CN109887043A - A kind of context management system based on color analysis - Google Patents
A kind of context management system based on color analysis Download PDFInfo
- Publication number
- CN109887043A CN109887043A CN201910127661.3A CN201910127661A CN109887043A CN 109887043 A CN109887043 A CN 109887043A CN 201910127661 A CN201910127661 A CN 201910127661A CN 109887043 A CN109887043 A CN 109887043A
- Authority
- CN
- China
- Prior art keywords
- color
- image
- dress ornament
- analysis
- subsystem
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 73
- 238000010191 image analysis Methods 0.000 claims abstract description 15
- 230000008451 emotion Effects 0.000 claims description 35
- 238000012549 training Methods 0.000 claims description 29
- 238000007726 management method Methods 0.000 claims description 15
- 238000003556 assay Methods 0.000 claims description 8
- 239000003086 colorant Substances 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000013316 zoning Methods 0.000 claims description 4
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 2
- 235000008434 ginseng Nutrition 0.000 claims description 2
- 241000208340 Araliaceae Species 0.000 claims 1
- 238000012505 colouration Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 11
- 238000004040 coloring Methods 0.000 abstract description 2
- 238000013461 design Methods 0.000 description 7
- 241000220317 Rosa Species 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 108091005950 Azurite Proteins 0.000 description 1
- 240000001432 Calendula officinalis Species 0.000 description 1
- 235000005881 Calendula officinalis Nutrition 0.000 description 1
- 244000215562 Heliotropium arborescens Species 0.000 description 1
- 241000692870 Inachis io Species 0.000 description 1
- 244000178870 Lavandula angustifolia Species 0.000 description 1
- 235000010663 Lavandula angustifolia Nutrition 0.000 description 1
- 240000007817 Olea europaea Species 0.000 description 1
- 244000170916 Paeonia officinalis Species 0.000 description 1
- 235000006484 Paeonia officinalis Nutrition 0.000 description 1
- 244000131316 Panax pseudoginseng Species 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 244000269722 Thea sinensis Species 0.000 description 1
- 235000006468 Thea sinensis Nutrition 0.000 description 1
- 235000009754 Vitis X bourquina Nutrition 0.000 description 1
- 235000012333 Vitis X labruscana Nutrition 0.000 description 1
- 240000006365 Vitis vinifera Species 0.000 description 1
- 235000014787 Vitis vinifera Nutrition 0.000 description 1
- 235000020279 black tea Nutrition 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000001102 lavandula vera Substances 0.000 description 1
- 235000018219 lavender Nutrition 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The context management system based on color analysis that the present invention relates to a kind of, including dress ornament Image Acquisition end, image analysis subsystem, instruction generation subsystem and situation output device;The image information for the dress ornament that user is worn directly is acquired by image capture device, dress ornament is analyzed according to the shape of dress ornament, coloring etc. factor, corresponding output data is pre-configured in conjunction with background data base, the two is interrelated, coordinate in this way without artificial, a more appropriate situation effect can be obtained, guarantees stage quality.
Description
Technical field
The present invention relates to intelligent data analysis application systems, more specifically to a kind of situation based on color analysis
Management system.
Background technique
Decorate the article general name of human body.Including clothes, shoes, cap, socks, gloves, scarf, necktie, bag, sunshade, hair decorations
Deng.And moderns are constantly progressive the understanding of new things, the material of dress ornament, pattern is also varied.And large-scale important events or
Person walks that demand of the elegant stage to dress ornament is more polynary, and different dress ornaments needs corresponding situation also different, generally according to clothes
The difference of decorations, music, text, the light etc. at corresponding scene are also required to make corresponding adjustment, and be all at present by dressmakers,
The multiple groups personnel such as tuner, light controller are linked up in advance, due to will appear adjustment repeatedly, if cannot in time, effectively
It links up, large effect can be generated to spot effect, and the cost of human resources expended is larger, while limiting entire activity existing
Freedom degree, the case where if there is not expecting, cannot be arranged in time.
Summary of the invention
In view of this, it is an object of the present invention to provide a kind of context management system based on color analysis, to solve above-mentioned ask
Topic.
In order to solve the above-mentioned technical problem, the technical scheme is that a kind of context management system based on color analysis
System, including dress ornament Image Acquisition end, image analysis subsystem, instruction generation subsystem and situation output device;
Dress ornament Image Acquisition end is used to acquire the equal bodies image of user, and the equal bodies image of user is sent to described image
Analyzing subsystem;
Described image analyzing subsystem includes dress ornament identification module, color identification module and format converting module, the dress ornament
Identification module is configured with corresponding dress ornament analysis strategy, and the dress ornament analysis strategy is used to determine user in described wait in bodies image
Figure area where each clothing type of wearing and using corresponding clothing type as the data stamp in the figure area, the color is known
Other module is used to wait bodies image that each figure zoning is divided into several segments according to preset color value range and will be corresponded to described
Color value range analyzed as the data stamp of the segment after equal bodies image, the format conversion module according to point
Equal bodies image after analysis obtains image analysis information, and it includes several pattern informations that described image, which analyzes information, each pattern information
Including clothing type stamp and color value range stamp, the clothing type stamp reflects the clothing type of the segment, described
Color value range stamp reflects the color value range of the segment, and described image analyzing subsystem sends described image analysis information
Subsystem is generated to instruction;
It includes sentiment analysis module and instruction linked database that described instruction, which generates subsystem,;The sentiment analysis module configuration
Have a preset sentiment analysis algorithm, the sentiment analysis algorithm according to described image analyze the ratio of color value range in information with
And the weight of clothing type generates emotion preference information, described instruction linked database is stored with several control instructions, Mei Yisuo
Control instruction is stated with the emotion preference information as index, described instruction generates subsystem according to the emotion preference information in institute
It states in instruction linked database and transfers corresponding control instruction to the situation output device, the situation output device is according to institute
State control instruction work.
Further: the sentiment analysis algorithm includes that color value is taken to determine step and color selecting step, the color
Value determines that pattern information is divided into jacket pattern information, trousers skirt pattern information and accessories segment according to the clothing type by step
Information, and the corresponding area accounting in the bodies image such as described of color value range is determined in above-mentioned three groups of pattern informations respectively most
Several big preceding pattern informations, and color is taken according to the total accounting determination of area of the obtained pattern information in the equal bodies image
Value;The color selecting step chooses quantity and takes the maximum several color value ranges of the area accounting of color value with life no more than described
At emotion preference information.
Further: the situation output device includes that audio output apparatus and/or light output equipment and/or display are defeated
Equipment out.
Further: the sentiment analysis algorithm configuration has human body a reference value, and the human body a reference value reflection user is in institute
The Theoretical Area accounting in equal bodies image is stated, the sentiment analysis algorithm is analyzed acquisition of information dress ornament according to described image and analyzed
Value, the dress ornament assay value reflection dress ornament is in the real area accounting for waiting bodies image, and the sentiment analysis algorithm is according to institute
The ratio for stating dress ornament assay value and human body a reference value generates accounting adjustment parameter, and the emotion preference information includes the accounting tune
Save parameter.
Further: described image analyzing subsystem further includes rivel identification module, and the rivel identification module is provided with
Rivel acquisition algorithm, the rivel acquisition algorithm is for capturing in the corresponding figure area of each clothing type in the equal bodies image
Rivel area simultaneously generates rivel data, and it includes the rivel data that described image, which analyzes information,;
The sentiment analysis algorithm generates rivel adjustment parameter according to rivel data, and the emotion preference information includes the rivel
Adjustment parameter.
Further: the sentiment analysis algorithm is also configured with bevel edge threshold range, and the sentiment analysis algorithm calculates every
The bevel edge number of the corresponding shape of one pattern information, and according to obtain bevel edge scold into bevel edge threshold range generate bevel edge adjust ginseng
Number, the emotion preference information includes the bevel edge adjustment parameter.
Further: the sentiment analysis algorithm also configures coloured area's threshold range, and the sentiment analysis algorithm calculates every
The numerical value for the pattern information for including in one figure area, and according to the numerical generation numerical value adjustment parameter of obtained pattern information, it is described
Emotion preference information includes the numerical value adjustment parameter.
Further: further including data training subsystem, the data training subsystem includes color training module, described
Data training subsystem is placed in the acquisition range at dress ornament Image Acquisition end configured with an identification colour table, the identification colour table
Among, the different base colors of several groups are presented on the identification colour table, when dress ornament Image Acquisition end collects equal bodies
When image, the color training module carries out color value analysis according to the identification colour table in equal bodies image to correct described image point
Analyse the color value range in subsystem.
Further: the data training subsystem further includes dress ornament training module, the data training subsystem configuration
There are wearable radio frequency unit and RF acquisition equipment, the wearable radio frequency unit is fixed on inside each dress ornament and is configured with
Corresponding identification coding, the identification coding reflect the clothing type, and the RF acquisition equipment is for receiving the identification
Coding, the dress ornament training module according to identification coding acquired results and the figure area that analyzes of described image analyzing subsystem it
Between difference correct the dress ornament analysis strategy.
The technology of the present invention effect major embodiment is in the following areas: being arranged in this way, is directly adopted by image capture device
The image information for the dress ornament that collection user is worn is analyzed dress ornament according to the shape of dress ornament, coloring etc. factor, in conjunction with rear
Platform database is pre-configured with corresponding output data, and the two is interrelated, coordinates in this way without artificial, can obtain one compared with
For suitable situation effect, guarantee stage quality.
Detailed description of the invention
Fig. 1: the system integrated stand composition of the context management system of the invention based on color analysis.
Appended drawing reference: 100, dress ornament Image Acquisition end;200, image analysis subsystem;210, dress ornament identification module;220,
Color identification module;230, format converting module;300, instruction generates subsystem;310, sentiment analysis module;320, instruction is closed
Join database;400, situation output device;500, data training subsystem.
Specific embodiment
Below in conjunction with attached drawing, a specific embodiment of the invention is described in further detail, so that technical solution of the present invention is more
It should be readily appreciated that and grasp.
Designer has centainly also paid attention to the expression of the spirit of the times, institute in subject element when creating subject element simultaneously
Reflection also must be when classic under epoch, most worthy, most influential correct values performance.But skill
Art expression is that comparison is abstract, and ordinary consumer can not realize the subject element of design.Design and consumption is allowed estrangement occur.It is logical
Music and text are crossed to express the subject element of Design of Popular Dress Ornaments, makes consumer more blunt, and is strong when realizing designer
For the expression of breath and artistic emotion.The design of brand dress ornament is allowed more to tend to sense of the times, artistic feeling and sexuality.So being based on
Above-mentioned reason is farthest mentioned the invention is intended to realize the quantitative analysis tended to color and emotion by intelligence system
High stage effect.
Shown in referring to Fig.1, a kind of context management system based on color analysis, including dress ornament Image Acquisition end 100, image
Analyzing subsystem 200, instruction generate subsystem 300 and situation output device 400;
Dress ornament Image Acquisition end 100 is used to acquire the equal bodies image of user, and described in the equal bodies image of user is sent to
Image analysis subsystem 200;Primarily with respect to dress ornament Image Acquisition end 100, it is however generally that be selected as that there is setting for image collecting function
It is standby.
Described image analyzing subsystem 200 includes dress ornament identification module 210, color identification module 220 and format conversion
Module 230, the dress ornament identification module 210 are configured with corresponding dress ornament analysis strategy, and the dress ornament analysis strategy is used in institute
State the figure area where determining each clothing type of user's wearing in equal bodies image and using corresponding clothing type as the figure area
Data stamp, the color identification module 220 is used for each figure in the equal bodies image according to preset color value range
Zoning is divided into several segments and using corresponding color value range as the data stamp of the segment with the equal bodies figure after being analyzed
Picture, the format conversion module obtain image analysis information according to the equal bodies image after analysis, and described image analysis information includes
Several pattern informations, each pattern information include clothing type stamp and color value range stamp, the clothing type stamp
Reflect the clothing type of the segment, the color value range stamp reflects the color value range of the segment, described image analysis
Described image analysis information is sent to instruction and generates subsystem 300 by system 200;And acquisition of the different acquisition equipment to image
Discrimination power, true degree are different, can all have an impact, image analyzing section be described in detail below, preferably to analysis result
It acquires multiple images and facilitates comparison, while reducing error, such as acquisition device is arranged in stage waiting area, model A appears on the stage
Stage waiting area is advanced into, image capture device gets the equal bodies image (namely whole body photograph) of model A, and is pair with that
Image is analyzed, and is the dress for analyzing model A first, determines that the human body contour outline of model A exists first by human bioequivalence algorithm
Position in equal bodies image, then determines clothing type according to human body contour outline region, is assured that clothes, trousers in this way
Skirt or be other accessories such as cap, shoes, jewellery, then corresponds to an area Ge Tu, such as clothes for the dress ornament of each type
In 1 figure area, trousers are in 2 figure areas and so on, and figure area one dress ornament of reflection is in the position of equal bodies image, then not according to color
With figure zoning is divided into several segments again, it is assured that segment, segment reflect the figure where the color value range by rgb value
Position in area can so simplify complicated graph data, obtain one it is relatively simple by color value
The graph data being spliced into, and this graph data is carried out simplifying the image analysis letter that can be obtained by a textual form again
Breath, and it is convenient to information progress quantification treatment.So preferably, the present invention is also provided with training effect, in sample size
In reliable situation, reduce the error generated by equipment, specifically, further including data training subsystem 500, the data training
Subsystem 500 includes color training module, and the data training subsystem 500 is configured with an identification colour table, the identification colour table
It is placed among the acquisition range at dress ornament Image Acquisition end 100, presents the different base of several groups on the identification colour table
Quasi- color, when dress ornament Image Acquisition end 100, which collects, waits bodies image, the color training module is according in equal bodies image
Identification colour table carry out color value analyze to correct the color value range in described image analyzing subsystem 200.The data instruction
Practicing subsystem 500 further includes dress ornament training module, and the data training subsystem 500 is configured with wearable radio frequency unit and penetrates
Frequency acquisition equipment, the wearable radio frequency unit is fixed on inside each dress ornament and encodes configured with corresponding identification, described to distinguish
Know coding and reflect the clothing type, the RF acquisition equipment is for receiving the identification coding, the dress ornament training module
The difference between obtained figure area, which is analyzed, according to identification coding acquired results and described image analyzing subsystem 200 corrects the clothes
Adorn analysis strategy.It is first the setting for recognizing colour table, due to factors such as equipment error, illumination condition difference, environmental structure differences
It will lead to Acquisition Error, so one identification colour table of setting, recognizes and be printed with base colors on colour table, identification colour table is waiting bodies
After being identified in image, corresponding color is also just known quantity, such as identification colour table is 174 waiting color value in bodies image,
238,238, and the color value for actually recognizing colour table is 168,208,238, then can be carried out correcting according to this error, is protected
Card result is more approached with actual color, and dress ornament identification is complex, can then pass through in record dress ornament information when training
Radio Frequency Identification Technology obtains information, judges whether the two information correspond to, if do not corresponded to, illustrates when human body contour outline determines
Sensitivity threshold need to adjust, mass data support under, can with the determination of training on body profile, once human body contour outline is true
It is fixed, then corresponding clothing type also can be determined accordingly.
It includes sentiment analysis module 310 and instruction linked database 320 that described instruction, which generates subsystem 300,;The feelings
Feel analysis module 310 and be configured with preset sentiment analysis algorithm, the sentiment analysis algorithm is analyzed in information according to described image
The ratio of color value range and the weight of clothing type generate emotion preference information, and described instruction linked database 320 stores
There are several control instructions, each control instruction is index with the emotion preference information, and described instruction generates subsystem 300
Corresponding control instruction to the situation is transferred in described instruction linked database 320 according to the emotion preference information to export
Device 400, the situation output device 400 work according to the control instruction.Sentiment analysis module 310 is that the present invention most attaches most importance to
The module wanted first is associated emotion according to color, then configures corresponding music, light or text further according to emotion
Word so that this system is relatively reliable, and has stronger adaptability.For below: strong --- at prime, plentiful --- Portugal
Grape color, susceptible --- rose color, magnificent --- peony, tenderness --- rose powder, romance --- light pink, life ---
Bright red, substantial --- black tea color, enthusiasm --- sun orange, soft --- colour of skin, joy --- pot marigold, movement ---
Chrome yellow, gracefulness --- Naples is yellow, nascent --- yellow green, mild --- apple green, fresh --- emerald green, biography
System --- it is olive green, high-spirited --- it is dark green, update --- peacock green, cherish the memory of --- celadon, rudiment --- green white,
Warm --- Bai Qing, pure --- water colour, classics --- green, intellectual --- Nile blue, calm --- azurite, upright ---
Ultramarine, fashion --- iris color, glamour --- Heliotropium arborescens, sentiment --- lavender, wisdom --- Chinese wistaria, dependence ---
Ancient times are purple, rule --- steel gray, pure --- shellfish color, lofty --- moistens rain color, the corresponding color value of each color
Range carries out situation configuration further according to emotion keyword in this way, so that it may play an associated effect, and for example scan dress ornament
Result be it is at prime, then then correspond to the light and audio of strong situation, and so on.The sentiment analysis algorithm includes taking color
It is worth and determines that step and color selecting step, the color-values determine that pattern information is divided by step according to the clothing type
Clothing pattern information, trousers skirt pattern information and accessories pattern information, and color value is determined in above-mentioned three groups of pattern informations respectively
Corresponding several the maximum preceding pattern informations of area accounting in the equal bodies image of range, and according to obtained pattern information
The total accounting determination of area in the equal bodies image takes color value;The color selecting step chooses quantity and takes color no more than described
The maximum several color value ranges of the area accounting of value are to generate emotion preference information.And the setting of general clothes has a variety of face
Colour cell is closed, so emotion preference cannot just be defined with a color, so each emotion preference information is one or more of colors
Combination, and thus need first to determine the number of colors of selection, pattern information be first divided into different types, then according to every
The area of one type determines the last color value that takes, specific as follows: A (upper body { two colors is taken to be greater than 3% segment maximum value })+B
(trousers or shorts skirt etc. { take two color module maximum values be greater than 3% segment })+∑ is { (C) accessory such as: taking a maximum figure
Block such as a(cap weight coefficient) * color area (color is maximum)+b(handbag traveling bag equal weight coefficient) * color area (face
Color is maximum)+c(waistband belt equal weight coefficient) * color area (color is maximum)+d(shoes weight coefficient) color area (color
It is maximum) } wherein weight is pre-configured with, such as its gross area then takes five colors if it is greater than 5, then and taking color value is 5, if always
Between area 3-5, then taking color value is 3, if it is 1 that the gross area, which less than three, takes color value, so, so that it may according to naked eyes
Identification and acceptable effect, which determine, takes color, and according to taking color value to choose several maximum colors of area, so that it may to the end
Emotion preference information.
The situation output device 400 includes that audio output apparatus and/or light output equipment and/or display output are set
It is standby.It has been shown that, music, light can thus be controlled.
The sentiment analysis algorithm configuration has human body a reference value, and the human body a reference value reflection user waits bodies image described
In Theoretical Area accounting, the sentiment analysis algorithm according to described image analyze acquisition of information dress ornament assay value, the dress ornament
Assay value reflects dress ornament in the real area accounting for waiting bodies image, and the sentiment analysis algorithm is according to the dress ornament assay value
Accounting adjustment parameter is generated with the ratio of human body a reference value, the emotion preference information includes the accounting adjustment parameter.Dress ornament
Profile and human body ratio are greater than 1.3 less than 1.6, then are judged as more loose dress ornament, so also to carry out according to dress ornament size
The adjusting of emotion preference information, dress ornament profile and human body ratio, which are greater than, is equal to greatly 1.6, then explanation is i.e. relatively simple using color, but
It is that entire dress ornament still more shows individual character, it is possible to be partial to the emotion preference information of more individual character.
Described image analyzing subsystem 200 further includes rivel identification module, and the rivel identification module is provided with rivel and catches
Obtain algorithm, the rivel acquisition algorithm is used to capture the rivel face in the corresponding figure area of each clothing type in the equal bodies image
Rivel data are accumulated and generate, it includes the rivel data that described image, which analyzes information,;
The sentiment analysis algorithm generates rivel adjustment parameter according to rivel data, and the emotion preference information includes the rivel
Adjustment parameter.If the rivel or area of any one upper body or lower part of the body cloth are greater than 0.1 less than 0.3, be equally dress ornament more
Embodiment abundant, and rivel area is greater than 0.3, then illustrates that dress ornament more makes widely known individual character.
The sentiment analysis algorithm is also configured with bevel edge threshold range, and the sentiment analysis algorithm calculates each pattern information
The bevel edge number of corresponding shape, and according to obtain bevel edge scold into bevel edge threshold range generate bevel edge adjustment parameter, the feelings
Feeling preference information includes the bevel edge adjustment parameter.The sentiment analysis algorithm also configures coloured area's threshold range, the emotion
Parser calculates the numerical value for the pattern information for including in each figure area, and according to the numerical generation numerical value of obtained pattern information
Adjustment parameter, the emotion preference information include the numerical value adjustment parameter.Such as any single Design of Popular Dress Ornaments bevel edge number or color
Block number being less than greater than 4 is with the dress ornament for design of behaving excellently less than 7, and any single Design of Popular Dress Ornaments bevel edge number or color lump number are big
Being equally construed as equal to 7 makes widely known the dress ornament of individual character.
According to the corresponding emotion preference information of actual clothing type selecting, so that it may it is more bonded the theory of designer,
Guarantee stage effect.
Certainly, above is representative instance of the invention, and in addition to this, the present invention can also have other a variety of specific implementations
Mode, all technical solutions formed using equivalent substitution or equivalent transformation, is all fallen within the scope of protection of present invention.
Claims (9)
1. a kind of context management system based on color analysis, which is characterized in that including dress ornament Image Acquisition end, image analysis
System, instruction generate subsystem and situation output device;
Dress ornament Image Acquisition end is used to acquire the equal bodies image of user, and the equal bodies image of user is sent to described image
Analyzing subsystem;
Described image analyzing subsystem includes dress ornament identification module, color identification module and format converting module, the dress ornament
Identification module is configured with corresponding dress ornament analysis strategy, and the dress ornament analysis strategy is used to determine user in described wait in bodies image
Figure area where each clothing type of wearing and using corresponding clothing type as the data stamp in the figure area, the color is known
Other module is used to wait bodies image that each figure zoning is divided into several segments according to preset color value range and will be corresponded to described
Color value range analyzed as the data stamp of the segment after equal bodies image, the format conversion module according to point
Equal bodies image after analysis obtains image analysis information, and it includes several pattern informations that described image, which analyzes information, each pattern information
Including clothing type stamp and color value range stamp, the clothing type stamp reflects the clothing type of the segment, described
Color value range stamp reflects the color value range of the segment, and described image analyzing subsystem sends described image analysis information
Subsystem is generated to instruction;
It includes sentiment analysis module and instruction linked database that described instruction, which generates subsystem,;The sentiment analysis module configuration
Have a preset sentiment analysis algorithm, the sentiment analysis algorithm according to described image analyze the ratio of color value range in information with
And the weight of clothing type generates emotion preference information, described instruction linked database is stored with several control instructions, Mei Yisuo
Control instruction is stated with the emotion preference information as index, described instruction generates subsystem according to the emotion preference information in institute
It states in instruction linked database and transfers corresponding control instruction to the situation output device, the situation output device is according to institute
State control instruction work.
2. a kind of context management system based on color analysis as described in claim 1, it is characterised in that: the sentiment analysis
Algorithm includes that color value is taken to determine step and color selecting step, and the color-values determine that step will be schemed according to the clothing type
Block message is divided into jacket pattern information, trousers skirt pattern information and accessories pattern information, and respectively in above-mentioned three groups of pattern informations
Corresponding several the maximum preceding pattern informations of area accounting in the equal bodies image of middle determining color value range, and according to
To area total accounting determination of the pattern information in the equal bodies image take color value;The color selecting step chooses quantity not
More than the maximum several color value ranges of the area accounting for taking color value to generate emotion preference information.
3. a kind of context management system based on color analysis as described in claim 1, it is characterised in that: the situation output
Device includes audio output apparatus and/or light output equipment and/or display output equipment.
4. a kind of context management system based on color analysis as claimed in claim 2, it is characterised in that: the sentiment analysis
Algorithm configuration has human body a reference value, and the human body a reference value reflection user is in the Theoretical Area accounting waited in bodies image, institute
It states sentiment analysis algorithm and acquisition of information dress ornament assay value is analyzed according to described image, the dress ornament assay value reflection dress ornament is described
The real area accounting of equal bodies image, the sentiment analysis algorithm are raw according to the ratio of the dress ornament assay value and human body a reference value
At accounting adjustment parameter, the emotion preference information includes the accounting adjustment parameter.
5. a kind of context management system based on color analysis as claimed in claim 2, it is characterised in that: described image analysis
Subsystem further includes rivel identification module, and the rivel identification module is provided with rivel acquisition algorithm, the rivel acquisition algorithm
For capturing the rivel area in the corresponding figure area of each clothing type in the equal bodies image and generating rivel data, the figure
As analysis information includes the rivel data;
The sentiment analysis algorithm generates rivel adjustment parameter according to rivel data, and the emotion preference information includes the rivel
Adjustment parameter.
6. a kind of context management system based on color analysis as claimed in claim 2, it is characterised in that: the sentiment analysis
Algorithm is also configured with bevel edge threshold range, and the sentiment analysis algorithm calculates the bevel edge number of the corresponding shape of each pattern information,
And according to obtain bevel edge scold into bevel edge threshold range generate bevel edge adjustment parameter, the emotion preference information include it is described tiltedly
Side adjustment parameter.
7. a kind of context management system based on color analysis as claimed in claim 2, it is characterised in that: the sentiment analysis
Algorithm also configures coloured area's threshold range, and the sentiment analysis algorithm calculates the numerical value for the pattern information for including in each figure area,
And according to the numerical generation numerical value adjustment parameter of obtained pattern information, the emotion preference information includes that the numerical value adjusts ginseng
Number.
8. a kind of context management system based on color analysis as described in claim 1, it is characterised in that: further include data instruction
Practice subsystem, the data training subsystem includes color training module, and the data training subsystem is configured with an episematic colouration
Plate, the identification colour table is placed among the acquisition range at dress ornament Image Acquisition end, if presenting on the identification colour table
The different base colors of dry group, when dress ornament Image Acquisition end collects equal bodies image, the color training module according to
Identification colour table in equal bodies image carries out color value and analyzes to correct the color value range in described image analyzing subsystem.
9. a kind of context management system based on color analysis as claimed in claim 8, it is characterised in that: the data training
Subsystem further includes dress ornament training module, and the data training subsystem is set configured with wearable radio frequency unit and RF acquisition
Standby, the wearable radio frequency unit is fixed on inside each dress ornament and encodes configured with corresponding identification, and the identification coding is anti-
The clothing type is reflected, the RF acquisition equipment is for receiving the identification coding, and the dress ornament training module is according to identification
The difference between figure area that coding acquired results and described image analyzing subsystem are analyzed corrects the dress ornament analysis strategy.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910127661.3A CN109887043B (en) | 2019-02-20 | 2019-02-20 | Situation management system based on color analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910127661.3A CN109887043B (en) | 2019-02-20 | 2019-02-20 | Situation management system based on color analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109887043A true CN109887043A (en) | 2019-06-14 |
CN109887043B CN109887043B (en) | 2020-10-09 |
Family
ID=66928671
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910127661.3A Expired - Fee Related CN109887043B (en) | 2019-02-20 | 2019-02-20 | Situation management system based on color analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109887043B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6301044B1 (en) * | 2000-03-30 | 2001-10-09 | Disney Enterprises, Inc. | Apparel color and image effect system |
CN204157094U (en) * | 2014-02-12 | 2015-02-11 | 深圳市日上光电股份有限公司 | A kind of control system for LED light emission device |
WO2016123977A1 (en) * | 2015-02-05 | 2016-08-11 | 努比亚技术有限公司 | Image colour identification method and device, terminal and storage medium |
CN205508402U (en) * | 2016-04-08 | 2016-08-24 | 殷瑞鸿 | System for perception mood changes control lamp light sum music |
CN107169508A (en) * | 2017-04-17 | 2017-09-15 | 杭州电子科技大学 | A kind of cheongsam Image emotional semantic method for recognizing semantics based on fusion feature |
CN207460565U (en) * | 2017-07-20 | 2018-06-05 | 上海思依暄机器人科技股份有限公司 | A kind of light regulating device and robot |
CN108184286A (en) * | 2017-12-27 | 2018-06-19 | 深圳迈睿智能科技有限公司 | The control method and control system and electronic equipment of lamps and lanterns |
CN108235831A (en) * | 2017-12-27 | 2018-06-29 | 深圳迈睿智能科技有限公司 | The control method and control system and electronic equipment of lamps and lanterns |
CN108647210A (en) * | 2018-05-15 | 2018-10-12 | 东华大学 | A kind of optimization method that colour-spun yarns parameter is docked with fabric Affective Evaluation Semantic interaction |
CN108764237A (en) * | 2018-05-30 | 2018-11-06 | 深圳万发创新进出口贸易有限公司 | A kind of intelligent domestic system |
CN108875047A (en) * | 2018-06-28 | 2018-11-23 | 清华大学 | A kind of information processing method and system |
CN109104786A (en) * | 2018-07-24 | 2018-12-28 | 广东金熙商业建设股份有限公司 | A kind of intelligence context aware light source management system |
-
2019
- 2019-02-20 CN CN201910127661.3A patent/CN109887043B/en not_active Expired - Fee Related
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6301044B1 (en) * | 2000-03-30 | 2001-10-09 | Disney Enterprises, Inc. | Apparel color and image effect system |
CN204157094U (en) * | 2014-02-12 | 2015-02-11 | 深圳市日上光电股份有限公司 | A kind of control system for LED light emission device |
WO2016123977A1 (en) * | 2015-02-05 | 2016-08-11 | 努比亚技术有限公司 | Image colour identification method and device, terminal and storage medium |
CN205508402U (en) * | 2016-04-08 | 2016-08-24 | 殷瑞鸿 | System for perception mood changes control lamp light sum music |
CN107169508A (en) * | 2017-04-17 | 2017-09-15 | 杭州电子科技大学 | A kind of cheongsam Image emotional semantic method for recognizing semantics based on fusion feature |
CN207460565U (en) * | 2017-07-20 | 2018-06-05 | 上海思依暄机器人科技股份有限公司 | A kind of light regulating device and robot |
CN108184286A (en) * | 2017-12-27 | 2018-06-19 | 深圳迈睿智能科技有限公司 | The control method and control system and electronic equipment of lamps and lanterns |
CN108235831A (en) * | 2017-12-27 | 2018-06-29 | 深圳迈睿智能科技有限公司 | The control method and control system and electronic equipment of lamps and lanterns |
CN108647210A (en) * | 2018-05-15 | 2018-10-12 | 东华大学 | A kind of optimization method that colour-spun yarns parameter is docked with fabric Affective Evaluation Semantic interaction |
CN108764237A (en) * | 2018-05-30 | 2018-11-06 | 深圳万发创新进出口贸易有限公司 | A kind of intelligent domestic system |
CN108875047A (en) * | 2018-06-28 | 2018-11-23 | 清华大学 | A kind of information processing method and system |
CN109104786A (en) * | 2018-07-24 | 2018-12-28 | 广东金熙商业建设股份有限公司 | A kind of intelligence context aware light source management system |
Non-Patent Citations (4)
Title |
---|
MARCEL P.LUCASSEN等: ""Texture Affects Color Emotion"", 《COLOR RESEARCH AND APPLICATION》 * |
张春艳: ""电商网站中面料商品的情感自动分类研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
张春艳等: ""电商网站中面料商品的情感语义自动识别和分类"", 《电脑知识与技术》 * |
汪珊娜: ""基于卷积神经网络的织物美感分类与情感标注研究"", 《中国优秀硕士学位论文全文数据库 工程科技I辑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN109887043B (en) | 2020-10-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108256975A (en) | Wearing for 3-D effect is provided for virtual fitting person take system and method based on artificial intelligence | |
CN110264299A (en) | Clothes recommended method, device and computer equipment based on recognition of face | |
CN107437073A (en) | Face skin quality analysis method and system based on deep learning with generation confrontation networking | |
US7392204B1 (en) | Method for selecting cosmetics | |
CN106108523A (en) | A kind of portable intelligent cosmetic mirror, cosmetic aid system and method | |
Eckert et al. | Facial cosmetics database and impact analysis on automatic face recognition | |
CN110232253A (en) | Generate computer installation, equipment, storage medium and the method for clothing matching scheme | |
CN106504751A (en) | Self adaptation lip reading exchange method and interactive device | |
CN109961426A (en) | A kind of detection method of face skin skin quality | |
CN106774856A (en) | Exchange method and interactive device based on lip reading | |
CN108920509A (en) | A kind of intelligent cosmetic mirror | |
CN103310234B (en) | The method of coupling hair style, dress ornament and/or accessories is obtained based on face signature analysis | |
CN110276360A (en) | Generate computer installation, equipment, storage medium and the method for clothing matching scheme | |
CN106485515A (en) | Intelligent clothing matching method, system, terminal unit and wardrobe | |
CN105809461A (en) | Method, system and intelligent device for recommending jewelry | |
CN108391052A (en) | Information processing method and electronic equipment | |
CN112001353A (en) | Pedestrian re-identification method based on multi-task joint supervised learning | |
KR101074691B1 (en) | Apparatus and method for providing personal image in on-line interface | |
CN105167290A (en) | Method for obtaining clothing matching index based on human body external image characteristic analysis | |
KR20190093040A (en) | Personal Color Analysis System with complex perception of the auditory and visual and fashion persona color matching method using the same | |
JP5599930B1 (en) | Color distribution chart and tools | |
CN106897327A (en) | Point out the method and apparatus of wearing | |
CN113180427A (en) | Multifunctional intelligent mirror | |
KR20110032733A (en) | Terminal and method for providing personal image | |
CN109284666B (en) | A kind of dress ornament recommended method based on image recognition and big data |
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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20221123 Address after: Room 3223, Building 8, No. 33 Guangshun Road, Changning District, Shanghai 200050 Patentee after: Youyu (Shanghai) Network Technology Co.,Ltd. Address before: 325000 C101, Libra, Yunzhong Huayuan, Binjiang Street, Lucheng District, Wenzhou City, Zhejiang Province Patentee before: Zheng Junyu |
|
TR01 | Transfer of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201009 |
|
CF01 | Termination of patent right due to non-payment of annual fee |