CN106599781A - Electric power business hall dressing normalization identification method based on color and Hu moment matching - Google Patents
Electric power business hall dressing normalization identification method based on color and Hu moment matching Download PDFInfo
- Publication number
- CN106599781A CN106599781A CN201610980144.7A CN201610980144A CN106599781A CN 106599781 A CN106599781 A CN 106599781A CN 201610980144 A CN201610980144 A CN 201610980144A CN 106599781 A CN106599781 A CN 106599781A
- Authority
- CN
- China
- Prior art keywords
- color
- moment
- dressing
- match
- matching
- 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
- 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
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G06V10/507—Summing image-intensity values; Histogram projection analysis
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides an electric power business hall dressing normalization identification method based on color and Hu moment matching. The method comprises: extracting a dressing color analysis area, wherein the process comprises the capture of fact identification, human body upper body identification and rectangle dressing color analysis area; performing color matching analysis of the captured rectangle area, and performing matching analysis through extraction of the maximum color of the identification area and the maximum color of the clothes in the frock picture base; extracting the identified upper body clothes outline and calculating the Hu moment, and performing Hu moment matching of the Hu moment and the outline Hu moment of the clothes in the frock picture base; and finally weighing and synthesizing the color matching result and the Hu moment matching result to obtain a clothing analysis result. The electric power business hall dressing normalization identification method based on the color and Hu moment matching solves the phenomenon that it is easy to generate errors in the traditional clothing identification process caused by single identification factor, and realizes the intelligence of the electric power business hall dressing management so as to reduce the work of the manual supervision management and improve the validity and the normalization of the work of the power electric business hall.
Description
Technical field
The present invention relates to a kind of electricity business hall dressing standardization recognition methodss based on color and Hu match by moment.
Background technology
In traditional clothing technology of identification, mostly using a certain single factor as matching condition, by single face
, used as matching condition, single matching condition produces certain impact, obtains to the degree of accuracy for matching for colour matching or outline
The matching result for taking often lacks enough cogencys, certain matching error easily occurs, therefore, single matching condition is past
It is past well to support matching effect.
Additionally, traditional Image outline identification matching technique mostly by feature extraction, set up template, by pattern match
Final match cognization function is completed, the matching to static picture profile has relatively good matching effect, but in battalion
Industry Room frock dressing monitoring identification process, because the clothes of people in monitor area is it is possible that the phenomenon that inclines or lose shape etc.,
Common outline technology cannot process clothes incline or lose shape the profile deformation for causing the problems such as, the matching effect of acquisition
The error caused because of problems of losing shape such as clothes inclinations cannot be just avoided, matching process can be because producing the problems such as clothes inclination, translation
Different results, so as to match degree of accuracy certain error is also generated.
The content of the invention
The purpose of the present invention is exactly, in order to solve problem above, to propose a kind of based on color and the electric power business of Hu match by moment
Room dressing standardization recognition methodss, by the two combined factors analysis of color and profile Hu squares, and as matching condition, improve
With degree of accuracy.Additionally, using the rotation of Hu squares, scaling, translation invariance, using Hu moment-matching methods outline is carried out, it is to avoid
Clothes inclines the matching error brought of losing shape.
To achieve these goals, the present invention adopts following scheme：
A kind of electricity business hall dressing standardization recognition methodss based on color and Hu match by moment, the method realizes step such as
Under：
Step A：Dressing color analysis region is extracted, first by recognition of face, is judged with the presence or absence of " people " in monitor area, its
The secondary people in video monitoring regional carries out upper part of the body identification, is then folded recognition of face region with upper part of the body identification region
Plus process, obtain the rectangular area of a clothing color analysis.
Step B：In extraction step A obtain color analysis region maximum color, and with frock picture library in maximum
Color carries out the matching analysis.
Step C：According to the upper part of the body region recognized in step A, the clothes profile of the upper part of the body is extracted, calculates profile Hu squares,
And Hu match by moment is carried out with frock picture profile, complete clothes profile and compare analysis.
Step D：In weighted comprehensive step B in clothes color matching results and step C clothes Hu match by moment results to frock
Dressing result is analyzed.
In step A, in face recognition process, thresholding is arranged according to the cluster feature of face complexion feature CgCr distribution
It is worth and is,
Value be 1, represent face complexion,Value be 0, then it represents that the non-face colour of skin.
In step B, in extraction step A obtain color analysis region maximum color, and with frock picture library in
Maximum color carry out the matching analysis, realize that step is as follows：
B1 expands and sets the regional extent of 10 kinds of colors.
Color region scope and color histogram that B2 sets according to B1 calculate the maximum face in clothes color analysis region
Color.
B3 judges whether rectangular area maximum color is consistent with frock picture maximum color, and if consistent rectangle analysis is carried out
The maximum color in region carries out the matching analysis, otherwise output matching failure result with the maximum color in frock picture library.
In step B1, monistic feature and human eye are had to image according to electricity business hall frock color
The characteristics of color-aware, sets 10 kinds of colors, in order to avoid because illumination is different and brightness difference causes color change so as to cause
The phenomenon of matching error, 10 kinds of color region scopes to setting are enlarged, the maxima and minima of setting area scope,
A kind of color is all classified as in some region of all pixels.
In step B2, the conversion in pixel color space is carried out first, HSV space is transformed into by rgb space, and calculate
The three-channel color histogram of H, S, V, according to the color category and color region scope of the setting of step B1 color histogram is asked for
The maximum color of figure, asking for foundation is, miFor the number of pixels of pixel i, M is image pixel total number, according toValue obtains maximum color regional extent.
In step B3, the maximum color in the maximum color in rectangle color analysis region and frock picture is carried out
Match somebody with somebody, first determine whether that both maximum color regional extents are whether consistent, if maximum color regional extent unanimously if carry out maximum face
Color similarity is matched, the direct output matching failure result if maximum color regional extent is inconsistent.
In step C, by recognize upper part of the body region, extract clothes profile, calculate Hu squares, and with frock picture wheel
Exterior feature carries out Hu match by moment, completes clothes profile and compares analysis, realizes that step includes：
C1 extracts clothes profile to the upper part of the body.
C2 calculates 7 of clothes profile picture not displacements.
C3 carries out Hu match by moment to the clothes for upper half of body profile for extracting with the profile of frock picture.
C4 output matching end values, the bigger expression of value is more matched.
In step C1, the color histogram calculated using step B2 obtains maximum color, and maximum color is set to
White, other colors are set to black, and with this clothes profile is obtained.
In step C2, the not displacement of calculation procedure C1 extract 7 of clothes profile, using second order and three ranks
Normalization central moment constructs above-mentioned 7 not displacements.
In step C3, Hu match by moment is carried out to monitoring personnel clothes profile and frock picture profile, calculate Hu square phases
More match like the bigger expression of degree similarity.
Beneficial effects of the present invention：
1st, instant invention overcomes in traditional clothing technology of identification, easily occurring showing for matching error because matching condition is single
As by with reference to clothes color matching and clothes profile Hu match by moment, for matching result enough supports being provided, it is ensured that matching
As a result accuracy.
2nd, the present invention adopts Hu match by moment technologies, and solving common profile matching technique cannot avoid because clothes inclination etc. is walked
The error that sample problem is caused, match cognization is carried out using the rotation of Hu squares, zooming and panning invariance to clothes profile, improves wheel
The degree of accuracy of exterior feature identification.
3rd, the accuracy service that the present invention is provided realizes the intellectuality of electricity business hall employee dressing management, reduces artificial
The work of supervision and management, improves the effectiveness and standardization of electricity business hall work.
Description of the drawings
Fig. 1 is a kind of electricity business hall dressing standardization recognition methodss flow chart based on color and Hu match by moment.
Fig. 2 is clothes color matching flow chart.
Fig. 3 is clothes profile Hu match by moment flow charts.
Specific embodiment
Below in conjunction with the accompanying drawings the invention will be further described with embodiment.
If Fig. 1 is a kind of electricity business hall dressing standardization recognition methodss flow chart based on color and Hu match by moment, should
Method realizes that step is as follows：
Step 101：Dressing color analysis region is extracted, first by recognition of face, is judged with the presence or absence of " people " in monitor area,
Realize the identification to " people ".Secondly upper part of the body identification is carried out to the people in video monitoring regional, is obtained in monitor area
The crown of " people ", shoulder, the scope of shirtfront, the face location according to determined by recognition of face, by set the people crown, shoulder,
Shirtfront and the relative position of face, obtain the upper part of the body of people, realize the identification of the upper part of the body.Finally carry out upper part of the body rectangular area
Intercept, recognition of face region and upper part of the body identification region are overlapped into process, obtain one comprising shoulder and shoulder top
Rectangular area, in order to reduce the interference of shoulder background above color, to intercept rectangular area carry out position optimization adjustment, to
Move down dynamic suitable distance.
Step 102：Rectangular area to intercepting carries out color analysis, extracts the maximum color in rectangle color analysis region,
And carry out the matching analysis with the maximum color in frock picture library.
Step 103：By the upper part of the body identification region for recognizing, clothes profile is extracted, clothes wheel is carried out by Hu match by moment
Exterior feature compares analysis, according to second order, three rank centre-to-centre spacing, calculates 7 of profile not displacements, and carries out Hu square Similarity Measures.
Step 104：Clothes color matching results and clothes Hu match by moment results in step 103 in weighted comprehensive step 102
Frock dressing result is analyzed.
The step of such as Fig. 2 is clothes color matching flow chart, the method is as follows：
Step 201：Expand and set the regional extent of 10 kinds of colors.
Step 202：Color analysis region is calculated according to the color region scope and color histogram of step 201 setting
Maximum color.
Step 203：Judge rectangular area maximum color regional extent and frock picture maximum color regional extent whether
Cause
Step 204：If step 203 judged result is inconsistent, output matching failure result.
Step 205：If step 203 judged result is consistent, the maximum color and frock picture of rectangle analyzed area is carried out
In maximum color similarity mode analysis.
Step 206：Output color matching similarity.
In step 201, in order to avoid the color error caused because of illumination condition and brightness conditions change, to color
Regional extent is enlarged, and the color in a certain regional extent is all classified as into a kind of color, additionally, according to electric power business
Room staff's frock color has monistic feature, sets the regional extent of 10 kinds of colors and each color.
In step 202：Carry out the conversion in pixel color space first, HSV space be transformed into by rgb space, and calculate H,
The three-channel color histogram of S, V, color histogram is asked for most according to the color category and regional extent of step 201 setting
Big color region, asking for foundation is, miFor the number of pixels of pixel i, M is image pixel total number, according to H
Value obtains maximum color regional extent.
In step 205：Rectangular area maximum color regional extent and frock picture maximum color area are judged according to step 203
Domain scope is consistent, and the maximum color and the maximum color in frock picture library for carrying out rectangle analyzed area carries out similarity and match point
Analysis, matching foundation is, distance is less to show that similarity is higher, otherwise output matching
Failure result, arranges the discrete function between matching distance and similarity, obtains the similarity of maximum color.
If Fig. 3 is clothes profile Hu match by moment flow charts, the method realizes that step is as follows：
301 pairs are extracted above the waist clothes profile and obtain maximum color region using the color histogram that step 202 is calculated, and will most
Big color is set to white, and other colors are set to black, and with this clothes profile is obtained.
302 calculate 7 of clothes profile pictures not displacements.
The clothes for upper half of body profile of 303 pairs of extractions carries out Hu match by moment with the profile of frock picture.
304 output matching results, as a result bigger expression is more matched.
In step 301, the color histogram calculated using step 202 obtains maximum color, and maximum color is set to white
Color, other colors are set to black, and with this clothes profile is obtained.
In step 303, difference calculation procedure E1, the monitoring personnel clothes profile of E2 acquisitions is with 7 of frock profile not
Displacement、, using second order and three rank normalization central moments above-mentioned 7 not displacements are constructed.
In step 304, Hu match by moment is carried out to monitoring personnel clothes profile and frock profile, calculates Hu square similarities dbR,, similarity it is bigger expression more match.
Embodiment 1：
In staff's frock supervision and management of electricity business hall, using a kind of electric power business based on color and Hu match by moment
Room dressing standardization recognition methodss, according to the cluster feature of face complexion in monitor area, determine human face region, specific skin
Color cluster areas are the region of a similar parallelogram, and expression formula is： .According to the human face region for capturing, and according to upper half of human body and the relative position of face, obtain
Upper part of the body region, by upper part of the body region and human face region process is overlapped, and obtains a rectangular area, and this rectangular area includes
Region above human body shoulder and shoulder, in order to reduce the interference of non-Garment region, by the rectangular area in embodiment
Move down the 40% of whole region height.
The regional extent of 10 kinds of colors of setting is as follows：
Hsv color space is transformed into by RGB color to the color space of pixel, transformation process is：
V=G
The three-channel color histogram of H, S, V is calculated, if miFor the number of pixels of pixel i, M is image pixel total number, then
For pixel i in color histogram ordinate value be pixel i in color histogram value, according to setting ten kinds of colors region
Scope, and maximum color is calculated according to color histogram, basis is：。
Judge whether rectangular area maximum color regional extent is consistent with frock picture maximum color region, enter if consistent
The similarity the matching analysis of the maximum color in the maximum color and frock picture library of row rectangle analyzed area, matching foundation is,It is less to show that similarity is higher, if judging rectangular area maximum color
Scope is inconsistent with frock picture maximum color scope, then output matching failure result.According to matching resultSet up with
The corresponding discrete function of similarity, obtains similarity, and maximum color similarityFor three Color Channel similarities
Meansigma methodss.
According to the upper half of human body that monitoring is obtained, and the color histogram in color analysis region will color in above the waist
Maximum color is set to white in rectangular histogram, and other pixels are set to black, and to clothes for upper half of body contours extract is carried out.Calculate successively
The second-order central of profile away from, three rank centre-to-centre spacing, 7 Hu squares.Wherein 7 Hu squares are：
According to, calculate the Hu squares and frock picture profile Hu squares of monitoring personnel clothes profile
Matching degree.Weighted comprehensive processes color histogram match result and Hu match by moment results：*, whereinFor weight of the color matching in comprehensive matching result, effect of the color matching in comprehensive matching result is set
Put larger,It is then 0.3 to be worth for 0.7, Hu match by moment weight.To final similarity mode result, similarity mode value is more than
0.8 is thought that the match is successful, otherwise it is assumed that matching is unsuccessful.
Claims (10)
1. a kind of electricity business hall dressing standardization recognition methodss based on color and Hu match by moment, it is characterised in that including following
Step：
Step A：Dressing color analysis region is extracted, first by recognition of face, is judged with the presence or absence of " people " in monitor area, its
The secondary people in video monitoring regional carries out upper part of the body identification, is then folded recognition of face region with upper part of the body identification region
Plus process, obtain the rectangular area of a clothing color analysis；
Step B：In extraction step A obtain color analysis region maximum color, and with frock picture library in maximum color
Carry out the matching analysis；
Step C：According in step A recognize upper part of the body region, extract the upper part of the body clothes profile, calculate profile Hu squares, and with
Frock picture profile carries out Hu match by moment, completes clothes profile and compares analysis；
Step D：In weighted comprehensive step B in clothes color matching results and step C clothes Hu match by moment result to frock dressing
As a result it is analyzed.
2. a kind of electricity business hall dressing standardization identification side based on color and Hu match by moment according to claim 1
The step of method, it is characterised in that in step A, extraction dressing color analysis region, includes：
Step A1：Recognition of face is carried out, recognition of face is carried out to the people of video monitoring regional, monitored space is judged according to face characteristic
Whether there is " people " in domain, realize the identification to " people "；
Step A2：Upper part of the body identification is carried out to the people in video monitoring regional, the face location according to determined by recognition of face is led to
The relative position of the setting people crown, shoulder, shirtfront and face is crossed, the upper part of the body of people is obtained, the identification of the upper part of the body is realized；
Step A3：The intercepting of dressing color analysis rectangular area is carried out, the human face region recognized in step A1 and step A2 are known
Other upper part of the body region is overlapped process, one is obtained comprising the rectangular area above shoulder and shoulder, in order to reduce shoulder
The interference of wing background above color, the rectangular area to intercepting carries out position optimization adjustment, is moved downward to suitable distance.
3. a kind of electricity business hall dressing standardization identification side based on color and Hu match by moment according to claim 1
Method, it is characterised in that in step B, the maximum color in the color analysis region obtained in extraction step A, and and tooling drawing
The step of maximum color in valut carries out the matching analysis includes：
B1 expands and sets the regional extent of 10 kinds of colors；
Color region scope and color histogram that B2 sets according to B1 calculate the maximum color in clothes color analysis region；
B3 judges whether rectangular area maximum color is consistent with frock picture library maximum color, and if consistent rectangle analysis area is carried out
The similarity the matching analysis of maximum color, otherwise output matching failure result in the maximum color and frock picture library in domain.
4. a kind of electricity business hall dressing standardization identification side based on color and Hu match by moment according to claim 3
Method, it is characterised in that in step B1, has monistic feature and human eye according to electricity business hall frock color
The characteristics of perceiving to color of image sets 10 kinds of colors, in order to avoid because illumination is different and brightness difference cause color change from
And easily causing the phenomenon of matching error, the regional extent of 10 kinds of colors to setting is enlarged, and setting area scope is most
Big value and minima, in some region of all pixels a kind of color is all classified as.
5. a kind of electricity business hall dressing standardization identification side based on color and Hu match by moment according to claim 3
Method, it is characterised in that in step B2, the color category set according to the color histogram and B1 of analyzed area and area
Domain, asks for the maximum color of analyzed area.
6. a kind of electricity business hall dressing standardization identification side based on color and Hu match by moment according to claim 3
Method, it is characterised in that in step B3, judges the maximum color in the maximum color and frock picture library of rectangle analyzed area
It is whether consistent, similarity matching is carried out to both maximum colors if consistent, if the maximum color for judging both is inconsistent
Output matching failure result.
7. a kind of electricity business hall dressing standardization identification side based on color and Hu match by moment according to claim 1
Method, it is characterised in that step C, according to the upper part of the body region recognized in step A, extracts the clothes profile of the upper part of the body, calculates
Profile Hu squares, and Hu match by moment is carried out with frock picture profile, complete clothes profile and compare analysis, including step：
C1 extracts clothes profile to the upper part of the body
C2 calculates 7 of clothes profile picture not displacements,
C3 carries out Hu match by moment to the clothes for upper half of body profile for extracting with the profile of frock picture,
C4 output matching end values, the bigger expression of value is more matched.
8. a kind of electricity business hall dressing standardization identification side based on color and Hu match by moment according to claim 7
Method, it is characterised in that in step C1, extracts maximum color in picture and is set to white using color histogram, and other are all
For black, so as to extract clothes profile.
9. a kind of electricity business hall dressing standardization identification side based on color and Hu match by moment according to claim 8
Method, it is characterised in that in step C3, using the rotation of 7, picture not bending moment, zooming and panning invariance calculates two
Hu match by moment similarity degree between profile.
10. a kind of electricity business hall dressing standardization identification side based on color and Hu match by moment according to claim 1
Method, it is characterised in that in step D, to color matching and Hu match by moment results process is weighted, and sets corresponding threshold
Value, meet threshold requirement then think clothing the match is successful, otherwise it fails to match.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610980144.7A CN106599781A (en) | 2016-11-08 | 2016-11-08 | Electric power business hall dressing normalization identification method based on color and Hu moment matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610980144.7A CN106599781A (en) | 2016-11-08 | 2016-11-08 | Electric power business hall dressing normalization identification method based on color and Hu moment matching |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106599781A true CN106599781A (en) | 2017-04-26 |
Family
ID=58590666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610980144.7A Pending CN106599781A (en) | 2016-11-08 | 2016-11-08 | Electric power business hall dressing normalization identification method based on color and Hu moment matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106599781A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107507263A (en) * | 2017-07-14 | 2017-12-22 | 西安电子科技大学 | A kind of Texture Generating Approach and system based on image |
| CN108156709A (en) * | 2017-12-25 | 2018-06-12 | 安徽极光照明工程有限公司 | A kind of bedroom LED lamp intelligent control system |
| CN109271846A (en) * | 2018-08-01 | 2019-01-25 | 深圳云天励飞技术有限公司 | Personal identification method, apparatus and storage medium |
| CN110334670A (en) * | 2019-07-10 | 2019-10-15 | 北京迈格威科技有限公司 | Object monitor method and device, electronic equipment, storage medium |
| CN110427808A (en) * | 2019-06-21 | 2019-11-08 | 武汉倍特威视系统有限公司 | Police uniform recognition methods based on video stream data |
| CN110472574A (en) * | 2019-08-15 | 2019-11-19 | 北京文安智能技术股份有限公司 | A kind of nonstandard method, apparatus of detection dressing and system |
| CN110705505A (en) * | 2019-10-14 | 2020-01-17 | 国网山东省电力公司泰安供电公司 | Intelligent identification device, method and system for service specification of electric power business hall |
| CN112200051A (en) * | 2020-09-30 | 2021-01-08 | 重庆天智慧启科技有限公司 | Case field inspection system and method |
| CN113392713A (en) * | 2021-05-20 | 2021-09-14 | 上海可深信息科技有限公司 | Work clothes wearing identification method |
| CN113516062A (en) * | 2021-06-24 | 2021-10-19 | 深圳开思信息技术有限公司 | Customer identification method and system for automobile repair shop |
| CN114267013A (en) * | 2021-12-16 | 2022-04-01 | 北京小龙潜行科技有限公司 | Pasture tool identification method applied to edge computing equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079109A (en) * | 2007-06-26 | 2007-11-28 | 北京中星微电子有限公司 | Identity identification method and system based on uniform characteristic |
| CN101477625A (en) * | 2009-01-07 | 2009-07-08 | 北京中星微电子有限公司 | Upper half of human body detection method and system |
| CN101996314A (en) * | 2009-08-26 | 2011-03-30 | 厦门市美亚柏科信息股份有限公司 | Content-based human body upper part sensitive image identification method and device |
| CN104268544A (en) * | 2014-10-14 | 2015-01-07 | 陶晨 | Evaluation system for clothes visual effect |
| CN103745226B (en) * | 2013-12-31 | 2015-03-18 | 国家电网公司 | Dressing safety detection method for worker on working site of electric power facility |
| CN105069466A (en) * | 2015-07-24 | 2015-11-18 | 成都市高博汇科信息科技有限公司 | Pedestrian clothing color identification method based on digital image processing |
| CN105447529A (en) * | 2015-12-30 | 2016-03-30 | 商汤集团有限公司 | Costume detection and attribute value identification method and system |
| CN105469087A (en) * | 2015-07-13 | 2016-04-06 | 百度在线网络技术（北京）有限公司 | Method for identifying clothes image, and labeling method and device of clothes image |
| CN106022375A (en) * | 2016-05-19 | 2016-10-12 | 东华大学 | HU invariant moment and support vector machine-based garment style identification method |
-
2016
- 2016-11-08 CN CN201610980144.7A patent/CN106599781A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079109A (en) * | 2007-06-26 | 2007-11-28 | 北京中星微电子有限公司 | Identity identification method and system based on uniform characteristic |
| CN101477625A (en) * | 2009-01-07 | 2009-07-08 | 北京中星微电子有限公司 | Upper half of human body detection method and system |
| CN101996314A (en) * | 2009-08-26 | 2011-03-30 | 厦门市美亚柏科信息股份有限公司 | Content-based human body upper part sensitive image identification method and device |
| CN103745226B (en) * | 2013-12-31 | 2015-03-18 | 国家电网公司 | Dressing safety detection method for worker on working site of electric power facility |
| CN104268544A (en) * | 2014-10-14 | 2015-01-07 | 陶晨 | Evaluation system for clothes visual effect |
| CN105469087A (en) * | 2015-07-13 | 2016-04-06 | 百度在线网络技术（北京）有限公司 | Method for identifying clothes image, and labeling method and device of clothes image |
| CN105069466A (en) * | 2015-07-24 | 2015-11-18 | 成都市高博汇科信息科技有限公司 | Pedestrian clothing color identification method based on digital image processing |
| CN105447529A (en) * | 2015-12-30 | 2016-03-30 | 商汤集团有限公司 | Costume detection and attribute value identification method and system |
| CN106022375A (en) * | 2016-05-19 | 2016-10-12 | 东华大学 | HU invariant moment and support vector machine-based garment style identification method |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107507263B (en) * | 2017-07-14 | 2020-11-24 | 西安电子科技大学 | Texture generation method and system based on image |
| CN107507263A (en) * | 2017-07-14 | 2017-12-22 | 西安电子科技大学 | A kind of Texture Generating Approach and system based on image |
| CN108156709A (en) * | 2017-12-25 | 2018-06-12 | 安徽极光照明工程有限公司 | A kind of bedroom LED lamp intelligent control system |
| CN109271846A (en) * | 2018-08-01 | 2019-01-25 | 深圳云天励飞技术有限公司 | Personal identification method, apparatus and storage medium |
| CN110427808A (en) * | 2019-06-21 | 2019-11-08 | 武汉倍特威视系统有限公司 | Police uniform recognition methods based on video stream data |
| CN110334670B (en) * | 2019-07-10 | 2021-08-17 | 北京迈格威科技有限公司 | Object monitoring method and device, electronic equipment and storage medium |
| CN110334670A (en) * | 2019-07-10 | 2019-10-15 | 北京迈格威科技有限公司 | Object monitor method and device, electronic equipment, storage medium |
| CN110472574A (en) * | 2019-08-15 | 2019-11-19 | 北京文安智能技术股份有限公司 | A kind of nonstandard method, apparatus of detection dressing and system |
| CN110705505A (en) * | 2019-10-14 | 2020-01-17 | 国网山东省电力公司泰安供电公司 | Intelligent identification device, method and system for service specification of electric power business hall |
| CN112200051A (en) * | 2020-09-30 | 2021-01-08 | 重庆天智慧启科技有限公司 | Case field inspection system and method |
| CN112200051B (en) * | 2020-09-30 | 2023-09-29 | 重庆天智慧启科技有限公司 | Case field inspection system and method |
| CN113392713A (en) * | 2021-05-20 | 2021-09-14 | 上海可深信息科技有限公司 | Work clothes wearing identification method |
| CN113516062A (en) * | 2021-06-24 | 2021-10-19 | 深圳开思信息技术有限公司 | Customer identification method and system for automobile repair shop |
| CN114267013A (en) * | 2021-12-16 | 2022-04-01 | 北京小龙潜行科技有限公司 | Pasture tool identification method applied to edge computing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106599781A (en) | Electric power business hall dressing normalization identification method based on color and Hu moment matching | |
| CN106339702A (en) | Multi-feature fusion based face identification method | |
| CN105160317B (en) | One kind being based on area dividing pedestrian gender identification method | |
| CN104361314B (en) | Based on infrared and transformer localization method and device of visual image fusion | |
| CN102592288B (en) | Method for matching pursuit of pedestrian target under illumination environment change condition | |
| CN102663411B (en) | Recognition method for target human body | |
| CN101697197B (en) | Method for recognizing human face based on typical correlation analysis spatial super-resolution | |
| CN105469113A (en) | Human body bone point tracking method and system in two-dimensional video stream | |
| CN103218605A (en) | Quick eye locating method based on integral projection and edge detection | |
| CN102214291A (en) | Method for quickly and accurately detecting and tracking human face based on video sequence | |
| Pandey et al. | Hand gesture recognition for sign language recognition: A review | |
| CN106778676A (en) | A kind of notice appraisal procedure based on recognition of face and image procossing | |
| CN104573713B (en) | A kind of transformer Infrared image recognition based on image texture characteristic | |
| CN103955680B (en) | Action identification method and device based on Shape context | |
| CN105160346B (en) | A kind of greasy recognition methods of curdy fur on tongue based on texture and distribution characteristics | |
| CN106097354B (en) | A kind of hand images dividing method of combining adaptive Gauss Face Detection and region growing | |
| CN106023151A (en) | Traditional Chinese medicine tongue manifestation object detection method in open environment | |
| CN112232332B (en) | Non-contact palm detection method based on video sequence | |
| CN104598888B (en) | A kind of recognition methods of face gender | |
| CN110032932B (en) | Human body posture identification method based on video processing and decision tree set threshold | |
| CN106778499B (en) | Method for rapidly positioning human iris in iris acquisition process | |
| CN110458041A (en) | A kind of face identification method and system based on RGB-D camera | |
| CN108875645A (en) | A kind of face identification method under the conditions of underground coal mine complex illumination | |
| CN104573628A (en) | Three-dimensional face recognition method | |
| CN106980864B (en) | A kind of pedestrian's recognition methods again based on support sample indirect type |
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: 20170426 |
|
| RJ01 | Rejection of invention patent application after publication |