CN112053281A - Intelligent identification method for tangram toy - Google Patents
Intelligent identification method for tangram toy Download PDFInfo
- Publication number
- CN112053281A CN112053281A CN202010956983.1A CN202010956983A CN112053281A CN 112053281 A CN112053281 A CN 112053281A CN 202010956983 A CN202010956983 A CN 202010956983A CN 112053281 A CN112053281 A CN 112053281A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- tangram
- data
- jigsaw puzzle
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000008569 process Effects 0.000 claims abstract description 20
- 238000001914 filtration Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000010191 image analysis Methods 0.000 claims description 12
- 230000003993 interaction Effects 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 3
- 230000003628 erosive effect Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 8
- 230000007547 defect Effects 0.000 abstract description 5
- 238000004364 calculation method Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/02—Affine transformations
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F9/00—Games not otherwise provided for
- A63F9/06—Patience; Other games for self-amusement
- A63F9/10—Two-dimensional jig-saw puzzles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/755—Deformable models or variational models, e.g. snakes or active contours
- G06V10/7553—Deformable models or variational models, e.g. snakes or active contours based on shape, e.g. active shape models [ASM]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Toys (AREA)
Abstract
An intelligent identification method for a tangram toy adopts internet equipment, a base, a reflector, a splicing base plate and an application software unit in the internet equipment as identification tools; the mobile phone is inserted into the groove of the base, the reflecting lens is horizontally arranged at the lower end of the shell, and the shell is clamped at the front side of the upper part of the mobile phone and is positioned at the upper part of the camera of the mobile phone; the base plate is positioned at the front end of the base; the application software unit comprises a calibration module, a game process module, an instruction module, an image processing module and a reward module; the identification is divided into eight steps. Based on AI technology, the invention directly obtains whether the position and the figure of the single tangram placed in the corresponding area of the base plate are correct or not according to the color by taking the color of each single tangram as the judgment basis of the placement position and the shape, thereby reducing the calculation amount, reducing the steps, correspondingly reducing the probability of image recognition errors and overcoming the defects of large calculation amount and more steps caused by adopting an edge matching method in the prior art. Based on the above, the invention has good application prospect.
Description
Technical Field
The invention relates to the technical field of educational toy application, in particular to an intelligent identification method for a tangram toy.
Background
With the development of science and technology, applications of intelligent internet devices, such as mobile phones and tablet computers, are very common, and more application software for game learning by using the internet devices are available. Currently, some game learning software in a learning-based game for developing an intelligence, etc., sets a certain task program in the game software in order to achieve a game effect. For example, in a puzzle game played by a player (generally, a low-age child) using a smart phone, a tablet computer, or the like, the APP may provide a puzzle set pattern shape to be spliced in a game display interface, and the player splices the puzzle set pattern according to a prompt. In the concrete application, APP progressively gives every single seven-piece puzzle appearance pattern that needs the concatenation, and after the player splices a plurality of single seven-piece puzzle in proper order through actual manual operation, the whole pattern of seven-piece board group that the completion needs the concatenation finally reaches certain degree's recreation learning effect.
The existing jigsaw puzzle is limited by technology, only has the function of prompting a player to splice a single jigsaw puzzle (seven in total) in sequence, lacks necessary guide, and cannot give rewards to the player in the jigsaw puzzle, so that the game enthusiasm of the player cannot be improved, and the playability is reduced; the spliced patterns cannot be judged to be correct or not, and the patterns spliced by players cannot be prompted even if the patterns are incorrect, so that the effect of benefiting intelligence cannot be achieved. With the development of science and technology, although the technology capable of identifying image data after splicing of players appears in the existing jigsaw puzzle splicing game, when the specific type of the spliced image is judged, an edge matching method is adopted, the defects of large calculation amount and multiple steps exist, and the probability of image recognition errors often appears in practical application, so that the application of the puzzle game is limited to a certain extent.
Disclosure of Invention
In order to overcome the defects that in the existing jigsaw puzzle splicing game based on an intelligent terminal, a player only executes a splicing task given by APP unilaterally, information interaction with the APP cannot be realized, the APP cannot judge whether a spliced pattern is correct or not, the spliced pattern of the player cannot be prompted even if the spliced pattern is incorrect, an intelligence-benefiting effect cannot be achieved, the calculated amount is large, the steps are multiple, and pattern recognition errors are easy to occur, the invention provides a tool for game learning based on a smart phone or a tablet computer and the like as hardware of the game, a base, a reflector and a splicing base plate are combined as tools for game learning, an application APP based on an AI technology is installed in the mobile phone and the like, in application, the base provides support for the mobile phone and the like, the reflector ensures that a front camera of the mobile phone can collect the graphic data of each single jigsaw puzzle after the front end and the lower end of a mobile phone screen are spliced in real time, the player respectively puts single jigsaw puzzle in a putting area according to, the mobile phone camera will shoot put seven-piece puzzle graphic data input and handle the comparison in the corresponding software of APP, with known shape in the APP go to match, and whether the concatenation that reachs the player is correct data, can give the player pronunciation encouragement and the bonus of integration when the concatenation is correct, can indicate the speech information of concatenation mistake when the concatenation is wrong, thereby realized the real-time data interaction of player and APP, player's the enthusiasm of playing has been improved, can reach better intellectual development effect, and through every single seven-piece puzzle colour as the judgement basis of locating position and shape, the calculated amount has been reduced, the step is few, a seven-piece puzzle toy intelligent recognition's method of corresponding wrong probability of image recognition has been reduced.
The technical scheme adopted by the invention for solving the technical problems is as follows:
an intelligent identification method for a tangram toy is characterized in that an internet device, a base, a reflector, a splicing base plate and an application software unit in the internet device are used as identification tools; the upper part of the base is provided with a groove, the lower part of the mobile phone is vertically inserted into the groove of the base, the reflective lens is horizontally arranged at the lower end of a shell, the rear side end of the shell is provided with a clamping groove, and the clamping groove is clamped at the front side of the upper part of the mobile phone and is positioned at the upper part of the front camera of the mobile phone; the splicing base plate is positioned at the front side end of the base; the application software unit comprises a calibration module, a game process module, an instruction module, an image processing module and a reward module; the image processing module comprises an image input sub-module, an image conversion sub-module, an image processing sub-module, an image analysis sub-module, a filtering sub-module and a comparison sub-module; the identification is divided into the following steps, step A: the method comprises the following steps that a base, a reflector, a base plate and an intelligent terminal are placed, an image input submodule of an image processing module controls a mobile phone camera to collect pictures of a lower base plate before the reflector is reflected to the camera, a calibration module calibrates the images of the base plate, and calibrated data serve as reference points for splicing a seven-piece board set pattern on the base plate subsequently; and B: in the game, the game process module gives a jigsaw appearance instruction task of the tangram group which needs to be spliced by a player through an instruction module and a mobile phone screen; c, a player places a plurality of single seven-piece puzzle on the backing plate according to the instruction graph; d: the image input submodule of the image processing module controls the mobile phone camera to collect single and all seven real tangram pictures reflected to the camera after splicing by the reflector, and outputs the pictures to the image conversion submodule; step E: the image conversion submodule converts each single and all spliced seven-piece puzzle RGB format images into HSV format images and inputs the HSV format images into the image processing submodule, and the image processing submodule performs image processing on the images and inputs the images into the image analysis submodule; step F: the image analysis submodule obtains appearance data of the spliced single or all the spliced tangram, and the data is input into the filtering submodule to be filtered; step G: the comparison submodule calls corresponding data in a game process module data unit, the filtered single tangram and all tangram data are compared with each single tangram and all tangram data given by the game process module to obtain whether the data of the single tangram spliced by the player is correct or not, and after all the single tangrams are spliced, whether the pattern of the tangram group spliced integrally is correct or not is obtained; step H: the reward module calls the data of comparing the submodule, compares every single seven-piece puzzle, seven-piece group concatenation data in the concatenation, can give the player pronunciation when the concatenation is correct and encourage and the bonus of integral, can indicate the speech information of concatenation mistake when the concatenation is wrong, realizes the real-time data interaction of player and APP.
Further, in the step A, after the base plate is placed, the calibration module can compare the base plate with the known pre-stored base plate data in the calibration module database according to the identified base plate, so as to obtain affine transformation parameters of the base plate, the subsequent APP obtains each frame of tangram graphs through the lens and transforms the parameters, and the graph data of the input single tangram without distortion and the orthographic views of all tangrams are recovered.
Furthermore, in the step B, a plurality of groups of shape pictures formed by splicing different single tangram are stored in the instruction module, and the game process module can randomly output the different shape pictures to be displayed on a screen.
Further, in the step E, the image conversion sub-module converts each single spliced RGB image of the tangram into an HSV image, and then separates color block data of each tangram according to the H color component, and converts the color block data into a gray image, and inputs the gray image to the image processing sub-module.
Further, in the step E, the image processing submodule performs an imaging process on the image by using a method of erosion and then expansion.
Further, in the step F, the image analysis sub-module obtains the shape data of the spliced single tangram, which is the triangle or quadrilateral outline data of the tangram.
Further, in the step F, the orientation, the position of the center point and the length of the longest side of each single jigsaw puzzle can be obtained by the filtering submodule in the image filtering process.
Further, in step B, C, D, E, F, G, H, when the game progress module gives the instruction task of the jigsaw puzzle shape of the jigsaw puzzle needing to be spliced by the player through the instruction module and the mobile phone screen, the image processing module controls the outline of the jigsaw puzzle needing to be displayed on the intelligent terminal screen, and then when the splicing position and the shape of a single jigsaw puzzle are correct, the corresponding single jigsaw puzzle displays color on the screen, and does not display color if the splicing position and the shape are incorrect; the player puts every single seven-piece puzzle figure in the corresponding position on the backing plate, the image processing module judges the basis according to every single seven-piece puzzle colour as putting position and shape, and then whether the single seven-piece puzzle position and figure that the corresponding region of backing plate put are correct according to the colour directly reachs, the position and the appearance image of the corresponding single seven-piece puzzle that the image processing module gathered, the module can all seek the color block profile that every seven-piece formed according to 7 colours to every frame image, it whether correct data is put up to reacing user's piece.
The invention has the beneficial effects that: the game learning method is based on the AI technology, adopts a smart phone or a tablet personal computer and the like, combines a base, a reflector and a square base plate as a game learning tool, installs an application APP in the mobile phone and the like, and in the application, the base provides support for the mobile phone and the like. The reflector ensures that the front camera of the mobile phone can collect the graphic data of the jigsaw puzzle after the front and the lower ends of the screen of the mobile phone are spliced in real time, a player splices the jigsaw puzzle set task on the base plate according to the game progress, and the base plate provides technical support for application software to obtain the relative position of the camera and the spliced jigsaw puzzle in the three-dimensional space. According to the invention, a player puts single tangram (total 7) according to APP prompts in a putting area, a mobile phone camera inputs shot data of the jigsaw puzzle putting graph into corresponding software of the APP for processing and comparison, the data are matched with the shape of the tangram group after the splicing is known in the APP, whether the splicing of the user is correct or not is obtained, voice encouragement and integral reward can be given to the player when the splicing is correct, voice information of splicing errors can be prompted when the splicing is wrong, real-time data interaction of the player and the APP is realized, the playing enthusiasm of the player is improved, and a better intelligence-benefiting effect can be achieved. According to the method, the color of each single tangram is used as the judgment basis of the placement position and the shape, and whether the position and the figure of the single tangram placed in the corresponding area of the base plate are correct or not is directly obtained according to the color, so that the calculated amount is reduced, the steps are fewer, the probability of image recognition errors is correspondingly reduced, the defects that the calculated amount is large and the steps are more due to the adoption of an edge matching method in the prior art are overcome, the probability of figure recognition errors is often generated in practical application, and the application of the puzzle game is more or less limited. Based on the above, the invention has good application prospect.
Drawings
The invention is further illustrated below with reference to the figures and examples.
FIG. 1 is a schematic view of a portion of the tool configuration used in the present invention.
FIG. 2 is a block diagram of the application software architecture of the present invention.
Figure 3 is a schematic diagram of the process of the image processing module of the present invention for processing a red triangular single jigsaw puzzle.
Detailed Description
As shown in fig. 1, an intelligent identification method for a jigsaw puzzle toy adopts an internet device 1 (in the embodiment, a smart phone is adopted) including a smart phone and a tablet personal computer, a base 2, a reflector 3, a spliced square backing plate 4 and an application software unit in the internet device as identification tools; in the tangram group 5, seven tangram 5 with different shapes have different colors, the base 2 is a square shell structure, the upper part of the base is an open rectangular groove 21 structure, the lower part of the mobile phone 1 is vertically inserted into the upper end of the base 2, the square reflecting lens 3 is horizontally arranged in the lower end of a square shell 6, the rear side end of the shell 6 is provided with a transversely distributed clamping groove 61, the clamping groove 61 is transversely clamped on the front side of the upper part of the mobile phone 1 and is positioned on the upper part of a front camera 11 of the mobile phone 1, the front end of the shell 6 with the rear lens 3 installed is high in height, the rear end of the shell is low in height and inclines by a certain angle, and images on a base plate 4 at the lower end of the; the splicing base plate 4 is positioned at the front side end of the base 2 (paper or other materials, and the white color and the size are consistent with those of seven single seven-piece puzzle after splicing).
FIG. 2 shows a method for intelligent recognition of a jigsaw puzzle, which employs application software units including a calibration module, a game progress module, an instruction module, an image processing module, and a reward module; the image processing module comprises an image input sub-module, an image conversion sub-module, an image processing sub-module, an image analysis sub-module, a filtering sub-module and a comparison sub-module.
Referring to fig. 1 and 2, a method for intelligently recognizing a jigsaw puzzle toy includes the following steps. Step A: the base, the reflector, the base plate and the intelligent terminal are placed, an image input submodule of the image processing module controls the mobile phone camera to collect base plate images reflected by the reflector to the front and the back of the camera, the calibration module calibrates the images of the base plate, and the calibrated data serve as subsequent reference points for splicing the seven-piece board set patterns on the base plate. In an actual situation, after the square base plates are placed, the calibration module compares the recognized square base plates with the known square base plate data prestored in the calibration module database, and then affine transformation parameters of the base plates are obtained. Because the image close to the lens is enlarged and the image far from the lens is reduced due to the angle problem when the image is shot from the lens, the graph of the square cushion plate in the flat view needs to be restored by the calibration module through an algorithm, namely four edges of the square are equal in length, so that the square cushion plate is selected as a reference graph; after the calibration module controls the mobile phone lens to take a picture, the calibration module finds out 4 vertex coordinates and compares the coordinates with known square vertexes prestored in a database to obtain a group of reflection transformation parameters of the lens lower cushion plate, each frame of tangram pictures obtained by the subsequent calibration module through the lens are transformed by using the parameters, and distortion-free front-view effective graphs input into a single tangram and all tangram groups are recovered.
Shown in fig. 1 and 2, step B: in the game, the game process module gives a jigsaw command task of the tangram group which needs to be spliced by a player through the command module and the mobile phone screen. The instruction module stores a plurality of groups of shape pictures formed by splicing different single (seven in total) tangram plates, and the game process module can randomly output the pictures with different shapes to be displayed on a screen.
Shown in fig. 1 and 2, step C: a player puts a plurality of single seven-piece puzzle on the backing plate according to the instruction graph; step D: and the image input submodule of the image processing module controls the mobile phone camera to collect single and all seven real tangram pictures reflected to the camera after splicing by the reflector, and outputs the pictures to the image conversion submodule. Step E: the image conversion submodule converts each single and all spliced seven-piece puzzle RGB format images into HSV format images and inputs the HSV format images into the image processing submodule, and the image processing submodule performs image processing on the images and inputs the images into the image analysis submodule; and the image conversion sub-module converts the RGB image of each spliced tangram into an HSV image, separates color block data of each tangram according to the H color component, converts the color block data into a gray image and inputs the gray image into the image processing sub-module. The image processing submodule processes the image by adopting a processing method of firstly corroding and then expanding (corroding can remove small interference points in the input picture).
Shown in fig. 1 and 2, step F: the image analysis submodule obtains the shape data of the spliced single or all the spliced tangram, the data is input into the filtering submodule to be filtered, and the image analysis submodule obtains the shape data of the spliced single tangram, which is the triangular or quadrilateral outline data of the tangram (the tangram only has triangular and quadrilateral structures). The orientation, the position of the center point, and the length of the longest edge of each single jigsaw puzzle can be obtained by the filtering submodule during image filtering processing.
Shown in fig. 1 and 2, step G: the comparison submodule calls corresponding data in the game process module data unit, the data of the single tangram and all tangram after filtering processing and the data of each single tangram and all tangram (total 7) given by the game process module are compared to obtain whether the data of the single tangram and the tangram groups spliced by the player are correct, and after all the single tangram are spliced, the data of the tangram groups spliced integrally are obtained. Under the actual conditions, judge whether the player correctly splices seven-piece puzzle group, need compare the distance of every seven-piece central point, the angle that seven-piece was put to and the distance between the seven-piece, these parameters are all up to standard, just can say that the user correctly splices out the seven-piece group figure that corresponds, and 7 makeup are all spliced out and are correct, just can calculate and close. In the invention, when a game progress module gives a jigsaw command task of the tangram group to be spliced by a player through a command module and a mobile phone screen, an image processing module controls the outline of the tangram to be displayed on an intelligent terminal screen, and then when the splicing position and the shape of a single tangram are correct, the corresponding single tangram displays color on the screen, and the color is not displayed incorrectly; the user puts every single seven-piece puzzle figure in the corresponding position on the backing plate, image processing module is as the judgement foundation of putting position and shape through every single seven-piece colour, and then whether the single seven-piece position and the figure that directly reachs the corresponding region of backing plate and put according to the colour are correct, the position and the appearance image of the corresponding single seven-piece puzzle that image processing module gathered, the module can all remove the colour block profile of looking for every seven-piece formation according to 7 colours to every frame image, and then whether the concatenation that reachs the user is correct data.
Shown in fig. 1 and 2, step H: in the reward module is used, the data of comparing the submodule is called, every single seven-piece puzzle in the concatenation, seven single seven-piece puzzle concatenation data in total are compared, can give the player pronunciation when the concatenation is correct and encourage and the bonus of total mark, can indicate the speech information of concatenation mistake when the concatenation is wrong, realize player and APP real-time data interaction, follow-up player total mark arrives a certain amount after, can promote the play time of player at every turn as the reward, improve player's recreation participation enthusiasm.
Figure 3 shows the image processing sub-module performing the image processing of a red triangular jigsaw puzzle in the jigsaw set (this example is only an example of a triangular red jigsaw puzzle, and the processing of other shapes and colours of the jigsaw puzzle is exactly the same as the triangular jigsaw puzzle), based on the fact that a single triangular jigsaw puzzle is red. 3-1, the image processing sub-module removes the non-red color (if the jigsaw is yellow, the non-yellow part in the picture is removed) which is not needed in the picture, thus reducing the calculation processing amount of other sub-modules; 3-2, a process of corroding the triangular picture, and small interference points in the input picture can be removed; and 3-3, expanding the triangular picture, and filling out the edge or the inner pit of the picture to facilitate subsequent processing. And 3-4, finding the edge of the triangle by the filtering submodule to perform fitting process, and further directly obtaining whether the position and the figure of the single triangular tangram arranged in the corresponding area of the base plate are correct or not according to the color.
As shown in figures 1, 2 and 3, the invention improves the playing enthusiasm of the player based on AI technology, and can achieve better intelligence-improving effect. According to the method, the color of each single tangram is used as the judgment basis of the placement position and the shape, and the correct data of the position of the single tangram placed in the corresponding area of the base plate and the correct data of the pattern are directly obtained according to the color, so that the calculated amount is reduced, the steps are fewer, the probability of image recognition errors is correspondingly reduced, the defects that the calculated amount is large and the steps are more due to the adoption of an edge matching method in the prior art are overcome, the probability of the pattern recognition errors is often generated in practical application, and the application of the puzzle game is limited to a certain extent.
While there have been shown and described what are at present considered the fundamental principles and essential features of the invention and its advantages, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Furthermore, it should be understood that although the present description refers to embodiments, the embodiments do not include only one independent technical solution, and such description is only for clarity, and those skilled in the art should take the description as a whole, and the technical solutions in the embodiments may be appropriately combined to form other embodiments that can be understood by those skilled in the art.
Claims (8)
1. An intelligent identification method for a tangram toy is characterized in that an internet device, a base, a reflector, a splicing base plate and an application software unit in the internet device are used as identification tools; the upper part of the base is provided with a groove, the lower part of the mobile phone is vertically inserted into the groove of the base, the reflective lens is horizontally arranged at the lower end of a shell, the rear side end of the shell is provided with a clamping groove, and the clamping groove is clamped at the front side of the upper part of the mobile phone and is positioned at the upper part of the front camera of the mobile phone; the splicing base plate is positioned at the front side end of the base; the application software unit comprises a calibration module, a game process module, an instruction module, an image processing module and a reward module; the image processing module comprises an image input sub-module, an image conversion sub-module, an image processing sub-module, an image analysis sub-module, a filtering sub-module and a comparison sub-module; the identification is divided into the following steps, step A: the method comprises the following steps that a base, a reflector, a base plate and an intelligent terminal are placed, an image input submodule of an image processing module controls a mobile phone camera to collect pictures of a lower base plate before the reflector is reflected to the camera, a calibration module calibrates the images of the base plate, and calibrated data serve as reference points for splicing a seven-piece board set pattern on the base plate subsequently; and B: in the game, the game process module gives a jigsaw appearance instruction task of the tangram group which needs to be spliced by a player through an instruction module and a mobile phone screen; c, a player places a plurality of single seven-piece puzzle on the backing plate according to the instruction graph; d: the image input submodule of the image processing module controls the mobile phone camera to collect single and all seven real tangram pictures reflected to the camera after splicing by the reflector, and outputs the pictures to the image conversion submodule; step E: the image conversion submodule converts each single and all spliced seven-piece puzzle RGB format images into HSV format images and inputs the HSV format images into the image processing submodule, and the image processing submodule performs image processing on the images and inputs the images into the image analysis submodule; step F: the image analysis submodule obtains appearance data of the spliced single or all the spliced tangram, and the data is input into the filtering submodule to be filtered; step G: the comparison submodule calls corresponding data in a game process module data unit, the filtered single tangram and all tangram data are compared with each single tangram and all tangram data given by the game process module to obtain whether the data of the single tangram spliced by the player is correct or not, and after all the single tangrams are spliced, whether the pattern of the tangram group spliced integrally is correct or not is obtained; step H: the reward module calls the data of comparing the submodule, compares every single seven-piece puzzle, seven-piece group concatenation data in the concatenation, can give the player pronunciation when the concatenation is correct and encourage and the bonus of integral, can indicate the speech information of concatenation mistake when the concatenation is wrong, realizes the real-time data interaction of player and APP.
2. The method for intelligently identifying the jigsaw puzzle toy according to claim 1, wherein in the step A, after the jigsaw puzzle is placed, the calibration module compares the identified jigsaw puzzle with the known prestored jigsaw puzzle data in the calibration module database to obtain affine transformation parameters of the jigsaw puzzle, each frame of jigsaw puzzle image obtained by the follow-up APP through the lens is transformed by using the parameters, and the image data of the input single jigsaw puzzle without distortion and all jigsaw puzzle fronts are recovered.
3. The intelligent jigsaw puzzle recognition method of claim 1, wherein in step B, the instruction module stores a plurality of sets of different jigsaw puzzle pieces which are spliced together, and the game progress module randomly outputs the different jigsaw puzzle pieces to be displayed on the screen.
4. The method for intelligently identifying a jigsaw puzzle according to claim 1, wherein in step E, the image conversion sub-module converts each single spliced jigsaw puzzle RGB image into an HSV image, and then separates color block data of each jigsaw puzzle according to H color components, converts the color block data into a gray image, and inputs the gray image to the image processing sub-module.
5. The intelligent recognition method for the jigsaw puzzle according to claim 1, wherein in the step E, the image processing submodule performs an image processing on the image by adopting a method of erosion and then expansion.
6. The method for intelligently identifying a jigsaw puzzle according to claim 1, wherein in step F, the image analysis sub-module obtains the shape data of the spliced single jigsaw puzzle, which is the triangle or quadrilateral outline data of the jigsaw puzzle.
7. A method as claimed in claim 1, wherein in step F, the filter submodule performs image filtering to obtain the orientation, position of center point and length of longest side of each single jigsaw puzzle.
8. The method for intelligently identifying a jigsaw puzzle according to claim 1, wherein in step B, C, D, E, F, G, H, when the game progress module gives the task of instructing the shape of the jigsaw puzzle to be spliced by the player through the instruction module via the mobile phone screen, the image processing module controls the outline of the jigsaw puzzle to be displayed on the intelligent terminal screen, and when the splicing position and the shape of a single jigsaw puzzle are correct, the corresponding single jigsaw puzzle displays color on the screen, and does not display color when the splicing position and the shape are incorrect; the player puts every single seven-piece puzzle figure in the corresponding position on the backing plate, the image processing module judges the basis according to every single seven-piece puzzle colour as putting position and shape, and then whether the single seven-piece puzzle position and figure that the corresponding region of backing plate put are correct according to the colour directly reachs, the position and the appearance image of the corresponding single seven-piece puzzle that the image processing module gathered, the module can all seek the color block profile that every seven-piece formed according to 7 colours to every frame image, it whether correct data is put up to reacing user's piece.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010956983.1A CN112053281A (en) | 2020-09-12 | 2020-09-12 | Intelligent identification method for tangram toy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010956983.1A CN112053281A (en) | 2020-09-12 | 2020-09-12 | Intelligent identification method for tangram toy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112053281A true CN112053281A (en) | 2020-12-08 |
Family
ID=73610180
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010956983.1A Withdrawn CN112053281A (en) | 2020-09-12 | 2020-09-12 | Intelligent identification method for tangram toy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112053281A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022156389A1 (en) * | 2021-01-22 | 2022-07-28 | 北京字跳网络技术有限公司 | Graphic display method, apparatus and device, and medium |
-
2020
- 2020-09-12 CN CN202010956983.1A patent/CN112053281A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022156389A1 (en) * | 2021-01-22 | 2022-07-28 | 北京字跳网络技术有限公司 | Graphic display method, apparatus and device, and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101187500B1 (en) | Light projection device and illumination device | |
| US9636588B2 (en) | System and method for object extraction for embedding a representation of a real world object into a computer graphic | |
| CN109034748B (en) | Method for building mould disassembly and assembly engineering training system based on AR technology | |
| CN105719318A (en) | Educational toy set and HSV based color identification method for Rubik's cube | |
| CN105498200A (en) | Educational toy set and tangram color recognition method thereof | |
| CN111242045A (en) | Automatic operation exercise right and wrong indication method and system | |
| CN106297492A (en) | A kind of Educational toy external member and utilize color and the method for outline identification programming module | |
| CN112883804A (en) | Error correction method and device for hand motion during musical instrument playing and electronic equipment | |
| CN112053281A (en) | Intelligent identification method for tangram toy | |
| CN112200230B (en) | Training board identification method and device and robot | |
| KR101700120B1 (en) | Apparatus and method for object recognition, and system inculding the same | |
| CN112818981A (en) | Musical instrument playing key position prompting method and device, electronic equipment and storage medium | |
| CN112057882A (en) | Intelligent identification method for splicing toys | |
| CN111840999A (en) | Game education method based on three-dimensional object graph recognition | |
| CN105701496A (en) | Go board surface identification method based on artificial intelligence technology | |
| CN113509266A (en) | Augmented reality information display device, method, readable storage medium, and apparatus | |
| CN112132750B (en) | Video processing method and device | |
| CN104933278B (en) | A kind of multi-modal interaction method and system for disfluency rehabilitation training | |
| CN108227346A (en) | Projection arrangement, projecting method and recording medium | |
| CN108040239B (en) | Knowledge training system and method based on image recognition | |
| CN115604887A (en) | Atmosphere lamp group control method, control console and device | |
| US7905610B1 (en) | Graphics processor system and associated method for projecting an image onto a three-dimensional object | |
| CN112121407A (en) | Puzzle solving game application method based on screen and real object | |
| CN112274932A (en) | Game resource data processing method and device, storage medium and computer equipment | |
| CN110960850A (en) | AR-based children learning and entertainment system |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201208 |