CN113569872A - Multi-resolution shoe wearing footprint sequence identification method based on pressure significance - Google Patents
Multi-resolution shoe wearing footprint sequence identification method based on pressure significance Download PDFInfo
- Publication number
- CN113569872A CN113569872A CN202110913759.9A CN202110913759A CN113569872A CN 113569872 A CN113569872 A CN 113569872A CN 202110913759 A CN202110913759 A CN 202110913759A CN 113569872 A CN113569872 A CN 113569872A
- Authority
- CN
- China
- Prior art keywords
- footprint
- pressure
- group
- resolution
- energy
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012216 screening Methods 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 42
- 238000010586 diagram Methods 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 3
- 230000005021 gait Effects 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a multi-resolution shoe wearing footprint sequence recognition method based on pressure significance, which relates to the technical field of footprint recognition and comprises an off-line training process and an on-line recognition process; the offline training process comprises at least the following steps: acquiring a footprint pressure energy graph group; calculating local gray scale statistical characteristics of the footprint pressure energy graph group; screening a pressure significance area of the footprint pressure energy map set; the online identification process comprises at least the following steps: acquiring a footprint pressure energy graph group; repairing the pressure significance region of the footprint pressure energy map group; constructing a multi-resolution footprint energy graph group; and calculating the matching score of the multi-resolution footprint energy image group to be identified and the multi-resolution footprint energy image group feature library so as to obtain the identification result of the multi-resolution shoe wearing footprint sequence. According to the method, the local information difference of the footprint image is considered, the image is divided into local area blocks to extract the gray statistical characteristics, and more accurate and stable characteristics are obtained.
Description
Technical Field
The invention relates to the technical field of footprint identification, in particular to a multi-resolution shoe wearing footprint sequence identification method based on pressure significance.
Background
Biometric identification based on sequence footprints is currently classified into online footprint sequence identification and offline footprint sequence identification. The online footprint sequence identification method comprises the following steps: (1) and extracting the pressure peak value, the time for obtaining the pressure peak value and the pressure change curve as features for identification. (2) And collecting images at all moments and accumulated images formed at all moments in the process of forming the footprints in one step, and combining a depth residual error network and an SVM for identification. However, online footprint sequence recognition is mainly directed to barefoot footprints, acquisition is difficult and application scenarios are rarely inconsistent with practical applications.
The off-line shoe-wearing footprint identification method comprises the following steps: (1) extracting footprint and stride characteristics: the step size, step width, step angle, etc. are quantitatively analyzed. (2) And constructing a footprint pressure energy graph group, and calculating a similarity matching score for recognition. However, footmarks of sequences of wearing shoes are mostly recognized based on stride characteristics, and the stride characteristics used quantitatively are unstable and cannot be recognized accurately; the identification method based on the footprint pressure energy map group is greatly influenced by the sole pattern, and the difference of information content in different areas in the shoe print image is not considered. In view of the above, there remains to be invented a footprint sequence recognition method considering local information differences of footprint images.
Disclosure of Invention
The invention provides a multi-resolution shoe-wearing footprint sequence recognition method based on pressure significance, and solves the problem that the existing footprint sequence recognition method does not consider local information difference of footprint images.
In order to achieve the above purposes, the technical scheme adopted by the invention is as follows:
a multi-resolution shoe-wearing footprint sequence recognition method based on pressure significance comprises an off-line training process and an on-line recognition process;
the offline training process comprises at least the following steps:
acquiring a footprint pressure energy graph group;
calculating local gray scale statistical characteristics of the footprint pressure energy graph group;
screening a pressure significance area of the footprint pressure energy map set;
repairing the pressure significance region of the footprint pressure energy map group;
extracting a pressure significance region of the footprint pressure energy map group;
constructing a multi-resolution footprint energy graph group;
constructing a multi-resolution footprint energy map group feature library;
the online identification process comprises at least the following steps:
acquiring a footprint pressure energy graph group;
calculating local gray scale statistical characteristics of the footprint pressure energy graph group;
screening a pressure significance area of the footprint pressure energy map set;
repairing the pressure significance region of the footprint pressure energy map group;
extracting a pressure significance region of the footprint pressure energy map group;
constructing a multi-resolution footprint energy graph group;
and calculating the matching score of the multi-resolution footprint energy image group to be identified and the multi-resolution footprint energy image group feature library so as to obtain the identification result of the multi-resolution shoe wearing footprint sequence.
Preferably, the construction of the footprint pressure energy map group comprises:
denoising the original footprint sequence image, segmenting, cutting and weighting and superposing the horizontal projection of the sequence image to obtain a left gait energy map group I1Right step energy diagram group I2Left step energy chart group I3Right step width energy chart group I4Left-step wide energy diagram group I5Right step wide energy map set I6The footprint pressure energy graph group is IS,IS={Ik,k=1,2,3,4,5,6}。
Preferably, the calculating the local gray scale statistical characteristics of the footprint pressure energy map group comprises: is selected fromSThe single image in (1) is marked as I, the I is divided into non-overlapping local area blocks with the size of t multiplied by t, the number of the local area blocks is m multiplied by n, the local information entropy H in each area block is calculated,
wherein p (v) represents the probability that the gray value of a pixel in the block is v,
generating a local entropy matrix I of IH,
Calculating the gray level mean value in each area block to generate a local mean value matrix I of IM,
Preferably, the screening of the pressure significance region comprises:
calculation of IHMean of non-0 elements;
calculation of IMMean of non-0 elements;
calculating a significance entropy binary matrix BOH;
will matrix IMThe BOH carries out AND operation according to elements to generate a matrix IMH;
To IMHPerforming Gaussian blur to obtain a matrix IMHG;
Calculating a matrix BOMHG;
and carrying out contour detection on the BOMHG to generate a binary matrix BMHG of the pressure significance region.
Preferably, the repairing the pressure significance region of the footprint pressure energy map set comprises:
amplifying the BMHG to be consistent with the size of the original image I by adopting a nearest neighbor interpolation method to obtain IBMHG;
extracting a pressure energy graph significance region IP;
generating a mask matrix (mu) according to the IP;
repairing the IP by adopting an image repairing method, wherein the repairing position is a point marked as 1 in M, and the image repairing is carried out by adopting a rapid advance method in the implementation;
updating the corresponding position value in the I through the repaired matrix IP;
and extracting a pressure significance area of the footprint pressure energy map group.
Preferably, the constructing the multi-resolution footprint energy map set comprises:
to ISCalculating local gray statistical characteristics and pressure significance region screening of the footprint pressure energy image group to obtain processed images;
and carrying out multi-scale Gaussian blur on the processed image to generate a multi-resolution footprint pressure energy map set.
The invention has the beneficial effects that:
according to the method, the local information difference of the footprint image is considered, the image is divided into local area blocks to extract the gray statistical characteristics, and more accurate and stable characteristics are obtained;
according to the method, the pressure significance region is extracted through screening of the gray statistical characteristics, and the region is given higher weight, so that the distinctiveness among different people can be increased;
according to the method, the image repairing is carried out on the image pressure significance region, then the multi-resolution footprint energy graph group is constructed, the footprint pressure energy graph group is represented in various forms, the influence of sole patterns can be reduced, and the extracted information is more complete.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a partial mean plot of a right step energy plot at a first resolution in an embodiment of the present invention.
FIG. 3 is a partial entropy diagram of a right step energy plot at a first resolution in an embodiment of the present invention.
FIG. 4 is a pressure saliency mean plot of a right step energy plot at a first resolution in an embodiment of the present invention.
FIG. 5 is a pressure significance entropy diagram of a right step energy plot at a first resolution in an embodiment of the present invention.
FIG. 6 is a partial mean plot of a right step energy plot at a second resolution in an embodiment of the present invention.
FIG. 7 is a partial entropy diagram of a right step energy plot at a second resolution in an embodiment of the present invention.
FIG. 8 is a pressure significance averaging plot of a right step energy plot at a second resolution in an embodiment of the present invention.
FIG. 9 is a pressure significance entropy diagram of a right step energy plot at a second resolution in an embodiment of the present invention.
FIG. 10 is a partial mean plot of a right step energy plot at a third resolution in an embodiment of the present invention.
FIG. 11 is a partial entropy diagram of a right step energy diagram at a third resolution in an embodiment of the present invention.
Fig. 12 is a pressure significance averaging diagram of the right step energy plot at the third resolution in an embodiment of the present invention.
FIG. 13 is a pressure significance entropy diagram of a right step energy plot at a third resolution in an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise. Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description. Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate. In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
In the description of the present invention, it is to be understood that the orientation or positional relationship indicated by the directional terms such as "front, rear, upper, lower, left, right", "lateral, vertical, horizontal" and "top, bottom", etc., are generally based on the orientation or positional relationship shown in the drawings, and are used for convenience of description and simplicity of description only, and in the absence of any contrary indication, these directional terms are not intended to indicate and imply that the device or element so referred to must have a particular orientation or be constructed and operated in a particular orientation, and therefore should not be considered as limiting the scope of the present invention: the terms "inner and outer" refer to the inner and outer relative to the profile of the respective component itself.
Spatially relative terms, such as "above … …," "above … …," "above … …," "above," and the like, may be used herein for ease of description to describe one device or feature's spatial relationship to another device or feature as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if a device in the figures is turned over, devices described as "above" or "on" other devices or configurations would then be oriented "below" or "under" the other devices or configurations. Thus, the exemplary term "above … …" can include both an orientation of "above … …" and "below … …". The device may be otherwise variously oriented (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
It should be noted that the terms "first", "second", and the like are used to define the components, and are only used for convenience of distinguishing the corresponding components, and the terms have no special meanings unless otherwise stated, and therefore, the scope of the present invention should not be construed as being limited.
Examples
The invention provides a technical scheme that: a multi-resolution shoe-wearing footprint sequence recognition method based on pressure significance is disclosed, and a flow chart of the method is shown in figure 1 and comprises an off-line training process and an on-line recognition process;
the off-line training process comprises at least the following steps:
acquiring a footprint pressure energy graph group;
calculating local gray scale statistical characteristics of the footprint pressure energy graph group;
screening a pressure significance area of the footprint pressure energy map set;
repairing the pressure significance region of the footprint pressure energy map group;
extracting a pressure significance region of the footprint pressure energy map group;
constructing a multi-resolution footprint energy map set, as shown in FIGS. 2-13;
constructing a multi-resolution footprint energy map group feature library;
the online identification process comprises at least the following steps:
acquiring a footprint pressure energy graph group;
calculating local gray scale statistical characteristics of the footprint pressure energy graph group;
screening a pressure significance area of the footprint pressure energy map set;
repairing the pressure significance region of the footprint pressure energy map group;
extracting a pressure significance region of the footprint pressure energy map group;
constructing a multi-resolution footprint energy graph group;
and calculating the matching score of the multi-resolution footprint energy image group to be identified and the multi-resolution footprint energy image group feature library so as to obtain the identification result of the multi-resolution shoe wearing footprint sequence.
1. Footprint pressure energy graph set construction
Denoising the original footprint sequence image, segmenting, cutting and weighting and superposing the horizontal projection of the sequence image to obtain a left gait energy map group I1Right step energy diagram group I2Left step energy chart group I3Right step width energy chart group I4Left-step wide energy diagram group I5Right-hand wide energy diagram group I6. I.e. footprint pressure energy map set IS={Ik,k=1,2,3,4,5,6}。
2. Pressure significant region extraction and repair
2.1 computing local Gray statistical features
Is selected fromSIn the method, a single image is marked as I, the I is divided into non-overlapping local area blocks with the size of t multiplied by t, the number of the local area blocks is m multiplied by n, and each area block is calculatedEntropy of local information within
p (v) representing the probability that the gray value of the pixel in the region block is v, and generating a local entropy matrix of ICalculating the gray level mean value in each area block to generate a local mean value matrix of I
2.2 pressure significance region screening
Calculation of IHMean of non-0 elementsnumHIs IHThe number of non-0 elements. Calculation of IMMean of non-0 elementsnumMIs IMThe number of non-0 elements.
A significance entropy binary matrix BOH is calculated,
will matrix IMThe BOH carries out AND operation according to elements to generate a matrix IMHI.e. IMH=IM&BOH,&Are operated by element and operation. To IMHPerforming Gaussian blur with standard deviation of Gaussian function of 2 sigma0In practice σ0Get the matrix I as 11MHG,The matrix BOMHG is calculated and,and carrying out contour detection on the BOMHG, filling the detected region with 1, and generating a pressure significance region binary matrix BMHG.
2.3 pressure saliency region image inpainting
And amplifying the BMHG to be consistent with the size of the original image I by adopting a nearest neighbor interpolation method to obtain the IBMHG. Extracting a pressure energy map significance region IP (I)&IBMHG, having a size of tm x tn,a mask matrix m is generated from the IP,
the IP is repaired by adopting an image repairing method, the repairing position is a point marked as 1 in M, the image repairing is carried out by adopting a rapid advancing method in the implementation, and the specific process is as follows: let us point to be repaired IPabAb, with coordinates (a, b). Selecting a 5x5 neighborhood B (epsilon), IP with (a, B) as the centerhlPoints within B (ε), abbreviated as hl, have coordinates (h, l). And v represents the gradient direction, T is the distance from the pixel point to the neighborhood boundary, and N is the normal direction.
w(ab,hl)=dir(ab,hl)·dst(ab,hl)·lev(ab,hl)
And updating the corresponding position value in the I through the repaired matrix IP, wherein the formula is as follows:
2.4 pressure significant region extraction
And repeating the steps in 2.1 and 2.2 on the updated matrix I, and regenerating a local mean matrix, a local entropy matrix and a pressure significance matrix. Calculating a pressure significance entropy matrix I'H=IH&BMHG, pressure significance mean matrix of l'M=IM&BMHG。
3. Constructing a multi-resolution footprint energy map set
To ISAfter each image is processed according to the method in the step 2, multi-scale Gaussian blur is carried out to generate a multi-resolution footprint pressure energy graph set
Where σ is the standard deviation of the gaussian function, F is the number of scales, and σ ═ 0 indicates that the original image is directly taken without gaussian filtering. In practice, F ═ 2, pair I follows the procedure in step 2SRThe above operation is performed on each image to generate a local entropy matrix, a local mean matrix, a pressure significance entropy matrix and a pressure significance mean matrix. Then each image may be generated IH,IM,I'H,I'MIs abbreviated as { I }cAnd c is 1,2,3,4 }. Then the multi-resolution footprint energy map set
4. Multi-resolution footprint energy map set matching score calculation
Each footprint sequence is represented by a multi-resolution footprint energy graph group, q is a footprint sequence to be identified, and g is a database footprint sequence. Calculating matching scores simz among different footprint energy maps, and then performing weighted fusion on different scores by adopting a weighting coefficient omega obtained by a hinge loss function training method to obtain a final matching score, namely:
score(q,g;ω)=ωTS(q,g)
the sim is obtained by calculating the normalized cross-correlation of the corresponding matrix:
wherein R representsu and v respectively represent the offset of the abscissa and the ordinate of the pixel point of the energy diagram,represents RgAt RqThe mean of the area under the coverage is,represents RqAt RgThe mean of the covered area, r, represents the resulting cross-correlation plot.
simd is obtained by calculating the normalized Euclidean distance of the corresponding matrix:
the above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (6)
1. A multi-resolution shoe-wearing footprint sequence identification method based on pressure significance is characterized by comprising the following steps: an off-line training process and an on-line identification process;
the offline training process comprises at least the following steps:
acquiring a footprint pressure energy graph group;
calculating local gray scale statistical characteristics of the footprint pressure energy graph group;
screening a pressure significance area of the footprint pressure energy map set;
repairing the pressure significance region of the footprint pressure energy map group;
extracting a pressure significance region of the footprint pressure energy map group;
constructing a multi-resolution footprint energy graph group;
constructing a multi-resolution footprint energy map group feature library;
the online identification process comprises at least the following steps:
acquiring a footprint pressure energy graph group;
calculating local gray scale statistical characteristics of the footprint pressure energy graph group;
screening a pressure significance area of the footprint pressure energy map set;
repairing the pressure significance region of the footprint pressure energy map group;
extracting a pressure significance region of the footprint pressure energy map group;
constructing a multi-resolution footprint energy graph group;
and calculating the matching score of the multi-resolution footprint energy image group to be identified and the multi-resolution footprint energy image group feature library so as to obtain the identification result of the multi-resolution shoe wearing footprint sequence.
2. The method for identifying a pressure significance-based multi-resolution shoe wearing footprint sequence according to claim 1, wherein the building of the footprint pressure energy map group comprises:
denoising the original footprint sequence image, segmenting, cutting and weighting and superposing the horizontal projection of the sequence image to obtain a left gait energy map group I1Right step energy diagram group I2Left step energy chart group I3Right step width energy chart group I4Left-step wide energy diagram group I5Right step wide energy map set I6The footprint pressure energy graph group is IS,IS={Ik,k=1,2,3,4,5,6}。
3. The method for identifying a pressure significance-based multi-resolution shoe wearing footprint sequence according to claim 2, wherein the calculating the local gray scale statistical characteristics of the footprint pressure energy map group comprises: is selected fromSThe single image in (1) is marked as I, the I is divided into non-overlapping local area blocks with the size of t multiplied by t, the number of the local area blocks is m multiplied by n, the local information entropy H in each area block is calculated,
wherein p (v) represents the probability that the gray value of a pixel in the block is v,
generating a local entropy matrix I of IH,
Calculating the gray level mean value in each area block to generate a local mean value matrix I of IM,
4. The method for identifying a pressure significance-based multi-resolution shoe wearing footprint sequence according to claim 3, wherein the screening of the pressure significance region comprises:
calculation of IHMean of non-0 elements;
calculation of IMMean of non-0 elements;
calculating a significance entropy binary matrix BOH;
will matrix IMThe BOH carries out AND operation according to elements to generate a matrix IMH;
To IMHPerforming Gaussian blur to obtain a matrix IMHG;
Calculating a matrix BOMHG;
and carrying out contour detection on the BOMHG to generate a binary matrix BMHG of the pressure significance region.
5. The method for identifying a pressure significance-based multi-resolution shoe wearing footprint sequence according to claim 4, wherein the repairing the pressure significance region of the footprint pressure energy map set comprises:
amplifying the BMHG to be consistent with the size of the original image I by adopting a nearest neighbor interpolation method to obtain IBMHG;
extracting a pressure energy graph significance region IP;
generating a mask matrix (mu) according to the IP;
repairing the IP by adopting an image repairing method, wherein the repairing position is a point marked as 1 in M, and the image repairing is carried out by adopting a rapid advance method in the implementation;
updating the corresponding position value in the I through the repaired matrix IP;
and extracting a pressure significance area of the footprint pressure energy map group.
6. The method for identifying a sequence of multi-resolution shoe wearing footprints based on pressure saliency as claimed in claim 5, wherein the constructing a group of multi-resolution footprint energy maps comprises:
to ISCalculating local gray statistical characteristics and pressure significance region screening of the footprint pressure energy image group to obtain processed images;
and carrying out multi-scale Gaussian blur on the processed image to generate a multi-resolution footprint pressure energy map set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110913759.9A CN113569872B (en) | 2021-08-10 | 2021-08-10 | Multi-resolution shoe-wearing footprint sequence identification method based on pressure significance |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110913759.9A CN113569872B (en) | 2021-08-10 | 2021-08-10 | Multi-resolution shoe-wearing footprint sequence identification method based on pressure significance |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113569872A true CN113569872A (en) | 2021-10-29 |
CN113569872B CN113569872B (en) | 2024-03-19 |
Family
ID=78171068
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110913759.9A Active CN113569872B (en) | 2021-08-10 | 2021-08-10 | Multi-resolution shoe-wearing footprint sequence identification method based on pressure significance |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113569872B (en) |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120014595A1 (en) * | 2010-07-16 | 2012-01-19 | Frederiksen Jeffrey E | Color Space Conversion for Efficient Filtering |
KR101288949B1 (en) * | 2012-06-20 | 2013-07-24 | 동국대학교 산학협력단 | Method for recognizing user by using shoe footprint image and apparatus thereof |
KR20130142723A (en) * | 2012-06-20 | 2013-12-30 | 동국대학교 산학협력단 | Method for recognizing user by using footprint energy image and apparatus thereof |
CN103500453A (en) * | 2013-10-13 | 2014-01-08 | 西安电子科技大学 | SAR(synthetic aperture radar) image significance region detection method based on Gamma distribution and neighborhood information |
CN106845516A (en) * | 2016-12-07 | 2017-06-13 | 大连海事大学 | A kind of footprint image recognition methods represented based on multisample joint |
CN106887019A (en) * | 2017-02-23 | 2017-06-23 | 大连海事大学 | A kind of footprint Pressure Distribution method for expressing |
CN107248139A (en) * | 2016-08-15 | 2017-10-13 | 南京大学 | Compressed sensing imaging method based on notable vision and dmd array zonal control |
US20170337221A1 (en) * | 2016-05-03 | 2017-11-23 | Republic of Korea (National Forensic Service Director Ministry of Public Administration and Sec | Footprint search method and system |
CN107506795A (en) * | 2017-08-23 | 2017-12-22 | 国家计算机网络与信息安全管理中心 | A kind of local gray level histogram feature towards images match describes sub- method for building up and image matching method |
CN109545323A (en) * | 2018-10-31 | 2019-03-29 | 贵州医科大学附属医院 | A kind of ankle rehabilitation system with VR simulation walking |
BR112019004905A2 (en) * | 2016-09-30 | 2019-06-04 | Pirelli | method and system for detecting a pressure distribution over a tire's footprint area. |
CN110009638A (en) * | 2019-04-12 | 2019-07-12 | 重庆交通大学 | Bridge cable picture appearance defect inspection method based on partial statistics characteristic |
CN111144165A (en) * | 2018-11-02 | 2020-05-12 | 银河水滴科技(北京)有限公司 | Gait information identification method, system and storage medium |
CN111815543A (en) * | 2020-08-04 | 2020-10-23 | 北京惠朗时代科技有限公司 | Image restoration-oriented multi-scale feature matching method |
CN111861943A (en) * | 2020-08-04 | 2020-10-30 | 北京惠朗时代科技有限公司 | Image restoration method for multi-scale pixel-level depth optimization |
CN112418223A (en) * | 2020-12-11 | 2021-02-26 | 互助土族自治县北山林场 | Wild animal image significance target detection method based on improved optimization |
CN112541934A (en) * | 2019-09-20 | 2021-03-23 | 百度在线网络技术(北京)有限公司 | Image processing method and device |
CN112862834A (en) * | 2021-01-14 | 2021-05-28 | 江南大学 | Image segmentation method based on visual salient region and active contour |
CN113111797A (en) * | 2021-04-19 | 2021-07-13 | 杭州电子科技大学 | Cross-view gait recognition method combining self-encoder and view transformation model |
-
2021
- 2021-08-10 CN CN202110913759.9A patent/CN113569872B/en active Active
Patent Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120014595A1 (en) * | 2010-07-16 | 2012-01-19 | Frederiksen Jeffrey E | Color Space Conversion for Efficient Filtering |
KR101288949B1 (en) * | 2012-06-20 | 2013-07-24 | 동국대학교 산학협력단 | Method for recognizing user by using shoe footprint image and apparatus thereof |
KR20130142723A (en) * | 2012-06-20 | 2013-12-30 | 동국대학교 산학협력단 | Method for recognizing user by using footprint energy image and apparatus thereof |
CN103500453A (en) * | 2013-10-13 | 2014-01-08 | 西安电子科技大学 | SAR(synthetic aperture radar) image significance region detection method based on Gamma distribution and neighborhood information |
US20170337221A1 (en) * | 2016-05-03 | 2017-11-23 | Republic of Korea (National Forensic Service Director Ministry of Public Administration and Sec | Footprint search method and system |
CN107248139A (en) * | 2016-08-15 | 2017-10-13 | 南京大学 | Compressed sensing imaging method based on notable vision and dmd array zonal control |
BR112019004905A2 (en) * | 2016-09-30 | 2019-06-04 | Pirelli | method and system for detecting a pressure distribution over a tire's footprint area. |
CN106845516A (en) * | 2016-12-07 | 2017-06-13 | 大连海事大学 | A kind of footprint image recognition methods represented based on multisample joint |
CN106887019A (en) * | 2017-02-23 | 2017-06-23 | 大连海事大学 | A kind of footprint Pressure Distribution method for expressing |
CN107506795A (en) * | 2017-08-23 | 2017-12-22 | 国家计算机网络与信息安全管理中心 | A kind of local gray level histogram feature towards images match describes sub- method for building up and image matching method |
CN109545323A (en) * | 2018-10-31 | 2019-03-29 | 贵州医科大学附属医院 | A kind of ankle rehabilitation system with VR simulation walking |
CN111144165A (en) * | 2018-11-02 | 2020-05-12 | 银河水滴科技(北京)有限公司 | Gait information identification method, system and storage medium |
CN110009638A (en) * | 2019-04-12 | 2019-07-12 | 重庆交通大学 | Bridge cable picture appearance defect inspection method based on partial statistics characteristic |
CN112541934A (en) * | 2019-09-20 | 2021-03-23 | 百度在线网络技术(北京)有限公司 | Image processing method and device |
CN111815543A (en) * | 2020-08-04 | 2020-10-23 | 北京惠朗时代科技有限公司 | Image restoration-oriented multi-scale feature matching method |
CN111861943A (en) * | 2020-08-04 | 2020-10-30 | 北京惠朗时代科技有限公司 | Image restoration method for multi-scale pixel-level depth optimization |
CN112418223A (en) * | 2020-12-11 | 2021-02-26 | 互助土族自治县北山林场 | Wild animal image significance target detection method based on improved optimization |
CN112862834A (en) * | 2021-01-14 | 2021-05-28 | 江南大学 | Image segmentation method based on visual salient region and active contour |
CN113111797A (en) * | 2021-04-19 | 2021-07-13 | 杭州电子科技大学 | Cross-view gait recognition method combining self-encoder and view transformation model |
Also Published As
Publication number | Publication date |
---|---|
CN113569872B (en) | 2024-03-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110148162B (en) | Heterogeneous image matching method based on composite operator | |
US10262190B2 (en) | Method, system, and computer program product for recognizing face | |
CN104778721B (en) | The distance measurement method of conspicuousness target in a kind of binocular image | |
CN109118528A (en) | Singular value decomposition image matching algorithm based on area dividing | |
Cheng et al. | Robust affine invariant feature extraction for image matching | |
CN110334762B (en) | Feature matching method based on quad tree combined with ORB and SIFT | |
CN105182350B (en) | A kind of multibeam sonar object detection method of application signature tracking | |
CN104751465A (en) | ORB (oriented brief) image feature registration method based on LK (Lucas-Kanade) optical flow constraint | |
CN110222661B (en) | Feature extraction method for moving target identification and tracking | |
JP4946878B2 (en) | Image identification apparatus and program | |
CN110378924A (en) | Level set image segmentation method based on local entropy | |
CN107862319B (en) | Heterogeneous high-light optical image matching error eliminating method based on neighborhood voting | |
CN110188694B (en) | Method for identifying shoe wearing footprint sequence based on pressure characteristics | |
CN110660089A (en) | Satellite image registration method and device | |
CN101630407A (en) | Method for positioning forged region based on two view geometry and image division | |
Ibragimov et al. | Accurate landmark-based segmentation by incorporating landmark misdetections | |
CN109583452A (en) | A kind of identification of individual method and system based on barefoot footprint | |
CN111126494A (en) | Image classification method and system based on anisotropic convolution | |
US7388990B2 (en) | Local mass distribution partitioning for object recognition | |
CN110929782B (en) | River channel abnormity detection method based on orthophoto map comparison | |
CN104573722A (en) | Three-dimensional face race classifying device and method based on three-dimensional point cloud | |
CN108876776B (en) | Classification model generation method, fundus image classification method and device | |
Jing et al. | Island road centerline extraction based on a multiscale united feature | |
Essa et al. | Volumetric directional pattern for spatial feature extraction in hyperspectral imagery | |
CN104318216A (en) | Method for recognizing and matching pedestrian targets across blind area in video surveillance |
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 |