Quantitative decomposition logic storage architecture for simplifying picture recognition

Abstract

The invention discloses a quantitative decomposition logic storage architecture for simplifying picture recognition, which relates to the technical field of computers, and comprises the following steps: step 1, collecting picture and video data; step 2, feature value extraction; 3, dividing by using a letter sequence in combination with the data; step 4, establishing an alphabet sorting form quantitative decomposition logic frame storage structure; step 5, matching the to-be-identified picture and video data; step 6, identifying and judging; according to the method, an independent logic storage space and independent identity letter sorting information are generated by constructing a letter sorting form quantitative decomposition logic storage architecture, the operation process is simplified, the address information transmission speed is increased, data processing can be efficiently operated under common hardware configuration, the recognition precision is greatly improved, and the recognition efficiency is improved. And the letter sorting form quantitative decomposition logic storage architecture has an encryption effect, so that the privacy leakage risk in the data distributed storage identification process can be effectively reduced, the data security is improved, and the management is more convenient.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a quantitative decomposition logic storage architecture for simplifying image recognition. Background Art

[0002] In today's era of rapid development of digital information, technologies related to image recognition are emerging in an endless stream. However, existing technologies still have the following shortcomings when processing images, videos and other data: 1. When recognizing images, existing technologies mostly use a large-scale, extensive matching method, and do not fully utilize the algorithm to simplify the matching and classification of images. Especially when faced with massive image data, due to the lack of effective simplification strategies, it is necessary to rely on high-frame core operation to maintain processing speed, which not only causes a huge waste of hardware resources, but also leads to low processing efficiency; 2. Existing image recognition technology lacks encryption measures, so there is a serious risk of privacy leakage. Summary of the invention

[0003] The purpose of the present invention is to provide a quantitative decomposition logic storage architecture for simplifying image recognition, so as to solve the problems raised in the above background technology.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a quantitative decomposition logic storage architecture for simplifying image recognition, comprising the following steps: step 1, collecting image and video data; step 2, extracting feature values; step 3, dividing the data by letter sequence; step 4, establishing a quantitative decomposition logic storage architecture of letter sorting form; step 5, matching the image and video data to be recognized; step 6, recognition and judgment;

[0005] In the above step 1, the image and video data are collected and pre-processed;

[0006] In the above step 2, feature values ​​are extracted from the pre-processed image and video data;

[0007] In the above step 3, the first group takes the total number of pictures as the base number, takes 1 / 24 of the total number of characteristic values ​​as the preliminary search standard, screens data from the characteristic values, and summarizes any data characteristic pictures that contain values ​​that meet 1 / 24 of the total number of characteristic values ​​into the first group, marks the first letter of the sequence as A, and writes the specific conditions for the characteristic value entry, and marks the remaining 22 letters in the same way, and the last letter is a variable, which is set to not contain the above 23 digital features; each letter in the first group represents the initial total number 1 / 24, and the second group uses the first group of letters representing the total number 1 / 24 as the total number, and divides the data according to the division method of the first group of data, and subdivides it 7 times in sequence to form an independent letter arrangement;

[0008] In the above step 4, all the pictures in step 3 are stored in folders respectively, and documents are created in the folders, data features are written into cells, and data features are used for screening. The letters of each subdivision are used to mark the document feature content and the folder name, and the subdivision is performed 7 times in sequence, and the feature data of each group of subdivisions are written into documents of multiple feature sets, thereby constructing a logical storage architecture for quantitative decomposition of alphabetical sorting morphology;

[0009] In the above step 5, feature values ​​are extracted from the image and video data to be identified, and the obtained feature values ​​are matched with the quantitative decomposition logic storage architecture of the alphabetical sorting form constructed in step 4 to obtain the alphabetical sorting position of the image and video data to be identified, as well as the specific storage position data information;

[0010] In the above step six, the alphabetical similarity between the image or video data to be identified and other images or video data is calculated, and identification is determined based on the similarity calculation result, and the result is output.

[0011] Preferably, in step one, the preprocessing of picture and video data is specifically as follows: the preprocessing of picture data includes image processing operations and numerical extraction operations, the image processing operations include background removal, decolorization and inversion, and adjustment to a line drawing, the numerical extraction operations include key data extraction, grid division, and digital labeling, and for video data, it is split into pictures and then processed in the manner of picture preprocessing.

[0012] Preferably, the image processing operation is implemented by Adobe Photoshop software, and the key data extraction is implemented by AutoCAD software.

[0013] Preferably, in step three, when filtering data from the characteristic values, a single value that satisfies the characteristic value filtering condition is preferentially selected.

[0014] Preferably, in step six, other pictures and video data are pre-stored in an alphabetical order morphological quantization decomposition logical storage architecture.

[0015] Preferably, in step six, the similarity calculation method adopts one of the following algorithms: an edit distance algorithm based on character matching, a cosine similarity algorithm based on letter occurrence frequency, and a Jaccard similarity coefficient algorithm based on set theory.

[0016] Preferably, in step six, the identification and determination method is specifically as follows: if the similarity reaches a set threshold, it is determined that the data to be identified matches the stored data successfully, and the matching picture and video data information is output; if the similarity does not reach the set threshold, no matching result is output.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention generates an independent logical storage space and independent identity alphabetical sorting information by constructing a quantitative decomposition logical storage architecture of alphabetical sorting morphology, which not only simplifies the calculation process, accelerates the address information transmission speed, and enables data processing to run efficiently under ordinary hardware configuration, but also greatly improves the recognition accuracy. The quantitative decomposition logical storage architecture of alphabetical sorting morphology comes with an encryption effect, which can effectively reduce the risk of privacy leakage in the process of data distributed storage and recognition, improve data security, and is more convenient for management. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flow chart of the method of the present invention;

[0019] Figure 2 Schematic diagram of data flow of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Please see attached Figure 1 -Attached Figure 2 , an embodiment provided by the present invention: a quantitative decomposition logic storage architecture for simplifying image recognition, comprising the following steps: step one, image and video data collection; step two, feature value extraction; step three, combining data with letter sequence division; step four, letter sorting form quantitative decomposition logic storage architecture establishment; step five, to-be-recognized image and video data matching; step six, recognition determination;

[0022] In the above step 1, image and video data are collected and preprocessed; the image and video data preprocessing is specifically as follows: the image data preprocessing includes image processing operations and numerical extraction operations, the image processing operations include background removal, decolorization and inversion, and adjustment to line drawings, the numerical extraction operations include key data extraction, grid division, and digital annotation, and for video data, it is split into images and then processed in the manner of image preprocessing; the image processing operation is implemented by Adobe Photoshop software, and the key data extraction is implemented by AutoCAD software;

[0023] In the above step 2, feature values ​​are extracted from the pre-processed image and video data;

[0024] In the above step 3, the first group takes the total number of pictures as the base number, takes 1 / 24 of the total number of eigenvalues ​​as the preliminary search standard, screens data from the eigenvalues, and gives priority to selecting a single value that meets the eigenvalue screening conditions, and summarizes any data feature pictures that contain values ​​that meet 1 / 24 of the total number of eigenvalues ​​into the first group, marks the first letter of the sequence as A, and writes the specific conditions for the eigenvalue entry, and so on, marks the remaining 22 letters, and the last letter is a variable, which is set to not contain the above 23 digital features; each letter in the first group represents the initial total number 1 / 24, and the second group uses the first group of letters representing the total number 1 / 24 as the total number, and divides the data according to the division method of the first group of data, and subdivides 7 times in sequence to form an independent letter arrangement;

[0025] In the above step 4, all the pictures in step 3 are stored in folders respectively, and documents are created in the folders, data features are written into cells, and data features are used for screening. The letters of each subdivision are used to mark the document feature content and the folder name, and the subdivision is performed 7 times in sequence, and the feature data of each group of subdivisions are written into documents of multiple feature sets, thereby constructing a logical storage architecture for quantitative decomposition of alphabetical sorting morphology;

[0026] In the above step 5, feature values ​​are extracted from the image and video data to be identified, and the obtained feature values ​​are matched with the quantitative decomposition logic storage architecture of the alphabetical sorting form constructed in step 4 to obtain the alphabetical sorting position of the image and video data to be identified, as well as the specific storage position data information;

[0027] In the above step six, the alphabetical similarity between the image and video data to be identified and other images and video data is calculated, and identification is determined based on the similarity calculation result, and the result is output; wherein, other images and video data are pre-stored in the alphabetical morphological quantization decomposition logic storage architecture, and the similarity calculation method adopts one of the following algorithms: an edit distance algorithm based on character matching, a cosine similarity algorithm based on the frequency of letter occurrence, and a Jaccard similarity coefficient algorithm based on set theory. The identification and determination method is specifically as follows: if the similarity reaches a set threshold, it is determined that the data to be identified matches the stored data successfully, and the matching image and video data information is output; if the similarity does not reach the set threshold, no matching result is output.

[0028] Based on the above, the advantage of the present invention is that when the present invention is used, by establishing a logical storage architecture of quantized decomposition of alphabetical ordering forms, the image recognition and matching process is simplified, the address information transmission speed is accelerated, the requirements for device configuration are reduced, and data processing can be efficiently run under ordinary hardware configuration. In addition, the logical storage architecture of quantized decomposition of alphabetical ordering forms comes with an encryption effect, which can effectively reduce the risk of privacy leakage and improve data security.

[0029] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A quantitative decomposition logic storage architecture for simplifying image recognition, comprising the following steps: Step 1: collect pictures and video data; Step 2: extract feature values; Step 3: divide the data by letter sequence; Step 4: establish the logic storage structure of letter sorting morphology quantification decomposition; Step 5: match the pictures and video data to be identified; Step 6: identify and judge; it is characterized by: In the above step 1, the image and video data are collected and pre-processed; In the above step 2, feature values ​​are extracted from the pre-processed image and video data; In the above step 3, the total number of pictures is taken as the base number, 1 / 24 of the total number of characteristic values ​​is taken as the preliminary search standard, data is screened from the characteristic values, and any data characteristic pictures containing numerical values ​​that meet 1 / 24 of the total number of characteristic values ​​are summarized as the first group, marked with the first letter of the sequence as A, and the specific conditions for characteristic value entry are written, and the remaining 22 letters are marked in the same way, and the last letter is a variable, which is set to not contain the above 23 digital features; each letter in the first group represents the initial total number 1 / 24, and the second group uses the first group of letters representing the total number 1 / 24 as the total number, and the data is divided according to the division method of the first group of data, and is subdivided 7 times in sequence to form an independent letter arrangement; In the above step 4, all the pictures in step 3 are stored in folders respectively, and documents are created in the folders, data features are written into cells, and data features are used for screening. The letters of each subdivision are used to mark the document feature content and the folder name, and the subdivision is performed 7 times in sequence, and the feature data of each group of subdivisions are written into documents of multiple feature sets, thereby constructing a logical storage architecture for quantitative decomposition of alphabetical sorting morphology; In the above step 5, feature values ​​are extracted from the image and video data to be identified, and the obtained feature values ​​are matched with the quantitative decomposition logic storage architecture of the alphabetical sorting form constructed in step 4 to obtain the alphabetical sorting position of the image and video data to be identified, as well as the specific storage position data information; In the above step six, the alphabetical similarity between the image or video data to be identified and other images or video data is calculated, and identification is determined based on the similarity calculation result, and the result is output.

2. The quantization decomposition logic storage architecture for simplifying image recognition according to claim 1, characterized in that: In the step one, the preprocessing of the image and video data is specifically as follows: the preprocessing of the image data includes image processing operations and numerical extraction operations. The image processing operations include background removal, decolorization and inversion, and adjustment to a line drawing. The numerical extraction operations include key data extraction, grid division, and digital labeling. For video data, it is split into images and then processed in the manner of image preprocessing.

3. The quantization decomposition logic storage architecture for simplifying image recognition according to claim 2, characterized in that: The image processing operation is implemented by Adobe Photoshop software, and the key data extraction is implemented by AutoCAD software.

4. The quantization decomposition logic storage architecture for simplifying image recognition according to claim 1, characterized in that: In the step three, when filtering data from the characteristic values, a single value that meets the characteristic value filtering condition is preferentially selected.

5. The quantization decomposition logic storage architecture for simplifying image recognition according to claim 1, characterized in that: In the step six, other pictures and video data are pre-stored in the alphabetical order morphological quantization decomposition logical storage architecture.

6. The quantization decomposition logic storage architecture for simplifying image recognition according to claim 1, characterized in that: In the step six, the similarity calculation method adopts one of the following algorithms: an edit distance algorithm based on character matching, a cosine similarity algorithm based on letter occurrence frequency, and a Jaccard similarity coefficient algorithm based on set theory.

7. The quantization decomposition logic storage architecture for simplifying image recognition according to claim 1, characterized in that: In step six, the identification and determination method is specifically as follows: if the similarity reaches a set threshold, the data to be identified is determined to be successfully matched with the stored data, and the matching picture and video data information is output; if the similarity does not reach the set threshold, no matching result is output.

Images