measuring mechanism includes multiple humidity measuring units, which are used to respectively measure the current surface humidity values ​​of the information judgment mechanism, the mode publishing mechanism, the successive establishment device and the data conversion device. The multiple humidity measuring units respectively used by the information judgment mechanism, the mode publishing mechanism, the successive establishment device and the data conversion device are multiple non-contact humidity sensors.

4. The data analysis system using the image processing mode of the file format as claimed in claim 3, characterized in that: The humidity measuring mechanism includes a plurality of humidity measuring units for respectively measuring the current surface humidity values ​​of the information judging mechanism, the mode issuing mechanism, the successive establishing device and the data converting device. The mechanism also includes: the internal structures of the plurality of non-contact humidity sensors respectively used by the information judging mechanism, the mode issuing mechanism, the successive establishing device and the data converting device are the same.

5. The data analysis system using the image processing mode of the file format as claimed in claim 3, characterized in that: The humidity measuring mechanism includes a plurality of humidity measuring units for respectively measuring the current surface humidity values ​​of the information judging mechanism, the mode issuing mechanism, the successive establishing device and the data converting device. The plurality of non-contact humidity sensors respectively used for the information judging mechanism, the mode issuing mechanism, the successive establishing device and the data converting device have the same humidity measurement upper limit threshold and humidity measurement lower limit threshold.

6. The data analysis system using the image processing mode of the file format as claimed in claim 5, characterized in that: The humidity measuring mechanism includes a plurality of humidity measuring units, which are used to respectively measure the current surface humidity values ​​of the information judgment mechanism, the mode issuing mechanism, the successive establishment device and the data conversion device. The mechanism also includes: a plurality of non-contact humidity sensors respectively used by the information judgment mechanism, the mode issuing mechanism, the successive establishment device and the data conversion device are at equal distances from the information judgment mechanism, the mode issuing mechanism, the successive establishment device and the data conversion device.

7. The data analysis system using the image processing mode of the file format as claimed in claim 2, characterized in that: The system further comprises: The instant notification mechanism is respectively connected to a plurality of non-contact humidity sensors respectively used by the information judgment mechanism, the pattern publishing mechanism, the successive establishment device and the data conversion device, and is used to perform corresponding humidity alarm actions based on the humidity measurement results of the plurality of non-contact humidity sensors respectively used by the information judgment mechanism, the pattern publishing mechanism, the successive establishment device and the data conversion device.

8. The data analysis system using the image processing mode of the file format as claimed in claim 7, characterized in that: The instant notification mechanism is respectively connected to a plurality of non-contact humidity sensors respectively used by the information judgment mechanism, the pattern publishing mechanism, the successive establishment device and the data conversion device, and is used to perform corresponding humidity alarm actions based on the humidity measurement results of the plurality of non-contact humidity sensors respectively used by the information judgment mechanism, the pattern publishing mechanism, the successive establishment device and the data conversion device, including: the instant notification mechanism has a built-in humidity receiving unit, a humidity judgment unit and a notification execution unit.

9. The data analysis system using the image processing mode of the file format as claimed in claim 8, characterized in that: The instant notification mechanism is respectively connected to a plurality of non-contact humidity sensors respectively used by the information judgment mechanism, the pattern publishing mechanism, the successive establishment device and the data conversion device, and is used to perform corresponding humidity alarm actions based on the humidity measurement results of the plurality of non-contact humidity sensors respectively used by the information judgment mechanism, the pattern publishing mechanism, the successive establishment device and the data conversion device. It also includes: within the instant notification mechanism, the humidity receiving unit, the humidity judgment unit and the notification execution unit are connected in sequence.

Images