CN111311359A - Jigsaw method for realizing human shape display effect based on e-commerce image - Google Patents

Jigsaw method for realizing human shape display effect based on e-commerce image Download PDF

Info

Publication number
CN111311359A
CN111311359A CN202010071799.9A CN202010071799A CN111311359A CN 111311359 A CN111311359 A CN 111311359A CN 202010071799 A CN202010071799 A CN 202010071799A CN 111311359 A CN111311359 A CN 111311359A
Authority
CN
China
Prior art keywords
picture
point
connecting line
effect based
display effect
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
Application number
CN202010071799.9A
Other languages
Chinese (zh)
Inventor
石克阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Weier Network Technology Co ltd
Original Assignee
Hangzhou Weier Network Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Weier Network Technology Co ltd filed Critical Hangzhou Weier Network Technology Co ltd
Priority to CN202010071799.9A priority Critical patent/CN111311359A/en
Publication of CN111311359A publication Critical patent/CN111311359A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0641—Shopping interfaces
    • G06Q30/0643—Graphical representation of items or shoppers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformation in the plane of the image
    • G06T3/40—Scaling the whole image or part thereof
    • G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images

Landscapes

  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The invention discloses a jigsaw method for realizing a human shape showing effect based on e-commerce images, and belongs to the technical field of image splicing. The jigsaw method comprises the following steps: s1, detecting key points in the first picture and key points in the second picture; s2, using the connecting line of key point as boundary, cutting out the pixel above the connecting line and k below the connecting line in the first picture1A pixel, cutting out the pixels below the connecting line and the k above the connecting line in the second picture2A plurality of pixels; wherein k is1≥0，k2Is not less than 0, and k1、k2Is not equal to 0 at the same time; and S3, fusing the first picture and the second picture to obtain a jigsaw puzzle. The picture splicing method can obtain a brand new commodity combined model display picture from two pictures containing human body trunks through picture splicing.

Description

Jigsaw method for realizing human shape display effect based on e-commerce image
Technical Field
The invention belongs to the technical field of image splicing, and particularly relates to a jigsaw method for realizing a human shape display effect based on an e-commerce image.
Background
In an e-commerce scenario, the images uploaded by the merchants are typically 2D images. Many times, because the time and money are limited, the model can not display all the commodity matching combinations, so the clothes displayed by the model in different pictures need to be spliced to obtain a new model picture of the commodity display combination. At present, a better human body key point detection technology exists, but a mature technical scheme for splicing two commodity pictures in a human body splicing mode does not exist.
Disclosure of Invention
In order to solve the problem that a mature technical scheme for splicing two commodity pictures in a human body splicing mode does not exist in the prior art, the invention provides a splicing method for realizing a human shape display effect based on e-commerce images.
The technical scheme adopted by the invention is as follows: a jigsaw method for realizing human-shaped display effect based on e-commerce images comprises the following steps:
s1, detecting key points in the first picture and key points in the second picture;
s2, using the connecting line of key point as boundary, cutting out the pixel above the connecting line and k below the connecting line in the first picture1A pixel, cutting out the pixels below the connecting line and the k above the connecting line in the second picture2A plurality of pixels; wherein k is1≥0，k2Is not less than 0, and k1、k2Is not equal to 0 at the same time;
and S3, fusing the first picture and the second picture to obtain a jigsaw puzzle.
The S3 adopts the formula:
Figure BDA0002377487530000011
fusing the first picture and the second picture;
wherein, Py(xi,y)、P1(xiY) and P2(xiY) are respectively (x) on the fused pictureiY) pixel value, on the first picture (x)iY) and (x) on the second pictureiY) pixel values; (x)iY) is xiPixel position of column, ymiRepresents a connecting line in xiThe ordinate of the column; k is a radical of1iIs xiNumber of pixels, k, in the first picture taken on the column below the connecting line2iIs xiThe number of pixels above the connecting line in the second picture on the column; w1、W2Is a weight coefficient, W2＝1-W1(ii) a h is the height of the fused picture.
Figure BDA0002377487530000021
The detection of the position of the key point adopts an AlphaPose model.
And after the positions of the key points are detected by the S1, when the sizes of the human bodies in the first picture and the second picture are inconsistent, the sizes of the first picture or the second picture are adjusted by adopting a resize algorithm, so that the sizes of the human bodies in the first picture and the second picture are consistent.
The key points are a left waist point and a right waist point.
Before the S4 fusion, key point alignment is further included: and overlapping the left waist point of the first picture with the left waist point of the second picture, and overlapping the right waist point of the first picture with the right waist point of the second picture.
In S1, a left ear point, a right ear point, a left eyebrow point, a right eyebrow point, a nose point, a neck point, a left shoulder point, a right shoulder point, a left elbow point, a right elbow point, a left wrist point, and a right wrist point in the first picture, and a left knee point, a right knee point, a left ankle point, and a right ankle point in the second picture are also detected.
In the S3, the k is intercepted1Each pixel includes a left wrist point and/or a right wrist point area below the connecting line.
The invention has the beneficial effects that: the method can obtain a brand new commodity combined model display picture from two pictures containing human body trunks through picture splicing.
Drawings
FIG. 1 is a flowchart illustrating a jigsaw method according to the present invention.
Fig. 2 is a schematic diagram of a first picture and a second picture in an embodiment of the invention, and a frame line is an area to be spliced.
Fig. 3 is a schematic diagram of key points of a first picture and a second picture according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of a mosaic of a first picture and a second picture according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and the embodiments. In order to highlight the focus of the present invention, some conventional devices, apparatuses, components and operations are omitted or simply described herein.
Referring to fig. 1, a jigsaw method for realizing a human-shaped display effect based on e-commerce images includes the following steps:
1) referring to fig. 2, a first picture and a second picture to be spliced are selected, wherein the first picture comprises the upper half body of the human body, and the second picture comprises the lower half body of the human body;
2) referring to fig. 3, in a preferred embodiment, an alphapos model is used to detect a position point O where a left waist point is located in a first picture11And the position point O of the right waist point111And the position point O of the left waist point in the second picture22And the position point O of the right waist point222；
In another preferred embodiment, an AlphaPose model is adopted to detect a left ear point, a right ear point, a left eyebrow point, a right eyebrow point, a nose point, a neck point, a left shoulder point, a right shoulder point, a left elbow point, a right elbow point, a left wrist point, a right wrist point, a left waist point and a right waist point in a first picture, and a left waist point, a right waist point, a left knee point, a right knee point, a left ankle point and a right ankle point in a second picture, so that a complete human shape can be presented after jigsaw puzzle splicing; marking a position point O of the left waist point in the first picture11And the position point O of the right waist point111And the position point O of the left waist point in the second picture22And the position point O of the right waist point222；
3) Calculating the point O11And point O22Distance between, point O11And point O222Distance between, point O111And point O22And a distance therebetween, and a point O111And point O222The distance between them. The calculation formula is as follows:
Figure BDA0002377487530000031
wherein D is the distance between a point in the first picture and a point in the second picture; x is the number of1Is the abscissa, y, of a point in the first picture1Is the ordinate of a point in the first picture; x is the number of2Is the abscissa, y, of a point in the second picture2Is the ordinate of the point in the second picture;
neutralizing the point O in the second picture11Point of minimum distance O22As point O11The corresponding point of (2) and the point O in the second picture111Point of minimum distance O222As point O111The corresponding point of (a); corresponding key points (namely the left waist point and the right waist point) are further confirmed through calculation, so that the influence of errors generated in key point detection on the jigsaw effect is avoided;
4) will point O11And point O22Coincidence, point O111And point O222Overlapping (when the sizes of the human bodies in the first picture and the second picture are not consistent, the size of the first picture or the second picture is adjusted by adopting a resize algorithm to enable the point O to be O11And point O111Equal to the point O22And point O222The distance therebetween);
5) in a preferred embodiment, at point O11And point O111The connecting line of (A) is used as a boundary, and the pixels above the connecting line and the k below the connecting line in the first picture are cut1A pixel, cutting out the pixels below the connecting line and the k above the connecting line in the second picture2A plurality of pixels;
in another preferred implementation, said k is truncated1Each pixel comprises a left wrist point and/or a right wrist point area below the connecting line, so that the picture mosaic can present a complete human shape;
6) referring to fig. 4, the first picture and the second picture are fused to obtain a jigsaw puzzle; the fusion formula is:
Figure BDA0002377487530000032
wherein, Py(xi,y)、P1(xiY) and P2(xiY) are respectively (x) on the fused pictureiY) pixel value, on the first picture (x)iY) and (x) on the second pictureiY) pixel values; (x)iY) is xiPixel position of column, ymiRepresents a connecting line in xiThe ordinate of the column; k is a radical of1iIs xiNumber of pixels, k, in the first picture taken on the column below the connecting line2iIs xiThe number of pixels above the connecting line in the second picture on the column; w1、W2In order to be the weight coefficient,
Figure BDA0002377487530000033
W2＝1-W1(ii) a h is the height of the fused picture. The weight of the fusion area is smaller and smaller when the pixels of the second picture are fused, and the weight of the pixels of the first picture is larger and larger when the pixels of the first picture are fused, so that the splicing and connecting part of the first picture and the second picture is more natural.
It is to be understood that: although the present invention has been described in considerable detail with reference to certain embodiments thereof, it is not intended to be limited to the details shown, since various changes in form and detail can be made therein without departing from the scope of the invention encompassed by the appended claims.

Claims (9)

1. A jigsaw method for realizing human shape display effect based on e-commerce images is characterized by comprising the following steps:
s1, detecting key points in the first picture and key points in the second picture;
s2, using the connecting line of key point as boundary, cutting out the pixel above the connecting line and k below the connecting line in the first picture1A pixel, cutting out the pixels below the connecting line and the k above the connecting line in the second picture2A plurality of pixels; wherein k is1≥0，k2Is not less than 0, and k1、k2Is not equal to 0 at the same time;
and S3, fusing the first picture and the second picture to obtain a jigsaw puzzle.
2. The jigsaw method for realizing human-shaped display effect based on e-commerce images as claimed in claim 1, wherein the S3 adopts the formula:
Figure FDA0002377487520000011
fusing the first picture and the second picture;
wherein, Py(xi,y)、P1(xiY) and P2(xiY) are respectively (x) on the fused pictureiY) pixel value, on the first picture (x)iY) and (x) on the second pictureiY) pixel values; (x)iY) is xiPixel position of column, ymiRepresents a connecting line in xiThe ordinate of the column; k is a radical of1iIs xiNumber of pixels, k, in the first picture taken on the column below the connecting line2iIs xiThe number of pixels above the connecting line in the second picture on the column; w1、W2Is a weight coefficient, W2＝1-W1(ii) a h is the height of the fused picture.
3. The jigsaw method for realizing human-shaped display effect based on e-commerce images as claimed in claim 2,
Figure FDA0002377487520000012
4. the jigsaw method for realizing human-shaped display effect based on e-commerce images as claimed in claim 1, wherein the detection of the positions of the key points in S1 adopts an alphadose model.
5. The jigsaw method for realizing human figure display effect based on e-commerce images as claimed in claim 1, wherein after the positions of the key points are detected in the S1, when the sizes of the human bodies in the first picture and the second picture are inconsistent, the resize algorithm is used to adjust the sizes of the first picture or the second picture so that the sizes of the human bodies in the first picture and the second picture are consistent.
6. The jigsaw method for realizing human-shaped display effect based on E-commerce images as claimed in any one of claims 1 to 5, wherein the key points are a left waist point and a right waist point.
7. The jigsaw method for realizing human-shaped display effect based on e-commerce images as claimed in claim 6, wherein before the S4 fusion, the method further includes key point alignment: and overlapping the left waist point of the first picture with the left waist point of the second picture, and overlapping the right waist point of the first picture with the right waist point of the second picture.
8. The jigsaw method of claim 6, wherein in step S1, the left ear point, the right ear point, the left eyebrow point, the right eyebrow point, the nose point, the neck point, the left shoulder point, the right shoulder point, the left elbow point, the right elbow point, the left wrist point and the right wrist point in the first picture, and the left knee point, the right knee point, the left ankle point and the right ankle point in the second picture are detected.
9. The jigsaw method for realizing human-shaped display effect based on e-commerce images as claimed in claim 8, wherein the k intercepted in the step S3 is1Each pixel includes a left wrist point and/or a right wrist point area below the connecting line.
CN202010071799.9A 2020-01-21 2020-01-21 Jigsaw method for realizing human shape display effect based on e-commerce image Pending CN111311359A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010071799.9A CN111311359A (en) 2020-01-21 2020-01-21 Jigsaw method for realizing human shape display effect based on e-commerce image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010071799.9A CN111311359A (en) 2020-01-21 2020-01-21 Jigsaw method for realizing human shape display effect based on e-commerce image

Publications (1)

Publication Number Publication Date
CN111311359A true CN111311359A (en) 2020-06-19

Family

ID=71148223

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010071799.9A Pending CN111311359A (en) 2020-01-21 2020-01-21 Jigsaw method for realizing human shape display effect based on e-commerce image

Country Status (1)

Country Link
CN (1) CN111311359A (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102142138A (en) * 2011-03-23 2011-08-03 深圳市汉华安道科技有限责任公司 Image processing method and subsystem in vehicle assisted system
CN102982581A (en) * 2011-09-05 2013-03-20 北京三星通信技术研究有限公司 Virtual try-on system and method based on images
CN104732485A (en) * 2015-04-21 2015-06-24 深圳市深图医学影像设备有限公司 Method and system for splicing digital X-ray images
CN105023260A (en) * 2014-04-22 2015-11-04 Tcl集团股份有限公司 Panorama image fusion method and fusion apparatus
CN105205781A (en) * 2015-08-24 2015-12-30 电子科技大学 Power transmission line aerial photographing image splicing method
CN105761211A (en) * 2016-03-30 2016-07-13 努比亚技术有限公司 Method and device for splicing frames of mobile terminal
CN108510445A (en) * 2018-03-30 2018-09-07 长沙全度影像科技有限公司 A kind of Panorama Mosaic method
CN109214983A (en) * 2017-06-30 2019-01-15 宏碁股份有限公司 Image acquiring device and its image split-joint method
CN109886144A (en) * 2019-01-29 2019-06-14 深圳市云之梦科技有限公司 Virtual examination forwarding method, device, computer equipment and storage medium
CN110209860A (en) * 2019-05-13 2019-09-06 山东大学 A kind of interpretable garment coordination method and device based on clothes attribute of template-directed

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102142138A (en) * 2011-03-23 2011-08-03 深圳市汉华安道科技有限责任公司 Image processing method and subsystem in vehicle assisted system
CN102982581A (en) * 2011-09-05 2013-03-20 北京三星通信技术研究有限公司 Virtual try-on system and method based on images
CN105023260A (en) * 2014-04-22 2015-11-04 Tcl集团股份有限公司 Panorama image fusion method and fusion apparatus
CN104732485A (en) * 2015-04-21 2015-06-24 深圳市深图医学影像设备有限公司 Method and system for splicing digital X-ray images
CN105205781A (en) * 2015-08-24 2015-12-30 电子科技大学 Power transmission line aerial photographing image splicing method
CN105761211A (en) * 2016-03-30 2016-07-13 努比亚技术有限公司 Method and device for splicing frames of mobile terminal
CN109214983A (en) * 2017-06-30 2019-01-15 宏碁股份有限公司 Image acquiring device and its image split-joint method
CN108510445A (en) * 2018-03-30 2018-09-07 长沙全度影像科技有限公司 A kind of Panorama Mosaic method
CN109886144A (en) * 2019-01-29 2019-06-14 深圳市云之梦科技有限公司 Virtual examination forwarding method, device, computer equipment and storage medium
CN110209860A (en) * 2019-05-13 2019-09-06 山东大学 A kind of interpretable garment coordination method and device based on clothes attribute of template-directed

Similar Documents

Publication Publication Date Title
US11734798B2 (en) Method and apparatus for person super resolution from low resolution image
CN110096156B (en) Virtual reloading method based on 2D image
TWI742690B (en) Method and apparatus for detecting a human body, computer device, and storage medium
US8421782B2 (en) Information displaying apparatus and information displaying method
CN105184253B (en) Face recognition method and face recognition system
US20170161956A1 (en) Head-mounted display device and computer program
CN106780303A (en) A kind of image split-joint method based on local registration
CN104599317B (en) A kind of mobile terminal and method for realizing 3D scanning modeling functions
WO2012030869A4 (en) Multi-image face-based image processing
CN112001859B (en) Face image restoration method and system
CN107507216A (en) The replacement method of regional area, device and storage medium in image
CN106981078A (en) Sight bearing calibration, device, intelligent meeting terminal and storage medium
CN107145224A (en) Human eye sight tracking and device based on three-dimensional sphere Taylor expansion
CN104657994B (en) A kind of method and system that image consistency is judged based on optical flow method
CN108229492B (en) Method, device and system for extracting features
CN105357513B (en) Single camera expression in the eyes correcting method in conversational video
CN104299143A (en) Virtual try-in method and device
CN111311359A (en) Jigsaw method for realizing human shape display effect based on e-commerce image
CN116152121B (en) Curved surface screen generating method and correcting method based on distortion parameters
CN110533777B (en) Three-dimensional face image correction method and device, electronic equipment and storage medium
CN111243106A (en) Method for correcting three-dimensional human body model based on 2D human body image
JP6116273B2 (en) Advertisement presentation device
EP3761260A1 (en) Storage and signaling of entrance pupil parameters for immersive media
CN112381749A (en) Image processing method, image processing device and electronic equipment
Zhang et al. See through occlusions: Detailed human shape estimation from a single image with occlusions

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