CN110791942A - Method for evaluating contamination degree of light-colored clothes in image analysis system - Google Patents
Method for evaluating contamination degree of light-colored clothes in image analysis system Download PDFInfo
- Publication number
- CN110791942A CN110791942A CN201911106040.3A CN201911106040A CN110791942A CN 110791942 A CN110791942 A CN 110791942A CN 201911106040 A CN201911106040 A CN 201911106040A CN 110791942 A CN110791942 A CN 110791942A
- Authority
- CN
- China
- Prior art keywords
- clothes
- threshold value
- light
- dirty
- area
- 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
Classifications
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06H—MARKING, INSPECTING, SEAMING OR SEVERING TEXTILE MATERIALS
- D06H3/00—Inspecting textile materials
- D06H3/08—Inspecting textile materials by photo-electric or television means
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Materials Engineering (AREA)
- Textile Engineering (AREA)
- Image Analysis (AREA)
Abstract
At present, stains on clothes are used as a standard substance for testing the performance of a detergent and a washing machine, and the washing evaluation of the stains has two subjective evaluation methods and an objective evaluation method. Subjective evaluation has large influence factors, objective evaluation requires testing by special equipment (such as whiteness and spectrophotometer, etc.) and operators, and the test result is susceptible to the influence of factors such as test position, area, light, etc., and the obtained result cannot comprehensively reflect the performance of stains. In order to solve the above problems, the present invention provides a method for evaluating the degree of soiling of light-colored laundry in an image analysis system. With the development and application of computer image analysis technology, the image analysis technology can rapidly, comprehensively, objectively and accurately analyze the whole image. The invention can better comprehensively analyze the stains on the clothes by utilizing the image analysis technology, thereby realizing intelligent washing and protecting and playing a guiding role for actual production.
Description
Technical Field
The invention relates to the field of computer processing, in particular to a method for evaluating the stain and dirt degree of light-color clothes.
Background
With the arrival of the artificial intelligence era, the intelligent integration of the household appliance field and the Internet of things is imperative, and intelligent laundry becomes the development trend of the washing machine industry. At present, the intelligent washing machine is mainly embodied in personalized washing, a wifi washing machine, intelligent detergent addition and the like, all of which are used for washing all clothes simultaneously, so that slightly-dirty clothes are easily washed excessively, the clothes are subjected to redundant abrasion, waste of water, electricity and detergent is caused, and the dirty clothes cannot be washed cleanly. If the degree of dirt and stain on clothes can be analyzed, intelligent washing can be realized by combining a detergent and a washing machine, and resources can be effectively and reasonably utilized under the condition of ensuring the washing effect. In addition, the washing effect of the detergent and the washing machine may be evaluated.
At present, stains on clothes are used as a standard substance for testing the performance of a detergent and a washing machine, and the washing evaluation of the stains has two subjective evaluation methods and an objective evaluation method. Subjective evaluation has large influence factors, objective evaluation requires testing by special equipment (such as whiteness and spectrophotometer, etc.) and operators, and the test result is susceptible to the influence of factors such as test position, area, light, etc., and the obtained result cannot comprehensively reflect the performance of stains.
Disclosure of Invention
The purpose of the invention is: a method for evaluating the degree of dirt on dirt is provided, which is beneficial to realizing intelligent washing.
In order to achieve the above object, the present invention provides a method for evaluating the degree of soiling of light-colored clothing in an image analysis system, comprising the steps of:
step 1, distributing independent clothes IDs for all different light-color clothes owned by a current user, respectively shooting non-dirty images of all light-color clothes by utilizing a camera before the light-color clothes are not stained with any stains, and storing the non-dirty images of all light-color clothes and the clothes IDs of all light-color clothes in a database in an associated manner;
step 2, obtaining the clothes ID of a piece of light-color clothes after the light-color clothes are stained with stains, and then shooting a stained image with the stains by using the same camera equipment as that in the step 1;
step 3, finding the non-dirty image associated with the current clothes ID in the database through the clothes ID obtained in the step 2;
step 4, converting the non-dirty image obtained in the step 3 into a non-dirty gray level image by using image processing software, and calculating to obtain a non-dirty gray level histogram of the non-dirty gray level image;
for the dirty image obtained in the step 2, on one hand, after the dirty image is converted into a dirty gray image by using image processing software, a dirty gray histogram of the dirty gray image is obtained through calculation; on the other hand, after all the dirty areas in the dirty image are segmented by adopting an image segmentation technology, the area size of each dirty area is calculated;
step 5, comparing the non-dirty gray level histogram with the dirty gray level histogram to obtain each gray level value with the changed gray level frequency, and taking the average value of all the gray level values as the gray level average value;
calculating the area average value of all the stain areas obtained in the step 4 as the area average value;
step 6, dividing the dirt degree into mild degree, moderate degree and severe degree, and respectively setting a gray threshold value I and an area threshold value I corresponding to the mild degree, a gray threshold value II and an area threshold value II corresponding to the moderate degree and a gray threshold value III corresponding to the severe degree, wherein the gray threshold value I is larger than the gray threshold value II and larger than the gray threshold value III, and the area threshold value I is smaller than the area threshold value II;
under the condition that the gray level mean value obtained in the step 5 is larger than the gray level threshold value one, if the area mean value obtained in the step 5 is smaller than the area threshold value two, judging the dirt degree of the current light-color clothes to be light, otherwise, judging the dirt degree of the current light-color clothes to be moderate;
under the condition that the gray level mean value obtained in the step 5 is smaller than the gray level threshold value one and larger than the gray level threshold value two, if the area mean value obtained in the step 5 is smaller than the area threshold value one, the degree of soiling of the current light-color clothes is judged to be light, if the area mean value obtained in the step 5 is larger than the area threshold value one and smaller than the area threshold value two, the degree of soiling of the current light-color clothes is judged to be moderate, and if the area mean value obtained in the step 5 is larger than the area threshold value two, the degree of soiling of the current light-color clothes is judged to be;
under the condition that the gray average value obtained in the step 5 is smaller than a gray threshold value two and larger than a gray threshold value three, if the area average value obtained in the step 5 is smaller than an area threshold value one, judging the dirt degree of the current light-color clothes to be moderate, otherwise, judging the dirt degree of the current light-color clothes to be severe;
and under the condition that the gray level mean value obtained in the step 5 is smaller than the gray level threshold value three, if the area mean value obtained in the step 5 is smaller than the area threshold value one, judging the contamination degree of the current light-color clothes to be moderate, otherwise, judging the contamination degree of the current light-color clothes to be severe.
Preferably, the clothes ID is recorded on a barcode label fixed on the light-colored clothes, and in step 2, the clothes ID of the light-colored clothes is obtained by reading the barcode label of the current light-colored clothes.
Preferably, the barcode label is a one-dimensional code label or a two-dimensional code label.
With the development and application of computer image analysis technology, the image analysis technology can rapidly, comprehensively, objectively and accurately analyze the whole image. The invention can better comprehensively analyze the stains on the clothes by utilizing the image analysis technology, thereby realizing intelligent washing and protecting and playing a guiding role for actual production.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.
As shown in fig. 1, the present invention provides a method for evaluating a degree of soiling of light-colored laundry in an image analysis system, including the steps of:
step 1, distributing independent clothes IDs for all different light-color clothes owned by the current user. The clothes ID is stored in the database, meanwhile, the clothes ID is also stored on the light-color clothes through some medium, for example, a two-dimensional code can be added on a collar label of the light-color clothes, the clothes ID of the current light-color clothes is stored in the two-dimensional code, and the user can obtain the clothes ID of the current light-color clothes after scanning the two-dimensional code through a mobile phone. The two-dimensional code can be added to the washing label of the light-colored clothes, and the user can obtain the clothes ID by scanning the two-dimensional code. Of course, one skilled in the art can also use a one-dimensional code instead of a two-dimensional code, and at the same time, the clothing ID can even be stored by an RFID tag, fixed on light-colored clothing, or integrated in a collar tag or a water washing tag, regardless of cost.
Before the light-colored clothes are not stained with any stains, a camera (such as a camera of a mobile phone used by a user) is used for shooting non-staining images of the light-colored clothes respectively. The method comprises the steps that a mobile phone of a user uploads a non-dirty image of each light-color piece of clothes and a clothes ID of each light-color piece of clothes to a server, and the server stores the non-dirty image and the clothes ID in a database in an associated mode.
And 2, when a certain light-color clothes is stained and needs to be cleaned when being worn, a user obtains the clothes ID of the current light-color clothes by scanning a collar label of the light-color clothes or a two-dimensional code on a washing label and the like, and then a camera of the used mobile phone is used for shooting a stained image with stains. And uploading the clothes ID and the corresponding dirty image to a server by a mobile phone of a user.
And 3, searching the non-dirty image associated with the current clothes ID in the database by the server through the clothes ID uploaded by the user.
And 4, in the following steps, the server can process the non-dirty image and the dirty image to judge the dirty degree of the light-color clothes, and can also issue the dirty image to the mobile phone, and the mobile phone locally processes the non-dirty image and the dirty image to judge the dirty degree of the light-color clothes.
And 3, converting the non-dirty image obtained in the step 3 into a non-dirty gray level image by using image processing software, and calculating to obtain a non-dirty gray level histogram of the non-dirty gray level image.
For the dirty image obtained in step 2, on one hand, the dirty image is converted into a dirty gray image by using image processing software, and then a dirty gray histogram of the dirty gray image is obtained by calculation. On the other hand, after all the dirty areas in the dirty image are segmented by adopting an image segmentation technology, the area size of each dirty area is calculated.
And 5, comparing the non-pollution gray level histogram with the pollution gray level histogram to obtain each gray level value with the frequency change of the gray level values, and taking the average value of all the gray level values as the gray level average value.
And (4) calculating the average value of the areas of all the stain areas obtained in the step (4) as the area average value.
Step 6, dividing the dirt degree into mild degree, moderate degree and severe degree, and respectively setting a gray threshold value I and an area threshold value I corresponding to the mild degree, a gray threshold value II and an area threshold value II corresponding to the moderate degree and a gray threshold value III corresponding to the severe degree, wherein the gray threshold value I is larger than the gray threshold value II and larger than the gray threshold value III, and the area threshold value I is smaller than the area threshold value II;
under the condition that the gray level mean value obtained in the step 5 is larger than the gray level threshold value one, if the area mean value obtained in the step 5 is smaller than the area threshold value two, judging the dirt degree of the current light-color clothes to be light, otherwise, judging the dirt degree of the current light-color clothes to be moderate;
under the condition that the gray level mean value obtained in the step 5 is smaller than the gray level threshold value one and larger than the gray level threshold value two, if the area mean value obtained in the step 5 is smaller than the area threshold value one, the degree of soiling of the current light-color clothes is judged to be light, if the area mean value obtained in the step 5 is larger than the area threshold value one and smaller than the area threshold value two, the degree of soiling of the current light-color clothes is judged to be moderate, and if the area mean value obtained in the step 5 is larger than the area threshold value two, the degree of soiling of the current light-color clothes is judged to be;
under the condition that the gray average value obtained in the step 5 is smaller than a gray threshold value two and larger than a gray threshold value three, if the area average value obtained in the step 5 is smaller than an area threshold value one, judging the dirt degree of the current light-color clothes to be moderate, otherwise, judging the dirt degree of the current light-color clothes to be severe;
and under the condition that the gray level mean value obtained in the step 5 is smaller than the gray level threshold value three, if the area mean value obtained in the step 5 is smaller than the area threshold value one, judging the contamination degree of the current light-color clothes to be moderate, otherwise, judging the contamination degree of the current light-color clothes to be severe.
Claims (3)
1. A method for evaluating the degree of soiling of light-colored clothing in an image analysis system, comprising the steps of:
step 1, distributing independent clothes IDs for all different light-color clothes owned by a current user, respectively shooting non-dirty images of all light-color clothes by utilizing a camera before the light-color clothes are not stained with any stains, and storing the non-dirty images of all light-color clothes and the clothes IDs of all light-color clothes in a database in an associated manner;
step 2, obtaining the clothes ID of a piece of light-color clothes after the light-color clothes are stained with stains, and then shooting a stained image with the stains by using the same camera equipment as that in the step 1;
step 3, finding the non-dirty image associated with the current clothes ID in the database through the clothes ID obtained in the step 2;
step 4, converting the non-dirty image obtained in the step 3 into a non-dirty gray level image by using image processing software, and calculating to obtain a non-dirty gray level histogram of the non-dirty gray level image;
for the dirty image obtained in the step 2, on one hand, after the dirty image is converted into a dirty gray image by using image processing software, a dirty gray histogram of the dirty gray image is obtained through calculation; on the other hand, after all the dirty areas in the dirty image are segmented by adopting an image segmentation technology, the area size of each dirty area is calculated;
step 5, comparing the non-dirty gray level histogram with the dirty gray level histogram to obtain each gray level value with the changed gray level frequency, and taking the average value of all the gray level values as the gray level average value;
calculating the area average value of all the stain areas obtained in the step 4 as the area average value;
step 6, dividing the dirt degree into mild degree, moderate degree and severe degree, and respectively setting a gray threshold value I and an area threshold value I corresponding to the mild degree, a gray threshold value II and an area threshold value II corresponding to the moderate degree and a gray threshold value III corresponding to the severe degree, wherein the gray threshold value I is larger than the gray threshold value II and larger than the gray threshold value III, and the area threshold value I is smaller than the area threshold value II;
under the condition that the gray level mean value obtained in the step 5 is larger than the gray level threshold value one, if the area mean value obtained in the step 5 is smaller than the area threshold value two, judging the dirt degree of the current light-color clothes to be light, otherwise, judging the dirt degree of the current light-color clothes to be moderate;
under the condition that the gray level mean value obtained in the step 5 is smaller than the gray level threshold value one and larger than the gray level threshold value two, if the area mean value obtained in the step 5 is smaller than the area threshold value one, the degree of soiling of the current light-color clothes is judged to be light, if the area mean value obtained in the step 5 is larger than the area threshold value one and smaller than the area threshold value two, the degree of soiling of the current light-color clothes is judged to be moderate, and if the area mean value obtained in the step 5 is larger than the area threshold value two, the degree of soiling of the current light-color clothes is judged to be;
under the condition that the gray average value obtained in the step 5 is smaller than a gray threshold value two and larger than a gray threshold value three, if the area average value obtained in the step 5 is smaller than an area threshold value one, judging the dirt degree of the current light-color clothes to be moderate, otherwise, judging the dirt degree of the current light-color clothes to be severe;
and under the condition that the gray level mean value obtained in the step 5 is smaller than the gray level threshold value three, if the area mean value obtained in the step 5 is smaller than the area threshold value one, judging the contamination degree of the current light-color clothes to be moderate, otherwise, judging the contamination degree of the current light-color clothes to be severe.
2. The method for evaluating the dirtiness of the light color clothes in the image analyzing system as claimed in claim 1, wherein said clothes ID is recorded on a bar code label fixed on the light color clothes, and in step 2, the clothes ID of the light color clothes is obtained by reading the bar code label of the current light color clothes.
3. The method for evaluating the dirtiness of light-colored clothes in an image analysis system according to claim 2, wherein said bar code label is a one-dimensional code label or a two-dimensional code label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911106040.3A CN110791942B (en) | 2019-11-13 | 2019-11-13 | Method for evaluating contamination degree of light-colored clothes in image analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911106040.3A CN110791942B (en) | 2019-11-13 | 2019-11-13 | Method for evaluating contamination degree of light-colored clothes in image analysis system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110791942A true CN110791942A (en) | 2020-02-14 |
| CN110791942B CN110791942B (en) | 2021-06-25 |
Family
ID=69444311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911106040.3A Active CN110791942B (en) | 2019-11-13 | 2019-11-13 | Method for evaluating contamination degree of light-colored clothes in image analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110791942B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI772985B (en) * | 2019-12-02 | 2022-08-01 | 奧地利商蘭仁股份有限公司 | Method and apparatus for determining at least one of degree of whiteness and color value of yarn |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5883971A (en) * | 1996-10-23 | 1999-03-16 | International Business Machines Corporation | System and method for determining if a fingerprint image contains an image portion representing a smudged fingerprint impression |
| CN102682514A (en) * | 2012-05-17 | 2012-09-19 | 广州广电运通金融电子股份有限公司 | Paper identification method and relative device |
| CN102720033A (en) * | 2012-06-26 | 2012-10-10 | 无锡小天鹅股份有限公司 | Method for distinguishing smudgy degree of clothes |
| CN103529057A (en) * | 2013-10-21 | 2014-01-22 | 国网河南省电力公司驻马店供电公司 | Device and method for detecting pollution of insulator by image analysis combined with ultrasonic principle |
| CN104775278A (en) * | 2015-03-26 | 2015-07-15 | 无锡小天鹅股份有限公司 | Washing machine, system of washing machine, detection method for dirt on inner bucket wall of washing machine and image processing device |
| CN105628563A (en) * | 2014-10-31 | 2016-06-01 | 五邑大学 | Rapid measuring method of detergency of washing agents on fabric, and measuring device thereof |
| CN105839355A (en) * | 2016-05-19 | 2016-08-10 | 无锡小天鹅股份有限公司 | Washing machine and method, and device for recognizing colors of clothes in washing machine |
| DE102016212976A1 (en) * | 2016-07-15 | 2018-01-18 | Henkel Ag & Co. Kgaa | Method and device for determining in particular a cleaning strategy |
| CN108921831A (en) * | 2018-06-22 | 2018-11-30 | 吉林大学 | It is a kind of that coin discriminating method is stained based on image processing techniques |
-
2019
- 2019-11-13 CN CN201911106040.3A patent/CN110791942B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5883971A (en) * | 1996-10-23 | 1999-03-16 | International Business Machines Corporation | System and method for determining if a fingerprint image contains an image portion representing a smudged fingerprint impression |
| CN102682514A (en) * | 2012-05-17 | 2012-09-19 | 广州广电运通金融电子股份有限公司 | Paper identification method and relative device |
| CN102720033A (en) * | 2012-06-26 | 2012-10-10 | 无锡小天鹅股份有限公司 | Method for distinguishing smudgy degree of clothes |
| CN103529057A (en) * | 2013-10-21 | 2014-01-22 | 国网河南省电力公司驻马店供电公司 | Device and method for detecting pollution of insulator by image analysis combined with ultrasonic principle |
| CN105628563A (en) * | 2014-10-31 | 2016-06-01 | 五邑大学 | Rapid measuring method of detergency of washing agents on fabric, and measuring device thereof |
| CN104775278A (en) * | 2015-03-26 | 2015-07-15 | 无锡小天鹅股份有限公司 | Washing machine, system of washing machine, detection method for dirt on inner bucket wall of washing machine and image processing device |
| CN105839355A (en) * | 2016-05-19 | 2016-08-10 | 无锡小天鹅股份有限公司 | Washing machine and method, and device for recognizing colors of clothes in washing machine |
| DE102016212976A1 (en) * | 2016-07-15 | 2018-01-18 | Henkel Ag & Co. Kgaa | Method and device for determining in particular a cleaning strategy |
| CN108921831A (en) * | 2018-06-22 | 2018-11-30 | 吉林大学 | It is a kind of that coin discriminating method is stained based on image processing techniques |
Non-Patent Citations (1)
| Title |
|---|
| 张谦等: "无纺布成品表面污渍机器视觉检测***的设计", 《华南理工大学学报(自然科学版)》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI772985B (en) * | 2019-12-02 | 2022-08-01 | 奧地利商蘭仁股份有限公司 | Method and apparatus for determining at least one of degree of whiteness and color value of yarn |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110791942B (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110004664B (en) | Clothes stain recognition method and device, washing machine and storage medium | |
| CN102393397B (en) | System and method for detecting surface defects of magnetic shoe | |
| Liong et al. | Leather defect classification and segmentation using deep learning architecture | |
| CN108765402B (en) | Non-woven fabric defect detection and classification method | |
| CN110866515B (en) | Method and device for identifying behaviors of objects in factory building and electronic equipment | |
| Lumauag et al. | Fish tracking and counting using image processing | |
| Furferi et al. | Machine vision-based pilling assessment: a review | |
| Fekri-Ershad et al. | A robust approach for surface defect detection based on one dimensional local binary patterns | |
| CN110791942B (en) | Method for evaluating contamination degree of light-colored clothes in image analysis system | |
| CN111160451A (en) | Flexible material detection method and storage medium thereof | |
| Meng et al. | Woven fabric density measurement by using multi-scale convolutional neural networks | |
| Pierleoni et al. | A machine vision system for manual assembly line monitoring | |
| CN114372980A (en) | Industrial defect detection method and system | |
| Dlamini et al. | Developing a surface mount technology defect detection system for mounted devices on printed circuit boards using a MobileNetV2 with Feature Pyramid Network | |
| WO2019151177A1 (en) | Information processing device, clothing sorting system, information processing method, and control program | |
| CN114226262A (en) | Flaw detection method, flaw classification method and flaw detection system | |
| CN112176642A (en) | Control processing method and device for washing machine | |
| Dawda et al. | Defects detection in highly specular surface using a combination of stereo and laser reconstruction | |
| CN116258703A (en) | Defect detection method, defect detection device, electronic equipment and computer readable storage medium | |
| Shreya et al. | Design of machine vision system for high speed manufacturing environments | |
| CN115399697A (en) | Self-cleaning method and device for cleaning equipment, storage medium and electronic device | |
| Orjuela et al. | Feature extraction of the wear label of carpets by using a novel 3d scanner | |
| CN101598675B (en) | Method for identifying mutual information of cotton foreign fiber | |
| Sharma et al. | Digital image patch based randomized crack detection in concrete structures | |
| CN114742850A (en) | UGNX model analysis-based electrode shape automatic identification implementation method |
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 |