CN114066828A - Image processing method and system based on multifunctional bottom layer algorithm - Google Patents
Image processing method and system based on multifunctional bottom layer algorithm Download PDFInfo
- Publication number
- CN114066828A CN114066828A CN202111292499.4A CN202111292499A CN114066828A CN 114066828 A CN114066828 A CN 114066828A CN 202111292499 A CN202111292499 A CN 202111292499A CN 114066828 A CN114066828 A CN 114066828A
- Authority
- CN
- China
- Prior art keywords
- processing
- image processing
- algorithm
- image
- docking
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an image processing method and system based on a multifunctional bottom layer algorithm, wherein the method comprises the following steps: obtaining a first target image; obtaining a first characteristic convolution kernel; performing traversal retrieval analysis on the first target image to obtain a first characteristic parameter set; obtaining a first processing requirement of a first target image; inputting the first processing requirement as input data into a first parameter docking model, and performing parameter docking to obtain output information of the first parameter docking model; acquiring a preset image processing algorithm library, and performing algorithm matching from the image processing algorithm library according to a first processing requirement and a first docking parameter set to acquire first processing algorithm information; and carrying out image processing on the first target image. The method solves the technical problems of low recognition accuracy, low matching degree of a processing algorithm and low image processing efficiency in image processing in the prior art.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an image processing method and system based on a multifunctional bottom layer algorithm.
Background
The 21 st century is an information-filled era, and images serve as visual bases for human perception of the world and are important means for human to acquire information, express information and transmit information. Image processing techniques are also known as image processing techniques, in which a computer analyzes an image to achieve a desired result. Image processing generally refers to digital image processing. Digital images are large two-dimensional arrays of elements called pixels and values called gray-scale values, which are captured by industrial cameras, video cameras, scanners, etc. Image processing techniques generally include image compression, enhancement and restoration, matching, description and recognition.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
the problems of low recognition accuracy, low matching degree of a processing algorithm and low image processing efficiency during image processing exist.
Disclosure of Invention
The embodiment of the application provides an image processing method and system based on a multifunctional bottom layer algorithm, and solves the technical problems that in the prior art, the recognition accuracy is low, the matching degree of a processing algorithm is not high, and the image processing efficiency is low during image processing. The method achieves the technical effects of improving the accuracy of feature recognition, realizing accurate matching of the bottom-layer algorithm and improving the image processing efficiency through the bottom-layer algorithm.
In view of the foregoing problems, embodiments of the present application provide an image processing method and system based on a multifunctional underlying algorithm.
In a first aspect, an embodiment of the present application provides an image processing method based on a multifunctional underlying algorithm, where the method includes: obtaining a first target image based on the image acquisition device; obtaining a first characteristic convolution kernel; according to the first characteristic convolution kernel, performing traversal retrieval analysis on the first target image to obtain a first characteristic parameter set; obtaining a first processing requirement of the first target image; inputting the first processing requirement as input data into a first parameter docking model, wherein the first parameter docking model performs parameter docking by docking the first characteristic parameter set to obtain output information of the first parameter docking model, and the output information comprises a first docking parameter set; obtaining a preset image processing algorithm library, wherein the preset image processing algorithm library is a bottom algorithm library for image processing; performing algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set to obtain first processing algorithm information; and carrying out image processing on the first target image according to the first processing algorithm information.
In another aspect, an embodiment of the present application provides an image processing system based on a multifunctional underlying algorithm, where the system includes: a first obtaining unit for obtaining a first target image based on an image acquisition device; a second obtaining unit for obtaining a first characteristic convolution kernel; a third obtaining unit, configured to perform traversal retrieval analysis on the first target image according to the first feature convolution kernel to obtain a first feature parameter set; a fourth obtaining unit configured to obtain a first processing requirement of the first target image; a fifth obtaining unit, configured to input the first processing requirement as input data into a first parameter docking model, where the first parameter docking model performs parameter docking by docking the first feature parameter set, and obtains output information of the first parameter docking model, where the output information includes a first docking parameter set; a sixth obtaining unit, configured to obtain a preset image processing algorithm library, where the preset image processing algorithm library is a bottom algorithm library for image processing; a seventh obtaining unit, configured to perform algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set, and obtain first processing algorithm information; a first execution unit, configured to perform image processing on the first target image according to the first processing algorithm information.
In a third aspect, an embodiment of the present application provides an image processing system based on a multifunctional underlying algorithm, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the method according to any one of the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
due to the adoption of the image acquisition device, a first target image is obtained; obtaining a first characteristic convolution kernel; according to the first characteristic convolution kernel, performing traversal retrieval analysis on the first target image to obtain a first characteristic parameter set; obtaining a first processing requirement of the first target image; inputting the first processing requirement as input data into a first parameter docking model, wherein the first parameter docking model performs parameter docking by docking the first characteristic parameter set to obtain output information of the first parameter docking model, and the output information comprises a first docking parameter set; obtaining a preset image processing algorithm library, wherein the preset image processing algorithm library is a bottom algorithm library for image processing; performing algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set to obtain first processing algorithm information; according to the technical scheme for processing the image of the first target image according to the first processing algorithm information, the embodiment of the application provides the image processing method and the image processing system based on the multifunctional bottom layer algorithm, so that the technical effects of improving the accuracy of feature recognition, realizing accurate matching of the bottom layer algorithm and improving the image processing efficiency through the bottom layer algorithm are achieved.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
FIG. 1 is a schematic flowchart of an image processing method based on a multifunctional underlying algorithm according to an embodiment of the present application;
FIG. 2 is a schematic view of a flow chart of performing multiple algorithm matching in an image processing method based on a multifunctional underlying algorithm according to an embodiment of the present application;
FIG. 3 is a schematic flowchart of a method for image processing based on a multifunctional underlying algorithm to obtain a first docking parameter set according to an embodiment of the present application;
FIG. 4 is a schematic flowchart illustrating similarity calculation performed by an image processing method based on a multifunctional underlying algorithm according to an embodiment of the present disclosure;
FIG. 5 is a schematic flowchart of a method for image processing based on a multifunctional underlying algorithm to obtain information of a second processing algorithm according to an embodiment of the present application;
fig. 6 is a schematic flowchart of a method for processing an image based on a multifunctional underlying algorithm to generate first matching auxiliary information according to an embodiment of the present application;
FIG. 7 is a schematic structural diagram of an image processing system based on a multifunctional underlying algorithm according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a fifth obtaining unit 15, a sixth obtaining unit 16, a seventh obtaining unit 17, a first executing unit 18, an electronic device 300, a memory 301, a processor 302, a communication interface 303, and a bus architecture 304.
Detailed Description
The embodiment of the application provides an image processing method and system based on a multifunctional bottom layer algorithm, and solves the technical problems that in the prior art, the recognition accuracy is low, the matching degree of a processing algorithm is not high, and the image processing efficiency is low during image processing. The method achieves the technical effects of improving the accuracy of feature recognition, realizing accurate matching of the bottom-layer algorithm and improving the image processing efficiency through the bottom-layer algorithm.
Summary of the application
The 21 st century is an information-filled era, and images serve as visual bases for human perception of the world and are important means for human to acquire information, express information and transmit information. Image processing techniques are also known as image processing techniques, in which a computer analyzes an image to achieve a desired result. Image processing generally refers to digital image processing. Digital images are large two-dimensional arrays of elements called pixels and values called gray-scale values, which are captured by industrial cameras, video cameras, scanners, etc. Image processing techniques generally include image compression, enhancement and restoration, matching, description and recognition. The technical problems of low recognition accuracy, low matching degree of a processing algorithm and low image processing efficiency in image processing exist in the prior art.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides an image processing method based on a multifunctional bottom layer algorithm, wherein the method comprises the following steps: obtaining a first target image based on the image acquisition device; obtaining a first characteristic convolution kernel; according to the first characteristic convolution kernel, performing traversal retrieval analysis on the first target image to obtain a first characteristic parameter set; obtaining a first processing requirement of the first target image; inputting the first processing requirement as input data into a first parameter docking model, wherein the first parameter docking model performs parameter docking by docking the first characteristic parameter set to obtain output information of the first parameter docking model, and the output information comprises a first docking parameter set; obtaining a preset image processing algorithm library, wherein the preset image processing algorithm library is a bottom algorithm library for image processing; performing algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set to obtain first processing algorithm information; and carrying out image processing on the first target image according to the first processing algorithm information.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, an embodiment of the present application provides an image processing method based on a multifunctional underlying algorithm, where the method is applied to an image processing system based on a multifunctional underlying algorithm, the system is communicatively connected to an image capture device, and the method includes:
s100: obtaining a first target image based on the image acquisition device;
s200: obtaining a first characteristic convolution kernel;
s300: according to the first characteristic convolution kernel, performing traversal retrieval analysis on the first target image to obtain a first characteristic parameter set;
specifically, the image capturing device is any device having an image capturing function, such as a camera, a video camera, and the like, and the first target image is obtained according to the first image capturing device, and the first target image is a target image to be processed. And obtaining the first characteristic convolution kernel, wherein the first characteristic convolution kernel is that when the image is processed, the given input image becomes each corresponding pixel in the output image after the weighted average of the pixels in a small area in the input image, and the weight is defined by a function which is called as the convolution kernel. The convolution kernel focuses on local features, namely a standard feature is set, and the matching degree of the features is evaluated according to the numerical value of the convolution kernel at the local feature part. Based on the first feature convolution kernel, performing traversal retrieval analysis on the first target image to obtain a first feature parameter set, that is, obtaining a necessary feature parameter set that needs to be processed by the first target image, such as a corresponding parameter set of frequency domain features, gray scale or color features, boundary features, region features, texture features, shape features, topology, relationship features, and the like. The first target image is subjected to traversal retrieval analysis by adopting the first feature convolution kernel, so that the accuracy of feature identification and extraction can be improved, and a relatively complete and representative feature parameter set can be obtained.
S400: obtaining a first processing requirement of the first target image;
s500: inputting the first processing requirement as input data into a first parameter docking model, wherein the first parameter docking model performs parameter docking by docking the first characteristic parameter set to obtain output information of the first parameter docking model, and the output information comprises a first docking parameter set;
specifically, based on the image processing task, the first processing requirement is obtained, which should be specifically implementable. And inputting the first processing requirement as input data into a first parameter docking model, performing parameter docking in the first characteristic parameter set, wherein the first parameter docking model is a neural network model, and a parameter set required to be processed can be obtained by inputting the first processing requirement, namely the first docking parameter set is obtained. For example, if the first processing requirement is image enhancement, the parameters of the docking may include noise, signal frequency, etc. Through the first docking parameter model, an accurate and reliable docking parameter set can be obtained, and a foundation is laid for subsequent algorithm matching.
S600: obtaining a preset image processing algorithm library, wherein the preset image processing algorithm library is a bottom algorithm library for image processing;
s700: performing algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set to obtain first processing algorithm information;
s800: and carrying out image processing on the first target image according to the first processing algorithm information.
Specifically, the preset image processing algorithm library is constructed by combining the currently known image processing underlying algorithm with the image processing task of the image processor, is substantially an underlying algorithm library, comprises a plurality of multifunctional image processing algorithms, and can quickly and accurately realize image processing. And performing algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set to obtain a required algorithm set, namely the first processing algorithm information, and performing image processing on the first target image according to the successfully matched first processing algorithm information. The method can realize the technical effects of accurately matching the bottom layer algorithm and improving the image processing efficiency through the application of the bottom layer algorithm.
Further, as shown in fig. 2, the performing algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set to obtain first processing algorithm information, and step S700 includes:
s710: performing template analysis on the first target image to obtain a first matching instruction;
s720: performing multiple times of algorithm matching on the first processing requirement and the first docking parameter set from the image processing algorithm library according to the first matching instruction to obtain a first matching result;
s730: and obtaining the first processing algorithm information according to the first matching result.
Specifically, the first target image is subjected to template analysis, specifically, the first target image is subjected to disassembly, template matching and feature extraction, so as to obtain the first matching instruction, wherein the template matching is realized by comparing the template image with the first target image, finding a part similar to the template image on a test image (the first target image), and calculating the similarity between the template image and the first target image, so that a predefined target can be quickly located in the first target image. The main idea of matching is to use an object prototype from which a template is created, search for the object in the first object image that is most similar to the template image, and find the region that is closest to the mean or variance of the template. The similarity, the rotation angle, the row and column coordinates, the scaling size and the like of the target can be obtained through template matching.
According to the first matching instruction, matching the plurality of processing requirements refined by the first processing requirement and different parameters in the first butting set from the image processing algorithm library to a plurality of multifunctional underlying algorithms in a successive matching mode to obtain a first matching result, and according to the first matching result, obtaining the matched information of the first processing algorithm, wherein the information of the first processing algorithm comprises a plurality of successfully matched multifunctional underlying algorithms. The multifunctional bottom layer algorithm comprises multifunctional functions of image basic operation, geometric operation, image combination and the like, is a fundamental stone of an image processing algorithm, embodies the basic concept and thought of graphics, and can quickly and efficiently solve the image processing problem. By performing template analysis on the first target image, the familiarity degree of the target image can be improved, and the matching speed and the success rate of a bottom-layer algorithm are improved.
Further, as shown in fig. 3, the step S500 of inputting the first processing requirement as a first target requirement condition into a first parameter docking model to obtain a first docking parameter set includes:
s510: obtaining basic information of a first processing requirement, wherein the basic information comprises a first processing environment;
s520: performing category analysis and judgment on the basic information of the first processing requirement to obtain a first classification result;
s530: obtaining first requirement category information according to the first classification result;
s540: and inputting the first requirement category information as a second target requirement condition into the first parameter docking model to obtain the first docking parameter set.
Specifically, the basic information of the first processing requirement is obtained by refining the first processing requirement, and the basic information includes a first processing environment, a scene including a processed image application, and the like. And performing category analysis based on the basic information of the first processing requirement, namely classifying the first processing requirement, wherein the classification standard can be determined according to the first processing environment. Therefore, a first classification result is obtained, and the first requirement category information is obtained, such as storage and transmission of images, improvement of visual quality of the images and the like. And then inputting the first requirement category information as a second target requirement condition into the first parameter docking model to obtain the first docking parameter set, and realizing requirement classification according to the refined requirement information, thereby improving the accuracy of parameter docking.
Further, as shown in fig. 4, after the image processing is performed on the first target image according to the first execution instruction, step S800 includes:
s810: obtaining a first image processing result of the first target image;
s820: performing similarity calculation on the first image processing result and the first processing requirement to obtain the first similarity coefficient;
s830: judging whether the first similarity coefficient meets a preset similarity threshold value or not;
s840: and when the first similarity coefficient meets the preset similarity threshold, taking the first image processing result as a final image processing result.
Specifically, after the first target image is subjected to image processing by the first processing algorithm information, the first image processing result is obtained. And calculating the similarity of the first image processing result and the first processing requirement to obtain the first similarity coefficient, so as to verify the processed image and judge whether the processing result meets the processing requirement. And obtaining the preset similar threshold, wherein the preset similar threshold is preset according to the error range allowed by a demand side. And if the requirement of the demand side for the image processing precision is higher, the preset similarity threshold range is smaller. The similarity calculation can be realized by the existing similarity calculation algorithm, a manual judgment method or a method combining the similarity calculation algorithm and the manual judgment method. And judging whether the first similarity coefficient meets a preset similarity threshold value, if so, indicating that the image processing result meets the first processing requirement, and further indicating that the matched first processing algorithm has a better information processing effect. And taking the first image processing result as a final image processing result. Through result verification, the applicability of the image processing algorithm can be judged, the processed image can be verified, and the processed image can meet the image processing requirement.
Further, as shown in fig. 5, after determining whether the first similarity coefficient satisfies a preset similarity threshold, step S830 includes:
s831: when the first similarity coefficient does not meet the preset similarity threshold, obtaining a second processing requirement;
s832: obtaining a second docking parameter set according to the second processing requirement;
s833: performing template analysis on the first image processing result to obtain a second matching instruction;
s834: performing multiple times of algorithm matching on the second processing requirement and the second docking parameter set from the image processing algorithm library according to the second matching instruction to obtain a second matching result;
s835: obtaining second processing algorithm information according to the second matching result;
s836: and carrying out image processing on the first target image according to the second processing algorithm information to obtain a second image processing result.
Specifically, if the first similarity coefficient does not satisfy the preset similarity threshold, the second processing requirement is obtained according to a difference between the first image processing result and the first processing requirement, and the second docking parameter set is obtained according to the second processing requirement and the first parameter docking model, where the second docking parameter set includes image parameters that do not match with customer requirements. Further, template analysis is carried out on the first image processing result to obtain a second matching instruction, multiple times of algorithm matching are carried out in the image processing algorithm library according to the second matching instruction to obtain a second matching result, and processing of the first target image is carried out according to the matched second processing algorithm information to obtain a second image processing result. And continuing to calculate the similarity of the second image processing result and the first processing requirement, judging whether the preset similarity threshold is met, if so, taking the second image processing result as a final image processing result, and if not, continuing to perform algorithm matching until the preset similarity threshold is met. By obtaining the second processing requirement and optimizing the first image processing result, more accurate algorithm matching results and image processing results can be obtained, a bottom-layer algorithm matching scheme can be provided for image processing of the same type or image processing of the same requirement, a large amount of data can be obtained through multiple matching, the bottom-layer algorithm matching scheme can be optimized, the accuracy of the image processing results is improved, and the satisfaction degree of customers is improved.
Further, after the taking the first image processing result as the final image processing result, the step S840 further includes:
s841: obtaining the first target image set, wherein the first target image set is an image set with the same processing requirement and comprises the first target image;
s842: and processing the first target image set in batches according to the first processing algorithm information.
In particular, image processing tasks tend to be highly repetitive, such as: the photo studio processes the identification photos, the shot identification photos of different clients have similar processing modes and processing requirements; the photo album is processed in a similar manner, with a group of photographs taken having similar elements. Therefore, the image set with the same processing requirement as the first target image can apply the processing algorithm with higher similarity. Thus, the first set of target images is obtained, which set has the same processing requirements, including the first target image. Further, the first target image set is processed in batch based on the first processing algorithm, so that the speed of image processing can be increased, an image processing mode can be conveniently formed, and the working efficiency is increased.
Further, as shown in fig. 6, the embodiment of the present application further includes:
s910: obtaining first format information of a first target image;
s920: acquiring convertible format information of the first target image based on image format conversion software;
s930: generating first matching auxiliary information based on the convertible format information;
s940: and performing algorithm matching from the image processing algorithm library according to the first processing requirement, the first docking parameter set and the first matching auxiliary information to obtain first processing algorithm information.
Specifically, since the image formats that can be processed by different image processing algorithms are known, and the image formats of the images to be processed are various and unknown, it is necessary to obtain the first format information of the first target image, and the image formats are usually JPEG, TIFF, RAW, BMP, PCX, GIF, PNG formats, and the like. Based on image conversion software, convertible format information of the first target image can be obtained, the number and types of the convertible formats obtained by different image conversion software are different, the different types of the convertible formats obtained by different image processing software are collected, and the first matching auxiliary information is obtained. And combining the first matching auxiliary information as a newly added matching element with the first processing requirement and the first docking parameter set, and performing algorithm matching from the image processing algorithm library, so that the successful matching probability can be increased, and the algorithm matching efficiency can be improved.
To sum up, the image processing method and system based on the multifunctional bottom layer algorithm provided by the embodiment of the application have the following technical effects:
1. due to the adoption of the image acquisition device, a first target image is obtained; obtaining a first characteristic convolution kernel; according to the first characteristic convolution kernel, performing traversal retrieval analysis on the first target image to obtain a first characteristic parameter set; obtaining a first processing requirement of the first target image; inputting the first processing requirement as input data into a first parameter docking model, wherein the first parameter docking model performs parameter docking by docking the first characteristic parameter set to obtain output information of the first parameter docking model, and the output information comprises a first docking parameter set; obtaining a preset image processing algorithm library, wherein the preset image processing algorithm library is a bottom algorithm library for image processing; performing algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set to obtain first processing algorithm information; according to the technical scheme for processing the image of the first target image according to the first processing algorithm information, the embodiment of the application provides the image processing method and the image processing system based on the multifunctional bottom layer algorithm, so that the technical effects of improving the accuracy of feature recognition, realizing accurate matching of the bottom layer algorithm and improving the image processing efficiency through the bottom layer algorithm are achieved.
2. The template analysis is carried out on the first target image, so that the target image can be deeply analyzed and deconstructed, and the technical effects of the matching speed and the matching success rate of the bottom layer algorithm are improved.
Example two
Based on the same inventive concept as the image processing method based on the multifunctional underlying algorithm in the foregoing embodiment, as shown in fig. 7, an embodiment of the present application provides an image processing system based on the multifunctional underlying algorithm, wherein the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain a first target image based on an image acquisition device;
a second obtaining unit 12, wherein the second obtaining unit 12 is configured to obtain a first characteristic convolution kernel;
a third obtaining unit 13, where the third obtaining unit 13 is configured to perform traversal retrieval analysis on the first target image according to the first feature convolution kernel to obtain a first feature parameter set;
a fourth obtaining unit 14, the fourth obtaining unit 14 being configured to obtain a first processing requirement of the first target image;
a fifth obtaining unit 15, where the fifth obtaining unit 15 is configured to input the first processing requirement as input data into a first parameter docking model, where the first parameter docking model performs parameter docking by docking the first feature parameter set, so as to obtain output information of the first parameter docking model, where the output information includes a first docking parameter set;
a sixth obtaining unit 16, where the sixth obtaining unit 16 is configured to obtain a preset image processing algorithm library, where the preset image processing algorithm library is a bottom-layer algorithm library for image processing;
a seventh obtaining unit 17, where the seventh obtaining unit 17 is configured to perform algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set, and obtain first processing algorithm information;
a first executing unit 18, where the first executing unit 18 is configured to perform image processing on the first target image according to the first processing algorithm information.
Further, the system comprises:
an eighth obtaining unit, configured to perform template analysis on the first target image to obtain a first matching instruction;
a ninth obtaining unit, configured to perform multiple times of algorithm matching on the first processing requirement and the first docking parameter set from the image processing algorithm library according to the first matching instruction, and obtain a first matching result;
a tenth obtaining unit, configured to obtain the first processing algorithm information according to the first matching result.
Further, the system comprises:
an eleventh obtaining unit configured to obtain basic information of a first processing requirement, wherein the basic information includes a first processing environment;
a twelfth obtaining unit, configured to perform category analysis and discrimination on the basic information of the first processing requirement, and obtain a first classification result;
a thirteenth obtaining unit configured to obtain first requirement category information according to the first classification result;
a fourteenth obtaining unit, configured to input the first requirement category information as a second target requirement condition into the first parameter docking model, and obtain the first docking parameter set.
Further, the system comprises:
a fifteenth obtaining unit configured to obtain a first image processing result of the first target image;
a sixteenth obtaining unit, configured to perform similarity calculation on the first image processing result and the first processing requirement, and obtain the first similarity coefficient;
a first judging unit, configured to judge whether the first similarity coefficient satisfies a preset similarity threshold;
a second execution unit, configured to take the first image processing result as a final image processing result when the first similarity coefficient satisfies the preset similarity threshold.
A seventeenth obtaining unit, configured to arrange the electronic tickets of each category from small to large according to the first weight ratio of the user object features, and obtain a first series category sequence.
Further, the system comprises:
an eighteenth obtaining unit, configured to obtain a second processing requirement when the first similarity coefficient does not satisfy the preset similarity threshold;
a nineteenth obtaining unit, configured to obtain a second docking parameter set according to the second processing requirement;
a twentieth obtaining unit, configured to perform template analysis on the first image processing result to obtain a second matching instruction;
a twenty-first obtaining unit, configured to perform multiple times of algorithm matching on the second processing requirement and the second docking parameter set from the image processing algorithm library according to the second matching instruction, and obtain a second matching result;
a twenty-second obtaining unit, configured to obtain second processing algorithm information according to the second matching result;
a twenty-third obtaining unit, configured to perform image processing on the first target image according to the second processing algorithm information, and obtain a second image processing result.
Further, the system comprises:
a twenty-fourth obtaining unit configured to obtain first format information of the first target image;
a twenty-fifth obtaining unit, configured to obtain convertible format information of the first target image based on image format conversion software;
a first generating unit configured to generate first matching side information based on the convertible format information;
a twenty-sixth obtaining unit, configured to perform algorithm matching from the image processing algorithm library according to the first processing requirement, the first docking parameter set, and the first matching auxiliary information, and obtain first processing algorithm information.
Exemplary electronic device
The electronic apparatus of the embodiment of the present application is described below with reference to fig. 8.
Based on the same inventive concept as the image processing method based on the multifunctional underlying algorithm in the foregoing embodiments, the embodiment of the present application further provides an image processing system based on the multifunctional underlying algorithm, including: a processor coupled to a memory, the memory for storing a program that, when executed by the processor, causes a system to perform the method of any of the first aspects.
The electronic device 300 includes: processor 302, communication interface 303, memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. Wherein, the communication interface 303, the processor 302 and the memory 301 may be connected to each other through a bus architecture 304; the bus architecture 304 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus architecture 304 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 8, but this is not intended to represent only one bus or type of bus.
The communication interface 303 may be any device, such as a transceiver, for communicating with other devices or communication networks, such as an ethernet, a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), a wired access network, and the like.
The memory 301 may be, but is not limited to, a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, an electrically erasable Programmable read-only memory (EEPROM), a compact-read-only-memory (CD-ROM) or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory may be self-contained and coupled to the processor through a bus architecture 304. The memory may also be integral to the processor.
The memory 301 is used for storing computer-executable instructions for executing the present application, and is controlled by the processor 302 to execute. The processor 302 is used for executing computer-executable instructions stored in the memory 301, so as to implement the image processing method based on the multifunctional underlying algorithm provided by the above-mentioned embodiment of the present application.
Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application program codes, which are not specifically limited in the embodiments of the present application.
The embodiment of the application provides an image processing method based on a multifunctional bottom layer algorithm, wherein the method comprises the following steps: obtaining a first target image based on the image acquisition device; obtaining a first characteristic convolution kernel; according to the first characteristic convolution kernel, performing traversal retrieval analysis on the first target image to obtain a first characteristic parameter set; obtaining a first processing requirement of the first target image; inputting the first processing requirement as input data into a first parameter docking model, wherein the first parameter docking model performs parameter docking by docking the first characteristic parameter set to obtain output information of the first parameter docking model, and the output information comprises a first docking parameter set; obtaining a preset image processing algorithm library, wherein the preset image processing algorithm library is a bottom algorithm library for image processing; performing algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set to obtain first processing algorithm information; and carrying out image processing on the first target image according to the first processing algorithm information.
Those of ordinary skill in the art will understand that: the various numbers of the first, second, etc. mentioned in this application are only used for the convenience of description and are not used to limit the scope of the embodiments of this application, nor to indicate the order of precedence. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one" means one or more. At least two means two or more. "at least one," "any," or similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one (one ) of a, b, or c, may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or multiple.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device including one or more available media integrated servers, data centers, and the like. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The various illustrative logical units and circuits described in this application may be implemented or operated upon by design of a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.
The steps of a method or algorithm described in the embodiments herein may be embodied directly in hardware, in a software element executed by a processor, or in a combination of the two. The software cells may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. For example, a storage medium may be coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may be disposed in a terminal. In the alternative, the processor and the storage medium may reside in different components within the terminal. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the present application has been described in conjunction with specific features and embodiments thereof, it will be evident that various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Accordingly, the specification and figures are merely exemplary of the present application as defined in the appended claims and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations.
Claims (9)
1. An image processing method based on a multifunctional underlying algorithm, wherein the method is applied to an image processing system based on the multifunctional underlying algorithm, the system is in communication connection with an image acquisition device, and the method comprises the following steps:
obtaining a first target image based on the image acquisition device;
obtaining a first characteristic convolution kernel;
according to the first characteristic convolution kernel, performing traversal retrieval analysis on the first target image to obtain a first characteristic parameter set;
obtaining a first processing requirement of the first target image;
inputting the first processing requirement as input data into a first parameter docking model, wherein the first parameter docking model performs parameter docking by docking the first characteristic parameter set to obtain output information of the first parameter docking model, and the output information comprises a first docking parameter set;
obtaining a preset image processing algorithm library, wherein the preset image processing algorithm library is a bottom algorithm library for image processing;
performing algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set to obtain first processing algorithm information;
and carrying out image processing on the first target image according to the first processing algorithm information.
2. The method of claim 1, wherein said performing algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set to obtain first processing algorithm information comprises:
performing template analysis on the first target image to obtain a first matching instruction;
performing multiple times of algorithm matching on the first processing requirement and the first docking parameter set from the image processing algorithm library according to the first matching instruction to obtain a first matching result;
and obtaining the first processing algorithm information according to the first matching result.
3. The method of claim 1, wherein said entering said first processing requirement as a first target requirement condition into a first parametric docking model, obtaining a first set of docking parameters, comprises:
obtaining basic information of a first processing requirement, wherein the basic information comprises a first processing environment;
performing category analysis and judgment on the basic information of the first processing requirement to obtain a first classification result;
obtaining first requirement category information according to the first classification result;
and inputting the first requirement category information as a second target requirement condition into the first parameter docking model to obtain the first docking parameter set.
4. The method of claim 1, wherein said image processing said first target image according to said first execution instruction, comprises:
obtaining a first image processing result of the first target image;
performing similarity calculation on the first image processing result and the first processing requirement to obtain the first similarity coefficient;
judging whether the first similarity coefficient meets a preset similarity threshold value or not;
and when the first similarity coefficient meets the preset similarity threshold, taking the first image processing result as a final image processing result.
5. The method of claim 4, wherein the determining whether the first similarity coefficient satisfies a preset similarity threshold comprises:
when the first similarity coefficient does not meet the preset similarity threshold, obtaining a second processing requirement;
obtaining a second docking parameter set according to the second processing requirement;
performing template analysis on the first image processing result to obtain a second matching instruction;
performing multiple times of algorithm matching on the second processing requirement and the second docking parameter set from the image processing algorithm library according to the second matching instruction to obtain a second matching result;
obtaining second processing algorithm information according to the second matching result;
and carrying out image processing on the first target image according to the second processing algorithm information to obtain a second image processing result.
6. The method of claim 5, wherein said taking said first image processing result as a final image processing result comprises
Obtaining the first target image set, wherein the first target image set is an image set with the same processing requirement and comprises the first target image;
and processing the first target image set in batches according to the first processing algorithm information.
7. The method of claim 1, wherein the method comprises:
obtaining first format information of a first target image;
acquiring convertible format information of the first target image based on image format conversion software;
generating first matching auxiliary information based on the convertible format information;
and performing algorithm matching from the image processing algorithm library according to the first processing requirement, the first docking parameter set and the first matching auxiliary information to obtain first processing algorithm information.
8. An image processing system based on a multifunctional underlying algorithm, wherein the system comprises:
a first obtaining unit for obtaining a first target image based on an image acquisition device;
a second obtaining unit for obtaining a first characteristic convolution kernel;
a third obtaining unit, configured to perform traversal retrieval analysis on the first target image according to the first feature convolution kernel to obtain a first feature parameter set;
a fourth obtaining unit configured to obtain a first processing requirement of the first target image;
a fifth obtaining unit, configured to input the first processing requirement as input data into a first parameter docking model, where the first parameter docking model performs parameter docking by docking the first feature parameter set, and obtains output information of the first parameter docking model, where the output information includes a first docking parameter set;
a sixth obtaining unit, configured to obtain a preset image processing algorithm library, where the preset image processing algorithm library is a bottom algorithm library for image processing;
a seventh obtaining unit, configured to perform algorithm matching from the image processing algorithm library according to the first processing requirement and the first docking parameter set, and obtain first processing algorithm information;
a first execution unit, configured to perform image processing on the first target image according to the first processing algorithm information.
9. An image processing system based on a multi-functional underlying algorithm, comprising: a processor coupled to a memory, the memory for storing a program that, when executed by the processor, causes a system to perform the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111292499.4A CN114066828B (en) | 2021-11-03 | 2021-11-03 | Image processing method and system based on multifunctional bottom layer algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111292499.4A CN114066828B (en) | 2021-11-03 | 2021-11-03 | Image processing method and system based on multifunctional bottom layer algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114066828A true CN114066828A (en) | 2022-02-18 |
| CN114066828B CN114066828B (en) | 2022-09-02 |
Family
ID=80236602
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111292499.4A Active CN114066828B (en) | 2021-11-03 | 2021-11-03 | Image processing method and system based on multifunctional bottom layer algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114066828B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114596593A (en) * | 2022-05-10 | 2022-06-07 | 慧医谷中医药科技(天津)股份有限公司 | Health-preserving data recommendation method and system based on image processing |
| CN114674231A (en) * | 2022-03-28 | 2022-06-28 | 大连理工大学 | Portable online vision displacement measurement system based on single chip microcomputer |
| WO2024094086A1 (en) * | 2022-11-02 | 2024-05-10 | 抖音视界有限公司 | Image processing method and apparatus, device, medium and product |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102322864A (en) * | 2011-07-29 | 2012-01-18 | 北京航空航天大学 | Airborne optic robust scene matching navigation and positioning method |
| CN103886167A (en) * | 2012-11-15 | 2014-06-25 | 上海联影医疗科技有限公司 | Medical image processing method and system, client side and server |
| CN104598212A (en) * | 2013-10-30 | 2015-05-06 | 上海联影医疗科技有限公司 | Image processing method and device based on algorithm library |
| CN107945152A (en) * | 2017-10-27 | 2018-04-20 | 深圳市创科自动化控制技术有限公司 | The defects of industrial camera detecting and controlling system and method |
| CN108109417A (en) * | 2017-12-14 | 2018-06-01 | 阜阳裕晟电子科技有限公司 | A kind of vehicle broadcasting method based on image processing techniques |
| WO2018120942A1 (en) * | 2016-12-31 | 2018-07-05 | 西安百利信息科技有限公司 | System and method for automatically detecting lesions in medical image by means of multi-model fusion |
| CN108846443A (en) * | 2018-06-22 | 2018-11-20 | 成都新西旺自动化科技有限公司 | A kind of screening of visual-alignment algorithm and parameter optimization method based on large nuber of images |
| CN109615578A (en) * | 2018-11-05 | 2019-04-12 | 重庆科技学院 | Study of Medical Image Interpolation processing method and its device applied to plurality of medical scene |
| CN112019803A (en) * | 2020-05-27 | 2020-12-01 | 今瞳半导体技术(上海)有限公司 | Image signal processor, image processing apparatus, and neural network image processing system |
| CN112182148A (en) * | 2020-09-14 | 2021-01-05 | 山西和耀科技有限公司 | Standard auxiliary compiling method based on full-text retrieval |
| CN112712264A (en) * | 2020-12-31 | 2021-04-27 | 无锡软美信息科技有限公司 | Smart community information sharing method and system |
| CN113537496A (en) * | 2021-06-07 | 2021-10-22 | 贵州优联博睿科技有限公司 | Deep learning model visual construction system and application and design method thereof |
| CN113554102A (en) * | 2021-07-27 | 2021-10-26 | 高小翎 | Aviation image DSM matching method for cost calculation dynamic programming |
-
2021
- 2021-11-03 CN CN202111292499.4A patent/CN114066828B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102322864A (en) * | 2011-07-29 | 2012-01-18 | 北京航空航天大学 | Airborne optic robust scene matching navigation and positioning method |
| CN103886167A (en) * | 2012-11-15 | 2014-06-25 | 上海联影医疗科技有限公司 | Medical image processing method and system, client side and server |
| CN104598212A (en) * | 2013-10-30 | 2015-05-06 | 上海联影医疗科技有限公司 | Image processing method and device based on algorithm library |
| WO2018120942A1 (en) * | 2016-12-31 | 2018-07-05 | 西安百利信息科技有限公司 | System and method for automatically detecting lesions in medical image by means of multi-model fusion |
| CN107945152A (en) * | 2017-10-27 | 2018-04-20 | 深圳市创科自动化控制技术有限公司 | The defects of industrial camera detecting and controlling system and method |
| CN108109417A (en) * | 2017-12-14 | 2018-06-01 | 阜阳裕晟电子科技有限公司 | A kind of vehicle broadcasting method based on image processing techniques |
| CN108846443A (en) * | 2018-06-22 | 2018-11-20 | 成都新西旺自动化科技有限公司 | A kind of screening of visual-alignment algorithm and parameter optimization method based on large nuber of images |
| CN109615578A (en) * | 2018-11-05 | 2019-04-12 | 重庆科技学院 | Study of Medical Image Interpolation processing method and its device applied to plurality of medical scene |
| CN112019803A (en) * | 2020-05-27 | 2020-12-01 | 今瞳半导体技术(上海)有限公司 | Image signal processor, image processing apparatus, and neural network image processing system |
| CN112182148A (en) * | 2020-09-14 | 2021-01-05 | 山西和耀科技有限公司 | Standard auxiliary compiling method based on full-text retrieval |
| CN112712264A (en) * | 2020-12-31 | 2021-04-27 | 无锡软美信息科技有限公司 | Smart community information sharing method and system |
| CN113537496A (en) * | 2021-06-07 | 2021-10-22 | 贵州优联博睿科技有限公司 | Deep learning model visual construction system and application and design method thereof |
| CN113554102A (en) * | 2021-07-27 | 2021-10-26 | 高小翎 | Aviation image DSM matching method for cost calculation dynamic programming |
Non-Patent Citations (1)
| Title |
|---|
| 王夷恬: "嵌入式视频监控系统的FPGA图像处理子系统设计", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114674231A (en) * | 2022-03-28 | 2022-06-28 | 大连理工大学 | Portable online vision displacement measurement system based on single chip microcomputer |
| CN114596593A (en) * | 2022-05-10 | 2022-06-07 | 慧医谷中医药科技(天津)股份有限公司 | Health-preserving data recommendation method and system based on image processing |
| WO2024094086A1 (en) * | 2022-11-02 | 2024-05-10 | 抖音视界有限公司 | Image processing method and apparatus, device, medium and product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114066828B (en) | 2022-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114066828B (en) | Image processing method and system based on multifunctional bottom layer algorithm | |
| CN109447154B (en) | Picture similarity detection method, device, medium and electronic equipment | |
| JP6000455B2 (en) | Form recognition method and form recognition apparatus | |
| JP3345350B2 (en) | Document image recognition apparatus, method thereof, and recording medium | |
| US20060029276A1 (en) | Object image detecting apparatus, face image detecting program and face image detecting method | |
| CN116664559B (en) | Machine vision-based memory bank damage rapid detection method | |
| KR102073468B1 (en) | System and method for scoring color candidate poses against a color image in a vision system | |
| WO2020052270A1 (en) | Video review method and apparatus, and device | |
| WO2017161636A1 (en) | Fingerprint-based terminal payment method and device | |
| CN112489063A (en) | Image segmentation method, and training method and device of image segmentation model | |
| CN111739071A (en) | Rapid iterative registration method, medium, terminal and device based on initial value | |
| WO2022116492A1 (en) | Image template selection method and apparatus, device and storage medium | |
| CN113781511A (en) | Conveyor belt edge wear detection method and device, computer equipment and storage medium | |
| CN112801141A (en) | Heterogeneous image matching method based on template matching and twin neural network optimization | |
| JP4612477B2 (en) | Pattern recognition apparatus, pattern recognition method, pattern recognition program, and pattern recognition program recording medium | |
| CN115578594A (en) | Edge positioning method and device based on computer vision and related equipment | |
| CN113298098B (en) | Fundamental matrix estimation method and related product | |
| CN112308836B (en) | Corner detection method and device, electronic equipment and readable storage medium | |
| CN112215784B (en) | Image decontamination method, image decontamination device, readable storage medium and computer equipment | |
| CN111753723B (en) | Fingerprint identification method and device based on density calibration | |
| CN110705568B (en) | Optimization method for image feature point extraction | |
| US20190228523A1 (en) | Detecting method, detecting apparatus, and computer readable storage medium | |
| WO2021250847A1 (en) | Object identification device, object identification method, and object identification program | |
| WO2022118442A1 (en) | Parallax learning device, merge data generation device, parallax learning method, merge data generation method, and parallax learning program | |
| CN112711748B (en) | Finger vein identity authentication 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 |