CN108073870A - Method and device based on seed region and communication path identification hand region - Google Patents
Method and device based on seed region and communication path identification hand region Download PDFInfo
- Publication number
- CN108073870A CN108073870A CN201611020211.7A CN201611020211A CN108073870A CN 108073870 A CN108073870 A CN 108073870A CN 201611020211 A CN201611020211 A CN 201611020211A CN 108073870 A CN108073870 A CN 108073870A
- Authority
- CN
- China
- Prior art keywords
- value
- pixel
- region
- hand region
- similarity
- 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
- G06V40/107—Static hand or arm
Abstract
The present invention provides a kind of method and device based on seed region and communication path identification hand region, the described method includes：The color value of the pixel in hand region to be identified is compared with the color value of seed region to obtain similarity value respectively, wherein the seed region is located in the hand region to be identified；The steady angle value of the pixel color variation in the pixel to the shortest path and the shortest path of the seed region in the hand region to be identified is determined respectively；Determine that the pixel is the probability value of pixel in hand region according to distance, the similarity value and the steady angle value of the pixel and the seed region；Hand region is determined according to the probability value.
Description
Technical field
The present invention relates to field of image recognition, and in particular to one kind is based on seed region and communication path identification hand region
Method and device.
Background technology
With integrating for the fast development of software and hardware relevant technical, such as wrist intelligent apparatus, smartwatch, Intelligent bracelet etc.
Spend higher and higher, function is increasingly abundanter, and the cell-phone function of significant proportion can be realized by smartwatch, Intelligent bracelet, greatly
The big method for simplifying user and receiving and transferring information.But compare with traditional smart phone, wrist intelligent apparatus is limited to small size
Display screen, on the one hand, user can not complete the operation of correlation function using touch screen or button well when in use, easily
Maloperation is caused, on the other hand, when smartwatch is worn on one on hand, to be operated on it, except waking up, dormancy etc.
Simple operations are not required the operation of another hand outer, remaining more complicated operation has the completion of another hand, can not use single
Hand independently smartwatch is operated, therefore, smartwatch on content shows and operates there are still it is very big the defects of.
The control mode based on user's hand gesture is some products provides in view of the above-mentioned problems, having at present, user can be with
By wearing the finger movement of wrist-watch come control device, principle is to utilize the photographic device acquisition hand figure set on wrist-watch
Picture, processor determine control content according to the variation of image.Such scheme needs identify the hand of user exactly from image
Portion region or profile need to reject background and other noises, only determine control content according to the variation of hand region.
Existing image identifying schemes are typically the shape feature according to target object, according to default characteristic parameter, profit
Target object is identified from image with means such as machine learning models.But this identification method resists the ability of background interference
It is poor, such as when user's local environment background is sufficiently complex, be likely to judge by accident according to shape feature, it can be seen that existing
Image identifying schemes accuracy is poor.
The content of the invention
The present invention is to solve the problem of existing image identifying schemes accuracy is poor.
In view of this, the present invention provides a kind of method based on seed region and communication path identification hand region, including：
The color value of the pixel in hand region to be identified is compared respectively to obtain similarity with the color value of seed region
Value, wherein the seed region is located in the hand region to be identified；It determines respectively in the hand region to be identified
Pixel to the shortest path and the shortest path of the seed region on pixel color variation steady angle value；According to
The pixel and distance, the similarity value and the steady angle value of the seed region determine that the pixel is hand region
The probability value of interior pixel；Hand region is determined according to the probability value.
Preferably, described respectively by the color value of the pixel in hand region to be identified and the color value of seed region
The step of being compared to obtain similarity value and the pixel determined respectively in the hand region to be identified are described in
Before the step of steady angle value of pixel color variation on the shortest path of seed region and the shortest path, also wrap
It includes：
Hand region to be identified is determined in the picture；
The seed region is rejected from the hand region to be identified.
Preferably, it is described according to the pixel and distance, the similarity value and the smoothness of the seed region
Value determines that the pixel is the probability value of pixel in hand region, including：
Determine the Euclidean distance values L of the pixel and the seed region；
Determine that the pixel is the probability value of pixel in hand region according to L, the similarity value and the steady angle value,
Wherein described probability value and the similarity value, the steady angle value correlation, the probability value and the negatively correlated passes of L
System.
Preferably, it is described to determine that the pixel is picture in hand region according to L, the similarity value and the steady angle value
The probability value of element, including：
The similarity value and the weights corresponding to the steady angle value are determined respectively；
According to the product of the similarity value and corresponding weights, the product of the steady angle value and corresponding weights and
The distance L determines the probability value.
Preferably, the hand region is determined using active contour model, and the probability value is as the active
The input value of Active contour model, the active contour model is according to the probability value, predetermined pull parameter, predetermined gravitational parameter
Hand region is obtained with predetermined initial profile.
Preferably, the similarity and the smoothness are the phases according to the color value under RGB, HSV and YCrCb space
It is determined like the summation of property indication information.
Correspondingly, the present invention also provides it is a kind of based on seed region and communication path identification hand region device, including：
Similarity determining unit, for respectively by the color value of the color value of the pixel in hand region to be identified and seed region into
Row is compared to obtain similarity value, wherein the seed region is located in the hand region to be identified；Smoothness determines list
Member, for determine respectively the pixel in the hand region to be identified to the seed region shortest path and it is described most
The steady angle value of pixel color variation on short path；Identifying unit, for according to the pixel and the seed region away from
Determine that the pixel is the probability value of pixel in hand region from, the similarity value and the steady angle value；Determination unit is used
In determining hand region according to the probability value.
Preferably, further include：
Recognition unit, for before the similarity determining unit and the smoothness determination unit are handled,
Hand region to be identified is determined in image；
Culling unit, for rejecting the seed region from the hand region to be identified.
Preferably, the identifying unit includes：
Metrics calculation unit, for determining the Euclidean distance values L of the pixel and the seed region；
Probability determining unit, for determining that the pixel is hand area according to L, the similarity value and the steady angle value
The probability value of pixel in domain, wherein the probability value and the similarity value, the steady angle value correlation, described general
Rate value and the negatively correlated relations of L.
Preferably, the probability determining unit includes：
Weights determination unit, for determining the similarity value and the weights corresponding to the steady angle value respectively；
Probability calculation unit, for according to the product of the similarity value and corresponding weights, the steady angle value and phase
The product for the weights answered and the distance L determine the probability value.
The method and device based on seed region and communication path identification hand region provided according to embodiments of the present invention,
By the way that the color value of the pixel in hand images to be identified is compared with the pixel color on each position, to determine figure
Each pixel as in is the probability value of the pixel in hand region, and then according to the probability value and each pixel and fate
The distance in domain determines hand region, and compared to the existing scheme that hand region is determined according to shape feature, the present invention is implemented
Example possesses higher accuracy.And color value similarity of this programme according to pixel and seed region to be identified, access
The color change smoothness of pixel on footpath and definite above-mentioned probability value is integrated apart from these three numerical value with seed region,
So that this programme possesses stronger antijamming capability.
Description of the drawings
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution of the prior art
Embodiment or attached drawing needed to be used in the description of the prior art are briefly described, it should be apparent that, in describing below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is a kind of structure diagram of wearable device；
Fig. 2 is the image of the shooting of equipment shown in Fig. 1；
Fig. 3 is to carry out discoloration treated image to Fig. 2；
Fig. 4 is the flow of the method provided in an embodiment of the present invention that hand region is identified based on seed region and communication path
Figure；
Fig. 5 is the structure of the device provided in an embodiment of the present invention that hand region is identified based on seed region and communication path
Figure.
Specific embodiment
Technical scheme is clearly and completely described below in conjunction with attached drawing, it is clear that described implementation
Example is part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill
Personnel's all other embodiments obtained without making creative work, belong to the scope of protection of the invention.
As long as in addition, technical characteristic involved in invention described below different embodiments non-structure each other
It can be combined with each other into conflict.
An embodiment of the present invention provides a kind of method based on seed region and communication path identification hand region, this method
Handled image is the image shot by the wearable device with photographic device, and the equipment is as shown in Figure 1, wherein camera shooting fills
It sets to 01 and gathers wearer's hand images along wearer's wrist to palm of the hand direction.Its image collected is as shown in Fig. 2, wearer
The integral position of palm in the picture is more fixed, and simply finger areas can be with user in a fixed scope
Movement changes.As shown in figure 3, method provided in this embodiment includes the following steps：
S1, the color value of the pixel in hand region to be identified is compared with the color value of seed region respectively with
Similarity value is obtained, wherein the seed region is located in the hand region to be identified；
S2 determines shortest path and institute of the pixel to the seed region in the hand region to be identified respectively
State the steady angle value of the pixel color variation on shortest path.
As shown in Fig. 2, wherein comprising seed region 11,12 and second presumptive area 13 of hand region to be identified.On
The selection in above three region can preset fixed position, as long as user normally wears, seed region 11 must be used
A part for family palm, the second presumptive area 13 must not include user's palm.In order to more clearly describe the embodiment of the present invention
The each area being related to uses and Fig. 2 Fig. 4 carried out after discoloration is illustrated, it is necessary to illustrate, the embodiment of the present invention below
The color for relying on pixel is needed to carry out subsequent processing, so Fig. 4 is intended merely to clearly demonstrate given image, practical application
When need not carry out discoloration processing.
Since the pixel in seed region must be the pixel in hand region, object pixel is got over its similarity
It is high, then it represents that object pixel is that the probability of hand region pixel is bigger.Wherein the color of seed region can be wherein all pictures
The average of plain color value.
Hand region it is close as color and closing region, the shortest path of each pixel to seed region
On each pixel between color change should be subtleer and gentle, then may if there is situation about changing greatly
Represent there is the situation of interruption on path, which may not be the pixel in hand region.Therefore object pixel and seed region
Shortest path on pixel color variation smoothness it is higher, then it represents that object pixel is that the probability of hand region pixel is got over
Greatly.In this step, after analyzing the path of each pixel to seed region, a steady angle value can be obtained.
As described above, the process of definite smoothness and similarity is two kinds of entirely different calculating process, therefore above-mentioned step
The execution sequence of rapid S1 and step S2 in no particular order, can also perform simultaneously.By the processing in above-mentioned steps, each it is judged
Pixel all corresponding there are one a similarity value w1 and steady angle value w2.
It is compared on the color value between pixel, the embodiment of the present invention can use the color value under a certain color space
It is compared, the combination of the color value under a variety of kinds of color spaces can also be used to be compared, such as can be according to RGB, HSV
And the summation of the similarity indices information of the color value under YCrCb spaces determines the similarity of two pixels.
S3 determines institute according to distance, the similarity value and the steady angle value of the pixel and the seed region
State the probability value that pixel is pixel in hand region.I.e. for each pixel in hand region 12 to be identified, it is utilized
Corresponding similarity value, steady angle value and go out a probability value apart from COMPREHENSIVE CALCULATING with seed region (such as regional center),
The probability value is more high, and it is that probability in hand region is also big to represent the pixel, on the contrary then smaller.Distance is in negative with probability value
Pass relation, i.e. distance are more remote, and probability value can be reduced accordingly.Such as above-mentioned pixel a respective distances L, similarity w1 and smoothness
W2, it is n% that the probability that pixel a is pixel in hand region can be obtained after COMPREHENSIVE CALCULATING.All pixels COMPREHENSIVE CALCULATING is completed
Afterwards, each pixel corresponds to a probability value.
S4 determines hand region according to probability value, and there are many methods of determination, such as can use simplest mode, leads to
Setting probability threshold value probability value corresponding with each pixel is crossed to compare, you can the pixel in all hand regions is filtered out, these
The summation of pixel is hand region.Preferably, in the present embodiment, a kind of active contour model may be employed (also referred to as
Snake models) identify hand region.Specifically, input value of the above-mentioned probability value as active contour model, active profile
Line model obtains in one's hands according to the corresponding probability value of each pixel, predetermined pull parameter, predetermined gravitational parameter and predetermined initial profile
Portion region.Each point on model will move to interest edges of regions under gravitation and pulling force effect, while profile keeps certain
Curvature, possess smooth characteristic.Finally, after each point movement stops, that is, the light of interest region (hand region) is identified
Sliding edge to get to be continuously smooth hand region outer profile.
There is provided according to embodiments of the present invention based on seed region and communication path identification hand region method, pass through by
The color value of pixel in hand images to be identified is compared with the pixel color on each position, to determine in image
Each pixel is the probability value of the pixel in hand region, so according to the probability value and each pixel and presumptive area away from
From hand region is determined, compared to the existing scheme that hand region is determined according to shape feature, the embodiment of the present invention possesses
Higher accuracy.And this programme is according on the color value similarity of pixel and seed region to be identified, communication path
The color change smoothness of pixel and definite above-mentioned probability value is integrated apart from these three numerical value with seed region so that this
Scheme possesses stronger antijamming capability.
As a preferred embodiment, before above-mentioned steps S1 and S2, can also include the following steps：
S01 determines hand region to be identified in the picture.As described above, according to the characteristics of image, hand to be identified
The position in region 12 can also be demarcated in advance, 1/2,3/4,4/5 region etc. e.g. from image border to image, specifically
Predetermined focal distance and viewfinder range when can be according to captured image determine.
S02 rejects seed region from hand region to be identified, since seed region must be a part for palm,
Therefore can this partial pixel be gone divided by be reduced calculation amount.
Above-mentioned preferred embodiment determines hand region to be identified in the picture, and must be hand region from wherein rejecting
Part so that subsequent step can be calculated just for remaining region, it is possible thereby to reduce calculation amount, improve identification effect
Rate.
As an optional embodiment, above-mentioned steps S2 may include steps of：
S21 calculates pixel to the cost value in each path of seed region respectively, and cost value is according to the pixel on path
What the value of point determined；
S22 chooses the path with minimum cost value from each path.
Further, above-mentioned steps S21 may include steps of：
The color value of pixel on path is built curve by S211 respectively；
S212, the second-order partial differential coefficient of calculated curve；
S213 calculates the variance of second order local derviation as cost value.
According to above-mentioned preferred embodiment, such image upper pathway can be searched in the picture first so that object pixel
For point to the Least-cost of the center of seed region 11, the calculating of cost can be a series of based on what is passed through on image path
What the color value of pixel determined, it can calculate in the following way：The value of pixel builds a curve successively on path, calculates
The second-order partial differential coefficient of the curve counts the variance of each point second order local derviation.Variance yields is cost, it is clear that second order local derviation represents
The stationarity of the variation of road diapoint, the variance of local derviation represent the variation stationarity of picture point pixel value in whole upper pathway.
As a preferred embodiment, above-mentioned steps S3 may include steps of：
S31 determines the Euclidean distance values L of pixel and seed region；
S32 determines that the pixel is the general of pixel in hand region according to L, the similarity value and the steady angle value
Rate value, wherein the probability value and the similarity value, the steady angle value correlation, the probability value is with L in negative
Correlativity.
Above-mentioned preferred embodiment is definite to integrate using Euclidean distance and similarity value, these three numerical value of steady angle value
Probability value so that this programme has stronger antijamming capability.
As described above, there are two types of comparison situations between pixel, there may be certain poor for the reliability of these comparison results
It is different, therefore may be incorporated into the concept of weights to calculate above-mentioned probability value, i.e. above-mentioned steps S32 may include steps of：
S321, determines the similarity value and the weights corresponding to the steady angle value respectively, such as above-mentioned w1, w2 can be with
Corresponding different weights；
S322, according to multiplying for the product of the similarity value and corresponding weights, the steady angle value and corresponding weights
Long-pending and described distance L determines the probability value, and the weights corresponding to similarity and smoothness can different can also be
Identical, it can specifically be set according to the reliability for comparing content, finally be corresponded to respectively according to similarity, smoothness and the two
Weights product and above-mentioned distance value integrate definite probability value, thus further improve identification accuracy.
An alternative embodiment of the invention additionally provides a kind of based on seed region and communication path identification hand region
Device, as shown in figure 5, the device includes：
Similarity determining unit 51, for respectively by the color value and seed region of the pixel in hand region to be identified
Color value be compared to obtain similarity value, wherein the seed region is located in the hand region to be identified；
Smoothness determination unit 52, for determining the pixel in the hand region to be identified to the seed zone respectively
The steady angle value of pixel color variation on the shortest path in domain and the shortest path；
Identifying unit 53, for according to the pixel and the seed region distance, the similarity value and described flat
Stability value determines that the pixel is the probability value of pixel in hand region；
Determination unit 54, for determining hand region according to the probability value.
There is provided according to embodiments of the present invention based on seed region and communication path identification hand region device, pass through by
The color value of pixel in hand images to be identified is compared with the pixel color on each position, to determine in image
Each pixel is the probability value of the pixel in hand region, so according to the probability value and each pixel and presumptive area away from
From hand region is determined, compared to the existing scheme that hand region is determined according to shape feature, the embodiment of the present invention possesses
Higher accuracy.And this programme is according on the color value similarity of pixel and seed region to be identified, communication path
The color change smoothness of pixel and definite above-mentioned probability value is integrated apart from these three numerical value with seed region so that this
Scheme possesses stronger antijamming capability.
Optionally, which can also include：
Recognition unit 501, for being handled in the similarity determining unit 51 and the smoothness determination unit 52
Before, hand region to be identified is determined in the picture；
Culling unit 502, for rejecting the seed region from the hand region to be identified.
Above-mentioned preferred embodiment determines hand region to be identified in the picture, and must be hand region from wherein rejecting
Part so that subsequent step can be calculated just for remaining region, it is possible thereby to reduce calculation amount, improve identification effect
Rate.
Optionally, identifying unit 52 can include：
Metrics calculation unit, for determining the Euclidean distance values L of the pixel and the seed region；
Probability determining unit, for determining that the pixel is hand area according to L, the similarity value and the steady angle value
The probability value of pixel in domain, wherein the probability value and the similarity value, the steady angle value correlation, described general
Rate value and the negatively correlated relations of L.
Above-mentioned preferred embodiment is definite to integrate using Euclidean distance and similarity value, these three numerical value of steady angle value
Probability value so that this programme has stronger antijamming capability.
Optionally, probability determining unit can include：
Weights determination unit, for determining the similarity value and the weights corresponding to the steady angle value respectively；
Probability calculation unit, for according to the product of the similarity value and corresponding weights, the steady angle value and phase
The product for the weights answered and the distance L determine the probability value.
Obviously, the above embodiments are merely examples for clarifying the description, and is not intended to limit the embodiments.It is right
For those of ordinary skill in the art, can also make on the basis of the above description it is other it is various forms of variation or
It changes.There is no necessity and possibility to exhaust all the enbodiments.And the obvious variation thus extended out or
Among changing still in the protection domain of the invention.
Claims (10)
- A kind of 1. method based on seed region and communication path identification hand region, which is characterized in that including：The color value of the pixel in hand region to be identified is compared respectively to obtain phase with the color value of seed region Like angle value, wherein the seed region is located in the hand region to be identified；Determine pixel in the hand region to be identified to the shortest path of the seed region and described most short respectively The steady angle value of pixel color variation on path；Determine that the pixel is according to the pixel and distance, the similarity value and the steady angle value of the seed region The probability value of pixel in hand region；Hand region is determined according to the probability value.
- 2. according to the method described in claim 1, it is characterized in that, described respectively by the pixel in hand region to be identified Color value the step of being compared with the color value of seed region to obtain similarity value and described determine described to wait to know respectively Pixel color variation in pixel to the shortest path and the shortest path of the seed region in other hand region Steady angle value the step of before, further include：Hand region to be identified is determined in the picture；The seed region is rejected from the hand region to be identified.
- 3. method according to claim 1 or 2, which is characterized in that described according to the pixel and the seed region Distance, the similarity value and the steady angle value determine that the pixel is the probability value of pixel in hand region, including：Determine the Euclidean distance values L of the pixel and the seed region；Determine that the pixel is the probability value of pixel in hand region according to L, the similarity value and the steady angle value, wherein The probability value and the similarity value, the steady angle value correlation, the probability value and the negatively correlated relations of L.
- It is 4. according to the method described in claim 3, it is characterized in that, described according to L, the similarity value and the steady angle value It is the probability value of pixel in hand region to determine the pixel, including：The similarity value and the weights corresponding to the steady angle value are determined respectively；According to the product of the similarity value and corresponding weights, the product of the steady angle value and corresponding weights and described Distance L determines the probability value.
- 5. according to the described method of any one of claim 1-4, which is characterized in that the hand region is to utilize active profile What line model determined, input value of the probability value as the active contour model, the active contour model according to The probability value, predetermined pull parameter, predetermined gravitational parameter and predetermined initial profile obtain hand region.
- 6. according to the method any one of claim 1-5, which is characterized in that the similarity and the smoothness are roots It is determined according to the summation of the similarity indices information of the color value under RGB, HSV and YCrCb space.
- 7. a kind of device based on seed region and communication path identification hand region, which is characterized in that including：Similarity determining unit, for respectively by the color of the color value of the pixel in hand region to be identified and seed region Value is compared to obtain similarity value, wherein the seed region is located in the hand region to be identified；Smoothness determination unit, for determining the pixel in the hand region to be identified to the seed region most respectively The steady angle value of pixel color variation on short path and the shortest path；Identifying unit, for distance, the similarity value and the steady angle value according to the pixel and the seed region It is the probability value of pixel in hand region to determine the pixel；Determination unit, for determining hand region according to the probability value.
- 8. device according to claim 7, which is characterized in that further include：Recognition unit, for before the similarity determining unit and the smoothness determination unit are handled, in image In determine hand region to be identified；Culling unit, for rejecting the seed region from the hand region to be identified.
- 9. the device according to claim 7 or 8, which is characterized in that the identifying unit includes：Metrics calculation unit, for determining the Euclidean distance values L of the pixel and the seed region；Probability determining unit, for determining that the pixel is in hand region according to L, the similarity value and the steady angle value The probability value of pixel, wherein the probability value and the similarity value, the steady angle value correlation, the probability value With the negatively correlated relations of L.
- 10. device according to claim 9, which is characterized in that the probability determining unit includes：Weights determination unit, for determining the similarity value and the weights corresponding to the steady angle value respectively；Probability calculation unit, for according to the product of the similarity value and corresponding weights, the steady angle value and corresponding The product of weights and the distance L determine the probability value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611020211.7A CN108073870A (en) | 2016-11-18 | 2016-11-18 | Method and device based on seed region and communication path identification hand region |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611020211.7A CN108073870A (en) | 2016-11-18 | 2016-11-18 | Method and device based on seed region and communication path identification hand region |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108073870A true CN108073870A (en) | 2018-05-25 |
Family
ID=62160573
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611020211.7A Pending CN108073870A (en) | 2016-11-18 | 2016-11-18 | Method and device based on seed region and communication path identification hand region |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108073870A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063876A (en) * | 2014-01-10 | 2014-09-24 | 北京理工大学 | Interactive image segmentation method |
| CN105184763A (en) * | 2014-06-23 | 2015-12-23 | 索尼公司 | Image processing method and device |
| CN105809651A (en) * | 2014-12-16 | 2016-07-27 | 吉林大学 | Image saliency detection method based on edge non-similarity comparison |
-
2016
- 2016-11-18 CN CN201611020211.7A patent/CN108073870A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063876A (en) * | 2014-01-10 | 2014-09-24 | 北京理工大学 | Interactive image segmentation method |
| CN105184763A (en) * | 2014-06-23 | 2015-12-23 | 索尼公司 | Image processing method and device |
| CN105809651A (en) * | 2014-12-16 | 2016-07-27 | 吉林大学 | Image saliency detection method based on edge non-similarity comparison |
Non-Patent Citations (1)
| Title |
|---|
| 赵小川: "《MATLAB图像处理 能力提高与应用案例》", 31 January 2014, 北京航空航天大学出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11546505B2 (en) | Touchless photo capture in response to detected hand gestures | |
| US11703951B1 (en) | Gesture recognition systems | |
| US20180081434A1 (en) | Eye and Head Tracking | |
| US8957857B2 (en) | Device and method for controlling mouse pointer | |
| KR101964397B1 (en) | Information processing apparatus and information processing method | |
| JP4238278B2 (en) | Adaptive tracking of gesture interfaces | |
| JP6998554B2 (en) | Image generator and image generation method | |
| KR101612605B1 (en) | Method for extracting face feature and apparatus for perforimg the method | |
| CN104408743A (en) | Image segmentation method and device | |
| CN110298297A (en) | Flame identification method and device | |
| US9280209B2 (en) | Method for generating 3D coordinates and mobile terminal for generating 3D coordinates | |
| CN105718844A (en) | blink detection method and device | |
| JP2007052609A (en) | Hand area detection device, hand area detection method and program | |
| KR20110021500A (en) | Method for real-time moving object tracking and distance measurement and apparatus thereof | |
| CN110909685A (en) | Posture estimation method, device, equipment and storage medium | |
| CN109328355A (en) | Method and system for intelligent group portrait | |
| KR20140132906A (en) | Device and method for mobile tooltip using eye detecting | |
| CN108073935A (en) | Method and device based on adjacent pixels and communication path identification hand region | |
| CN108073871A (en) | Method and device based on two kinds of presumptive area identification hand regions | |
| CN108073271A (en) | Method and device based on presumptive area identification hand region | |
| CN108073870A (en) | Method and device based on seed region and communication path identification hand region | |
| JP2007510994A (en) | Object tracking in video images | |
| CN108073878A (en) | Method and device based on presumptive area and communication path identification hand region | |
| CN108073882A (en) | Hand region recognition methods and device based on communication path | |
| CN108073881A (en) | Method and device based on presumptive area and adjacent pixels identification hand region |
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: 20180525 |
|
| RJ01 | Rejection of invention patent application after publication |