CN104715449A - Method and device for generating mosaic image - Google Patents
Method and device for generating mosaic image Download PDFInfo
- Publication number
- CN104715449A CN104715449A CN201510149873.3A CN201510149873A CN104715449A CN 104715449 A CN104715449 A CN 104715449A CN 201510149873 A CN201510149873 A CN 201510149873A CN 104715449 A CN104715449 A CN 104715449A
- Authority
- CN
- China
- Prior art keywords
- image
- proper vector
- picture material
- vector table
- memory location
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 239000000463 material Substances 0.000 claims abstract description 345
- 239000013598 vector Substances 0.000 claims abstract description 328
- 238000004513 sizing Methods 0.000 claims description 38
- 238000013507 mapping Methods 0.000 claims description 21
- 238000010276 construction Methods 0.000 claims description 16
- 238000007906 compression Methods 0.000 claims description 9
- 230000006835 compression Effects 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000002910 structure generation Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 description 16
- 238000005516 engineering process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 239000000203 mixture Substances 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- HUTDUHSNJYTCAR-UHFFFAOYSA-N ancymidol Chemical compound C1=CC(OC)=CC=C1C(O)(C=1C=NC=NC=1)C1CC1 HUTDUHSNJYTCAR-UHFFFAOYSA-N 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007907 direct compression Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
-
- 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
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a method for generating a mosaic image. One concrete implementation way of the method comprises the steps of dividing a target image into a plurality of image blocks with preset sizes; extracting feature vectors of all the image blocks; acquiring a feature vector table corresponding to a material library; acquiring the storage positions of material feature vectors matched with the feature vectors of all the image blocks in a material feature vector table; acquiring the storage addresses of the corresponding image materials according to the storage positions based on the correspondence relationship between the image materials and material feature vectors; acquiring the corresponding image materials according to the storage addresses to generate the mosaic image. After the implementation way is adopted, the generation efficiency of the mosaic image can be improved.
Description
Technical field
The application relates to field of computer technology, is specifically related to electronic pictures processing technology field, particularly relates to a kind of method and apparatus generating mosaic image.
Background technology
Along with the development of Internet technology, digital entertainment product starts to appear at people at one's side.Digital entertainment product refers to the amusing products based on digital technology such as animation, cartoon, online game, mosaic image.Wherein, mosaic image is the image be spliced by multiple little image block.In prior art, the method for more existing splicing mosaic images, can the image of a type by the image mosaic of another kind of type out, such as, use multiple character image to be spliced into a secondary landscape image as material.
In the generative process of current mosaic image, usually need target image to be divided into multiple image block, then these image blocks are mated with the picture material in material database respectively.Such generative process also exists repeated matching thus causes the problem that mosaic image formation efficiency is lower.
Summary of the invention
The object of the application is the method and apparatus of the generation mosaic image proposing a kind of improvement, solves one or more technical matterss that above background technology part is mentioned.
First aspect, this application provides a kind of method generating mosaic image, described method comprises: image block target image being divided into multiple pre-sizing; Image block characteristics vector is extracted to each image block; Obtain and material database characteristic of correspondence vector table, wherein, described proper vector table is for storing the material proper vector of each picture material in described material database; For each image block characteristics vector, obtain the memory location of material proper vector in described proper vector table matched; Based on the corresponding relation of described picture material and described material proper vector, obtain the memory address of corresponding picture material according to described memory location; According to each memory address, obtain corresponding picture material and generate mosaic image.
In certain embodiments, described for each image block characteristics vector, obtain the memory location of material proper vector in described proper vector table matched to comprise: the index structure obtaining described proper vector table, wherein, described index structure is used for when retrieving each material proper vector, provides sorted order and the memory location of material proper vector in described proper vector table; For each image block characteristics vector, the material proper vector going out to match from described proper vector table search according to described index structure; The mated memory location of each material proper vector in described proper vector table is obtained from described index structure.
In certain embodiments, described index structure is generated by following steps: split according to the neighbor relationships of each material proper vector by described proper vector table, and spanning tree structure; Each material proper vector corresponding in described tree construction is replaced to generate the index structure of described proper vector table with the memory location of each material proper vector in described proper vector table.
In certain embodiments, the described corresponding relation based on described picture material and described material proper vector, the memory address obtaining corresponding picture material according to described memory location comprises: obtain the mapping relations of material proper vector in proper vector table that the memory address of described picture material in the storage file of described material database is corresponding with described picture material; Based on described mapping relations, obtain the memory address of corresponding picture material in the storage file of described material database according to described memory location.
In certain embodiments, described according to each memory address, obtain corresponding picture material and generate mosaic image and comprise: read described storage file; In described storage file, corresponding picture material is obtained respectively according to each memory address; Replace each image block corresponding in described target image with each picture material obtained and generate mosaic image.
In certain embodiments, described target image is divided into the image block of multiple pre-sizing before, also comprise: obtain image; Judge that the pixel size of described image is whether within the scope of the pixel size preset; If the pixel size of described image is not within the scope of the pixel size preset, described image pixel size is adjusted within the scope of default pixel size using as target image.
In certain embodiments, described method also comprises: obtain original image; The image described original image being modified as pre-sizing is using as picture material, and wherein, described amendment comprises following at least one item: image-region is selected, pixel compression.
In certain embodiments, the described image described original image being modified as pre-sizing is also to comprise as picture material: described original image is first mapped to spherical model Shang Hou back projection in plane; Image back projection being modified as pre-sizing to the original image in plane is using as picture material.
In certain embodiments, also comprise: picture material classification is stored in multiple material database, for user, material database is selected.
Second aspect, this application provides a kind of device generating mosaic image, comprising: divide module, be configured for image block target image being divided into multiple pre-sizing; Extraction module, is configured for and extracts image block characteristics vector to each image block; Vector table acquisition module, be configured for and obtain and material database characteristic of correspondence vector table, wherein, described proper vector table is for storing the material proper vector of each picture material in described material database; Position acquisition module, is configured for for each image block characteristics vector, obtains the memory location of material proper vector in described proper vector table matched; Address acquisition module, based on the corresponding relation of described picture material and described material proper vector, obtains the memory address of corresponding picture material according to described memory location; Generation module, is configured for according to each memory address, obtains corresponding picture material and generates mosaic image.
In certain embodiments, described position acquisition module also comprises: index structure acquiring unit, be configured for the index structure obtaining described proper vector table, wherein, described index structure is used for when retrieving each material proper vector, provides sorted order and the memory location of material proper vector in described proper vector table; Retrieval unit, is configured for for each image block characteristics vector, the material proper vector going out to match from described proper vector table search according to described index structure; Memory location acquiring unit, is configured for and obtains the mated memory location of each material proper vector in described proper vector table from described index structure.
In certain embodiments, described position acquisition module also comprises index structure generation unit, is configured for: split according to the neighbor relationships of each material proper vector by described proper vector table, and spanning tree structure; Each material proper vector corresponding in described tree construction is replaced to generate the index structure of described proper vector table with the memory location of each material proper vector in described proper vector table.
In certain embodiments, described address acquisition module also comprises: mapping relations acquiring unit, is configured for and obtains the memory address of described picture material in the storage file of the described material database material proper vector mapping relations in proper vector table corresponding with described picture material; Memory address acquiring unit, is configured for based on described mapping relations, obtains the memory address of corresponding picture material in the storage file of described material database according to described memory location.
In certain embodiments, described generation module also comprises: reading unit, is configured for and reads described storage file; Material obtaining unit, is configured for and in described storage file, obtains corresponding picture material according to each memory address respectively; Replacement unit, is configured for and replaces each image block generation mosaic image corresponding in described target image with each picture material obtained.
In certain embodiments, also comprise screening module, described screening module comprises: image acquisition unit, is configured for acquisition image; Pixel size judging unit, be configured for judge described image pixel size whether within the scope of the pixel size preset; Pixel size adjustment unit, if the pixel size being configured for described image is not within the scope of the pixel size preset, adjusts to described image pixel size within the scope of default pixel size using as target image.
In certain embodiments, described device also comprises picture material generation module, and described picture material generation module comprises: original image acquiring unit, is configured for acquisition original image; Amending image unit, be configured for and described original image be modified to pre-sizing using as picture material, wherein, described amendment comprises following at least one item: image-region is selected, pixel compression.
In certain embodiments, picture material generation module also comprises: image conversion unit, is configured for and described original image is first mapped to spherical model Shang Zai back projection in plane; Converted image amendment unit, is configured for and back projection is modified to pre-sizing using as picture material to the original image in plane.
The method and apparatus of the generation mosaic image that the application provides, being mated by the material proper vector in the proper vector of image block that Target Photo is divided into and the proper vector table of material database, obtaining the memory location of material proper vector in proper vector table of the picture material for replacing image block; And then, based on the corresponding relation of picture material and material proper vector, obtain the memory address of corresponding picture material according to above-mentioned memory location; Finally, according to each memory address, obtain corresponding picture material and generate mosaic image.The method and apparatus of the generation mosaic image that the application provides improves the formation efficiency of mosaic image.
Accompanying drawing explanation
By reading the detailed description done non-limiting example done with reference to the following drawings, the other features, objects and advantages of the application will become more obvious:
Fig. 1 is the process flow diagram of an embodiment of the method for generation mosaic image according to the application;
Fig. 2 is the process flow diagram obtaining an embodiment of the memory location of the material proper vector matched with image block characteristics vector according to index structure from proper vector table according to the application;
Fig. 3 is the point of the geography information as the picture material sectional drawing schematic diagram according to the application;
Fig. 4 is the process flow diagram of another embodiment of the method for generation mosaic image according to the application;
Fig. 5 a, Fig. 5 b are initial pictures, the mosaic image schematic diagram of an embodiment of the method for generation mosaic image according to the application respectively;
Fig. 6 is the structural representation of an embodiment of the device of generation mosaic image according to the application.
Embodiment
Below in conjunction with drawings and Examples, the application is described in further detail.Be understandable that, specific embodiment described herein is only for explaining related invention, but not the restriction to this invention.It also should be noted that, for convenience of description, in accompanying drawing, illustrate only the part relevant to Invention.
It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combine mutually.Below with reference to the accompanying drawings and describe the application in detail in conjunction with the embodiments.
Please refer to Fig. 1, it illustrates a flow process 100 of the method generating mosaic image.The present embodiment is mainly applied in this way in the electronic equipment including display screen and illustrates, this electronic equipment can comprise smart mobile phone, panel computer, E-book reader, MP3 player (Moving Picture Experts Group Audio Layer III, dynamic image expert compression standard audio frequency aspect 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert compression standard audio frequency aspect 4) player, pocket computer on knee and desk-top computer etc.The application generates the method for mosaic image, comprises the following steps:
Step S101, is divided into the image block of multiple pre-sizing by target image.
In the present embodiment, the target image of mosaic image to be produced can be divided into the image block of multiple pre-sizing by electronic equipment (such as generating mosaic image class application operation smart mobile phone thereon).Here, electronic equipment from the target image locally or remotely obtaining mosaic image to be produced, also can take a photo as target image.Target image according to pixels can be divided into the image block of pre-sizing, such as, can be divided into the image block of 32 × 32 pixel sizes.Wherein, pre-sizing represents that the image block that division target image obtains can have identical pixel size with the picture material for generating mosaic image.
In the optional implementation of the present embodiment, target image also can be sent to remote server (such as applying to the generation mosaic image class on electronic equipment the background server provided support) by electronic equipment.Target image can be divided into the image block of multiple pre-sizing by remote server.Here remote server can be a station server, also can be the server cluster linked together by network.At this moment, this electronic equipment can receive these information by wired connection mode or radio connection from remote server.Above-mentioned radio connection includes but not limited to 3G/4G connection, WiFi connection, bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection and other radio connection developed known or future now.
Step S102, extracts image block characteristics vector to each image block.
In the present embodiment, electronic equipment can extract image block characteristics vector to ready-portioned each image block.Wherein, image block characteristics vector can be used to the vector of the some of token image block or multiple feature (such as color characteristic etc.), such as, can be the vector of the color value composition of multiple unique point.
As an example of image block characteristics vector, image block characteristics vector can the color characteristic of only token image block.Such as, existing display can adopt RGB color standard, namely over the display, by electron gun beat red (R), green (G) of screen, blue (B) three-colour light-emitting extremely on produce color.Wherein, RGB color standard is by obtaining color miscellaneous to the change of red (R), green (G), blue (B) three Color Channels and their superpositions each other.Therefore, the color value of image block can be represented by the numerical value (color value) of unique point respectively on R, G, B tri-Color Channels.Specifically, to each image block, first electronic equipment can choose multiple point on image, such as 25 points are as unique point, secondly the numerical value on R, G, B tri-Color Channels is obtained to each unique point, finally these 25 × 3 numerical value are rearranged in order the vector of one 25 × 3 dimension, i.e. image block characteristics vector.Wherein, 25 points as unique point can be that the rule given tacit consent to is chosen.Such as, image block has 32 × 32 pixels, can choose 5 points, choose 5 row altogether in every a line, forms the dot matrix of 5 × 5.25 unique points also can be in 32 × 32 pixels × and type chooses, or chooses with other forms, and the application does not limit this.Alternatively, in the vector of above-mentioned 25 × 3 dimensions, the order of the numerical value on R, G, B tri-Color Channels of each unique point, can have multiple.Such as 25 × 3 dimension vectors can first be each unique point R Color Channel on numerical value, be then each unique point G Color Channel on numerical value, be finally each unique point B Color Channel on numerical value.25 × 3 dimension vectors also can be arrange by the order of a unique point, the numerical value on R, G, B tri-Color Channels of a unique point, be then next unique point R, G, B tri-Color Channels on numerical value.In practice, the vector of 25 × 3 dimensions can set the order of numerical value according to practical application, the application does not limit this.
Alternatively, also can be completed by remote server the step of each image block extraction image block characteristics vector.
Step S103, obtains and material database characteristic of correspondence vector table.
In the present embodiment, electronic equipment obtains the proper vector table corresponding with acquiescence or selected material database from Local or Remote server.Wherein, material database may be used for the related data (storage file of such as material image etc.) storing material image.Here, material database can be a material database of acquiescence, also can be a material database selected from multiple alternative material database.Alternatively, when material database has multiple, can be store by the classification of different sorting techniques.Such as, multiple material database can be the street view image material database stored by geographic area (as city Beijing, Shanghai etc.), also can be the character image material database stored by sex (as man, female etc.), can also be the scene image material database stored by Various Seasonal (as spring, winter etc.), etc.Alternatively, multiple material database can also be simultaneously by the picture material storehouse that the classification of multiple sorting technique stores, such as, by the Various Seasonal scene image material database that (summer etc. in Pekinese spring, Suzhou), classification stored of geographic area, etc.The application does not limit this.
In the present embodiment, proper vector table is for storing the material proper vector of each picture material in corresponding material database.Proper vector table can be stored in advance in electronic equipment Local or Remote server.Wherein, material proper vector can be used to the vector of the some of token image material or multiple feature (such as color characteristic etc.), such as, can be the vector of the color value composition of multiple unique point.It will be understood by those skilled in the art that the material proper vector of each picture material can have identical method for expressing with the proper vector of above-mentioned image block for the ease of coupling.Such as: on picture material, choose 25 points as unique point, secondly the numerical value on R, G, B tri-Color Channels is obtained to each unique point, finally these 25 × 3 numerical value are rearranged in order the vector of one 25 × 3 dimension, i.e. the proper vector of picture material.Wherein, the proper vector for token image material can have identical putting in order with the proper vector for token image block to the numerical value on unique point R, G, B tri-Color Channels.
Alternatively, acquisition and material database characteristic of correspondence vector table step also can be completed by remote server.
Step S104, for each image block characteristics vector, obtains the memory location of material proper vector in proper vector table matched.
In the present embodiment, for each image block characteristics vector, electronic equipment carries out Vectors matching according to the material proper vector in the proper vector table obtained in step 103, obtains the memory location of material proper vector in proper vector table matched.Wherein, electronic equipment judges whether material proper vector and image block characteristics vector match, and can judge according to the matching degree of proper vector.For example, this matching degree can represent by the variance of material proper vector with the corresponding numerical value of image block characteristics vector, and variance larger expression matching degree is less, and variance less expression matching degree is larger.This matching degree can also represent with weighting percentage.Such as, weight percentage can be obtained by following methods: suppose that vector dimension is 75 dimensions, the weight then often tieed up is 1/75, by the numerical value often tieed up in the material proper vector numerical value divided by the corresponding dimension of image block characteristics vector, the business obtained is multiplied by weight 1/75, as the weight percentage of this dimension, the weight percentage of each dimension is added, and namely obtains the weighting percentage of material proper vector for image block characteristics vector.The value of weighting percentage is larger, and represent that matching degree is larger, the value less expression matching degree of weighting percentage is less.This matching degree can also represent with additive method.The application does not limit this.It will be appreciated by those skilled in the art that, electronic equipment can select the material proper vector the highest with image block characteristics Vectors matching degree, or match first matching degree value is greater than the material proper vector of threshold value (can be such as that weighting percentage is greater than 80%), as the material proper vector that match vectorial with image block characteristics, etc.
In the present embodiment, when electronic equipment carries out Vectors matching, can mate successively according to the material proper vector order stored in vector table, the sorted order that also can provide according to the index structure of proper vector table (such as tree-like index structure) mates, and can also mate according to other orders.The application does not limit this.As an example, Fig. 2 gives a kind of flow process 200 obtaining an embodiment of the memory location of the material proper vector matched with image block characteristics vector according to index structure in proper vector table.The concrete steps of this flow process 200 are as follows:
Step S201, obtains the index structure of proper vector table.
In the present embodiment, electronic equipment can from the index structure locally or remotely obtaining proper vector table.Wherein, this index structure can be tree construction, also can be list structure, for when retrieving each material proper vector, provides sorted order and the memory location of material proper vector in above-mentioned proper vector table.When index structure is tree construction, if this tree construction is reasonable in design, after a node of tree completes coupling, the match is successful or get rid of one of the left subtree, right subtree of this node, greatly can accelerate rate matched.
Step S202, for each image block characteristics vector, the material proper vector going out to match from proper vector table search according to index structure.
In the present embodiment, for each image block characteristics vector, the sorted order that electronic equipment or remote server provide according to index structure goes out the material proper vector matched with image block characteristics vector from proper vector table search.
Step S203, obtains each mated material proper vector memory location in proper vector table from index structure.
In the present embodiment, electronic equipment or remote server, according to the matching result of step S202, obtain each material proper vector memory location in proper vector table matched from index structure.Wherein, this memory location can be the logical address (can be such as the storage sequence number of proper vector in proper vector table) of material proper vector, also can be the physical address (actual address in the physical memory space at proper vector place) of material proper vector.This memory location and material proper vector have certain mapping relations.Alternatively, these mapping relations can be such as: this memory location is stored in proper vector table with target form under the index of material proper vector.
In some optional implementations of the present embodiment, above-mentioned index structure can be tree construction.The index structure of this tree construction type can generate according to following step: first, the neighbor relationships of proper vector table according to each material proper vector split, and spanning tree structure; Then, each material proper vector corresponding in tree construction is replaced with the index structure of generating feature vector table with the memory location of each material proper vector in proper vector table.Here, in the tree construction split according to the neighbor relationships of the material proper vector in proper vector table, material proper vector can distribute according to arest neighbors relation.And the actual data deposited of the Nodes of tree construction can be the memory location of material proper vector in proper vector table, reduce the data volume of tree construction, simplify tree construction.Electronic equipment or remote server according to the relation of the material proper vector in this memory location and proper vector table, can read corresponding material proper vector from the memory location of this tree construction Nodes.For example, in the image block characteristics Vectors matching process of reality, electronic equipment or far-end server mate according to the order of tree construction.The such as root node of first Match Tree structure, electronic equipment or far-end server read the memory location at root node place, by the mapping relations of this memory location and material proper vector, read corresponding material proper vector also to compare with image block characteristics vector, whether match according to the matching degree determination material proper vector of material proper vector and image block characteristics vector and image block characteristics vector.Wherein, matching degree is the sign of the matching degree of material proper vector and image block characteristics vector.If matching degree is greater than first threshold, then determine that the material proper vector corresponding with root node and this image block characteristics vector match, then obtain the memory location at root node place; If matching degree is greater than Second Threshold and be less than first threshold, then continue the right subtree of Match Tree structure; If matching degree is less than Second Threshold, then continue the left subtree of Match Tree structure.By that analogy.
In some optional implementations of the present embodiment, this index structure can be that k-d sets (k-dimensional tree, k Wei Shu) structure.Wherein, k-d tree is a kind of data structure splitting k dimension data space.K-d tree is the binary tree of each node for k dimension point.All non-leaf nodes of k-d tree can regard as a lineoid and compartition is become two parts.Wherein, represent the left subtree of this non-leaf nodes at the point on the lineoid left side, the point on the right of lineoid represents the right subtree of this non-leaf nodes.The direction of lineoid can be selected by following relation: each node tie up with k in that one dimension perpendicular to lineoid relevant.Such as, select to divide according to x-axis, the node that all x values are less than designated value all can appear at left subtree, and the node that all x values are greater than designated value all can appear at right subtree.The defined basis that k-d sets index structure does not have overlap, very fast in process mass data hourly velocity.
Step S105, based on the corresponding relation of picture material and material proper vector, obtains the memory address of corresponding picture material according to above-mentioned memory location.
In the present embodiment, based on the corresponding relation of picture material and material proper vector, electronic equipment or remote server can obtain the memory address of corresponding picture material according to above-mentioned memory location.Wherein, the memory address of picture material can be the storage sequence number of picture material in material database or actual address (physical address).It will be appreciated by those skilled in the art that, due to the proper vector that material proper vector is picture material, there is relation one to one between them, therefore, also relation is one to one had between the memory address of above-mentioned memory location and corresponding picture material, or mapping relations.Alternatively, picture material the material proper vector corresponding with it can have identical storage order.
In some implementations of the present embodiment, first electronic equipment or remote server obtain the memory address of picture material in the storage file of the material database material proper vector mapping relations in proper vector table corresponding with picture material, secondly based on above-mentioned mapping relations, the memory address of corresponding picture material in the storage file of material database is obtained according to memory location.Wherein, above-mentioned mapping relations can be kept in the storer of electronic equipment or remote server in advance.The existence form that above-mentioned storage file is all picture materials in material database on the storer of electronic equipment or remote server.Alternatively, storage file can comprise the compressed format (as jpg form etc.) of picture, also can be the binary format of the color value of pixel, etc., the application does not limit this.For example, the storage file binary file that can be made up of the numerical value of each pixel of picture material on R, G, B tri-Color Channels.Now, when obtaining this binary file, according to the numerical value of each pixel of picture material on R, G, B tri-Color Channels, picture material can be shown.
Step S106, according to each memory address, obtains corresponding picture material and generates mosaic image.
In the present embodiment, electronic equipment or remote server first according to each memory address obtained in step S105, can obtain corresponding picture material, secondly the picture material obtained are replaced corresponding image block and generate mosaic image.
In some implementations of the present embodiment, electronic equipment or remote server can read the storage file of material database from storer, then in storage file, obtain corresponding picture material according to each memory address respectively; Then replace each image block corresponding in target image with each picture material obtained and generate mosaic image.Alternatively, whether the image block that electronic equipment or remote server can also detect in target image is replaced completely, if not, then return step S102, again extract the image block characteristics vector of the image block be not replaced, carry out Vectors matching, obtain corresponding material image.
In some optional implementations of the present embodiment, picture material can be obtained by following steps: first electronic equipment or remote server obtain original image, and the image then original image being modified as pre-sizing is using as picture material.Wherein, above-mentioned amendment includes but not limited to following at least one item: image-region is selected, pixel is compressed etc.Wherein, original image can be arbitrary image, such as character image, landscape image, street view image etc.The pre-sizing of image is the pixel value (can be such as 32 × 32 pixels) of the picture material preset.Alternatively, this pixel value can be the value rule of thumb obtained, and also can be to be trained according to the generation effect of the mosaic image of pixel value and generation the pixel value obtained by sample set, etc., the application does not limit this.When the size of original image is greater than above-mentioned pre-sizing, electronic equipment or remote server can be modified to original image, obtain the picture material of pre-sizing.Alternatively, electronic equipment or remote server can choose the certain area in original image, such as, choose the head image part etc. of character image.Electronic equipment or remote server can also carry out pixel compression to the image of original image or selected area part, to obtain the picture material of pre-sizing.In practice, if original image is Streetscape picture, regional choice can also be carried out, to increase meaningfulness and the interest of picture material according to the geography information point (a geography information point can be a house, retail shop, a landmark building etc.) in street view image.As shown in Figure 3, be from part sight spot, Beijing image as original image, behind selected geography information point region, carry out the picture material of compressed shape one-tenth.
In some optional implementations of the present embodiment, electronic equipment or remote server can also carry out following process to original image: first original image is mapped to spherical model Shang Zai back projection in plane; Then image back projection being modified as pre-sizing to the original image in plane is using as picture material.It will be appreciated by those skilled in the art that, when original image is the street view image in electronic chart, original image may be the image comprising fish-eye image, size very large (being such as 8192 × 4096 pixels), if be directly compressed to the details that pre-sizing (can be such as 32 × 32 pixels) may lose picture, simultaneously, fish-eye image can be the image formed to plane with the image projection at flake visual angle (being greater than the visual angle of 180 °), directly carrying out compression to it may cause edge distortion, and impact generates the effect of mosaic image.Therefore, for the image comprising fish-eye image, image first can be mapped on three-dimensional ball model, with flake visual angle restituting image, then back projection is in plane, forms the image at 180 ° of visual angles, with the distortion in removal of images modification process.
For the present embodiment, the scene of application can be, user selects image (also input inquiry condition can obtain image from remote server, such as character image) and selected material database (such as selecting city: Beijing etc.) after, electronic equipment or far-end server obtain image, matching image material from material database, replaces image block and generates mosaic image and show.Image can be divided into image block by electronic equipment or far-end server, and the memory address of each picture material that proper vector matches with image block can be obtained based on the index structure of the proper vector table of material database and proper vector table, after the storage file reading material database, corresponding picture material generation mosaic image can be obtained successively.The method that above-described embodiment of the application provides contributes to the formation efficiency improving mosaic image.
What deserves to be explained is, the method for the generation mosaic image that the present embodiment provides, be only exemplary, the step in flow process 100 does not comprise temporal sequencing.Some steps wherein can adjust in actual applications as required.The change of sequence of steps does not affect the execution result of the method for the generation mosaic image of the application.Such as, step 103 and step 102 can perform simultaneously, also can perform by reversed order.The application does not limit this.
Refer to Fig. 4.Fig. 4 is the flow process 400 of another embodiment of the method for generation mosaic image according to the application.Flow process 400 comprises the following steps:
Step S401, obtains image.
In the present embodiment, electronic equipment, first from locally or remotely obtaining an image, also can take a photo as image.Wherein, this image can be the image of arbitrary content and size.
Step S402, judges that the pixel size of image is whether within the scope of the pixel size preset.
In the present embodiment, whether the pixel size of the image obtained in electronic equipment determining step S401 is within the scope of the pixel size preset.Electronic equipment also can by the image uploading that obtains in step S401 to remote server.Remote server obtain judge image after image pixel size whether within the scope of the pixel size preset.It will be understood by those skilled in the art that if the image pixel of electronic equipment or remote server acquisition is too little, then can have a strong impact on the generation effect of mosaic image.For example, the pixel size of image is 96 × 96 pixels, divides, suppose that the pre-sizing of image block is 32 × 32 pixels, then can only be divided into 3 × 3 image blocks image.If generate the mosaic image of face with Streetscape picture splicing, then may not see it being a face completely.Therefore, first electronic equipment or remote server can judge the pixel size of image.
In the present embodiment, the pixel size scope preset can be the better pixel size scope (can be such as 512 × 512 pixel to 8192 × 4096 pixels) generating mosaic image.This pixel size scope preset can be obtained by empirical value, also can be obtained by training sample set.The application does not limit this.
Step S403, if the pixel size of image is not within the scope of the pixel size preset, adjusts to the pixel size of image within the scope of default pixel size using as target image.
In the present embodiment, if the pixel size of image not preset pixel size within the scope of, electronic equipment or remote server the pixel size of image can be adjusted within the scope of default pixel size using by image as target image.Wherein, if image pixel size is less than the minimum pixel value of pixel size scope, then electronic equipment or remote server image is stretched, after the adjustment such as wide or high polishing as target image, if image pixel size is greater than the max pixel value of pixel size scope, then image is carried out pixel compression, region cutting etc. adjustment after as target image.
Step S404, is divided into the image block of multiple pre-sizing by target image.
In the present embodiment, the target image of mosaic image to be produced can be divided into the image block of multiple pre-sizing by electronic equipment or remote server.Wherein, pre-sizing represents that the image block of division can have identical pixel size with the picture material for generating mosaic image.
Step S405, extracts image block characteristics vector to each image block.
In the present embodiment, electronic equipment can extract image block characteristics vector to ready-portioned each image block.Wherein, image block characteristics vector can be used to the vector of the some of token image block or multiple feature (such as color characteristic etc.), such as, can be the vector of the color value composition of multiple unique point.
Step S406, obtains and material database characteristic of correspondence vector table.
In the present embodiment, electronic equipment obtains the proper vector table corresponding with acquiescence or selected material database from Local or Remote server.Wherein, material database may be used for the related data (can be such as storage file of material image etc.) storing material image.In the present embodiment, proper vector table is for storing the material proper vector of each picture material in corresponding material database.Proper vector table can be stored in advance in electronic equipment Local or Remote server.Here, material proper vector can have identical extracting mode and method for expressing with image block characteristics vector.
Step S407, for each image block characteristics vector, obtains the memory location of material proper vector in proper vector table matched.
In the present embodiment, for each image block characteristics vector, electronic equipment or remote server carry out Vectors matching according to the material proper vector in the proper vector table obtained in step 407, obtain the memory location of material proper vector in proper vector table matched.Wherein, electronic equipment judges whether material proper vector and image block characteristics vector match, and can judge according to the matching degree of proper vector.When electronic equipment or remote server carry out Vectors matching to image block characteristics vector sum material proper vector, can mate successively according to the material proper vector order stored in vector table, the sorted order that also can provide according to the index structure of proper vector table (such as tree-like index structure) mates, and can also mate according to other orders.The application does not limit this.
Step S408, based on the corresponding relation of picture material and material proper vector, obtains the memory address of corresponding picture material according to above-mentioned memory location.
In the present embodiment, based on the corresponding relation of picture material and material proper vector, electronic equipment or remote server can obtain the memory address of corresponding picture material according to above-mentioned memory location.Wherein, the memory address of picture material can be the storage sequence number of picture material in material database or actual address.It will be appreciated by those skilled in the art that, due to the proper vector of picture material during material proper vector, there is relation one to one between them, therefore, also relation is one to one had between the memory address of above-mentioned memory location and corresponding picture material, or mapping relations.Alternatively, picture material the material proper vector corresponding with it can have identical storage order.
Step S409, according to each memory address, obtains corresponding picture material and generates mosaic image.
In the present embodiment, electronic equipment or remote server can first according to each memory addresss obtained in step S408, read the storage file of material database, from storage file, obtain corresponding picture material successively, secondly the picture material obtained is replaced corresponding image block and generate mosaic image.
In the present embodiment, step 404 in above-mentioned realization flow, step 405, step 406, step 407, step 408 and step 409 are substantially identical with the step 101 in previous embodiment, step 102, step 103, step 104, step 105 and step 106 respectively, do not repeat them here.
Fig. 5 a, 5b show the example using the method for the generation mosaic image of the application target image to be generated mosaic image.Wherein, Fig. 5 b is the mosaic image generated the character image in Fig. 5 a as picture material by the geography information point in a city.In Fig. 5 a, Fig. 5 b, Fig. 5 a is the image that electronic equipment or remote server obtain, and pixel is larger.Image carries out after the cutting of region as target image generation mosaic image as shown in Figure 5 b by electronic equipment or remote server.Mosaic image in Fig. 5 b contains only the head image of character image in Fig. 5 a.Each picture material with this city local characteristic can be demonstrated after mosaic image in Fig. 5 b is exaggerated.
As can be seen from Figure 4, the embodiment corresponding with Fig. 1 has had more the step S401 obtaining image unlike the flow process 400 of, the generation mosaic image in the present embodiment, has judged the step S402 of image pixel size and adjust image size using the step S403 as target image.By the step S401, S402 and S403 that increase, the image that the scheme that the present embodiment describes contributes to selecting user or taking screens and adjusts, and makes the validity of the mosaic image of generation higher, better effects if.
With further reference to Fig. 6, as the realization to said method, this application provides a kind of embodiment generating the device of mosaic image, this device embodiment is corresponding with the embodiment of the method shown in Fig. 1, and this device specifically can be applied in electronic equipment (as generated mosaic image application operation smart mobile phone thereon) or server (such as applying to the generation mosaic image class on electronic equipment the background server provided support).
As shown in Figure 6, the device 600 of the generation mosaic image described in the present embodiment comprises: divide module 601, extraction module 602, vector table acquisition module 603, position acquisition module 604, address acquisition module 605 and generation module 606.Wherein, divide module 601, be configured for image block target image being divided into multiple pre-sizing; Extraction module 602, is configured for and extracts image block characteristics vector to each image block; Vector table acquisition module 603, be configured for and obtain and material database characteristic of correspondence vector table, this proper vector table is for storing the material proper vector of each picture material in material database; Position acquisition module 604, is configured for for each image block characteristics vector, obtains the memory location of material proper vector in proper vector table matched; Address acquisition module 605, is configured for the corresponding relation based on described picture material and described material proper vector, obtains the memory address of corresponding picture material according to described memory location; Generation module 606, is configured for according to each memory address, obtains corresponding picture material and generates mosaic image.
In the present embodiment, the image block that target image according to pixels can be divided into pre-sizing by module 601 is divided.Wherein, pre-sizing represents that the image block that division target image obtains can have identical pixel size with the picture material for generating mosaic image.
In the present embodiment, the image block that extraction module 602 can mark off division module 601 extracts image block characteristics vector.Wherein, image block characteristics vector can be used to the vector of the some of token image block or multiple feature (such as color characteristic etc.), such as, can be the vector of the color value composition of multiple unique point.
In the present embodiment, vector table acquisition module 603 can obtain the proper vector table corresponding with acquiescence or selected material database from Local or Remote server.Wherein, proper vector table is for storing the material proper vector of each picture material in corresponding material database.Material proper vector can be used to the vector of the some of token image material or multiple feature (such as color characteristic etc.), such as, can be the vector of the color value composition of multiple unique point.It will be understood by those skilled in the art that the material proper vector of each picture material can have identical extracting mode and method for expressing with the proper vector of above-mentioned image block for the ease of coupling.
In the present embodiment, each image block characteristics vector that position acquisition module 604 can obtain extraction module 602, material proper vector in the proper vector table obtained with vector table acquisition module 603 carries out Vectors matching, obtains the memory location of material proper vector in proper vector table matched.Alternatively, position acquisition module 604 is when carrying out Vectors matching, can mate successively according to the material proper vector order stored in vector table, the sorted order that also can provide according to the index structure of proper vector table (such as tree-like index structure) mates, and can also mate according to other orders.The application does not limit this.
In the present embodiment, based on the corresponding relation of picture material and material proper vector, address acquisition module 605 can obtain the memory address of corresponding picture material according to above-mentioned memory location.Wherein, the memory address of picture material can be the storage sequence number of picture material in material database or actual address.
In the present embodiment, first generation module 606 according to each memory address that address acquisition module 605 obtains, obtains corresponding picture material, secondly the picture material obtained is replaced corresponding image block and generates mosaic image.
In the optional implementation of the present embodiment, position acquisition module 604 also comprises: index structure acquiring unit (not shown), is configured for the index structure obtaining proper vector table; Retrieval unit (not shown), is configured for for each image block characteristics vector, the material proper vector going out to match from proper vector table search according to index structure; Memory location acquiring unit (not shown), is configured for and obtains each mated material proper vector memory location in proper vector table from index structure.Wherein, index structure is used for when retrieving each material proper vector, provides sorted order and the memory location of material proper vector in described proper vector table.
In the optional implementation of the present embodiment, address acquisition module 605 comprises: mapping relations acquiring unit (not shown), is configured for and obtains the memory address of picture material in the storage file of the material database material proper vector mapping relations in proper vector table corresponding with picture material; Memory address acquiring unit (not shown), is configured for based on these mapping relations, obtains the memory address of corresponding picture material in the storage file of material database according to above-mentioned memory location.
In the optional implementation of the present embodiment, generation module 606 comprises: reading unit (not shown), is configured for and reads above-mentioned storage file; Material obtaining unit (not shown), is configured for and in this storage file, obtains corresponding picture material according to each memory address respectively; Replacement unit (not shown), is configured for and replaces each image block generation mosaic image corresponding in target image with each picture material obtained.
In the optional implementation of the present embodiment, the device 600 generating mosaic image also comprises screening module (not shown), and this screening module can comprise: image acquisition unit (not shown), is configured for acquisition image; Pixel size judging unit (not shown), be configured for judge described image pixel size whether within the scope of the pixel size preset; Pixel size adjustment unit, if the pixel size being configured for described image is not within the scope of the pixel size preset, adjusts to the pixel size of image within the scope of default pixel size using as target image.
In the optional implementation of the present embodiment, the device 600 generating mosaic image also comprises picture material generation module (not shown), this picture material generation module can comprise: original image acquiring unit (not shown), is configured for acquisition original image; Amending image unit (not shown), is configured for and original image is modified to pre-sizing using as picture material.Wherein, above-mentioned amendment includes but not limited to following at least one item: image-region is selected, pixel is compressed etc.Alternatively, when original image is Streetscape picture (Streetscape picture in such as panorama sketch), this Streetscape picture may be the image comprising fish-eye image.The details of picture may be lost to the direct compression of this Streetscape picture or cause edge distortion.Now, picture material generation module can also comprise: image conversion unit (not shown), is configured for and original image is first mapped to spherical model Shang Zai back projection in plane; Converted image amendment unit (not shown), is configured for and is modified to pre-sizing using as picture material to back projection to the original image in plane.
It will be understood by those skilled in the art that the device 600 of above-mentioned generation mosaic image also comprises some other known features, such as processor, storeies etc., in order to unnecessarily fuzzy embodiment of the present disclosure, these known structures are not shown in figure 6.
Module involved in the embodiment of the present application or unit can be realized by the mode of software, also can be realized by the mode of hardware.Described module or unit also can be arranged within a processor, such as, can be described as: a kind of processor comprises division module, extraction module, vector table acquisition module, position acquisition module, address acquisition module and generation module.Wherein, the title of these modules does not form the restriction to this module itself under certain conditions, such as, divides module and can also be described to " being configured for the module of image block target image being divided into multiple pre-sizing ".
As another aspect, present invention also provides a kind of computer-readable recording medium, this computer-readable recording medium can be the computer-readable recording medium comprised in device described in above-described embodiment; Also can be individualism, be unkitted the computer-readable recording medium allocated in terminal.Described computer-readable recording medium stores more than one or one program, and described program is used for performance description in the method for the generation mosaic image of the application by one or more than one processor.
More than describe and be only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art are to be understood that, invention scope involved in the application, be not limited to the technical scheme of the particular combination of above-mentioned technical characteristic, also should be encompassed in when not departing from described inventive concept, other technical scheme of being carried out combination in any by above-mentioned technical characteristic or its equivalent feature and being formed simultaneously.The technical characteristic that such as, disclosed in above-mentioned feature and the application (but being not limited to) has similar functions is replaced mutually and the technical scheme formed.
Claims (17)
1. generate a method for mosaic image, it is characterized in that, comprising:
Target image is divided into the image block of multiple pre-sizing;
Image block characteristics vector is extracted to each image block;
Obtain and material database characteristic of correspondence vector table, wherein, described proper vector table is for storing the material proper vector of each picture material in described material database;
For each image block characteristics vector, obtain the memory location of material proper vector in described proper vector table matched;
Based on the corresponding relation of described picture material and described material proper vector, obtain the memory address of corresponding picture material according to described memory location;
According to each memory address, obtain corresponding picture material and generate mosaic image.
2. method according to claim 1, is characterized in that, described for each image block characteristics vector, obtains the memory location of material proper vector in described proper vector table matched and comprises:
Obtain the index structure of described proper vector table, wherein, described index structure is used for when retrieving each material proper vector, provides sorted order and the memory location of material proper vector in described proper vector table;
For each image block characteristics vector, the material proper vector going out to match from described proper vector table search according to described index structure;
The mated memory location of each material proper vector in described proper vector table is obtained from described index structure.
3. method according to claim 2, is characterized in that, described index structure is generated by following steps:
Described proper vector table is split according to the neighbor relationships of each material proper vector, and spanning tree structure;
Each material proper vector corresponding in described tree construction is replaced to generate the index structure of described proper vector table with the memory location of each material proper vector in described proper vector table.
4. method according to claim 1, is characterized in that, the described corresponding relation based on described picture material and described material proper vector, and the memory address obtaining corresponding picture material according to described memory location comprises:
Obtain the mapping relations of the memory address of described picture material in the storage file of the described material database material proper vector memory location in proper vector table corresponding with described picture material;
Based on described mapping relations, obtain the memory address of corresponding picture material in the storage file of described material database according to described memory location.
5. method according to claim 4, is characterized in that, described according to each memory address, obtains corresponding picture material and generate mosaic image to comprise:
Read described storage file;
In described storage file, corresponding picture material is obtained respectively according to each memory address;
Each image block corresponding in described target image is replaced to generate mosaic image with each picture material obtained.
6., according to described method arbitrary in claim 1-5, it is characterized in that, described target image is divided into the image block of multiple pre-sizing before, also comprise:
Obtain image;
Judge that the pixel size of described image is whether within the scope of the pixel size preset;
If the pixel size of described image is not within the scope of the pixel size preset, the pixel size of described image is adjusted within the scope of default pixel size using as target image.
7., according to the arbitrary described method of claim 1-5, it is characterized in that, described method also comprises:
Obtain original image;
The image described original image being modified as pre-sizing is using as picture material, and wherein, described amendment comprises following at least one item: image-region is selected, pixel compression.
8. method according to claim 7, is characterized in that, the described image described original image being modified as pre-sizing is also to comprise as picture material:
Described original image is first mapped to spherical model Shang Zai back projection in plane;
Image back projection being modified as pre-sizing to the original image in plane is using as picture material.
9. method according to claim 7, is characterized in that, also comprises:
Picture material classification is stored in multiple material database, for user, material database is selected.
10. generate a device for mosaic image, it is characterized in that, comprising:
Divide module, be configured for image block target image being divided into multiple pre-sizing;
Extraction module, is configured for and extracts image block characteristics vector to each image block;
Vector table acquisition module, be configured for and obtain and material database characteristic of correspondence vector table, wherein, described proper vector table is for storing the material proper vector of each picture material in described material database;
Position acquisition module, is configured for for each image block characteristics vector, obtains the memory location of material proper vector in described proper vector table matched;
Address acquisition module, based on the corresponding relation of described picture material and described material proper vector, obtains the memory address of corresponding picture material according to described memory location;
Generation module, is configured for according to each memory address, obtains corresponding picture material and generates mosaic image.
11. devices according to claim 1, is characterized in that, described position acquisition module also comprises:
Index structure acquiring unit, be configured for the index structure obtaining described proper vector table, wherein, described index structure is used for when retrieving each material proper vector, provides sorted order and the memory location of material proper vector in described proper vector table;
Retrieval unit, is configured for for each image block characteristics vector, the material proper vector going out to match from described proper vector table search according to described index structure;
Memory location acquiring unit, is configured for and obtains the mated memory location of each material proper vector in described proper vector table from described index structure.
12. devices according to claim 11, is characterized in that, described position acquisition module also comprises index structure generation unit, is configured for:
Described proper vector table is split according to the neighbor relationships of each material proper vector, and spanning tree structure;
Each material proper vector corresponding in described tree construction is replaced to generate the index structure of described proper vector table with the memory location of each material proper vector in described proper vector table.
13. devices according to claim 10, is characterized in that, described address acquisition module also comprises:
Mapping relations acquiring unit, is configured for and obtains the memory address of described picture material in the storage file of the described material database material proper vector mapping relations in proper vector table corresponding with described picture material;
Memory address acquiring unit, is configured for based on described mapping relations, obtains the memory address of corresponding picture material in the storage file of described material database according to described memory location.
14. devices according to claim 13, is characterized in that, described generation module also comprises:
Reading unit, is configured for and reads described storage file;
Material obtaining unit, is configured for and in described storage file, obtains corresponding picture material according to each memory address respectively;
Replacement unit, is configured for and replaces each image block generation mosaic image corresponding in described target image with each picture material obtained.
15. according to described device arbitrary in claim 10-14, and it is characterized in that, also comprise screening module, described screening module comprises:
Image acquisition unit, is configured for acquisition image;
Pixel size judging unit, be configured for judge described image pixel size whether within the scope of the pixel size preset;
Pixel size adjustment unit, if the pixel size being configured for described image is not within the scope of the pixel size preset, adjusts to the pixel size of described image within the scope of default pixel size using as target image.
16. according to the arbitrary described device of claim 10-14, and it is characterized in that, described device also comprises picture material generation module, and described picture material generation module comprises:
Original image acquiring unit, is configured for acquisition original image;
Amending image unit, be configured for and described original image be modified to pre-sizing using as picture material, wherein, described amendment comprises following at least one item: image-region is selected, pixel compression.
17. devices according to claim 16, is characterized in that, picture material generation module also comprises:
Image conversion unit, is configured for and described original image is first mapped to spherical model Shang Zai back projection in plane;
Converted image amendment unit, is configured for and back projection is modified to pre-sizing using as picture material to the original image in plane.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510149873.3A CN104715449A (en) | 2015-03-31 | 2015-03-31 | Method and device for generating mosaic image |
| JP2016560518A JP2017520036A (en) | 2015-03-31 | 2015-12-29 | Mosaic image generation method and apparatus |
| PCT/CN2015/099457 WO2016155382A1 (en) | 2015-03-31 | 2015-12-29 | Mosaic image generation method and device |
| KR1020167027049A KR101785982B1 (en) | 2015-03-31 | 2015-12-29 | Method and apparatus for generating mosaic image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510149873.3A CN104715449A (en) | 2015-03-31 | 2015-03-31 | Method and device for generating mosaic image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104715449A true CN104715449A (en) | 2015-06-17 |
Family
ID=53414744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510149873.3A Pending CN104715449A (en) | 2015-03-31 | 2015-03-31 | Method and device for generating mosaic image |
Country Status (4)
| Country | Link |
|---|---|
| JP (1) | JP2017520036A (en) |
| KR (1) | KR101785982B1 (en) |
| CN (1) | CN104715449A (en) |
| WO (1) | WO2016155382A1 (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016155382A1 (en) * | 2015-03-31 | 2016-10-06 | 百度在线网络技术（北京）有限公司 | Mosaic image generation method and device |
| CN107133920A (en) * | 2017-06-13 | 2017-09-05 | 华侨大学 | A kind of automatic generation method of the mosaic of view-based access control model feature |
| CN107767340A (en) * | 2017-10-26 | 2018-03-06 | 厦门理工学院 | The synthesis preparation method of electronic photo |
| CN108010102A (en) * | 2017-12-19 | 2018-05-08 | 刘邵宏 | Mosaic image generation method, device, terminal device and storage medium |
| CN109325170A (en) * | 2018-08-06 | 2019-02-12 | 江西清华泰豪三波电机有限公司 | Material method for pushing and device |
| CN110390637A (en) * | 2019-07-18 | 2019-10-29 | 天津塔米智能科技有限公司 | A kind of mosaic image generation method, device, equipment and storage medium |
| WO2019216824A1 (en) * | 2018-05-11 | 2019-11-14 | Brickzle Pte. Ltd. | Method and system for optimizing the fabrication of mosaic artwork and assembly thereof |
| CN110688962A (en) * | 2019-09-29 | 2020-01-14 | 武汉秀宝软件有限公司 | Face image processing method, user equipment, storage medium and device |
| CN110891195A (en) * | 2019-11-22 | 2020-03-17 | 腾讯科技（深圳）有限公司 | Method, device and equipment for generating screen image and storage medium |
| CN111782849A (en) * | 2019-11-27 | 2020-10-16 | 北京沃东天骏信息技术有限公司 | Image retrieval method and device |
| CN111986089A (en) * | 2020-08-28 | 2020-11-24 | 计易数据科技(上海)有限公司 | Image storage and comparison method, device, equipment and medium with characteristic value being integer |
| CN113868440A (en) * | 2020-06-30 | 2021-12-31 | 华为技术有限公司 | Method, device, equipment and medium for managing feature library |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102241486B1 (en) * | 2019-02-14 | 2021-05-17 | 엔에이치엔 주식회사 | Method that provides and creates mosaic image based on image tag-word |
| CN111353532A (en) * | 2020-02-26 | 2020-06-30 | 北京三快在线科技有限公司 | Image generation method and device, computer-readable storage medium and electronic device |
| CN112308036A (en) * | 2020-11-25 | 2021-02-02 | 杭州睿胜软件有限公司 | Bill identification method and device and readable storage medium |
| CN114040223B (en) * | 2021-11-05 | 2023-11-24 | 亿咖通(湖北)技术有限公司 | Image processing method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101706793A (en) * | 2009-11-16 | 2010-05-12 | 中兴通讯股份有限公司 | Method and device for searching picture |
| CN101739697A (en) * | 2008-11-25 | 2010-06-16 | 王源源 | Synthesis method of picture mosaic pattern and system therefor |
| CN102609894A (en) * | 2012-01-14 | 2012-07-25 | 暨南大学 | Synthetic method for mosaic image and device thereof |
| CN103049755A (en) * | 2012-12-28 | 2013-04-17 | 合一网络技术(北京)有限公司 | Method and device for realizing dynamic video mosaic |
| CN103678661A (en) * | 2013-12-24 | 2014-03-26 | 中国联合网络通信集团有限公司 | Image searching method and terminal |
| CN103729430A (en) * | 2013-12-26 | 2014-04-16 | 北京京东尚科信息技术有限公司 | Method and device for generating image files |
| CN103927387A (en) * | 2014-04-30 | 2014-07-16 | 成都理想境界科技有限公司 | Image retrieval system, method and device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08110912A (en) * | 1994-10-07 | 1996-04-30 | Canon Inc | Device and method for retrieving moving image |
| JP2000090092A (en) * | 1998-09-08 | 2000-03-31 | Canon Inc | System, device and method for processing image and storage medium |
| JP2000089991A (en) * | 1998-09-09 | 2000-03-31 | Fujitsu Ltd | Document management system |
| JP4355535B2 (en) * | 2003-08-07 | 2009-11-04 | 株式会社岩根研究所 | 360 degree image conversion processing device |
| CN102831593A (en) * | 2012-07-23 | 2012-12-19 | 陈华 | Digital picture splicing system and method for carrying out mosaic picture splicing by using system |
| US9058673B2 (en) * | 2013-03-15 | 2015-06-16 | Oracle International Corporation | Image mosaicking using a virtual grid |
| CN104715449A (en) * | 2015-03-31 | 2015-06-17 | 百度在线网络技术（北京）有限公司 | Method and device for generating mosaic image |
-
2015
- 2015-03-31 CN CN201510149873.3A patent/CN104715449A/en active Pending
- 2015-12-29 KR KR1020167027049A patent/KR101785982B1/en active IP Right Grant
- 2015-12-29 JP JP2016560518A patent/JP2017520036A/en active Pending
- 2015-12-29 WO PCT/CN2015/099457 patent/WO2016155382A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739697A (en) * | 2008-11-25 | 2010-06-16 | 王源源 | Synthesis method of picture mosaic pattern and system therefor |
| CN101706793A (en) * | 2009-11-16 | 2010-05-12 | 中兴通讯股份有限公司 | Method and device for searching picture |
| CN102609894A (en) * | 2012-01-14 | 2012-07-25 | 暨南大学 | Synthetic method for mosaic image and device thereof |
| CN103049755A (en) * | 2012-12-28 | 2013-04-17 | 合一网络技术(北京)有限公司 | Method and device for realizing dynamic video mosaic |
| CN103678661A (en) * | 2013-12-24 | 2014-03-26 | 中国联合网络通信集团有限公司 | Image searching method and terminal |
| CN103729430A (en) * | 2013-12-26 | 2014-04-16 | 北京京东尚科信息技术有限公司 | Method and device for generating image files |
| CN103927387A (en) * | 2014-04-30 | 2014-07-16 | 成都理想境界科技有限公司 | Image retrieval system, method and device |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016155382A1 (en) * | 2015-03-31 | 2016-10-06 | 百度在线网络技术（北京）有限公司 | Mosaic image generation method and device |
| CN107133920A (en) * | 2017-06-13 | 2017-09-05 | 华侨大学 | A kind of automatic generation method of the mosaic of view-based access control model feature |
| CN107133920B (en) * | 2017-06-13 | 2021-07-30 | 华侨大学 | Automatic mosaic generation method based on visual features |
| CN107767340A (en) * | 2017-10-26 | 2018-03-06 | 厦门理工学院 | The synthesis preparation method of electronic photo |
| CN108010102B (en) * | 2017-12-19 | 2021-03-05 | 刘邵宏 | Mosaic image generation method and device, terminal equipment and storage medium |
| CN108010102A (en) * | 2017-12-19 | 2018-05-08 | 刘邵宏 | Mosaic image generation method, device, terminal device and storage medium |
| WO2019216824A1 (en) * | 2018-05-11 | 2019-11-14 | Brickzle Pte. Ltd. | Method and system for optimizing the fabrication of mosaic artwork and assembly thereof |
| CN109325170A (en) * | 2018-08-06 | 2019-02-12 | 江西清华泰豪三波电机有限公司 | Material method for pushing and device |
| CN110390637A (en) * | 2019-07-18 | 2019-10-29 | 天津塔米智能科技有限公司 | A kind of mosaic image generation method, device, equipment and storage medium |
| CN110390637B (en) * | 2019-07-18 | 2022-12-13 | 天津塔米智能科技有限公司 | Mosaic image generation method, device, equipment and storage medium |
| CN110688962A (en) * | 2019-09-29 | 2020-01-14 | 武汉秀宝软件有限公司 | Face image processing method, user equipment, storage medium and device |
| CN110688962B (en) * | 2019-09-29 | 2022-05-20 | 武汉秀宝软件有限公司 | Face image processing method, user equipment, storage medium and device |
| CN110891195A (en) * | 2019-11-22 | 2020-03-17 | 腾讯科技（深圳）有限公司 | Method, device and equipment for generating screen image and storage medium |
| CN111782849A (en) * | 2019-11-27 | 2020-10-16 | 北京沃东天骏信息技术有限公司 | Image retrieval method and device |
| CN111782849B (en) * | 2019-11-27 | 2024-03-01 | 北京沃东天骏信息技术有限公司 | Image retrieval method and device |
| CN113868440A (en) * | 2020-06-30 | 2021-12-31 | 华为技术有限公司 | Method, device, equipment and medium for managing feature library |
| CN113868440B (en) * | 2020-06-30 | 2023-06-27 | 华为技术有限公司 | Feature library management method, device, equipment and medium |
| CN111986089A (en) * | 2020-08-28 | 2020-11-24 | 计易数据科技(上海)有限公司 | Image storage and comparison method, device, equipment and medium with characteristic value being integer |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2016155382A1 (en) | 2016-10-06 |
| KR20160130792A (en) | 2016-11-14 |
| KR101785982B1 (en) | 2017-10-18 |
| JP2017520036A (en) | 2017-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104715449A (en) | Method and device for generating mosaic image | |
| CN101894168B (en) | Method and system for layout display of web page of mobile terminal | |
| US20180276882A1 (en) | Systems and methods for augmented reality art creation | |
| CN105323252A (en) | Method and system for realizing interaction based on augmented reality technology and terminal | |
| CN104394422A (en) | Video segmentation point acquisition method and device | |
| CN105898520A (en) | Video frame interception method and device | |
| CN104102678A (en) | Method and device for realizing augmented reality | |
| US20150286364A1 (en) | Editing method of the three-dimensional shopping platform display interface for users | |
| CN102693553B (en) | Method and device for creating charts achieving three-dimensional effect | |
| CN106897295B (en) | Hadoop-based power transmission line monitoring video distributed retrieval method | |
| CN109002452B (en) | Map tile updating method and device and computer readable storage medium | |
| CN104281864A (en) | Method and equipment for generating two-dimensional codes | |
| CN104331515B (en) | A kind of method and system for automatically generating tourism diary | |
| US20240038274A1 (en) | 3d media elements in 2d video | |
| CN105117399A (en) | Image search method and device | |
| CN110070616A (en) | Memory, statistical data rendering method, device and equipment based on GIS platform | |
| WO2023193521A1 (en) | Video inpainting method, related apparatus, device and storage medium | |
| CN105531740A (en) | Expanding a digital representation of a physical plane | |
| Kerim et al. | NOVA: Rendering virtual worlds with humans for computer vision tasks | |
| CN104133845A (en) | Multimedia information display method and multimedia information display processing equipment | |
| CN108388636A (en) | Streetscape method for retrieving image and device based on adaptive segmentation minimum enclosed rectangle | |
| KR102572415B1 (en) | Method and apparatus for creating a natural three-dimensional digital twin through verification of a reference image | |
| CN117112090A (en) | Business page theme generation method, device, computer equipment, medium and product | |
| CN106875480B (en) | Method for organizing urban three-dimensional data | |
| CN114820988A (en) | Three-dimensional modeling method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150617 |