CN108021603A - A kind of fabrics sample searches apparatus and method based on texture analysis and cloud computing - Google Patents

A kind of fabrics sample searches apparatus and method based on texture analysis and cloud computing Download PDF

Info

Publication number
CN108021603A
CN108021603A CN201710871870.XA CN201710871870A CN108021603A CN 108021603 A CN108021603 A CN 108021603A CN 201710871870 A CN201710871870 A CN 201710871870A CN 108021603 A CN108021603 A CN 108021603A
Authority
CN
China
Prior art keywords
fabrics
fabrics sample
photo
sample
textural characteristics
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
CN201710871870.XA
Other languages
Chinese (zh)
Inventor
胡晨鹏
顾道平
王卫军
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.)
Jiashan Sharp Lace Co Ltd
Original Assignee
Jiashan Sharp Lace Co Ltd
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 Jiashan Sharp Lace Co Ltd filed Critical Jiashan Sharp Lace Co Ltd
Priority to CN201710871870.XA priority Critical patent/CN108021603A/en
Publication of CN108021603A publication Critical patent/CN108021603A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5862Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using texture

Landscapes

  • Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Image Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a kind of fabrics sample searches device based on texture analysis and cloud computing, including the mobile equipment of front end and the high in the clouds computing engines with the rear end of the communication connection;User obtains the photo of fabrics sample by the camera unit of mobile equipment;Then the target area of fabrics sample is selected by APP on the man machine operation interface of mobile equipment;The photo of the target area of fabrics sample is uploaded to high in the clouds computing engines by the first communication unit of mobile equipment again, texture feature extraction unit carries out the photo of fabrics sample the extraction of textural characteristics;The textural characteristics extracted are compared with all textural characteristics data stored in database, draw the highest one or more comparison results of similarity;Comparison result is returned to the man machine operation interface of mobile equipment by high in the clouds computing engines, and user is presented.

Description

A kind of fabrics sample searches apparatus and method based on texture analysis and cloud computing
Technical field
The present invention relates to search technique and mobile technology field, specifically, is related specifically to a kind of based on texture point The fabrics sample searches apparatus and method of analysis and cloud computing.
Background technology
In recent years, as the expansion of dress ornament market capacity, market propose more the speed of Design of Popular Dress Ornaments and manufacturing High requirement.Within a very long time in past, design and the manufacturer of clothes are merely able to by fabrics raw material market The mode inquired select oneself need sewing material (such as lace, lace etc.).But for sewing material, Oral inquiry is a kind of method of efficiency very underground;First, oral inquiry is difficult the feature of one fabrics sample of accurate description; Secondly, the one-to-one talk of designer and businessman can take quite some effort, and the time of one day is likely to that ten can only be carried out Talk inquiry several times, is so difficult to carry out efficiently design and manufacturing process.
The content of the invention
It is an object of the invention to for deficiency of the prior art, there is provided a kind of fabrics sample searches technology, passes through base In the algorithm of textural characteristics, searched for from sample storehouse and obtain the fabrics sample with fabrics sample photo similarity maximum input by user This.
Technical problem solved by the invention can be realized using following technical scheme:
A kind of fabrics sample searches device based on texture analysis and cloud computing, including the mobile equipment of front end, Yi Jiyu The high in the clouds computing engines of the rear end of the mobile device communication connection;
The mobile equipment include man machine operation interface, photo for obtaining fabrics sample camera unit, for pair APP that the photo of the fabrics sample is handled, the first communication unit for being communicated to connect with the cloud computing platform;
The high in the clouds computing engines include the second communication unit, texture feature extraction unit and database;
Second communication unit is communicated to connect with first communication unit, for receiving the photo of fabrics sample, and Texture feature extraction unit is sent it to, the texture feature extraction unit is used to carry out line to the photo of the fabrics sample Feature extraction is managed, database is used to store the textural characteristics data imported in advance.
A kind of method based on fabrics sample searches device as claimed in claim 1, includes the following steps:
1) photo of fabrics sample is obtained by the camera unit of mobile equipment;
2) target area of fabrics sample is selected by APP on the man machine operation interface of mobile equipment;
3) photo of the target area of fabrics sample is uploaded to high in the clouds by the first communication unit of mobile equipment to calculate Second communication unit of engine;
4) photo of the fabrics sample received is sent to high in the clouds and calculated and drawn by the second communication unit of high in the clouds computing engines The texture feature extraction unit held up, and carrying for textural characteristics is carried out to the photo of fabrics sample by the texture feature extraction unit Take;
5) textural characteristics extracted are compared with all textural characteristics data stored in database, draw similar Spend highest one or more comparison results;
6) comparison result is returned to the man machine operation interface of mobile equipment by high in the clouds computing engines, and user is presented.
Further, the mobile equipment is portable equipment, including can increase the intelligent hand of the convenience of user's operation Machine and tablet computer.
Further, user selects, removes by the fabrics sample photo that APP collects camera unit into edlin Disturbing factor in sample photo, increases the accuracy of comparison result.
Further, the mobile equipment is used for the data acquisition and pretreatment for completing front end, and high in the clouds computing engines are used for Complete texture feature extraction and the comparison of rear end.
Further, the high in the clouds computing engines carry out the textural characteristics of fabrics sample photo using texture blending algorithm Extraction, textural characteristics will not be deformed with the rotation of picture, and color is changed and changed, and is appropriate for lace and lace figure The search work of case.
Further, the main step of the extraction algorithm of textural characteristics includes:
(1) local feature of fabrics samples pictures is extracted;The local feature refers to being different from surrounding in fabrics picture Partial region, the region have it is higher can discrimination, the searching of extreme point is carried out to the regional area using extraction algorithm, Extract position, scale and rotational invariants;
(2) position extracted according to step (1) step, scale and rotational invariants generation key point, and determine key point Direction and size;
(3) the description value of key point is generated according to key point;The description value possesses the energy of resistance deformation and illumination variation Power, will describe eventually for the feature of fabrics picture.
Further, the cloud computing engines have some servers using distributed deployment.
Further, the computing engines in high in the clouds are carried out using the textural characteristics that extraction obtains in pre-stored storehouse to be searched Search arithmetic, draws the highest one or more results of similarity.
Compared with prior art, beneficial effects of the present invention are as follows:
The search procedure of fabrics sample is aided in using intelligent mobile terminal and cloud computing technology, artificial inquiry is changed For the search procedure of machine;Feature extraction based on texture can solve the problems, such as that word picture is inaccurate, and the calculating in high in the clouds With storage cluster the practitioner of Design of Popular Dress Ornaments and manufacturing can be allowd to access easily all in worldwide Fabrics sample, greatly improves the efficiency for obtaining sample, and then promotes the efficiency of Design of Popular Dress Ornaments manufacture.
Brief description of the drawings
Fig. 1 is the block diagram of the fabrics sample searches device of the present invention based on texture analysis and cloud computing.
Fig. 2 is the flow chart of the fabrics sample searches method of the present invention based on texture analysis and cloud computing.
Embodiment
To make the technical means, the creative features, the aims and the efficiencies achieved by the present invention easy to understand, with reference to Embodiment, the present invention is further explained.
Referring to Fig. 1, a kind of fabrics sample searches device based on texture analysis and cloud computing of the present invention, including it is preceding The mobile equipment at end and the high in the clouds computing engines for the rear end being connected with the mobile device communication;
The mobile equipment include man machine operation interface, photo for obtaining fabrics sample camera unit, for pair APP that the photo of the fabrics sample is handled, the first communication unit for being communicated to connect with the cloud computing platform;
The high in the clouds computing engines include the second communication unit, texture feature extraction unit and database;
Second communication unit is communicated to connect with first communication unit, for receiving the photo of fabrics sample, and Texture feature extraction unit is sent it to, the texture feature extraction unit is used to carry out line to the photo of the fabrics sample Feature extraction is managed, database is used to store all textural characteristics data.
Referring to Fig. 2, a kind of fabrics sample searches method based on texture analysis and cloud computing, includes the following steps:
1) photo of fabrics sample is obtained by the camera unit of mobile equipment;
2) target area of fabrics sample is selected by APP on the man machine operation interface of mobile equipment;
3) photo of the target area of fabrics sample is uploaded to high in the clouds by the first communication unit of mobile equipment to calculate Second communication unit of engine;
4) photo of the fabrics sample received is sent to high in the clouds and calculated and drawn by the second communication unit of high in the clouds computing engines The texture feature extraction unit held up, and carrying for textural characteristics is carried out to the photo of fabrics sample by the texture feature extraction unit Take;
5) textural characteristics extracted are compared with all textural characteristics data stored in database, draw similar Spend highest one or more comparison results;
6) comparison result is returned to the man machine operation interface of mobile equipment by high in the clouds computing engines, and user is presented.
The mobile equipment is portable equipment, including can increase the smart mobile phone and tablet electricity of the convenience of user's operation Brain.
By the fabrics sample photo that APP collects camera unit into edlin, selection, removes in sample photo user Disturbing factor, increase the accuracy of comparison result.
The mobile equipment is used for the data acquisition and pretreatment for completing front end, and high in the clouds computing engines are used to complete rear end Texture feature extraction and comparison.
The high in the clouds computing engines extract the textural characteristics of fabrics sample photo using texture blending algorithm, texture Feature will not be deformed with the rotation of picture, and color is changed and changed, and is appropriate for the search work of lace and lace pattern Make.
The step that the extraction algorithm of textural characteristics is main includes:
(1) local feature of fabrics samples pictures is extracted;The local feature refers to being different from surrounding in fabrics picture Partial region, the region have it is higher can discrimination, the searching of extreme point is carried out to the regional area using extraction algorithm, Extract position, scale and rotational invariants;
(2) position extracted according to step (1) step, scale and rotational invariants generation key point, and determine key point Direction and size;
(3) the description value of key point is generated according to key point;The description value possesses the energy of resistance deformation and illumination variation Power, will describe eventually for the feature of fabrics picture.
The cloud computing engines have some servers using distributed deployment.
The computing engines in high in the clouds scan for computing using the textural characteristics that extraction obtains in pre-stored storehouse to be searched, Draw the highest one or more results of similarity.
Compared with prior art, the features of the present invention is as follows:
1. using mobile equipment, such as smart mobile phone, tablet computer etc., the photo acquisition work of fabrics sample is carried out, can be with Greatly increase the convenience of user's operation.
2. user can select so that user can use up to the fabrics sample photo that mobile equipment collects into edlin Amount removes the disturbing factor in sample photo, increases the accuracy of search result.
3. the texture feature extraction that fabrics sample photo is carried out using the computing engines in high in the clouds is worked, the computing of mobile terminal Ability and battery capacity are all limited, are not appropriate for the work largely calculated, the present invention uses the framework of cloud computing, by calculation amount The computing engines of big work arrangements beyond the clouds are completed.
4. the computing engines in high in the clouds extract the textural characteristics of fabrics sample photo using texture blending algorithm, texture Feature will not be deformed with the rotation of picture, and color is changed and changed, and be particularly suitable for carrying out the pattern such as lace, lace Search work.
5. the fabrics sample storehouse with search has carried out the extraction work of textural characteristics in advance via high in the clouds computing engines, and Among the storage cluster of storage beyond the clouds.
6. by the computing engines in high in the clouds by the texture feature information of the fabrics sample newly obtained and pre-stored textural characteristics Storehouse scans for calculating, and obtains the highest one or more results of similarity;This search calculating process can be in distributed deployment Multiple servers on carry out, to obtain highest operation efficiency.
7. search result can be returned directly on the mobile terminal device of user, user can be very easily in mobile equipment It is upper to carry out browsing for search result.
The basic principles, main features and the advantages of the invention have been shown and described above.The technology of the industry Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this The principle of invention, without departing from the spirit and scope of the present invention, various changes and modifications of the present invention are possible, these changes Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its Equivalent thereof.

Claims (9)

1. a kind of fabrics sample searches device based on texture analysis and cloud computing, it is characterised in that the movement including front end is set The high in the clouds computing engines of rear end that are standby and being connected with the mobile device communication;
The mobile equipment includes man machine operation interface, the camera unit of photo for obtaining fabrics sample, for described APP that the photo of fabrics sample is handled, the first communication unit for being communicated to connect with the cloud computing platform;
The high in the clouds computing engines include the second communication unit, texture feature extraction unit and database;
Second communication unit and first communication unit communicate to connect, for receiving the photo of fabrics sample, and by its Texture feature extraction unit is sent to, the texture feature extraction unit is used to carry out the photo of the fabrics sample texture spy Sign extraction, database are used to store the textural characteristics data imported in advance.
A kind of 2. method based on fabrics sample searches device as claimed in claim 1, it is characterised in that including following step Suddenly:
1) photo of fabrics sample is obtained by the camera unit of mobile equipment;
2) target area of fabrics sample is selected by APP on the man machine operation interface of mobile equipment;
3) photo of the target area of fabrics sample is uploaded to high in the clouds computing engines by the first communication unit of mobile equipment The second communication unit;
4) photo of the fabrics sample received is sent to high in the clouds computing engines by the second communication unit of high in the clouds computing engines Texture feature extraction unit, and by extraction of the texture feature extraction unit to the photo progress textural characteristics of fabrics sample;
5) textural characteristics extracted are compared with all textural characteristics data stored in database, draw similarity most High one or more comparison results;
6) comparison result is returned to the man machine operation interface of mobile equipment by high in the clouds computing engines, and user is presented.
3. the fabrics sample searches device according to claim 1 based on texture analysis and cloud computing, it is characterised in that institute It is portable equipment to state mobile equipment, including can increase the smart mobile phone and tablet computer of the convenience of user's operation.
4. the fabrics sample searches method according to claim 2 based on texture analysis and cloud computing, it is characterised in that use Family by the fabrics sample photo that APP collects camera unit into edlin, selection, remove interference in sample photo because Element, increases the accuracy of comparison result.
5. the fabrics sample searches method according to claim 2 based on texture analysis and cloud computing, it is characterised in that institute Data acquisition and pretreatment that mobile equipment is used to complete front end are stated, the textural characteristics that high in the clouds computing engines are used to complete rear end carry Take and compare.
6. the fabrics sample searches method according to claim 2 based on texture analysis and cloud computing, it is characterised in that institute State high in the clouds computing engines to extract the textural characteristics of fabrics sample photo using texture blending algorithm, textural characteristics will not be with The rotation of picture, is deformed, color is changed and changed, and is appropriate for the search work of lace and lace pattern.
7. according to claim 2 fill method based on the fabrics sample searches of texture analysis and cloud computing, it is characterised in that The step that the extraction algorithm of textural characteristics is main includes:
(1) local feature of fabrics samples pictures is extracted;The local feature refers to being different from peripheral part in fabrics picture Region, the region have it is higher can discrimination, the searching of extreme point, extraction are carried out to the regional area using extraction algorithm Position, scale and rotational invariants;
(2) position extracted according to step (1) step, scale and rotational invariants generation key point, and determine the side of key point To and size;
(3) the description value of key point is generated according to key point;The description value possesses the ability of resistance deformation and illumination variation, will Described eventually for the feature of fabrics picture.
8. the fabrics sample searches device according to claim 1 based on texture analysis and cloud computing, it is characterised in that institute Stating cloud computing engines has some servers using distributed deployment.
9. the fabrics sample searches method according to claim 2 based on texture analysis and cloud computing, it is characterised in that cloud The computing engines at end scan for computing using the textural characteristics that extraction obtains in pre-stored storehouse to be searched, draw similarity Highest one or more result.
CN201710871870.XA 2017-09-25 2017-09-25 A kind of fabrics sample searches apparatus and method based on texture analysis and cloud computing Pending CN108021603A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710871870.XA CN108021603A (en) 2017-09-25 2017-09-25 A kind of fabrics sample searches apparatus and method based on texture analysis and cloud computing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710871870.XA CN108021603A (en) 2017-09-25 2017-09-25 A kind of fabrics sample searches apparatus and method based on texture analysis and cloud computing

Publications (1)

Publication Number Publication Date
CN108021603A true CN108021603A (en) 2018-05-11

Family

ID=62079574

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710871870.XA Pending CN108021603A (en) 2017-09-25 2017-09-25 A kind of fabrics sample searches apparatus and method based on texture analysis and cloud computing

Country Status (1)

Country Link
CN (1) CN108021603A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102231148A (en) * 2010-11-29 2011-11-02 辜进荣 Visual information searching method
CN103064981A (en) * 2013-01-18 2013-04-24 浪潮电子信息产业股份有限公司 Method for searching images on basis of cloud computing
CN106547760A (en) * 2015-09-18 2017-03-29 广州盖特软件有限公司 A kind of leather cloth colour atla image indexing system
CN106557489A (en) * 2015-09-25 2017-04-05 南京理工大学 A kind of dress ornament searching method based on mobile terminal
CN106599311A (en) * 2016-12-29 2017-04-26 广州市奥威亚电子科技有限公司 Cloud computation-based internet education platform resource library image retrieval method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102231148A (en) * 2010-11-29 2011-11-02 辜进荣 Visual information searching method
CN103064981A (en) * 2013-01-18 2013-04-24 浪潮电子信息产业股份有限公司 Method for searching images on basis of cloud computing
CN106547760A (en) * 2015-09-18 2017-03-29 广州盖特软件有限公司 A kind of leather cloth colour atla image indexing system
CN106557489A (en) * 2015-09-25 2017-04-05 南京理工大学 A kind of dress ornament searching method based on mobile terminal
CN106599311A (en) * 2016-12-29 2017-04-26 广州市奥威亚电子科技有限公司 Cloud computation-based internet education platform resource library image retrieval method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
ADMIN: "基于特征提取的布料花纹图像检索系统", 《HTTPS://WWW.ZJSRU.EDU.CN/INFO/1055/3041.HTM》 *
梁翯: "基于手机的服装检索系统设计与实现", 《万方学术论文库》 *

Similar Documents

Publication Publication Date Title
US9396560B2 (en) Image-based color palette generation
US9552656B2 (en) Image-based color palette generation
US9311889B1 (en) Image-based color palette generation
CN100456300C (en) Method for searching 3D model based on 2D sketch
CN100578508C (en) Interactive type image search system and method
US20150379738A1 (en) Automatic color palette based recommendations
Chen et al. Poseshop: Human image database construction and personalized content synthesis
CN104765891A (en) Searching shopping method based on pictures
CN107209631A (en) User terminal and its method for displaying image for display image
WO2016091114A1 (en) Information pushing method and device
CN107169247A (en) The household profession service platform designed based on 3D clouds
JP2018081692A (en) Aesthetic search engine
CN105117399B (en) Image searching method and device
CN105868219A (en) Information release method and apparatus
JP2011221606A (en) Information processing method and graphical user interface
KR102517961B1 (en) Method for providing clothing recommendation information based on user-selected clothing, and server and program using the same
CN111767817B (en) Dress collocation method and device, electronic equipment and storage medium
CN105701300A (en) Spacecraft electrical information query system
CN104951770A (en) Construction method and application method for face image database as well as corresponding devices
CN109145911A (en) A kind of street is taken a picture target person extracting method
CN108875828A (en) A kind of fast matching method and system of similar image
CN105247606B (en) A kind of photo display methods and user terminal
CN106557489B (en) Clothing searching method based on mobile terminal
GB2501473A (en) Image based clothing search and virtual fitting
CN104361347A (en) Numerically-controlled machine tool design module three-dimension model retrieval method based on single image

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

Application publication date: 20180511

RJ01 Rejection of invention patent application after publication