CN106339479A - Picture naming method and terminal - Google Patents
Picture naming method and terminal Download PDFInfo
- Publication number
- CN106339479A CN106339479A CN201610777038.9A CN201610777038A CN106339479A CN 106339479 A CN106339479 A CN 106339479A CN 201610777038 A CN201610777038 A CN 201610777038A CN 106339479 A CN106339479 A CN 106339479A
- Authority
- CN
- China
- Prior art keywords
- picture
- named
- pictures
- information
- classification
- 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- Withdrawn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
Classifications
-
- 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
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Library & Information Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a picture naming method and a terminal, wherein the method comprises the following steps of obtaining a picture to be named; performing integral contour division on the picture to be named so as to generate one or a plurality of contours; recognizing a main contour from the contour according to a preset recognition rule; generating the main contour recognition information according to the recognized main contour; matching the main contour recognition information and the pre-stored picture set recognition information to obtain the category of a picture to be processed, wherein a pre-stored picture set comprises a plurality of categories, and each category corresponds to one piece of recognition information; finding a similar picture from the classified picture of the pre-stored picture set; if the similar picture is found, obtaining tag information of the similar picture, wherein the tag information is included in the name of the similar picture; naming the picture to be named according to the classified and obtained tag information. According to the embodiment of the invention, the picture to be named is renamed according to the classification and the tag information; the picture retrieval efficiency and the retrieval precision can be improved.
Description
Technical field
The present invention relates to electronic technology field, more particularly, to a kind of picture naming method and terminal.
Background technology
With network technology, memory technology, shooting technology development, the picture that we use in daily life is increasingly
Many, the expression that often can use of such as chatting, sectional drawing, daily take pictures etc..At present people can only by search for whole pictures or
Scanned for according to picture name, or be to be classified according to the Photo folder of acquiescence to check, above-mentioned search method is made
For passive image searching method it will usually due to picture is described inaccurate and the factors such as image link cannot be obtained it is impossible to
Identification is accurately searched for picture, is reduced the accuracy of picture searching.And in the face of great picture amount, this passive
Way of search people can be allowed to search for every time all can expend considerable time and effort during the picture oneself wanted.
The defect of above-mentioned prior art is: when user carries out picture searching, due to not having in the name of picture
With image content related assist in identifying content, need to carry out artificial cognition, the limitation that this allows for picture search process is big,
Time-consuming, inefficient.
Content of the invention
The embodiment of the present invention provides a kind of picture naming method and terminal, and efficiency and the retrieval that can improve picture retrieval are accurate
Really property.
In a first aspect, embodiments providing a kind of picture naming method, the method includes:
Obtain picture to be named and overall profile division is carried out, to generate one or more wheels to described picture to be named
Wide；
Main outline is identified from profile according to default recognition rule；
Main outline identification information is generated according to the described main outline identifying；
Main outline identification information and the identification information of the pictures that prestore are carried out mate and obtain dividing of described pending picture
Class, the described pictures that prestore include multiple classifications, and each classification corresponds to an identification information；
Similar pictures are searched from the picture of the described classification of the described pictures that prestore；
If finding similar pictures, obtain the label information of described similar pictures, described label information is contained in described phase
Like in the name of picture；
According to the label information of described classification and acquisition, described picture to be named is named.
Second aspect, embodiments provides a kind of terminal, and this terminal includes:
Division unit, for obtaining picture to be named and carrying out overall profile division to described picture to be named, to generate
One or more profiles；
Recognition unit, for identifying main outline according to default recognition rule from profile；
Signal generating unit, for generating main outline identification information according to the described main outline identifying；
Matching unit, for main outline identification information and the identification information of the pictures that prestore are carried out mating obtain described in treat
Process the classification of picture, the described pictures that prestore include multiple classifications, each classification corresponds to an identification information；
First searching unit, for searching similar pictures from the picture of the described classification of the described pictures that prestore；
Label acquiring unit, if for finding similar pictures, obtain the label information of described similar pictures, described label
Information is contained in the name of described similar pictures；
First name unit, for ordering to described picture to be named according to the label information of described classification and acquisition
Name.
The embodiment of the present invention can carry out specification name to picture by said method and terminal, decreases in identification process
Manual intervention, fast and accurately can automatically carry out picture searching identification, especially when in the face of great picture amount, can carry
The work efficiency of high picture searching.
Brief description
In order to be illustrated more clearly that embodiment of the present invention technical scheme, required use in embodiment being described below
Accompanying drawing be briefly described it should be apparent that, drawings in the following description are some embodiments of the present invention, general for this area
For logical technical staff, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of picture naming method provided in an embodiment of the present invention；
Fig. 2 is a kind of schematic flow sheet of picture naming method that another embodiment of the present invention provides；
Fig. 3 to Fig. 5 is the picture searching interface schematic diagram in another embodiment of the present invention；
Fig. 6 is with respect to the difference schematic flow sheet in Fig. 1 of the present invention；
Fig. 7 is with respect to another difference schematic flow sheet in Fig. 1 of the present invention；
Fig. 8 is a kind of structural representation of terminal provided in an embodiment of the present invention；
Fig. 9 is a kind of structural representation of terminal that another embodiment of the present invention provides；
Figure 10 is with respect to the difference structural representation in Fig. 8 of the present invention；
Figure 11 is with respect to another difference structural representation in Fig. 8 of the present invention；
Figure 12 is the structural representation of the householder methods system based on picture searching provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation description is it is clear that described embodiment a part of embodiment that is the present invention, rather than whole embodiments.Based on this
Embodiment in bright, the every other enforcement that those of ordinary skill in the art are obtained under the premise of not making creative work
Example, broadly falls into the scope of protection of the invention.
It should be appreciated that when using in this specification and in the appended claims, term " inclusion " and "comprising" indicate
The presence of described feature, entirety, step, operation, element and/or assembly, but it is not precluded from one or more of the other feature, whole
Body, step, operation, the presence of element, assembly and/or its set or interpolation.It is also understood that in this description of the invention institute
The term using is not intended to limit the present invention merely for the sake of the purpose of description specific embodiment.As in description of the invention
As used in appended claims, unless context clearly indicates other situations, otherwise singulative
" one ", " one " and " being somebody's turn to do " are intended to including plural form.It will be further appreciated that, will in description of the invention and appended right
Term "and/or" used in book is asked to refer to any combinations of one or more of the associated item listed and be possible to
Combination, and include these combinations.
Referring to Fig. 1, embodiments provide a kind of picture naming method, the method includes:
Step s101: obtain picture to be named and overall profile division is carried out, to generate one to described picture to be named
Or multiple profile.
Step s102: main outline is identified from profile according to default recognition rule.
Step s103: main outline identification information is generated according to the described main outline identifying.
Step s104: main outline identification information and the identification information of the pictures that prestore are carried out mating obtain described pending
The classification of picture, the described pictures that prestore include multiple classifications, and each classification corresponds to an identification information.
Step s105: search similar pictures from the picture of the described classification of the described pictures that prestore.
Step s106: if finding similar pictures, obtain the label information of described similar pictures, described label information comprises
In the name of described similar pictures.
Step s107: described picture to be named is named according to the label information of described classification and acquisition.
As can be seen here, the embodiment of the present invention is passed through to obtain picture to be named and carry out overall profile to described picture to be named
Divide, to generate one or more profiles, judgement is made a distinction with the body matter to picture, so that the identification to picture
More accurate.Furthermore, main outline is identified from profile according to default recognition rule, is given birth to according to the described main outline identifying
Become main outline identification information, main outline identification information and the identification information of the pictures that prestore are carried out mating obtain described pending
The classification of picture, the described pictures that prestore include multiple classifications, and each classification corresponds to an identification information；From the described picture that prestores
Similar pictures are searched in the picture of described classification of collection；If finding similar pictures, obtain the label information of described similar pictures,
Described label information is contained in the name of described similar pictures；Awaited orders to described according to the label information of described classification and acquisition
Name picture is named.Said process can decrease the manual intervention in identification process by carrying out Classification And Nomenclature to picture,
Fast and accurately can automatically carry out picture searching identification, especially when in the face of great picture amount, picture searching can be improved
Work efficiency.
Referring to Fig. 2, another embodiment of the present invention provides a kind of picture naming method, and the method includes:
Step s201: obtain picture to be named and overall profile division is carried out, to generate one to described picture to be named
Or multiple profile.
Wherein, the acquisition of picture to be named can be utilized and cut using the picture of camera function acquisition or user
The picture that screen function obtains, can also be that user utilizes the picture that picture download function obtains, in addition, treating described in the present embodiment
Name picture can also be and generates picture by mapping software, those skilled in the art and for can as needed and terminal unit
Function be configured, the embodiment of the present invention is not construed as limiting to this.
Also have be exactly, according to corner angle show things in picture name or darkness join etc. treat name picture carry out whole
Body profile divides, for example, can be profile, profile of the profile of landscape, the profile of object and font of personage etc..
Step s202: main outline is identified from profile according to default recognition rule.
Wherein, default recognition rule can be specifically, when in a picture to be named, existing character contour, and there is wind again
During scape profile, if the area percentage shared by character contour is more than the area percentage shared by landscape profile, determine that personage takes turns
Wide is main outline.It is of course also possible to main outline is determined according to the position of each profile, in addition can also be rational according to remaining
Method is used for determining main outline.Determine that main outline is classified in order to more precisely treat name picture, improve picture
The efficiency joined.
Step s203: main outline identification information is generated according to the described main outline identifying.
Step 204: main outline identification information and the identification information of the pictures that prestore are carried out mating obtain described pending
The classification of picture, the described pictures that prestore include multiple classifications, and each classification corresponds to an identification information.
Wherein, the identification information of pictures of prestoring mainly includes the outline identification information that prestores, will lead in identification process
Outline identification information is compared with the outline identification information prestoring prestoring in pictures and is mated, and can treat name picture and enter
Row classification, the pictures that specifically prestore include four big classifications, such as personage's type, landscape type, object type and font type, and
Personage then corresponds to character contour identification information, and landscape then corresponds to landscape outline identification information, and object then corresponds to object outline identification
Information, font corresponds to character contour identification information.When main outline identification information and the character contour prestoring prestoring in pictures
When identification information matches, that is, judge the image content of this picture to be named as figure kind's type.When main outline identification information and in advance
Deposit in pictures prestore landscape outline identification information match when, that is, judge the image content of this picture to be named as landscape
Type.When main outline identification information is matched with the contour of object identification information prestoring prestoring in pictures, that is, judging should
Image content to be named is object type.When main outline identification information and the text profile identification letter prestoring prestoring in pictures
During manner of breathing coupling, that is, judge the content of this picture to be named as literal type.
Step s205: search similar pictures from the picture of the described classification of the described pictures that prestore.
The classification of picture to be named then obtains in the picture of this classification from the pictures that prestore after determining and treats name figure
The similar picture of piece.As when when naming picture to be figure kind's type, then identified in picture to be named by face recognition technology
Personage, obtains the identification information of personage in representative picture, finds the picture with its human face similarity.
Face recognition technology, is a kind of biological identification technology that facial feature information based on people carries out identification.With
Video camera or the photographic head image containing face for the collection or video flowing, and automatic detect and track face in the picture, so right
The face detecting carries out a series of correlation techniques of face, generally also referred to as Identification of Images, facial recognition.Face recognition technology
Mainly include four ingredients, be respectively as follows: man face image acquiring and detection, facial image pretreatment, facial image feature carry
Take and mate and identification.Recognition of face needs the related data of a large amount of facial images that accumulation collects, for verification algorithm,
Improve constantly identification accuracy.
Man face image acquiring and the main inclusion of detection, obtain character image, accurate calibration goes out face in the picture simultaneously
Position and size.The pattern feature very abundant comprising in facial image, such as histogram feature, color characteristic, template characteristic, knot
Structure feature and haar feature etc..Face datection is exactly that information useful among these is picked out, and realizes people using these features
Face detects.
Facial image pretreatment mainly includes, and the Image semantic classification for face is based on Face datection result, to image
Processed and finally served the process of feature extraction.The original image that system obtains due to being limited by various conditions and
Random disturbances, tend not to direct use it is necessary to the commitment in image procossing carries out gray correction, noise filtering etc. to it
Image semantic classification.For facial image, its preprocessing process mainly include the light compensation of facial image, greyscale transformation,
Histogram equalization, normalization, geometric correction, filtering and sharpening etc..
Facial image feature extraction mainly includes, and face characteristic extracts and is aiming at what some features of face were carried out.People
Face feature extraction, also referred to as face characterize, and it is the process that face is carried out with feature modeling.The method that face characteristic extracts is concluded
To be divided into two big class: one kind is Knowledge based engineering characterizing method；Another is the sign based on algebraic characteristic or statistical learning
Method.Facial image feature is generally divided into visual signature, pixels statisticses feature, facial image conversion coefficient feature, facial image
Algebraic characteristic etc..
Equally, the picture to the picture of landscape type, the picture of object type and literal type, all by image recognition
Technology carries out contrast coupling, thus obtaining corresponding similar pictures.
Treat after name picture is classified and obtain similar pictures again, can not only be easy-to-look-up, and can utilize
The existing pictures that prestore realize quickly contrast coupling.
Step s206: if finding similar pictures, obtain the label information of described similar pictures, described label information comprises
In the name of described similar pictures.
Step s207: obtain the generation time of picture to be named, by described classification, label information and temporal information according to pre-
If rule carries out the name of picture to be named described in arrangement form.
Wherein, the generation time of picture to be named picture generally to be named from information.
When, after naming picture to be confirmed as personage's type, contrast in the picture of classification in the pictures that can prestore is mated,
Carry out face search identification, thus obtaining corresponding label information, i.e. people information.If finding corresponding label information,
This picture to be named is carried out with the name of appropriate section, further can attach the generation of picture to be named in name
Time.
For example, when when naming the main outline in picture to be character contour, according to people in recognition of face, with the pictures that prestore
Picture inside species type carries out contrast coupling, finds similar pictures, obtains the label information of described similar pictures, then can root
Label information according to personage's type and acquisition is named to described picture to be named.
And when obtaining after naming the generation time of picture, can be pressed according to described classification, label information and temporal information
Carry out the name of picture to be named described in arrangement form according to preset rules.Specifically, preset rules therein can for " classification/
Content/time ", such as, when the label information of the picture of personage's type is " Obama ", is then named as " personage Ao Ba
Horse 20****** "；When personage's type the label information of picture be unknown when, then can be named as that " personage is unknown
20******”.
And when when naming picture to be landscape type, according to picture recognition technology and the name of above-mentioned personage's type picture
Method understand, when a landscape type picture label information be " Great Wall at Badaling " " Chinese " " Beijing " when, then by it
It is named as " landscape BeiJing, China Great Wall at Badaling 20****** ".The rest may be inferred, if the label information of the picture of object type is
When " toothbrush ", then it is named as " object toothbrush 20****** ".If the label information of the picture of a literal type is picture
In content, namely when " I recognizes that I is not intended to put you and walks but you must not me all the time ", be then named as " word I hold
Recognize me and be not intended to put you to walk but you all the time must not my 20****** ".
Above-mentioned name can effectively improve follow-up picture searching efficiency, reduce idle work, can also improve inspection simultaneously
The accuracy of rope.
Step s208: generate corresponding index information, described index information is used for subsequently according to classification and label information
It is indexed.
Specifically picture searching interface shown in visible Fig. 3 to Fig. 5.Picture searching interface shown in Figure 3, click on content
During frame, drop-down menu can be ejected, including personage, landscape, object and type options, now be changed into shown in Fig. 4.As subdivision,
Landscape content is also possible to be divided into natural landscape and the places of cultural interest, thus when select landscape option when, menu can eject natural landscape with
And the places of cultural interest two are for selection.
In addition, time frame can be configured to the generation time of picture.When the time, frame was not filled in, default search owns
Time picture.When only filling in a time point, then acquiescence only search to should time point picture.Finally enter shown in Fig. 5, can
Scanned for inputting keyword click search button, in order to obtain Search Results.Not only recall precision is high for the present invention, saves
Time spent by retrieval work, also improve the accuracy rate of retrieval.
Referring to Fig. 6, it is with respect to the difference schematic flow sheet in Fig. 1 of the present invention, with the method in the embodiment shown in Fig. 1
Distinctive points be, the method also includes:
Step s106 ': if not finding similar pictures from the described pictures that prestore, display tag information input frame for
Family input label information.
Step s107 ': if receiving the label information of user input, according to the label information of described classification and user input
Described picture to be named is named.
Such as, its name preset rules can be " classification/content ", when personage's type picture fail from described pre-
When depositing pictures and not finding similar pictures, then can be named as " personage is unknown ".When landscape type picture fail
When the described pictures that prestore do not find similar pictures, then can be named as " landscape is unknown ".When object type
Picture fails when the described pictures that prestore do not find similar pictures, then can be named as " object is unknown ".Work as word
Type picture fail when the described pictures that prestore do not find similar pictures, then can be named as that " word is not
Know ".Can certainly be named according to user's use habit.
Referring to Fig. 7, it is with respect to another difference schematic flow sheet in Fig. 1 of the present invention, in the embodiment shown in Fig. 1
The distinctive points of method are, the method also includes:
Step s106 ": if not finding similar pictures from the described pictures that prestore, display lookup input frame is defeated for user
Enter look-up command.
Step s107 ": if receiving the look-up command of user input, searching from the webserver and treating name figure with described
The similar picture of piece.
Wherein, the classification of the picture in the webserver is corresponding consistent with the classification of the picture in default pictures.
Step s108 ": extract label information from the picture finding.
Step s109 ": described picture is named according to the label information extracting and described classification.
Referring to Fig. 8, it is a kind of schematic block diagram of terminal provided in an embodiment of the present invention.
Embodiments provide a kind of terminal, this terminal 100 includes:
Division unit 101, for obtaining picture to be named and carrying out overall profile division to described picture to be named, with life
Become one or more profiles；
Recognition unit 102, for identifying main outline according to default recognition rule from profile；
Signal generating unit 103, for generating main outline identification information according to the described main outline identifying；
Matching unit 104, obtains institute for carrying out mating with the identification information of the pictures that prestore to main outline identification information
State the classification of pending picture, the described pictures that prestore include multiple classifications, each classification corresponds to an identification information；
First searching unit 105, for searching similar pictures from the picture of the described classification of the described pictures that prestore；
Label acquiring unit 106, if for finding similar pictures, obtaining the label information of described similar pictures, described
Label information is contained in the name of described similar pictures；
First name unit 107, for carrying out to described picture to be named according to the label information of described classification and acquisition
Name.
Referring to Fig. 9, it is a kind of structural representation of terminal that another embodiment of the present invention provides.
Present invention another kind embodiment provides another kind of terminal, and this terminal 100 includes:
Division unit 201, for obtaining picture to be named and carrying out overall profile division to described picture to be named, with life
Become one or more profiles.
Wherein, the acquisition of picture to be named can be utilized and cut using the picture of camera function acquisition or user
The picture that screen function obtains, can also be that user utilizes the picture that picture download function obtains, in addition, treating described in the present embodiment
Name picture can also be and generates picture by mapping software, those skilled in the art and for can as needed and terminal unit
Function be configured, the embodiment of the present invention is not construed as limiting to this.
Also have be exactly, according to corner angle show things in picture name or darkness join etc. treat name picture carry out whole
Body profile divides, for example, can be profile, profile of the profile of landscape, the profile of object and font of personage etc..
Recognition unit 202, for identifying main outline according to default recognition rule from profile.
Wherein, default recognition rule can be specifically, when in a picture to be named, existing character contour, and there is wind again
During scape profile, if the area percentage shared by character contour is more than the area percentage shared by landscape profile, determine that personage takes turns
Wide is main outline.It is of course also possible to main outline is determined according to the position of each profile, in addition can also be rational according to remaining
Method is used for determining main outline.Determine that main outline is classified in order to more precisely treat name picture, improve picture
The efficiency joined.
Signal generating unit 203, for generating main outline identification information according to the described main outline identifying.
Matching unit 205, obtains institute for carrying out mating with the identification information of the pictures that prestore to main outline identification information
State the classification of pending picture, the described pictures that prestore include multiple classifications, each classification corresponds to an identification information.
Wherein, the identification information of pictures of prestoring mainly includes the outline identification information that prestores, will lead in identification process
Outline identification information is compared with the outline identification information prestoring prestoring in pictures and is mated, and can treat name picture and enter
Row classification, the pictures that specifically prestore include four big classifications, such as personage's type, landscape type, object type and font type, and
Personage then corresponds to character contour identification information, and landscape then corresponds to landscape outline identification information, and object then corresponds to object outline identification
Information, font corresponds to character contour identification information.When main outline identification information and the character contour prestoring prestoring in pictures
When identification information matches, that is, judge the image content of this picture to be named as figure kind's type.When main outline identification information and in advance
Deposit in pictures prestore landscape outline identification information match when, that is, judge the image content of this picture to be named as landscape
Type.When main outline identification information is matched with the contour of object identification information prestoring prestoring in pictures, that is, judging should
Image content to be named is object type.When main outline identification information and the text profile identification letter prestoring prestoring in pictures
During manner of breathing coupling, that is, judge the content of this picture to be named as literal type.
First searching unit 205, for searching similar pictures from the picture of the described classification of the described pictures that prestore.
The classification of picture to be named then obtains in the picture of this classification from the pictures that prestore after determining and treats name figure
The similar picture of piece.As when when naming picture to be figure kind's type, then identified in picture to be named by face recognition technology
Personage, obtains the identification information of personage in representative picture, finds the picture with its human face similarity.
Face recognition technology, is a kind of biological identification technology that facial feature information based on people carries out identification.With
Video camera or the photographic head image containing face for the collection or video flowing, and automatic detect and track face in the picture, so right
The face detecting carries out a series of correlation techniques of face, generally also referred to as Identification of Images, facial recognition.Face recognition technology
Mainly include four ingredients, be respectively as follows: man face image acquiring and detection, facial image pretreatment, facial image feature carry
Take and mate and identification.Recognition of face needs the related data of a large amount of facial images that accumulation collects, for verification algorithm,
Improve constantly identification accuracy.
Man face image acquiring and the main inclusion of detection, obtain character image, accurate calibration goes out face in the picture simultaneously
Position and size.The pattern feature very abundant comprising in facial image, such as histogram feature, color characteristic, template characteristic, knot
Structure feature and haar feature etc..Face datection is exactly that information useful among these is picked out, and realizes people using these features
Face detects.
Facial image pretreatment mainly includes, and the Image semantic classification for face is based on Face datection result, to image
Processed and finally served the process of feature extraction.The original image that system obtains due to being limited by various conditions and
Random disturbances, tend not to direct use it is necessary to the commitment in image procossing carries out gray correction, noise filtering etc. to it
Image semantic classification.For facial image, its preprocessing process mainly include the light compensation of facial image, greyscale transformation,
Histogram equalization, normalization, geometric correction, filtering and sharpening etc..
Facial image feature extraction mainly includes, and face characteristic extracts and is aiming at what some features of face were carried out.People
Face feature extraction, also referred to as face characterize, and it is the process that face is carried out with feature modeling.The method that face characteristic extracts is concluded
To be divided into two big class: one kind is Knowledge based engineering characterizing method；Another is the sign based on algebraic characteristic or statistical learning
Method.Facial image feature is generally divided into visual signature, pixels statisticses feature, facial image conversion coefficient feature, facial image
Algebraic characteristic etc..
Equally, the picture to the picture of landscape type, the picture of object type and literal type, all by image recognition
Technology carries out contrast coupling, thus obtaining corresponding similar pictures.
Treat after name picture is classified and obtain similar pictures again, can not only be easy-to-look-up, and can utilize
The existing pictures that prestore realize quickly contrast coupling.
Label acquiring unit 206, if for finding similar pictures, obtaining the label information of described similar pictures, described
Label information is contained in the name of described similar pictures.
First name unit 207, for carrying out to described picture to be named according to the label information of described classification and acquisition
Name.
Wherein, the generation time of picture to be named picture generally to be named from information.
When, after naming picture to be confirmed as personage's type, contrast in the picture of classification in the pictures that can prestore is mated,
Carry out face search identification, thus obtaining corresponding label information, i.e. people information.If finding corresponding label information,
This picture to be named is carried out with the name of appropriate section, further can attach the generation of picture to be named in name
Time.
For example, when when naming the main outline in picture to be character contour, according to people in recognition of face, with the pictures that prestore
Picture inside species type carries out contrast coupling, finds similar pictures, obtains the label information of described similar pictures, then can root
Label information according to personage's type and acquisition is named to described picture to be named.
And when obtaining after naming the generation time of picture, can be pressed according to described classification, label information and temporal information
Carry out the name of picture to be named described in arrangement form according to preset rules.Specifically, preset rules therein can for " classification/
Content/time ", such as, when the label information of the picture of personage's type is " Obama ", is then named as " personage Ao Ba
Horse 20****** "；When personage's type the label information of picture be unknown when, then can be named as that " personage is unknown
20******”.
And when when naming picture to be landscape type, according to picture recognition technology and the name of above-mentioned personage's type picture
Method understand, when a landscape type picture label information be " Great Wall at Badaling " " Chinese " " Beijing " when, then by it
It is named as " landscape BeiJing, China Great Wall at Badaling 20****** ".The rest may be inferred, if the label information of the picture of object type is
When " toothbrush ", then it is named as " object toothbrush 20****** ".If the label information of the picture of a literal type is picture
In content, namely when " I recognizes that I is not intended to put you and walks but you must not me all the time ", be then named as " word I hold
Recognize me and be not intended to put you to walk but you all the time must not my 20****** ".
Above-mentioned name can effectively improve follow-up picture searching efficiency, reduce idle work, can also improve inspection simultaneously
The accuracy of rope.
Index information signal generating unit 208, for generating corresponding index information, described index information is used for follow-up basis point
Class and label information are indexed.It is specifically shown in the description of above-mentioned Fig. 3 to Fig. 5, here is omitted.
Referring to Figure 10, it is with respect to the difference structural representation in Fig. 8 of the present invention, with the end in the embodiment shown in Fig. 1
The distinctive points at end 100 are, this terminal 100 also includes:
First display unit 106 ', if for not finding similar pictures, display tag information from the described pictures that prestore
Input frame is for user input label information.
Second name unit 107 ', if for the label information receiving user input, defeated according to described classification and user
The label information entering is named to described picture to be named.
Such as, its name preset rules can be " classification/content ", when personage's type picture fail from described pre-
When depositing pictures and not finding similar pictures, then can be named as " personage is unknown ".When landscape type picture fail
When the described pictures that prestore do not find similar pictures, then can be named as " landscape is unknown ".When object type
Picture fails when the described pictures that prestore do not find similar pictures, then can be named as " object is unknown ".Work as word
Type picture fail when the described pictures that prestore do not find similar pictures, then can be named as that " word is not
Know ".Can certainly be named according to user's use habit.
Referring to Figure 11, it is with respect to another difference structural representation in Fig. 8 of the present invention, in the embodiment shown in Fig. 8
The distinctive points of terminal 100 be, this terminal 100 also includes:
Second display unit 106 ", if for not finding similar pictures from the described pictures that prestore, input is searched in display
Frame is for user input look-up command.
Second searching unit 107 ", if for the look-up command receiving user input, from the webserver search with
The similar picture of described picture to be named；Wherein, the picture in the classification of the picture in the webserver and default pictures
Classification is that correspondence is consistent.
Tag extraction unit 108 ", for extracting label information from the picture finding.
3rd name unit 109 ", for being named to described picture according to the label information extracting and described classification.
Referring to Figure 12, it is a kind of terminal schematic block diagram that another embodiment of the present invention provides.The present embodiment as depicted
In terminal may include that one or more processors 301；One or more input equipments 302, one or more outut devices
303 and memorizer 304.Above-mentioned processor 301, input equipment 302, outut device 303 and memorizer 304 pass through bus 305 even
Connect.Memorizer 304 is used for store instruction, and processor 301 is used for executing the instruction of memorizer 302 storage.
Wherein, processor 301 is used for:
Obtain picture to be named and overall profile division is carried out, to generate one or more wheels to described picture to be named
Wide；Main outline is identified from profile according to default recognition rule；Generate main outline according to the described main outline identifying to know
Other information；Main outline identification information and the identification information of the pictures that prestore are carried out mate and obtain dividing of described pending picture
Class, the described pictures that prestore include multiple classifications, and each classification corresponds to an identification information；Prestore described in pictures from described
Similar pictures are searched in the picture of classification；If finding similar pictures, obtain the label information of described similar pictures, described label
Information is contained in the name of described similar pictures；According to the label information of described classification and acquisition, described picture to be named is entered
Row name.
Described processor 301 is additionally operable to, and obtains the generation time of picture to be named, according to described classification and label information
Described picture to be named is named specifically including: described classification, label information and temporal information are entered according to preset rules
The name of picture to be named described in row arrangement form.
If described processor 301 is additionally operable to not find similar pictures from the described pictures that prestore, display tag information is defeated
Enter frame for user input label information；If receiving the label information of user input, according to described classification and user input
Label information is named to described picture to be named.
Described processor 301 is additionally operable to, if not finding similar pictures from the described pictures that prestore, input frame is searched in display
For user input look-up command；If receiving the look-up command of user input, searching from the webserver and awaiting orders with described
The similar picture of name picture；Label information is extracted from the picture finding；Right according to the label information extracting and described classification
Described picture is named.
Described processor 301 is additionally operable to, and generates corresponding index information, described index information be used for follow-up according to classification with
And label information is indexed.
It should be appreciated that in embodiments of the present invention, alleged processor 301 can be CPU (central
Processing unit, cpu), this processor can also be other general processors, digital signal processor (digital
Signal processor, dsp), special IC (application specific integrated circuit,
Asic), ready-made programmable gate array (field-programmable gate array, fpga) or other FPGAs
Device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or this at
Reason device can also be any conventional processor etc..
Input equipment 302 can include Trackpad, fingerprint adopts sensor (for gathering the finger print information of user and fingerprint
Directional information), mike etc., outut device 303 can include display (lcd etc.), speaker etc..
This memorizer 304 can include read only memory and random access memory, and provides instruction to processor 301
Data.The a part of of memorizer 304 can also include nonvolatile RAM.For example, memorizer 304 also may be used
Information with storage device type.
In implementing, processor 301 described in the embodiment of the present invention, input equipment 302, outut device 303 can
Execute the enforcement represented by embodiment, another embodiment and Fig. 6 and Fig. 7 of picture naming method provided in an embodiment of the present invention
Implementation described in example, also can perform the implementation of the terminal described by the embodiment of the present invention, will not be described here.
Those of ordinary skill in the art are it is to be appreciated that combine the list of each example of the embodiments described herein description
Unit and algorithm steps, can be with electronic hardware, computer software or the two be implemented in combination in, in order to clearly demonstrate hardware
With the interchangeability of software, generally describe composition and the step of each example in the above description according to function.This
A little functions to be executed with hardware or software mode actually, the application-specific depending on technical scheme and design constraint.Specially
Industry technical staff can use different methods to each specific application realize described function, but this realization is not
It is considered as beyond the scope of this invention.
Those skilled in the art can be understood that, for convenience of description and succinctly, foregoing description be
The specific work process of system, terminal and unit, may be referred to the corresponding process in preceding method embodiment, will not be described here.
It should be understood that disclosed system, terminal and method in several embodiments provided herein, permissible
Realize by another way.For example, device embodiment described above is only schematically, for example, described unit
Divide, only a kind of division of logic function, actual can have other dividing mode when realizing, for example multiple units or assembly
Can in conjunction with or be desirably integrated into another system, or some features can be ignored, or does not execute.In addition, it is shown or beg for
By coupling each other or direct-coupling or communication connection can be INDIRECT COUPLING by some interfaces, device or unit
Or communication connection or electricity, machinery or other forms connect.
The described unit illustrating as separating component can be or may not be physically separate, show as unit
The part showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected according to the actual needs to realize embodiment of the present invention scheme
Purpose.
In addition, can be integrated in a processing unit in each functional unit in each embodiment of the present invention it is also possible to
It is that unit is individually physically present or two or more units are integrated in a unit.Above-mentioned integrated
Unit both can be to be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If described integrated unit is realized and as independent production marketing or use using in the form of SFU software functional unit
When, can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part in other words prior art being contributed, or all or part of this technical scheme can be in the form of software product
Embody, this computer software product is stored in a storage medium, including some instructions with so that a computer
Equipment (can be personal computer, server, or network equipment etc.) executes the complete of each embodiment methods described of the present invention
Portion or part steps.And aforesaid storage medium includes: u disk, portable hard drive, read only memory (rom, read-only
Memory), random access memory (ram, random access memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The above, the only specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, and any
Those familiar with the art the invention discloses technical scope in, various equivalent modifications can be readily occurred in or replace
Change, these modifications or replacement all should be included within the scope of the present invention.Therefore, protection scope of the present invention should be with right
The protection domain requiring is defined.
Claims (10)
1. a kind of picture naming method is it is characterised in that include:
Obtain picture to be named and overall profile division is carried out, to generate one or more profiles to described picture to be named；
Main outline is identified from profile according to default recognition rule；
Main outline identification information is generated according to the described main outline identifying；
Carry out mating the classification obtaining described pending picture, institute to main outline identification information with the identification information of the pictures that prestore
State the pictures that prestore and include multiple classifications, each classification corresponds to an identification information；
Similar pictures are searched from the picture of the described classification of the described pictures that prestore；
If finding similar pictures, obtain the label information of described similar pictures, described label information is contained in described similar diagram
In the name of piece；
According to the label information of described classification and acquisition, described picture to be named is named.
2. picture naming method according to claim 1 is it is characterised in that methods described also includes obtaining picture to be named
Generation time, according to described classification and label information described picture to be named is named specifically including:
Described classification, label information and temporal information are carried out the life of picture to be named described in arrangement form according to preset rules
Name.
3. picture naming method according to claim 1 is it is characterised in that methods described also includes:
If not finding similar pictures from the described pictures that prestore, display tag information input frame is believed for user input label
Breath；
If receiving the label information of user input, name figure is treated to described according to the label information of described classification and user input
Piece is named.
4. picture naming method according to claim 1 is it is characterised in that methods described also includes:
If not finding similar pictures from the described pictures that prestore, display searches input frame for user input look-up command；
If receiving the look-up command of user input, search the picture similar to described picture to be named from the webserver；
Label information is extracted from the picture finding；
According to the label information extracting and described classification, described picture is named.
5. picture naming method according to any one of claim 1 to 4 it is characterised in that
Described according to classification and after label information is named to described picture name, also include generating and index accordingly
Information, described index information is used for subsequently being indexed according to classification and label information.
6. a kind of terminal is it is characterised in that include:
Division unit, for obtaining picture to be named and carrying out overall profile division to described picture to be named, to generate one
Or multiple profile；
Recognition unit, for identifying main outline according to default recognition rule from profile；
Signal generating unit, for generating main outline identification information according to the described main outline identifying；
Matching unit, for main outline identification information and the identification information of the pictures that prestore are carried out mating obtain described pending
The classification of picture, the described pictures that prestore include multiple classifications, and each classification corresponds to an identification information；
First searching unit, for searching similar pictures from the picture of the described classification of the described pictures that prestore；
Label acquiring unit, if for finding similar pictures, obtain the label information of described similar pictures, described label information
It is contained in the name of described similar pictures；
First name unit, for being named to described picture to be named according to the label information of described classification and acquisition.
7. terminal according to claim 6 is it is characterised in that described terminal also includes:
Time determining unit, for obtaining the generation time of picture to be named, according to described classification and label information to described
Picture to be named is named specifically including:
Described classification, label information and temporal information are carried out the life of picture to be named described in arrangement form according to preset rules
Name.
8. terminal according to claim 6 is it is characterised in that described terminal also includes:
First display unit, if for not finding similar pictures from the described pictures that prestore, display tag information input frame with
For user input label information；
Second name unit, if for the label information receiving user input, according to the label of described classification and user input
Information is named to described picture to be named.
9. terminal according to claim 6 is it is characterised in that described terminal also includes:
Second display unit, if for not finding similar pictures from the described pictures that prestore, display search input frame for
Family inputs look-up command；
Second searching unit, if for the look-up command receiving user input, is searched from the webserver and is awaited orders with described
The similar picture of name picture；
Tag extraction unit, for extracting label information from the picture finding；
3rd name unit, for being named to described picture according to the label information extracting and described classification.
10. the terminal according to any one of claim 6 to 9 it is characterised in that
Index information signal generating unit, for generating corresponding index information, described index information be used for follow-up according to classification and
Label information is indexed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610777038.9A CN106339479A (en) | 2016-08-30 | 2016-08-30 | Picture naming method and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610777038.9A CN106339479A (en) | 2016-08-30 | 2016-08-30 | Picture naming method and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106339479A true CN106339479A (en) | 2017-01-18 |
Family
ID=57823087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610777038.9A Withdrawn CN106339479A (en) | 2016-08-30 | 2016-08-30 | Picture naming method and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106339479A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256216A (en) * | 2017-04-17 | 2017-10-17 | 捷开通讯(深圳)有限公司 | Mobile terminal, the method and storage device for managing picture |
| CN107369196A (en) * | 2017-06-30 | 2017-11-21 | 广东欧珀移动通信有限公司 | Expression, which packs, makees method, apparatus, storage medium and electronic equipment |
| CN108124478A (en) * | 2017-12-05 | 2018-06-05 | 深圳前海达闼云端智能科技有限公司 | Picture searching method and apparatus |
| CN108460095A (en) * | 2018-01-31 | 2018-08-28 | 维沃移动通信有限公司 | The determination method and device of target user |
| CN108763580A (en) * | 2018-06-08 | 2018-11-06 | Oppo广东移动通信有限公司 | Image processing method and device, electronic equipment, computer storage media |
| WO2019109223A1 (en) * | 2017-12-04 | 2019-06-13 | 华为技术有限公司 | Method and device for generating album title |
| WO2020030131A1 (en) * | 2018-08-09 | 2020-02-13 | 中兴通讯股份有限公司 | Image processing method and device and storage medium |
| CN110851630A (en) * | 2019-10-14 | 2020-02-28 | 武汉市慧润天成信息科技有限公司 | Management system and method for deep learning labeled samples |
| CN111291208A (en) * | 2020-05-09 | 2020-06-16 | 支付宝(杭州)信息技术有限公司 | Front-end page element naming method and device and electronic equipment |
| CN111897984A (en) * | 2020-05-28 | 2020-11-06 | 广州市玄武无线科技股份有限公司 | Picture labeling method and device, terminal equipment and storage medium |
| CN112132783A (en) * | 2020-08-21 | 2020-12-25 | 成都飞机工业（集团）有限责任公司 | Part identification method based on digital image processing technology |
| CN117271819A (en) * | 2023-11-17 | 2023-12-22 | 上海闪马智能科技有限公司 | Image data processing method and device, storage medium and electronic device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514231A (en) * | 2012-06-29 | 2014-01-15 | 联想(北京)有限公司 | File naming method and electronic device |
| CN103631819A (en) * | 2012-08-27 | 2014-03-12 | 华为技术有限公司 | Method and system for naming picture |
| CN104572847A (en) * | 2014-12-15 | 2015-04-29 | 广东欧珀移动通信有限公司 | Method and device for naming photo |
| CN105808782A (en) * | 2016-03-31 | 2016-07-27 | 广东小天才科技有限公司 | Picture label adding method and device |
-
2016
- 2016-08-30 CN CN201610777038.9A patent/CN106339479A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514231A (en) * | 2012-06-29 | 2014-01-15 | 联想(北京)有限公司 | File naming method and electronic device |
| CN103631819A (en) * | 2012-08-27 | 2014-03-12 | 华为技术有限公司 | Method and system for naming picture |
| CN104572847A (en) * | 2014-12-15 | 2015-04-29 | 广东欧珀移动通信有限公司 | Method and device for naming photo |
| CN105808782A (en) * | 2016-03-31 | 2016-07-27 | 广东小天才科技有限公司 | Picture label adding method and device |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256216A (en) * | 2017-04-17 | 2017-10-17 | 捷开通讯(深圳)有限公司 | Mobile terminal, the method and storage device for managing picture |
| CN107369196A (en) * | 2017-06-30 | 2017-11-21 | 广东欧珀移动通信有限公司 | Expression, which packs, makees method, apparatus, storage medium and electronic equipment |
| CN110178130B (en) * | 2017-12-04 | 2021-08-13 | 华为技术有限公司 | Method and equipment for generating photo album title |
| WO2019109223A1 (en) * | 2017-12-04 | 2019-06-13 | 华为技术有限公司 | Method and device for generating album title |
| CN110178130A (en) * | 2017-12-04 | 2019-08-27 | 华为技术有限公司 | A kind of method and apparatus generating album title |
| CN108124478A (en) * | 2017-12-05 | 2018-06-05 | 深圳前海达闼云端智能科技有限公司 | Picture searching method and apparatus |
| CN108460095A (en) * | 2018-01-31 | 2018-08-28 | 维沃移动通信有限公司 | The determination method and device of target user |
| CN108763580A (en) * | 2018-06-08 | 2018-11-06 | Oppo广东移动通信有限公司 | Image processing method and device, electronic equipment, computer storage media |
| WO2020030131A1 (en) * | 2018-08-09 | 2020-02-13 | 中兴通讯股份有限公司 | Image processing method and device and storage medium |
| CN110851630A (en) * | 2019-10-14 | 2020-02-28 | 武汉市慧润天成信息科技有限公司 | Management system and method for deep learning labeled samples |
| CN112307235A (en) * | 2020-05-09 | 2021-02-02 | 支付宝(杭州)信息技术有限公司 | Front-end page element naming method and device and electronic equipment |
| CN111291208A (en) * | 2020-05-09 | 2020-06-16 | 支付宝(杭州)信息技术有限公司 | Front-end page element naming method and device and electronic equipment |
| WO2021227951A1 (en) * | 2020-05-09 | 2021-11-18 | 支付宝(杭州)信息技术有限公司 | Naming of front-end page element |
| CN112307235B (en) * | 2020-05-09 | 2024-02-20 | 支付宝(杭州)信息技术有限公司 | Naming method and device of front-end page element and electronic equipment |
| CN111897984A (en) * | 2020-05-28 | 2020-11-06 | 广州市玄武无线科技股份有限公司 | Picture labeling method and device, terminal equipment and storage medium |
| CN112132783A (en) * | 2020-08-21 | 2020-12-25 | 成都飞机工业（集团）有限责任公司 | Part identification method based on digital image processing technology |
| CN117271819A (en) * | 2023-11-17 | 2023-12-22 | 上海闪马智能科技有限公司 | Image data processing method and device, storage medium and electronic device |
| CN117271819B (en) * | 2023-11-17 | 2024-03-01 | 上海闪马智能科技有限公司 | Image data processing method and device, storage medium and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106339479A (en) | Picture naming method and terminal | |
| US20240070214A1 (en) | Image searching method and apparatus | |
| US11238310B2 (en) | Training data acquisition method and device, server and storage medium | |
| CN106255968B (en) | Natural language image search | |
| US20170351934A1 (en) | Object recognition device, object recognition method, and program | |
| CN110555372A (en) | Data entry method, device, equipment and storage medium | |
| US9613296B1 (en) | Selecting a set of exemplar images for use in an automated image object recognition system | |
| CN109829375A (en) | A kind of machine learning method, device, equipment and system | |
| US10489637B2 (en) | Method and device for obtaining similar face images and face image information | |
| CN111275060A (en) | Recognition model updating processing method and device, electronic equipment and storage medium | |
| CN113221918B (en) | Target detection method, training method and device of target detection model | |
| US11600088B2 (en) | Utilizing machine learning and image filtering techniques to detect and analyze handwritten text | |
| CN109522970A (en) | Image classification method, apparatus and system | |
| CN106156794B (en) | Character recognition method and device based on character style recognition | |
| CN106815253B (en) | Mining method based on mixed data type data | |
| WO2022247403A1 (en) | Keypoint detection method, electronic device, program, and storage medium | |
| JP2016103759A (en) | Image processing apparatus, image processing method, and program | |
| JP5755046B2 (en) | Image recognition apparatus, image recognition method, and program | |
| CN108124478A (en) | Picture searching method and apparatus | |
| US20210406595A1 (en) | Automatically generating training data sets for object recognition | |
| JP5413156B2 (en) | Image processing program and image processing apparatus | |
| CN114417860A (en) | Information detection method, device and equipment | |
| CN115546824A (en) | Taboo picture identification method, equipment and storage medium | |
| CN115273177A (en) | Method, device and equipment for recognizing face types of heterogeneous faces and storage medium | |
| CN110472079B (en) | Target image retrieval 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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170118 |
|
| WW01 | Invention patent application withdrawn after publication |