CN108596189A - A kind of general Digital Image Processing frame - Google Patents

A kind of general Digital Image Processing frame Download PDF

Info

Publication number
CN108596189A
CN108596189A CN201810335584.6A CN201810335584A CN108596189A CN 108596189 A CN108596189 A CN 108596189A CN 201810335584 A CN201810335584 A CN 201810335584A CN 108596189 A CN108596189 A CN 108596189A
Authority
CN
China
Prior art keywords
image processing
digital image
feature
standard
processing frame
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.)
Pending
Application number
CN201810335584.6A
Other languages
Chinese (zh)
Inventor
迟冬祥
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Dianji University
Original Assignee
Shanghai Dianji University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Dianji University filed Critical Shanghai Dianji University
Priority to CN201810335584.6A priority Critical patent/CN108596189A/en
Publication of CN108596189A publication Critical patent/CN108596189A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/44Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/44Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/56Extraction of image or video features relating to colour

Abstract

The invention discloses a kind of general Digital Image Processing frames, which is characterized in that includes the following steps:Step 1. reads the feature of digital picture;Step 2. setting convergence target carries out calculation process, monitoring convergence target component to the digital picture feature of input;Step 3. checks whether convergence target component is up to standard, if not up to standard, continue to execute edge filter operation, carries out step 2;Otherwise, terminating edge filtering operation carries out step 4;The result of step 4. output digital image processing.In the application of any Digital Image Processing, the frame of the present invention is a design implementation framework being referred to, the frame has the advantages that restrain certainly, be automatically performed, and has real value in practical applications, in theory have stability and exploitativeness.

Description

A kind of general Digital Image Processing frame
Technical field
The present invention relates to a kind of general Digital Image Processing frames, belong to digital image processing field.
Background technology
Patent " frame (the application number based on study for personalized image quality evaluation and optimization: 201610901175.9) ", be it is a kind of for provide for user carry out individuation picture quality optimization it is computer implemented Method comprising:Computer is received the raw image data that is obtained from image scanner and is marked based on raw image data Know one or more original image quality features.Computer by one or more user preferences by being applied to one or more originals Beginning Image quality measures automatically determine one or more objective image quality features.Computer also mesh based on one or more Logo image qualitative character automatically determines one or more processing parameters.Then computer can use one or more processing Parameter handles raw image data to generate image.Such as above-mentioned existing patent is typically directed to concrete application and implements Different algorithms lacks technology implementation framework that can be general.
Invention content
The technical problem to be solved by the present invention is to:Solve the problems, such as how to realize general technology implementation framework.
In order to solve the above-mentioned technical problem, the technical solution of the present invention is to provide a kind of general Digital Image Processing frames Frame, which is characterized in that include the following steps:
Step 1. reads the feature of digital picture;
Step 2. setting convergence target carries out calculation process, monitoring convergence target component to the digital picture feature of input;
Step 3. checks whether convergence target component is up to standard, if not up to standard, continue to execute edge filter operation, is walked Rapid 2;Otherwise, terminating edge filtering operation carries out step 4;
The result of step 4. output digital image processing.
Preferably, the feature of the digital picture refers to the digital picture to be calculated based on Pixel of Digital Image value Feature.
Preferably, the feature of the digital picture includes pixel grey scale feature, color character, provincial characteristics, texture spy One or more of sign, contour feature, edge feature, corner feature.
Preferably, border template is used to the digital picture in the step 2, carries out the filtering operation of individual element, A variance yields is preset, and using default variance yields and calculates the difference of variance yields as convergence target component.
Preferably, check that convergence target component criterion whether up to standard is in the step 3:It is primary complete executing After whole edge filter operates, the difference preset variance yields with calculate variance yields is calculated, if difference still above 0, is not It is up to standard;Otherwise, as up to standard.
Preferably, the result in the step 4 is content associated with Digital Image Processing,
Preferably, the content associated with Digital Image Processing is a kind of image processing effect or an identification mesh Mark.
In the application of any Digital Image Processing, frame of the invention is that frame is implemented in a design being referred to Frame, the frame make any one Digital Image Processing application that can follow this method, realize that adaptive iteration executes, with Reach design object, has the advantages that restrain certainly, be automatically performed, have real value in practical applications, in theory There are stability and exploitativeness.
Description of the drawings
Fig. 1 is a kind of flow chart of general Digital Image Processing frame.
Specific implementation mode
In order to make the present invention more obvious and understandable, hereby with preferred embodiment, and attached drawing is coordinated to be described in detail below.
The present invention is a kind of general Digital Image Processing frame, refers to the process flow of a set of processing digital picture, the stream Journey have general structure, including digital picture feature input, can be with the output of convergent iterative processing method, frame.Such as Shown in Fig. 1 comprising following steps:
Step 1. read digital picture feature, such as pixel grey scale feature, color character, provincial characteristics, textural characteristics, One or more of contour feature, edge feature, corner feature etc.;
In instances, a gray-scale image is selected, using its gray-scale pixel values directly as the spy of the digital picture Sign;
Step 2. setting convergence target carries out calculation process, monitoring convergence target component to the digital picture feature of input;
Convergence target should be the limiting value or boundary value of a certain parameter calculated value, in image per treatment and count in this way Undated parameter after calculation, calculating parameter value restrain the difference of desired value with it.Restraining the difference of desired value and calculating parameter should be It gradually reduces, be intended to 0.
In instances, the border template for using the digital picture 3 × 3, carries out the filtering operation of individual element, due to every After the marginal operation of complete image, the variance of the pixel value of image can all become larger, therefore preset a greater variance value, and It regard default variance yields as convergence target component with the difference (default variance yields, which subtracts, calculates variance yields) for calculating variance yields;
Step 3. checks whether convergence target component is up to standard, with determine whether to continue can convergent iterative processing side Method;If not up to standard, edge filter operation is continued to execute, step 2 is carried out;Otherwise, terminating edge filtering operation carries out step 4;
In instances, it after executing primary complete edge filter operation, calculates and presets variance yields and calculate variance yields Difference (default variance yields subtract calculate variance yields), it is no if difference still above 0, continues to execute edge filter operation Then with regard to terminating edge filtering operation;
The result of step 4. output digital image processing;
In instances, the digital picture iterated to calculate by multiple edge filter is provided.
By above scheme, the adaptive approach frame that can be executed with iteration by one completes preset processing mesh Mark.The versatility of the program ensure that the stabilization of algorithm frame and can restrain, and have real value in practical applications, in theory Have stability and exploitativeness.
Digital picture feature:It refer to the feature of the digital picture to be calculated based on Pixel of Digital Image value.These are special Sign be calculated by common digital image processing method, such as pixel grey scale feature, color character, provincial characteristics, Textural characteristics, contour feature, edge feature, corner feature etc..Certainly, it is not limited to that, as long as pixel value can be passed through The characteristic quantity being calculated all can serve as the feature of digital picture.With the progress of correlative study, more digitized maps are had As feature extraction comes.
It can convergent iterative processing method:Refer under the frame, the method used can be executed with loop iteration, And in operation each time, it can determine whether the iteration execution under the frame continues to execute by monitoring some parameter Or terminate to execute.
The output (i.e. the result of output digital image processing) of frame:Referring to the frame, convergence target, complete can reaching After convergent iterative processing method, expected results are produced.This result is usually a kind of image processing effect, an identification Target etc. content associated with Digital Image Processing.
Processing target based on the digital picture feature of frame input of the invention, and output;The processing frame it Under, it is that iteration is supported to execute that can apply a variety of digital image processing methods, these methods to the digital picture feature of input, And it can be to some target convergence.
The characteristics of present invention is according to Digital Image Processing, a kind of frame that can be executed with iteration of design, under the frame, Pixel value based on picture and color character so that any one relevant Digital Image Processing application can follow we Method realizes that adaptive iteration executes, realizes approaching for design object, to complete design target.

Claims (7)

1. a kind of general Digital Image Processing frame, which is characterized in that include the following steps:
Step 1. reads the feature of digital picture;
Step 2. setting convergence target carries out calculation process, monitoring convergence target component to the digital picture feature of input;
Step 3. checks whether convergence target component is up to standard, if not up to standard, continue to execute edge filter operation, carries out step 2; Otherwise, terminating edge filtering operation carries out step 4;
The result of step 4. output digital image processing.
2. a kind of general Digital Image Processing frame as described in claim 1, which is characterized in that the digital picture Feature refers to the feature of the digital picture to be calculated based on Pixel of Digital Image value.
3. a kind of general Digital Image Processing frame as claimed in claim 1 or 2, which is characterized in that the digitized map The feature of picture includes pixel grey scale feature, color character, provincial characteristics, textural characteristics, contour feature, edge feature, angle point spy One or more of sign.
4. a kind of general Digital Image Processing frame as described in claim 1, which is characterized in that in the step 2 Digital picture use border template, carry out the filtering operation of individual element, preset a variance yields, and by default variance yields with The difference of variance yields is calculated as convergence target component.
5. a kind of general Digital Image Processing frame as described in claim 1, which is characterized in that examined in the step 3 It checks and accepts and holds back target component criterion whether up to standard and be:After executing primary complete edge filter operation, calculate default Variance yields and the difference for calculating variance yields, if difference still above 0, is not up to standard;Otherwise, as up to standard.
6. a kind of general Digital Image Processing frame as described in claim 1, which is characterized in that in the step 4 As a result it is content associated with Digital Image Processing.
7. a kind of general Digital Image Processing frame as claimed in claim 6, which is characterized in that described and digital picture It is a kind of image processing effect or an identification target to handle associated content.
CN201810335584.6A 2018-04-13 2018-04-13 A kind of general Digital Image Processing frame Pending CN108596189A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810335584.6A CN108596189A (en) 2018-04-13 2018-04-13 A kind of general Digital Image Processing frame

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810335584.6A CN108596189A (en) 2018-04-13 2018-04-13 A kind of general Digital Image Processing frame

Publications (1)

Publication Number Publication Date
CN108596189A true CN108596189A (en) 2018-09-28

Family

ID=63622391

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810335584.6A Pending CN108596189A (en) 2018-04-13 2018-04-13 A kind of general Digital Image Processing frame

Country Status (1)

Country Link
CN (1) CN108596189A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102156966A (en) * 2011-04-11 2011-08-17 北方工业大学 Medical image denoising
US20120269458A1 (en) * 2007-12-11 2012-10-25 Graziosi Danillo B Method for Generating High Resolution Depth Images from Low Resolution Depth Images Using Edge Layers
CN104240189A (en) * 2013-06-17 2014-12-24 富士通株式会社 Filtering method and device for restoring anti-aliasing edges

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120269458A1 (en) * 2007-12-11 2012-10-25 Graziosi Danillo B Method for Generating High Resolution Depth Images from Low Resolution Depth Images Using Edge Layers
CN102156966A (en) * 2011-04-11 2011-08-17 北方工业大学 Medical image denoising
CN104240189A (en) * 2013-06-17 2014-12-24 富士通株式会社 Filtering method and device for restoring anti-aliasing edges

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
吴一全 等: "改进投影梯度NMF的NSST域多光谱与全色图像融合", 《光学学报》 *

Similar Documents

Publication Publication Date Title
US8411979B2 (en) Digital image processing and enhancing system and method with function of removing noise
WO2013168618A1 (en) Image processing device and image processing method
WO2016206087A1 (en) Low-illumination image processing method and device
CN109978890A (en) Target extraction method, device and terminal device based on image procossing
JPH11150669A (en) Image improving device
CN107784631B (en) Image deblurring method and device
CN105404846A (en) Image processing method and apparatus
CN108182671B (en) Single image defogging method based on sky area identification
JP5703255B2 (en) Image processing apparatus, image processing method, and program
KR101682830B1 (en) Image processing apparatus and image processing method
CN113592782B (en) Method and system for extracting X-ray image defects of composite material carbon fiber core rod
WO2020107308A1 (en) Low-light-level image rapid enhancement method and apparatus based on retinex
Vyavahare et al. Segmentation using region growing algorithm based on CLAHE for medical images
JP6800676B2 (en) Image processing equipment, image processing methods and programs
CN108596189A (en) A kind of general Digital Image Processing frame
CN108717699B (en) Ultrasonic image segmentation method based on continuous minimum segmentation
EP3028251B1 (en) Image manipulation
JP4742068B2 (en) Image processing method, image processing system, and image processing program
EP3384673B1 (en) Noise-cancelling filter for video images
CN107220952B (en) Multi-scale image smoothing method based on significance
CN109636735A (en) A kind of fast video defogging method based on space-time consistency constraint
JP2009050035A (en) Image processing method, image processing system, and image processing program
CN108734703B (en) Polished tile printing pattern detection method, system and device based on machine vision
KR100565209B1 (en) Apparatus and method for improving image sharpness based on human visual system
CN109284769A (en) A kind of underwater picture adaptive classification method based on quantization parameter

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180928