CN109299721A - A kind of vegetable identifying system and method based on image recognition technology - Google Patents
A kind of vegetable identifying system and method based on image recognition technology Download PDFInfo
- Publication number
- CN109299721A CN109299721A CN201810820901.3A CN201810820901A CN109299721A CN 109299721 A CN109299721 A CN 109299721A CN 201810820901 A CN201810820901 A CN 201810820901A CN 109299721 A CN109299721 A CN 109299721A
- Authority
- CN
- China
- Prior art keywords
- module
- picture
- recognition
- vegetable
- identification
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K19/00—Record carriers for use with machines and with at least a part designed to carry digital markings
- G06K19/06—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code
- G06K19/06009—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code with optically detectable marking
- G06K19/06046—Constructional details
- G06K19/06103—Constructional details the marking being embedded in a human recognizable image, e.g. a company logo with an embedded two-dimensional code
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of vegetable identifying system and method based on image recognition technology, including obtaining module, picture processing module, picture recognition module, control module and coding generation module, the acquisition module includes photo module and receiving module, the photo module is identified for shooting photo, directly using camera function by information shoot come, the receiving module is used to receive the picture transmitted by network, then it is identified, the picture processing module includes filtering module, binaryzation and denoising module and segmentation module, the filtering module is used to filter the illegal picture with illegal feature, the binaryzation and denoising module are for removing picture some useless frames and boundary.The vegetable identifying system and method based on image recognition technology, can not only quickly identify vegetable, easy to operate, but also can the picture after identification be stored and be encoded, and subsequent use is convenient for.
Description
Technical field
The present invention relates to a kind of vegetable identifying system and method based on image recognition technology, belong to vegetable technical field.
Background technique
Vegetable refers to that a course, each grand hotel have tens vegetables to select for client, such as: grandmother's pork braised in brown sauce, chopped chilli fish
Head, side fish meat.Vegetable photographs is added, then is come out by menu manufacturing company design and printing, in this way more convenient for client's choosing
It is very clear to select.The dish of each veriety.Southern Dynasties's beam is heavy about " with about Master's book ": " year when packet a round bamboo basket, every to see request, all vegetables of fainting must
It enables to recommend." Song Hong xun, one of the Eight Diagrams " the unrestrained record of Yang paddy ": " vegetable the first is green onion Spice.".Now with Chinese and Western culture exchange gradually plus
It is deep, the cuisine of many cooks' study be also it is more and more, the type that a person sponging on an aristocrat touches vegetable is more and more abundant, however in cook and
In itself outgoing learning process of a person sponging on an aristocrat, if cannot understand in time for those still unacquainted vegetables liked, will be
Unfortunately, one kind is sorry for the portion of one cuisines hobby, misses if not understanding, that is a kind of matter of regret.
It is present to solve the problems, such as because of a kind of vegetable identifying system and method based on image recognition technology of the invention,
It is the current most important thing.
Summary of the invention
It is an object of the invention to invent a kind of vegetable identifying system and method based on image recognition technology, on solving
State the problem of proposing in background technique.
Realizing the technical solution of above-mentioned purpose is: the vegetable identifying system based on image recognition technology of one of present invention,
Including obtaining module, picture processing module, picture recognition module, control module and coding generation module, the acquisition module, figure
Piece processing module, picture recognition module, control module and coding generation module are placed in inside identification device.
Preferably, the acquisition module includes photo module and receiving module, the photo module for shoot photo into
Row identification is directly shot information then to be identified, the receiving module by network for connecing using camera function
The picture transmitted is received, is then identified.
Preferably, the picture processing module includes filtering module, binaryzation and denoising module and segmentation module, institute
Filtering module is stated for filtering the illegal picture with illegal feature.
Preferably, the binaryzation and denoising module are described for removing picture some useless frames and boundary
Divide module to be used to picture segmentation be one or more picture with notable feature.
Preferably, the picture recognition module includes outline identification unit, feature identification unit and color recognition unit, institute
Outline identification unit is stated for carrying out overall profile identification to picture, and generates outline identification information, the feature identification unit
For carrying out feature identification to the picture after segmentation module segmentation, and feature identification information is generated, the color recognition unit is used
In carrying out overall color identification to picture, and color identification information is generated.
Preferably, the control module includes processor, storage device, network module, display screen and key, the processing
Device is used for integrated treatment information, and is connected to the network Cloud Server, realizes search and identification function, the storage device is for depositing
Common pictorial information is stored up, convenient for carrying out Direct Recognition to simple picture.
Preferably, the network module includes 4G module, 5G module and WIFI module, network module for network transmission and
Receive information, the display screen for showing pictorial information and segment word information, the key for execution part order and
Importation explanation.
Preferably, the coding generation module is used for after picture recognition success, carries out coding of graphics processing, generates picture
Picture recognition is encoded deposit storage device by identification coding, and use when facilitating next picture recognition increases inner capacities.
Preferably, identification device is robot, mobile phone, tablet computer, desktop computer or industrial personal computer;
Identification device further include: be stored with the big data platform of all kinds of vegetable picture features;
When the picture recognition module is analyzed and processed image data, with the vegetable stored in the big data platform
Picture feature data are compared.
The recognition methods of the vegetable identifying system based on image recognition technology of the two of the present invention, comprising the following steps:
S1: picture, the picture being filmed from photo module, data transmission or network downloading from receiving module are obtained
Picture, and show on a display screen, after confirmation, selection is identified;
S2: being filtered picture by filtering module, avoids the importing and propagation of illegal contents,
It is then carried out if normal picture in next step,
It then feeds back if illegal picture to processor, illegal contents processing is marked, and store information into storage dress
It sets, Direct Recognition is illegal contents when next time identifies;
S3: being removed processing to picture by binaryzation and denoising module, remove extra frame and boundary, side
Content is more accurate when continuing identification after an action of the bowels, removes some interference informations;
S4: processing is split to picture by dividing module, to be partitioned into one or more notable feature, is convenient for
Subsequent carry out picture recognition;
S5: identifying picture by picture recognition module, carries out overall profile identification before this, then carries out feature knowledge
Not, color recognition is finally carried out, and records identification information content;
S6: processed information being compared with the vegetable picture in storage device by processor,
If Direct Recognition as a result, if show recognition result,
If it is unidentified go out as a result, if processor Cloud Server entered by network scan for,
If Direct Recognition as a result, if show recognition result,
If it is unidentified go out as a result, if show approximate multiple recognition results;
S7: result is shown by display screen, and carries out last artificial information's confirmation;
S8: the picture after will confirm that successfully carries out coding of graphics processing by coding generation module, generates picture recognition and compiles
Picture recognition is encoded deposit storage device, use when facilitating next picture recognition by code.
The beneficial effects of the present invention are: being somebody's turn to do vegetable identifying system and method based on image recognition technology, pass through mould of taking pictures
Block and receiving module carry out acquisition picture, so that the mode obtained is more various, facilitate the acquisition of picture, increased filtering module
The illegal picture with illegal feature, binaryzation and denoising module are filtered for removing picture some useless frames and side
Boundary, reduces the workload of subsequent operation, and segmentation module is used to picture segmentation be one or more figure with notable feature
Piece, is convenient for subsequent identification, and increased coding generation module carries out coding of graphics processing after confirming successfully, generates picture recognition
Picture recognition is encoded deposit storage device by coding, and use when facilitating next picture recognition should the dish based on image recognition technology
Product identifying system and method can not only quickly identify vegetable, easy to operate, but also can be to the picture after identification
It is stored and is encoded, be convenient for subsequent use.
Detailed description of the invention
Fig. 1 is the frame diagram of vegetable identifying system of the invention;
Fig. 2 is the frame diagram of acquisition module of the invention;
Fig. 3 is the frame diagram of picture processing module of the invention;
Fig. 4 is the frame diagram of picture recognition module of the invention;
Fig. 5 is the frame diagram of control module of the invention;
Fig. 6 is the flow diagram of vegetable recognition methods of the invention.
In figure: 1 obtains module, 2 picture processing modules, 3 picture recognition modules, 4 control modules, 5 coding generation modules, 6
Photo module, 7 receiving modules, 8 filtering modules, 9 binaryzations and denoising module, 10 segmentation modules, 11 outline identification units,
12 feature identification units, 13 color recognition units, 14 processors, 15 storage devices, 16 network modules, 17 display screens, 18 keys.
Specific embodiment
The present invention will be further described with reference to the accompanying drawings.
The present invention provides the vegetable identifying system based on image recognition technology of one of the present invention as shown in Figs. 1-5,
Including obtaining module 1, picture processing module 2, picture recognition module 3, control module 4 and coding generation module 5, the acquisition mould
Block 1, picture processing module 2, picture recognition module 3, control module 4 and coding generation module 5 are placed in inside identification device.Identification
Device is robot, mobile phone, tablet computer, desktop computer or industrial personal computer.
The acquisition module 1 includes photo module 6 and receiving module 7, and the photo module 6 is known for shooting photo
Not, directly information is shot then to be identified, the receiving module 7 is used to receive by network using camera function
The picture transmitted, is then identified, a variety of acquisition modes, so that the mode for obtaining picture is more convenient.The picture
Processing module 2 includes filtering module 8, binaryzation and denoising module 9 and segmentation module 10, and the filtering module 8 was used for
The illegal picture with illegal feature is filtered, the propagation to illegal picture is avoided and misreads, cause certain trouble, the binaryzation
With denoising module 9 for removing picture some useless frames and boundary, so that the workload of subsequent operation reduces, it is described
Divide module 10 to be used to picture segmentation be one or more picture with notable feature, convenient for the identification of subsequent pictures.
The picture recognition module 3 includes outline identification unit 11, feature identification unit 12 and color recognition unit 13, and the profile is known
Other unit 11 is used to carry out overall profile identification to picture, and generates outline identification information, and the feature identification unit 12 is used for
Picture after dividing to segmentation module 10 carries out feature identification, and generates feature identification information, and the color recognition unit 13 is used
In carrying out overall color identification to picture, and color identification information is generated.The control module 4 includes processor 14, storage dress
15, network module 16, display screen 17 and key 18 are set, the processor 14 is used for integrated treatment information, and is connected to the network cloud
Server realizes search and identification function, and the storage device 15 is for storing common pictorial information, convenient for simple picture
Direct Recognition is carried out, the network module 16 includes 4G module, 5G module and WIFI module, and network module 16 is used for network transmission
With reception information, the display screen 17 is for showing that pictorial information and segment word information, the key 18 are used for execution part
Order and importation explanation.The coding generation module 5 is used for after picture recognition success, carries out coding of graphics processing, raw
It is encoded at picture recognition, picture recognition is encoded into deposit storage device 15, use when facilitating next picture recognition increases content
Amount, and it can also be transferred to Cloud Server, so that information is shared.Further to promote speed and accuracy rate, identification device
It further include the big data platform for being stored with all kinds of vegetable picture features;Picture recognition module 3 is analyzed and processed image data
When, it is compared with the vegetable picture feature data stored in the big data platform.
Referring to Fig. 6, the recognition methods of the two of the present invention vegetable identifying system based on image recognition technology, including with
Lower step:
S1: picture, the picture being filmed from photo module 6, under data transmission on receiving module 7 or network are obtained
The picture of load, and shown on display screen 17, after confirmation, selection is identified;
S2: being filtered picture by filtering module 8, avoids the importing and propagation of illegal contents,
It is then carried out if normal picture in next step,
It then feeds back if illegal picture to processor 14, illegal contents processing is marked, and store information into storage
Device 15, Direct Recognition is illegal contents when next time identifies;
S3: being removed processing to picture by binaryzation and denoising module 9, remove extra frame and boundary,
Content is more accurate when facilitating subsequent identification, removes some interference informations;
S4: processing is split to picture by dividing module 10, to be partitioned into one or more notable feature, just
In subsequent carry out picture recognition;
S5: identifying picture by picture recognition module 3, carries out overall profile identification before this, then carries out feature
Identification, finally carries out color recognition, and record identification information content;
S6: processed information being compared with the vegetable picture in storage device 15 by processor 14,
If Direct Recognition as a result, if show recognition result,
If it is unidentified go out as a result, if processor 14 Cloud Server entered by network scan for,
If Direct Recognition as a result, if show recognition result,
If it is unidentified go out as a result, if show approximate multiple recognition results;
S7: result is shown by display screen 17, and carries out last artificial information's confirmation;
S8: the picture after will confirm that successfully carries out coding of graphics processing by coding generation module 5, generates picture recognition and compiles
Picture recognition is encoded deposit storage device 15, use when facilitating next picture recognition by code.
Above embodiments are used for illustrative purposes only, rather than limitation of the present invention, the technology people in relation to technical field
Member, without departing from the spirit and scope of the present invention, can also make various transformation or modification, therefore all equivalent
Technical solution also should belong to scope of the invention, should be limited by each claim.
Claims (10)
1. a kind of vegetable identifying system based on image recognition technology, which is characterized in that including obtaining module (1), picture processing
Module (2), picture recognition module (3), control module (4) and coding generation module (5), the acquisition module (1), picture processing
Module (2), picture recognition module (3), control module (4) and coding generation module (5) are placed in inside identification device.
2. the vegetable identifying system according to claim 1 based on image recognition technology, which is characterized in that the acquisition mould
Block (1) includes photo module (6) and receiving module (7), and the photo module (6) is identified for shooting photo, directly benefit
Information is shot then to be identified, the receiving module (7) is used to transmit by network reception with camera function
Picture, then identified.
3. the vegetable identifying system according to claim 2 based on image recognition technology, which is characterized in that at the picture
Reason module (2) includes filtering module (8), binaryzation and denoising module (9) and segmentation module (10), the filtering module
(8) for filtering the illegal picture with illegal feature.
4. the vegetable identifying system according to claim 3 based on image recognition technology, which is characterized in that the binaryzation
It is used for for removing picture some useless frames and boundary, the segmentation module (10) by picture with denoising module (9)
It is divided into one or more picture with notable feature.
5. the vegetable identifying system according to claim 4 based on image recognition technology, which is characterized in that the picture is known
Other module (3) includes outline identification unit (11), feature identification unit (12) and color recognition unit (13), the outline identification
Unit (11) is used to carry out overall profile identification to picture, and generates outline identification information, and the feature identification unit (12) is used
Picture after dividing to segmentation module (10) carries out feature identification, and generates feature identification information, the color recognition unit
(13) for carrying out overall color identification to picture, and color identification information is generated.
6. the vegetable identifying system according to claim 5 based on image recognition technology, which is characterized in that the control mould
Block (4) includes processor (14), storage device (15), network module (16), display screen (17) and key (18), the processor
(14) it is used for integrated treatment information, and is connected to the network Cloud Server, realizes search and identification function, the storage device (15)
For storing common pictorial information, convenient for carrying out Direct Recognition to simple picture.
7. the vegetable identifying system according to claim 6 based on image recognition technology, which is characterized in that the network mould
Block (16) includes 4G module, 5G module and WIFI module, and network module (16) is for network transmission and receives information, the display
Screen (17) for showing pictorial information and segment word information, defend oneself for execution part order and input unit by the key (18)
It is bright.
8. the vegetable identifying system according to claim 7 based on image recognition technology, which is characterized in that the coding life
It is used for after picture recognition success at module (5), carries out coding of graphics processing, generated picture recognition coding, picture recognition is compiled
Code deposit storage device (15), use when facilitating next picture recognition increase inner capacities.
9. the vegetable identifying system according to claim 1 based on image recognition technology, which is characterized in that identification device is
Robot, mobile phone, tablet computer, desktop computer or industrial personal computer;
Identification device further include: be stored with the big data platform of all kinds of vegetable picture features;
When the picture recognition module (3) is analyzed and processed image data, with the vegetable stored in the big data platform
Picture feature data are compared.
10. a kind of recognition methods of the vegetable identifying system according to any one of claims 8 based on image recognition technology, feature exist
In, comprising the following steps:
S1: picture, the picture being filmed from photo module (6), under data transmission on receiving module (7) or network are obtained
The picture of load, and shown on display screen (17), after confirmation, selection is identified;
S2: being filtered picture by filtering module (8), avoids the importing and propagation of illegal contents,
It is then carried out if normal picture in next step,
It then feeds back if illegal picture to processor (14), illegal contents processing is marked, and store information into storage dress
It sets (15), Direct Recognition is illegal contents when next time identifies;
S3: being removed processing to picture by binaryzation and denoising module (9), remove extra frame and boundary, side
Content is more accurate when continuing identification after an action of the bowels, removes some interference informations;
S4: processing is split to picture by dividing module (10), to be partitioned into one or more notable feature, is convenient for
Subsequent carry out picture recognition;
S5: identifying picture by picture recognition module (3), carries out overall profile identification before this, then carries out feature knowledge
Not, color recognition is finally carried out, and records identification information content;
S6: processed information being compared with the vegetable picture in storage device (15) by processor (14),
If Direct Recognition as a result, if show recognition result,
If it is unidentified go out as a result, if processor (14) Cloud Server entered by network scan for,
If Direct Recognition as a result, if show recognition result,
If it is unidentified go out as a result, if show approximate multiple recognition results;
S7: result is shown by display screen (17), and carries out last artificial information's confirmation;
S8: the picture after will confirm that successfully carries out coding of graphics processing by coding generation module (5), generates picture recognition and compiles
Picture recognition is encoded deposit storage device (15), use when facilitating next picture recognition by code.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810820901.3A CN109299721A (en) | 2018-07-24 | 2018-07-24 | A kind of vegetable identifying system and method based on image recognition technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810820901.3A CN109299721A (en) | 2018-07-24 | 2018-07-24 | A kind of vegetable identifying system and method based on image recognition technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109299721A true CN109299721A (en) | 2019-02-01 |
Family
ID=65167978
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810820901.3A Pending CN109299721A (en) | 2018-07-24 | 2018-07-24 | A kind of vegetable identifying system and method based on image recognition technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109299721A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111222496A (en) * | 2020-02-17 | 2020-06-02 | 重庆忽米网络科技有限公司 | Identification code generation method and system based on 5G communication and image recognition |
CN111640267A (en) * | 2020-04-16 | 2020-09-08 | 浙江口碑网络技术有限公司 | Self-service settlement method and device, storage medium and computer equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104463167A (en) * | 2014-11-20 | 2015-03-25 | 中国科学院上海微系统与信息技术研究所 | Automatic restaurant settlement method and system |
CN105653636A (en) * | 2015-12-25 | 2016-06-08 | 北京搜狗科技发展有限公司 | Information processing method and apparatus as well as information processing apparatus |
CN106845527A (en) * | 2016-12-29 | 2017-06-13 | 南京江南博睿高新技术研究院有限公司 | A kind of vegetable recognition methods |
-
2018
- 2018-07-24 CN CN201810820901.3A patent/CN109299721A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104463167A (en) * | 2014-11-20 | 2015-03-25 | 中国科学院上海微系统与信息技术研究所 | Automatic restaurant settlement method and system |
CN105653636A (en) * | 2015-12-25 | 2016-06-08 | 北京搜狗科技发展有限公司 | Information processing method and apparatus as well as information processing apparatus |
CN106845527A (en) * | 2016-12-29 | 2017-06-13 | 南京江南博睿高新技术研究院有限公司 | A kind of vegetable recognition methods |
Non-Patent Citations (1)
Title |
---|
顾理琴: "基于图像识别技术的食品种类检测方法", 《食品研究与开发》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111222496A (en) * | 2020-02-17 | 2020-06-02 | 重庆忽米网络科技有限公司 | Identification code generation method and system based on 5G communication and image recognition |
CN111640267A (en) * | 2020-04-16 | 2020-09-08 | 浙江口碑网络技术有限公司 | Self-service settlement method and device, storage medium and computer equipment |
CN111640267B (en) * | 2020-04-16 | 2021-12-24 | 浙江口碑网络技术有限公司 | Self-service settlement method and device, storage medium and computer equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Vogels et al. | Denoising with kernel prediction and asymmetric loss functions | |
US10891465B2 (en) | Methods and apparatuses for searching for target person, devices, and media | |
US20220383649A1 (en) | System and method for facilitating graphic-recognition training of a recognition model | |
CN107273503A (en) | Method and apparatus for generating the parallel text of same language | |
CN106611015B (en) | Label processing method and device | |
CN110363084A (en) | A kind of class state detection method, device, storage medium and electronics | |
US10733479B2 (en) | System and method for providing a recipe | |
US20170337222A1 (en) | Image searching method and apparatus, an apparatus and non-volatile computer storage medium | |
CN108319641A (en) | Dish information input method and device | |
CN112487207A (en) | Image multi-label classification method and device, computer equipment and storage medium | |
US20210089825A1 (en) | Systems and methods for cleaning data | |
CN109299721A (en) | A kind of vegetable identifying system and method based on image recognition technology | |
CN108174237A (en) | Image combining method and device | |
CN116934907A (en) | Image generation method, device and storage medium | |
CN109829364A (en) | A kind of expression recognition method, device and recommended method, device | |
CN103609098B (en) | Method and apparatus for being registered in telepresence system | |
CN109241930B (en) | Method and apparatus for processing eyebrow image | |
CN109658501B (en) | Image processing method, image processing device and terminal equipment | |
CN110675389A (en) | Food recommendation method, storage medium and intelligent household equipment | |
CN108319722B (en) | Data access method and device, electronic equipment and computer readable storage medium | |
CN113888425A (en) | Industrial quality inspection image character matching method and system based on multi-frame fusion | |
CN108289176A (en) | One kind, which is taken pictures, searches topic method, searches topic device and terminal device | |
CN108334602B (en) | Data annotation method and device, electronic equipment and computer storage medium | |
CN109784131B (en) | Object detection method, device, storage medium and processor | |
Wang et al. | An improved nonlocal sparse regularization-based image deblurring via novel similarity criteria |
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: 20190201 |