CN109410241A - The metamorphic testing method of image-region growth algorithm - Google Patents
The metamorphic testing method of image-region growth algorithm Download PDFInfo
- Publication number
- CN109410241A CN109410241A CN201811265885.2A CN201811265885A CN109410241A CN 109410241 A CN109410241 A CN 109410241A CN 201811265885 A CN201811265885 A CN 201811265885A CN 109410241 A CN109410241 A CN 109410241A
- Authority
- CN
- China
- Prior art keywords
- image
- growth
- case
- region
- test
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3684—Test management for test design, e.g. generating new test cases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3688—Test management for test execution, e.g. scheduling of test suites
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to image-region growth algorithm the field of test technology, and in particular to a kind of metamorphic testing method of image-region growth algorithm.Image-region growth is one of critical function of scan picture.However, being difficult to obtain the test judgement of image-region growth algorithm in actual test due to operating probabilistic factor.Based on this, metamorphic testing method is applied in the test of image-region growth algorithm by the present invention, a series of transformation relationships are extracted by the geometric attribute, numerical attribute and algorithmic characteristic of parser, the metamorphic testing method that image-region growth algorithm is formed based on these transformation relationships, can efficiently solve the test judgement problem of image-region growth algorithm.
Description
Technical field
The invention belongs to image-region growth algorithm the field of test technology, and in particular to a kind of image-region growth algorithm
Metamorphic testing method.
Background technique
In recent years, with the rapid development of the technologies such as virtual reality, big data, artificial intelligence, aerospace, realtime graphic
Processing has been commonly applied to the every field such as military battlefield environment, Intelligent life, aerospace, and is in different fields
Reveal it is specialized, detailed-oriented, precision, real time implementation the characteristics of.Image-region growth is the basic function of scan picture, it
Refer to the process of pixel groups of in image or the region regional development Cheng Geng great.Since the set of seed point, region growing
It is by with each seed point will there is the adjacent pixel of like attribute such as intensity, gray level, texture color etc. to be merged into this area
The process in domain.
Currently, passing through the standard of artificial reconstruction's image-region growth algorithm for the test job of image-region growth procedure
The method that model compares carries out, comprising steps of
Step 1: the description reconstruction of standard model according to image-region growth algorithm.
Step 2: the input of construction image algorithm of region growing test case.
Step 3: test case input data being used for tested program, exports measured result.
Step 4: test case input data being used for master pattern, exports expected result.
Step 5: test judgement, i.e. comparison measured result and standard results determine tested program just if result is consistent
Really, if result is inconsistent, determine tested program mistake.
In software test field, test judgement typically refer to one kind be able to detect the whether correct mechanism of test result (on
It states step 5 and belongs to test judgement).The core of the above method is the artificial description reconstruct mark according to image-region growth algorithm
Quasi-mode type, and implementation of test cases obtains the expected result that output is used as tested software test judgement, is used for tested program
Test judgement, the maximum defect of this method is, since reconstruction of standard model is realized by h coding, therefore reconstruction of standard model
The correctness of itself introduces the uncertainty of test judgement, is difficult to obtain the expected results being absolutely correct in other words, depend on
The data that non-algorithm built-in attribute but external master pattern generate.It, may be to figure if mistake occurs in reconstruction of standard model
As the test job of region growing program brings following two categories problem:
One, tested program is correct, but due to master pattern mistake, test judgement is caused not pass through, and judges program error by accident, i.e.,
False retrieval.
Two, tested program mistake, but due to master pattern mistake, cause test judgement to pass through, erroneous judgement program is correct, that is, leaks
Inspection.
Above-mentioned analysis it is found that image-region growth algorithm because use the output of reconstruction of standard model as expected result carry out
Test judgement introduces false retrieval and missing inspection problem, if obtains the expected results being absolutely correct and is difficult to define.It therefore can only be to survey
Examination determines whether there is other feasible patterns and conducts a research
Summary of the invention
(1) technical problems to be solved
Sentence the technical problem to be solved by the present invention is how to solve to test in image-region growth algorithm conventional test methodologies
Surely it is difficult to the problem of obtaining.
(2) technical solution
In order to solve the above technical problems, the present invention provides a kind of metamorphic testing method of image-region growth algorithm, packet
Include following steps:
Step 1: it is raw that geometric attribute, numerical attribute, algorithmic characteristic according to image-region growth algorithm extract image-region
The transformation relationship of long algorithm；
Step 2: according to original test case, constructing additional testing use-case in conjunction with transformation relationship；
Step 3: the image-region growth procedure that original test case and the input of additional testing use-case are tested judges to change in quality
Whether relationship meets.
Wherein, include: that transformation relationship is extracted according to the geometric attribute of image-region growth algorithm in the step 1:
Gray level image is handled by image-region growth algorithm, constructs transformation relationship according to image geometry rotational characteristics；According to
The data orga-nizational format of gray level image constructs transverse and longitudinal coordinate using picture centre as origin；Given starting seed point S (j, k),
In the case where growing threshold and growth number threshold value, original image I rotates around x axis to obtain new image I ', corresponding seed point
Become S ' (j, k), the region growing result of I ' symmetric relation corresponding with the holding of the growth result of I；Original image I is revolved around y-axis
Turn to obtain new image I ', corresponding seed point becomes S ' (j, k), and the region growing result of I ' keeps phase with the growth result of I
The symmetric relation answered；Original image I rotates to obtain new image I ' around leading diagonal, and corresponding seed point becomes S ' (j, k), I '
Region growing result symmetric relation corresponding with the holding of the growth result of I.
It wherein, include: that transformation relationship is extracted according to the numerical attribute of image growth algorithm in the step 1；
Whether the judgment criterion of image-region growth algorithm is the gray scale difference value of two neighboring pixel in growing threshold,
If therefore whole increase and decrease and scaling are done to the gray value of whole image, then the result after region growing should remain unchanged.
It wherein, include: that transformation relationship is extracted according to the algorithmic characteristic of image growth algorithm in the step 1；
Select a certain seed point, by this put centered on divide the image into four pieces, four blocks of images after segmentation are done respectively
Region growing, the result after growth should be consistent with the result after original image region growing after splicing again；For image-region
The principle features of growth, if image is expressed as A, B there are two pieces of disconnected growth domains, if input seed point is in A
Portion, then region growing cannot grow into B area；
The selection of seed point is changed, other parameters do not adjust；
If seed point is still in threshold value growth scope, then growth result should be consistent；If seed point is not given
In threshold value growth scope, then growth result and initial growth result must be without overlapping regions；Change growing threshold, other parameters are not
It adjusts, if increasing growing threshold, growth scope should also be as expanding accordingly, if growth number is reduced, then growth scope is answered
Reduce or remain unchanged when accordingly.
Wherein, the step 2: according to original test case, additional testing use-case is constructed in conjunction with transformation relationship；
For metamorphic testing, if the distance between original use-case and additional use-case are bigger, their execution difference is just
It is bigger；Therefore, during metamorphic testing, it is believed that original use-case and additional use-case can preferentially be selected to use apart from biggish test
Example；Based on this priori knowledge, self-adapting random Test Strategy is introduced to the generation of original test case and additional testing use-case
Cheng Zhong, referred to as the metamorphic testing use-case generating algorithm based on self-adapting random Test Strategy；It is original to calculate separately multiple candidates
Test case selects to use apart from maximum use-case as next test the distance between to their corresponding additional testing use-cases
Example；If there is the distance of multiple candidate use-cases is maximum, then compare them to the distance of implementation of test cases set, selects distance
It is maximum to be used as next test case, i.e. additional testing use-case.
Wherein, the tested image-region of original test case and the input of additional testing use-case the step 3: is grown into journey
Sequence, judges whether transformation relationship meets.
The step is directed to the original test case of every a pair and additional testing use-case, is input in image-region growth procedure,
Check whether original test output and additional testing output meet requirement of the transformation relationship for output, if transformation relationship meets
Illustrate not find tested image-region growth procedure mistake, if transformation relationship is unsatisfactory for, illustrates tested image-region growth journey
There are software defects for sequence；After recording current use-case phenomenon, other use-cases are continued to execute, until all use-cases are finished.
(3) beneficial effect
Compared with prior art, metamorphic testing method is applied to the test of image-region growth algorithm program by the present invention
In, the metamorphic testing method of image-region growth algorithm is formed, solves the test of image-region growth algorithm conventional test methodologies
Judgement is difficult to the problem of obtaining.
Detailed description of the invention
Fig. 1 is flow chart of the method for the present invention.
Specific embodiment
To keep the purpose of the present invention, content and advantage clearer, with reference to the accompanying drawings and examples, to of the invention
Specific embodiment is described in further detail.
Metamorphic testing is a kind of test method for test judgement problem, has already been through the development of last decade, extensively
In test applied to different field software, for example, the test of Solving Partial Differential Equations program, the test of embedded program, machine
The test of device learning software, the test of computer graphical software for calculation, the test of graph theory program, the test of numerical analysis software,
The test of stochastic optimization program, classification and clustering algorithm realize the test of program, and planning algorithm realizes the test of program, emulation
The test of software and Biomedical Model realize that the test of program, the application being no lack of on class of algorithms software have been compared at present
It is more mature.Metamorphic testing basic ideas are that inherent transformation relationship is established based on demand (i.e. when program input meets certain pass
When being, corresponding output also just must satisfy certain relationship), according to transformation relationship and original Test cases technology additional testing
Use-case, then by finding to whether there is defect in program to the satisfaction of transformation relationship between two kinds of test case outputs,
And defect is positioned.Briefly, metamorphic testing is exactly that follow-up test use is generated using some successful test cases
A kind of technology of example, since subsequent test case and the relationship between the former are referred to as transformation relationship, such test
Technology is also referred to as metamorphic testing technology.
Traditional reconstruction of standard Model test Method, model are h coding, and different testers can reconstruct not
Same master pattern, the subjective factor of tester will lead to the great uncertainty that master pattern has, since it is to non-
The dependence of objective factor inside algorithm leads to not learn whether the model output for test case expected result is absolutely quasi-
Really, it will affect the credibility of test result when so being used for test judgement.And the basic thought of metamorphic testing method is to work as
Its corresponding output must satisfy certain transformation relationship when program input meets certain relationship, several inside algorithm
What attribute, numerical attribute and algorithmic characteristic, since reconstruct mark can be well solved without obtaining absolutely accurate expected result
The problem of the test judgement uncertainty of quasi-mode type.
In order to solve the above technical problems, the present invention provides a kind of metamorphic testing method of image-region growth algorithm, such as Fig. 1
It is shown comprising following steps:
Step 1: it is raw that geometric attribute, numerical attribute, algorithmic characteristic according to image-region growth algorithm extract image-region
The transformation relationship of long algorithm；
Step 2: according to original test case, constructing additional testing use-case in conjunction with transformation relationship；
Step 3: the image-region growth procedure that original test case and the input of additional testing use-case are tested judges to change in quality
Whether relationship meets.
Wherein, include: that transformation relationship is extracted according to the geometric attribute of image-region growth algorithm in the step 1:
Gray level image is handled by image-region growth algorithm, constructs transformation relationship according to image geometry rotational characteristics；According to
The data orga-nizational format of gray level image constructs transverse and longitudinal coordinate using picture centre as origin；Given starting seed point S (j, k),
In the case where growing threshold and growth number threshold value, original image I rotates around x axis to obtain new image I ', corresponding seed point
Become S ' (j, k), the region growing result of I ' symmetric relation corresponding with the holding of the growth result of I；Original image I is revolved around y-axis
Turn to obtain new image I ', corresponding seed point becomes S ' (j, k), and the region growing result of I ' keeps phase with the growth result of I
The symmetric relation answered；Original image I rotates to obtain new image I ' around leading diagonal, and corresponding seed point becomes S ' (j, k), I '
Region growing result symmetric relation corresponding with the holding of the growth result of I.
It wherein, include: that transformation relationship is extracted according to the numerical attribute of image growth algorithm in the step 1；
Whether the judgment criterion of image-region growth algorithm is the gray scale difference value of two neighboring pixel in growing threshold,
If therefore whole increase and decrease and scaling are done to the gray value of whole image, then the result after region growing should remain unchanged.
It wherein, include: that transformation relationship is extracted according to the algorithmic characteristic of image growth algorithm in the step 1；
Select a certain seed point, by this put centered on divide the image into four pieces, four blocks of images after segmentation are done respectively
Region growing, the result after growth should be consistent with the result after original image region growing after splicing again；For image-region
The principle features of growth, if image is expressed as A, B there are two pieces of disconnected growth domains, if input seed point is in A
Portion, then region growing cannot grow into B area；
The selection of seed point is changed, other parameters do not adjust；
If seed point is still in threshold value growth scope, then growth result should be consistent；If seed point is not given
In threshold value growth scope, then growth result and initial growth result must be without overlapping regions；Change growing threshold, other parameters are not
It adjusts, if increasing growing threshold, growth scope should also be as expanding accordingly, if growth number is reduced, then growth scope is answered
Reduce or remain unchanged when accordingly.
Wherein, the step 2: according to original test case, additional testing use-case is constructed in conjunction with transformation relationship；
For metamorphic testing, if the distance between original use-case and additional use-case are bigger, their execution difference is just
It is bigger；Therefore, during metamorphic testing, it is believed that original use-case and additional use-case can preferentially be selected to use apart from biggish test
Example；Based on this priori knowledge, self-adapting random Test Strategy is introduced to the generation of original test case and additional testing use-case
Cheng Zhong, referred to as the metamorphic testing use-case generating algorithm based on self-adapting random Test Strategy；It is original to calculate separately multiple candidates
Test case selects to use apart from maximum use-case as next test the distance between to their corresponding additional testing use-cases
Example；If there is the distance of multiple candidate use-cases is maximum, then compare them to the distance of implementation of test cases set, selects distance
It is maximum to be used as next test case, i.e. additional testing use-case.
Wherein, the tested image-region of original test case and the input of additional testing use-case the step 3: is grown into journey
Sequence, judges whether transformation relationship meets.
The step is directed to the original test case of every a pair and additional testing use-case, is input in image-region growth procedure,
Check whether original test output and additional testing output meet requirement of the transformation relationship for output, if transformation relationship meets
Illustrate not find tested image-region growth procedure mistake, if transformation relationship is unsatisfactory for, illustrates tested image-region growth journey
There are software defects for sequence；After recording current use-case phenomenon, other use-cases are continued to execute, until all use-cases are finished.
To sum up, the invention belongs to image-region growth algorithm the field of test technology, and in particular to a kind of image-region growth
The metamorphic testing method of algorithm.Image-region growth is one of critical function of scan picture.However, not true due to operating
Qualitative factor is difficult in actual test to obtain the test judgement of image-region growth algorithm.Based on this, the present invention, which will change in quality, to be surveyed
Method for testing is applied in the test of image-region growth algorithm, passes through the geometric attribute, numerical attribute and algorithm of parser
Feature extraction goes out a series of transformation relationships, and the metamorphic testing method of image-region growth algorithm is formed based on these transformation relationships,
The test judgement problem of image-region growth algorithm can be efficiently solved.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (6)
1. a kind of metamorphic testing method of image-region growth algorithm, which is characterized in that it includes the following steps:
Step 1: geometric attribute, numerical attribute, algorithmic characteristic according to image-region growth algorithm extract image-region growth and calculate
The transformation relationship of method；
Step 2: according to original test case, constructing additional testing use-case in conjunction with transformation relationship；
Step 3: by the image-region growth procedure that original test case and the input of additional testing use-case are tested, judging transformation relationship
Whether meet.
2. the metamorphic testing method of image-region growth algorithm as described in claim 1, which is characterized in that in the step 1
Include: that transformation relationship is extracted according to the geometric attribute of image-region growth algorithm:
Gray level image is handled by image-region growth algorithm, constructs transformation relationship according to image geometry rotational characteristics；According to gray scale
The data orga-nizational format of image constructs transverse and longitudinal coordinate using picture centre as origin；In given starting seed point S (j, k), growth
In the case where threshold value and growth number threshold value, original image I rotates around x axis to obtain new image I ', and corresponding seed point becomes
The region growing result of S ' (j, k), I ' symmetric relation corresponding with the holding of the growth result of I；Original image I is rotated around y-axis
To new image I ', corresponding seed point becomes S ' (j, k), and the region growing result of I ' is corresponding with the holding of the growth result of I
Symmetric relation；Original image I rotates to obtain new image I ' around leading diagonal, and corresponding seed point becomes S ' (j, k), the area of I '
Domain growth result symmetric relation corresponding with the holding of the growth result of I.
3. the metamorphic testing method of image-region growth algorithm as described in claim 1, which is characterized in that in the step 1
It include: that transformation relationship is extracted according to the numerical attribute of image growth algorithm；
Whether the judgment criterion of image-region growth algorithm is the gray scale difference value of two neighboring pixel in growing threshold, therefore
If whole increase and decrease and scaling are done to the gray value of whole image, then the result after region growing should remain unchanged.
4. the metamorphic testing method of image-region growth algorithm as described in claim 1, which is characterized in that in the step 1
It include: that transformation relationship is extracted according to the algorithmic characteristic of image growth algorithm；
Select a certain seed point, by this put centered on divide the image into four pieces, region is done respectively to four blocks of images after segmentation
Growth, the result after growth should be consistent with the result after original image region growing after splicing again；It is grown for image-region
Principle features, if image is expressed as A, B there are two pieces of disconnected growth domains, if input seed point inside A, that
Region growing cannot grow into B area；
The selection of seed point is changed, other parameters do not adjust；
If seed point is still in threshold value growth scope, then growth result should be consistent；If seed point is not in given threshold value
In growth scope, then growth result and initial growth result must be without overlapping regions；Change growing threshold, other parameters are not adjusted
Whole, if increasing growing threshold, growth scope should also be as expanding accordingly, if growth number is reduced, then growth scope should phase
The reduction answered remains unchanged.
5. the metamorphic testing method of image-region growth algorithm as described in claim 1, which is characterized in that the step 2: according to
According to original test case, additional testing use-case is constructed in conjunction with transformation relationship；
For metamorphic testing, if the distance between original use-case and additional use-case are bigger, their execution difference is bigger；
Therefore, during metamorphic testing, it is believed that can preferentially select original use-case and additional use-case apart from biggish test case；Base
In this priori knowledge, self-adapting random Test Strategy is introduced into original test case and the generating process of additional testing use-case,
The referred to as metamorphic testing use-case generating algorithm based on self-adapting random Test Strategy；The original test of multiple candidates is calculated separately to use
Example arrives the distance between their corresponding additional testing use-cases, selects apart from maximum use-case as next test case；Such as
Fruit has the distance of multiple candidate use-cases maximum, then compares them to the distance of implementation of test cases set, and selection is apart from maximum
The next test case of conduct, i.e. additional testing use-case.
6. the metamorphic testing method of image-region growth algorithm as described in claim 1, which is characterized in that the step 3: will
The image-region growth procedure that original test case and the input of additional testing use-case are tested, judges whether transformation relationship meets.
The step is directed to the original test case of every a pair and additional testing use-case, is input in image-region growth procedure, checks
Whether original test output and additional testing output meet requirement of the transformation relationship for output, illustrate if transformation relationship meets
Tested image-region growth procedure mistake is not found, if transformation relationship is unsatisfactory for, illustrates that tested image-region growth procedure is deposited
In software defect；After recording current use-case phenomenon, other use-cases are continued to execute, until all use-cases are finished.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811265885.2A CN109410241A (en) | 2018-10-29 | 2018-10-29 | The metamorphic testing method of image-region growth algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811265885.2A CN109410241A (en) | 2018-10-29 | 2018-10-29 | The metamorphic testing method of image-region growth algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109410241A true CN109410241A (en) | 2019-03-01 |
Family
ID=65470071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811265885.2A Pending CN109410241A (en) | 2018-10-29 | 2018-10-29 | The metamorphic testing method of image-region growth algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109410241A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111124895A (en) * | 2019-12-06 | 2020-05-08 | 北京京航计算通讯研究所 | Metamorphic testing method for primary and secondary peak ratio calculation algorithm |
| CN111124896A (en) * | 2019-12-06 | 2020-05-08 | 北京京航计算通讯研究所 | Metamorphic test system for primary and secondary peak ratio calculation algorithm |
| CN111552649A (en) * | 2020-05-18 | 2020-08-18 | 支付宝(杭州)信息技术有限公司 | Packet testing method and device |
| CN111830935A (en) * | 2020-07-23 | 2020-10-27 | 深圳慕智科技有限公司 | Metamorphic test method for automatic driving system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104572462A (en) * | 2014-12-31 | 2015-04-29 | 中国人民解放军理工大学 | Method for generating metamorphic test case based on adaptive random strategy |
| CN107808322A (en) * | 2017-10-19 | 2018-03-16 | 河海大学 | User oriented big data personalized recommendation system metamorphic testing method |
-
2018
- 2018-10-29 CN CN201811265885.2A patent/CN109410241A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104572462A (en) * | 2014-12-31 | 2015-04-29 | 中国人民解放军理工大学 | Method for generating metamorphic test case based on adaptive random strategy |
| CN107808322A (en) * | 2017-10-19 | 2018-03-16 | 河海大学 | User oriented big data personalized recommendation system metamorphic testing method |
Non-Patent Citations (2)
| Title |
|---|
| CHAO JIANG ET AL.: "Metamorphic Testing of Image Region Growth Programs in Image Processing Applications", 《2018 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE QUALITY, RELIABILITY AND SECURITY COMPANION (QRS-C)》 * |
| 刘俊等: "一种改进的基于区域生长的彩色图像分割方法", 《计算机应用与软件》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111124895A (en) * | 2019-12-06 | 2020-05-08 | 北京京航计算通讯研究所 | Metamorphic testing method for primary and secondary peak ratio calculation algorithm |
| CN111124896A (en) * | 2019-12-06 | 2020-05-08 | 北京京航计算通讯研究所 | Metamorphic test system for primary and secondary peak ratio calculation algorithm |
| CN111552649A (en) * | 2020-05-18 | 2020-08-18 | 支付宝(杭州)信息技术有限公司 | Packet testing method and device |
| CN111552649B (en) * | 2020-05-18 | 2022-02-22 | 支付宝(杭州)信息技术有限公司 | Packet testing method and device |
| CN111830935A (en) * | 2020-07-23 | 2020-10-27 | 深圳慕智科技有限公司 | Metamorphic test method for automatic driving system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109410241A (en) | The metamorphic testing method of image-region growth algorithm | |
| CN113362326A (en) | Method and device for detecting welding spot defects of battery | |
| CN110136101B (en) | Tire X-ray defect detection method based on twinning distance comparison | |
| CN104680542B (en) | Remote sensing image variation detection method based on on-line study | |
| CN110310262A (en) | A kind of method, apparatus and system for detection wheel tyre defect | |
| WO2023050563A1 (en) | Autoencoder-based detection method for defective area of colored textured fabric | |
| CN109919934A (en) | A kind of liquid crystal display panel defect inspection method based on the study of multi-source domain depth migration | |
| CN109447968A (en) | The metamorphic testing system of image-region growth algorithm | |
| CN107966444B (en) | Textile flaw detection method based on template | |
| CN109002792B (en) | SAR image change detection method based on layered multi-model metric learning | |
| CN111178392B (en) | Aero-engine hole detection image damage segmentation method based on deep neural network | |
| CN113643268A (en) | Industrial product defect quality inspection method and device based on deep learning and storage medium | |
| US20220076404A1 (en) | Defect management apparatus, method and non-transitory computer readable medium | |
| CN117152484B (en) | Small target cloth flaw detection method based on improved YOLOv5s | |
| CN111124895B (en) | Metamorphic testing method for primary and secondary peak ratio calculation algorithm | |
| CN103839271A (en) | Method for image texture synthesis based on optimum matching | |
| CN110033434A (en) | A kind of detection method of surface flaw based on texture conspicuousness | |
| CN110660049A (en) | Tire defect detection method based on deep learning | |
| CN111753877B (en) | Product quality detection method based on deep neural network migration learning | |
| CN116205876A (en) | Unsupervised notebook appearance defect detection method based on multi-scale standardized flow | |
| CN118196095B (en) | Textile surface defect detection method | |
| CN111124896B (en) | Metamorphic test system for primary and secondary peak ratio calculation algorithm | |
| CN113554630A (en) | Chip surface defect detection method, system, computer device and storage medium | |
| CN115222649A (en) | System, apparatus and method for detecting and classifying patterns of heatmaps | |
| CN110458809B (en) | Yarn evenness detection method based on sub-pixel edge detection |
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: 20190301 |