CN105447513A - File ink mark data automation contrast realization method and system thereof - Google Patents
File ink mark data automation contrast realization method and system thereof Download PDFInfo
- Publication number
- CN105447513A CN105447513A CN201510791503.XA CN201510791503A CN105447513A CN 105447513 A CN105447513 A CN 105447513A CN 201510791503 A CN201510791503 A CN 201510791503A CN 105447513 A CN105447513 A CN 105447513A
- Authority
- CN
- China
- Prior art keywords
- data
- characteristic
- value
- correlation
- item
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Abstract
The invention provides a file ink mark data automation contrast realization method. The method comprises the following steps of acquiring characteristic data formed by a file ink mark sample to be detected, wherein the characteristic data comprises light splitting spectrum data, a peak value related to the light splitting spectrum data, fluorescence quantification data, an ultraviolet light quantification data, expansion light quantification data and data formed by characteristic items of color, a type and creation time; selecting a certain time scope in a preset database, acquiring a plurality of contrast data which is the same with a value in a type characteristic item of the characteristic data in time scope, according to a preset contrast mode, comparing the acquired plurality of contrast data with the characteristic data one by one, screening the contrast data whose contrast result satisfies a preset condition as a matching result of the file ink mark sample and outputting. By using the method, rapid, high-efficient and accurate performance is possessed; an error of manual operation can be reduced and screening time is saved.
Description
Technical field
The present invention relates to ink marks authenticate technology field, particularly relate to the method and system that a kind of file ink data realizes contrast automatically.
Background technology
Document forming time is an important content of Forensic science qualification, be also a difficult problem in inspection of document technology, and the screening of file ink sample is the precondition of carrying out document forming time analysis.
In prior art, the screening of file ink sample also needs manually to carry out, on the one hand based on file ink sample classification such as chemical method, spectroscopic methodology, chromatographys, checking procedure is loaded down with trivial details, process is very long, is difficult to be formed distinguish fast, efficiently and accurately, particularly in more complicated case, often need to spend the longer cycle, thus larger impact is caused on the work in later stage; On the other hand, manual operation often causes certain error, also causes serious impact to the qualification work in later stage.In addition, do not form the file ink database in a large number with timeliness, the contrast of the file ink marks of current various kind cannot be met.Often cause and the fubaritic consequence of time case is made to heap file.
Summary of the invention
Embodiment of the present invention technical matters to be solved is, provides a kind of file ink data to realize the method and system of contrast automatically, has quick, efficient and accuracy, can reduce manually-operated error, save screening time.
In order to solve the problems of the technologies described above, embodiments provide a kind of method that file ink data realizes contrast automatically, described method comprises:
A, obtain file ink sample to be checked formed characteristic; Wherein, described characteristic is comprised spectrophotometric spectra data by characteristic item, with the crest value of described spectrophotometric spectra data correlation, fluorescence quantized data, infrared light quantized data, ultraviolet light quantized data, expanded the data that light quantization data, color, type and creation-time formed;
B, preset database in select certain hour scope, obtain multiple correlation datas identical with value in the type feature item of described characteristic in described time range, and according to the way of contrast preset, described multiple correlation data of obtaining and described characteristic are contrasted one by one, filters out comparing result and meet pre-conditioned correlation data and export as the matching result of described file ink sample to be checked.
Wherein, described step b specifically comprises:
In the database preset, select certain hour scope, obtain multiple correlation datas identical with value in the type feature item of described characteristic in described time range;
According to the value of R, G, B in the value of R, G, B in the color characteristic item of the described multiple correlation datas obtained and the color characteristic item of described characteristic, the Color pair ratio that the multiple correlation datas obtained described in calculating are formed with described characteristic respectively, and in the described multiple correlation datas obtained, filter out the correlation data that Color pair ratio is less than or equal to first threshold further;
The matching result of the described correlation data filtered out as described file ink sample to be checked is exported.
Wherein, described the step that the described correlation data filtered out exports as the matching result of described file ink sample to be checked to be comprised further:
According to the spectral reflectivity of spectrophotometric spectra data characteristics item in the spectral reflectivity of spectrophotometric spectra data characteristics item in the described correlation data filtered out and described characteristic, the spectrophotometric spectra Data Comparison value that the correlation data filtered out described in calculating is formed with described characteristic respectively;
According to associating the numerical value associating corresponding crest value characteristic item in the numerical value of corresponding crest value characteristic item and described characteristic with spectrophotometric spectra data item in the described correlation data filtered out with spectrophotometric spectra data item, the crest correlative value that the correlation data filtered out described in calculating is formed with described characteristic respectively;
Quantize fluorescence in the numerical value of data characteristics item and described characteristic according to fluorescence in the described correlation data filtered out and quantize the numerical value of data characteristics item, the fluorescence volume correlative value that the correlation data filtered out described in calculating is formed with described characteristic respectively;
According to the numerical value of the described correlation data mid-infrared light quantized data characteristic item filtered out and the numerical value of described characteristic mid-infrared light quantized data characteristic item, the amount of infrared light correlative value that the correlation data filtered out described in calculating is formed with described characteristic respectively;
According to the numerical value of the described correlation data medium ultraviolet light quantization data characteristics item filtered out and the numerical value of described characteristic medium ultraviolet light quantization data characteristics item, the ultraviolet light quantity correlative value that the correlation data filtered out described in calculating is formed with described characteristic respectively;
According to expanding the numerical value expanding light quantization data characteristics item in the numerical value of light quantization data characteristics item and described characteristic in the described correlation data filtered out, the expansion light quantity correlative value that the correlation data filtered out described in calculating is formed with described characteristic respectively;
In the described correlation data filtered out, obtain that the spectrophotometric spectra Data Comparison value calculated in same correlation data is less than or equal to Second Threshold, crest correlative value is less than or equal to the 3rd threshold value, fluorescence volume correlative value is less than or equal to the 4th threshold value, amount of infrared light correlative value is less than or equal to the 5th threshold value, ultraviolet light quantity correlative value is less than or equal to the 6th threshold value and expansion light quantity correlative value is less than or equal to the correlation data that the 7th threshold value meets simultaneously, and the matching result of the described correlation data got as described file ink sample is exported.
Wherein, described first threshold span is [0,100]; The span of described Second Threshold is [0,0.2]; The span of described 3rd threshold value, the 4th threshold value, the 5th threshold value, the 6th threshold value and the 7th threshold value is [0,0.1].
Wherein, before described step a, described method comprises further:
Build database in advance, and each data, all for being comprised spectrophotometric spectra data by characteristic item, with the crest value of described spectrophotometric spectra data correlation, fluorescence quantized data, infrared light quantized data, ultraviolet light quantized data, expanding the data that light quantization data, color, type and creation-time formed, and to be saved in a storer in time ascending order mode in described database.
Wherein, described method further comprises:
After described multiple correlation data of obtaining and described characteristic contrast one by one, the comparing result of acquisition do not meet described pre-conditioned time, described characteristic is saved in described default database.
The embodiment of the present invention additionally provides the system that a kind of file ink data realizes contrast automatically, and described system comprises:
Acquiring unit, for obtaining the characteristic that file ink marks sample to be checked is formed; Wherein, described characteristic is comprised spectrophotometric spectra data by characteristic item, with the crest value of described spectrophotometric spectra data correlation, fluorescence quantized data, infrared light quantized data, ultraviolet light quantized data, expanded the data that light quantization data, color, type and creation-time formed;
Matching result output unit, for selecting certain hour scope in the database preset, obtain multiple correlation datas identical with value in the type feature item of described characteristic in described time range, and according to the way of contrast preset, described multiple correlation data of obtaining and described characteristic are contrasted one by one, filters out comparing result and meet pre-conditioned correlation data and export as the matching result of described file ink sample to be checked.
Wherein, described matching result output unit comprises:
Type matching module, for selecting certain hour scope in the database preset, obtains multiple correlation datas identical with value in the type feature item of described characteristic in described time range;
Dithering module, for the value of R, G, B in the value of R, G, B in the color characteristic item of multiple correlation datas that obtains described in basis and the color characteristic item of described characteristic, the Color pair ratio that the multiple correlation datas obtained described in calculating are formed with described characteristic respectively, and in the described multiple correlation datas obtained, filter out the correlation data that Color pair ratio is less than or equal to first threshold further;
Matching result output module, for exporting the matching result of the described correlation data filtered out as described file ink sample to be checked.
Wherein, described system also comprises:
Preset unit, for building database in advance, and each data, all for being comprised spectrophotometric spectra data by characteristic item, with the crest value of described spectrophotometric spectra data correlation, fluorescence quantized data, infrared light quantized data, ultraviolet light quantized data, expanding the data that light quantization data, color, type and creation-time formed, and to be saved in a storer in time ascending order mode in described database.
Wherein, described system also comprises:
Updating block, for when described in after multiple correlation data of obtaining and described characteristic contrast one by one, the comparing result of acquisition do not meet described pre-conditioned time, described characteristic is saved in described default database.
Implement the embodiment of the present invention, there is following beneficial effect:
In embodiments of the present invention, because file ink sample forms the characteristic with special characteristic item after treatment, this characteristic can be carried out rapid comparison with the data in database and mate, thus correctly identified, therefore there is quick, efficient and accuracy, manually-operated error can be reduced, save screening time.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, the accompanying drawing obtaining other according to these accompanying drawings still belongs to category of the present invention.
The process flow diagram of the method that a kind of file ink data realization that Fig. 1 provides for the embodiment of the present invention contrasts automatically;
The structural representation of the system that a kind of file ink data realization that Fig. 2 provides for the embodiment of the present invention contrasts automatically.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, the present invention is described in further detail.
As shown in Figure 1, in the embodiment of the present invention, a kind of file ink data provided realizes the method for contrast automatically, and it realizes on the server being provided with matching database, and described method comprises:
Step S1, obtain file ink sample to be checked formed characteristic; Wherein, described characteristic is comprised spectrophotometric spectra data by characteristic item, with the crest value of described spectrophotometric spectra data correlation, fluorescence quantized data, infrared light quantized data, ultraviolet light quantized data, expanded the data that light quantization data, color, type and creation-time formed;
Detailed process is, file ink sample after specific method processes, can generate the characteristic with multiple fixed character item in front end (as client).Because this file ink sample carries out Classification and Identification by point optical wavelength of multiple different length, therefore the characteristic generated can be adopt multiple light splitting wavelength detecting and form one group of data after process, also can be adopt single light splitting wavelength detecting and form data after process.
With single features data instance, the serial data that this characteristic can be formed by formula (1) represents:
Y＝Fgi(i＝1,n)|X(p＝1,m)|Yg|Hwg|Zwg|Qtg|MjColor(R,G,B)|Type|CreateDate(1)；
In formula (1), Y is characteristic, contained by it, characteristic item comprises: spectrophotometric spectra data Fgi (i=1, n), with the critical data (crest value X (p=1 of spectrophotometric spectra data correlation, m)), fluorescence quantized data Yg, infrared light quantized data Hwg, ultraviolet light quantized data Zwg, expansion light quantization data Qtg, color MjColor (R, G, B), type Type and creation-time CreateDate;
Wherein, the data that Fgi (i=1, n) is corresponding are expressed as the spectral value of file ink sample, as adopted point optical wavelength i to identify the spectral reflectivity formed, span be (0,120];
The data that X (p=1, m) is corresponding are expressed as and adopt a point P crest value of optical wavelength i formation, and itself and Fgi (i=1, n) are corresponding;
The data that Yg is corresponding are expressed as the fluorescence quantized data of file ink sample, span be (0,255];
The data that Hwg is corresponding are expressed as the infrared light quantized data of file ink sample, span be (0,255];
The data that Zwg is corresponding are expressed as the ultraviolet light quantized data of file ink sample, span be (0,255];
The data that Qtg is corresponding are expressed as the expansion light quantization data of file ink sample, span be (0,255];
The data that MjColor (R, G, B) is corresponding are expressed as the color value of file ink sample, the span of R, G and B is (0,255];
The data that Type is corresponding are expressed as the type quantification value of file ink sample, span is [0,255], as ball pen ink value be 0, neutral pen ink value is 1, tap water ink value is 2, print that carbon dust value is 03, pad-ink value is 4, stamp-inkpad value is 5, stamp-pad ink value is 6;
The data that CreateDate is corresponding are expressed as the formation date of file ink sample, as 20080101 are expressed as foundation on January 1st, 2008.
In the invention process process, realize the match cognization to current file ink sample, need the database that correlation data is formed, therefore before step S1, described method comprises further: build database in advance, and each data, all for being comprised spectrophotometric spectra data by characteristic item, with the crest value of spectrophotometric spectra data correlation, fluorescence quantized data, infrared light quantized data, ultraviolet light quantized data, expanding the data that light quantization data, color, type and creation-time formed, and to be saved in a storer in time ascending order mode in database.
Step S2, preset database in select certain hour scope, obtain multiple correlation datas identical with value in the type feature item of described characteristic in described time range, and according to the way of contrast preset, described multiple correlation data of obtaining and described characteristic are contrasted one by one, filters out comparing result and meet pre-conditioned correlation data and export as the matching result of described file ink sample.
Detailed process is, step S21, in the database preset, selects certain hour scope, obtains multiple correlation datas identical with value in the type feature item of characteristic in time range;
Step S22, value according to R, G, B in the value of R, G, B in the color characteristic item of multiple correlation datas obtained and the color characteristic item of characteristic, calculate the Color pair ratio that multiple correlation datas of obtaining are formed with characteristic respectively, and in the multiple correlation datas obtained, filter out the correlation data that Color pair ratio is less than or equal to first threshold further;
Step S23, the matching result of the correlation data filtered out as file ink sample to be checked to be exported.
In one embodiment, in the database preset, obtain the N number of correlation data identical with feature data types, the value of R, G, B in the value of R, G, B in the color characteristic item of multiple correlation data and the color characteristic item of characteristic is imported in formula (2), calculate the Color pair ratio that N number of correlation data and characteristic are formed respectively, and in N number of correlation data, obtain the correlation data that K Color pair ratio is less than or equal to first threshold, and further the matching result of K the correlation data obtained as file ink sample to be checked is exported.
C
j＝Sqrt[(R
0-R
j)
2+(G
0-G
j)
2+(B
0-B
j)
2](2)；
In formula (2), C
jfor a jth Color pair ratio; R
0, G
0and B
0be respectively the value of color R in characteristic, G and B; R
j, G
jand B
jbe respectively the value of color R, G and B in a jth correlation data; 1≤j≤N, and be natural number; 1≤K≤N, and be natural number; First threshold span is [0,100].
In embodiments of the present invention, mating more accurately to realize file ink sample to be checked, obtaining the matching result that accuracy is higher, can carry out the screening of more many condition to the matching result exported in step S23, therefore step 23 comprises step further:
Step 231, spectral reflectivity according to spectrophotometric spectra data characteristics item in the spectral reflectivity of spectrophotometric spectra data characteristics item in the correlation data that filters out and characteristic, calculate the spectrophotometric spectra Data Comparison value that the correlation data that filters out is formed with characteristic respectively;
Step 232, according to associating the numerical value associating corresponding crest value characteristic item in the numerical value of corresponding crest value characteristic item and characteristic with spectrophotometric spectra data item in the correlation data that filters out with spectrophotometric spectra data item, calculate the crest correlative value that the correlation data that filters out is formed with characteristic respectively;
In step 233, the numerical value quantizing data characteristics item according to fluorescence in the correlation data that filters out and characteristic, fluorescence quantizes the numerical value of data characteristics item, calculates the fluorescence volume correlative value that the correlation data that filters out is formed with characteristic respectively;
Step 234, according to the numerical value of correlation data mid-infrared light quantized data characteristic item that filters out and the numerical value of characteristic mid-infrared light quantized data characteristic item, calculate the amount of infrared light correlative value that the correlation data that filters out is formed with characteristic respectively;
Step 235, according to the numerical value of correlation data medium ultraviolet light quantization data characteristics item that filters out and the numerical value of characteristic medium ultraviolet light quantization data characteristics item, calculate the ultraviolet light quantity correlative value that the correlation data that filters out is formed with characteristic respectively;
Step 236, according to expanding the numerical value expanding light quantization data characteristics item in the numerical value of light quantization data characteristics item and characteristic in the correlation data that filters out, calculate the expansion light quantity correlative value that the correlation data that filters out is formed with characteristic respectively;
Step 237, in the correlation data filtered out, obtain that the spectrophotometric spectra Data Comparison value calculated in same correlation data is less than or equal to Second Threshold, crest correlative value is less than or equal to the 3rd threshold value, fluorescence volume correlative value is less than or equal to the 4th threshold value, amount of infrared light correlative value is less than or equal to the 5th threshold value, ultraviolet light quantity correlative value is less than or equal to the 6th threshold value and expansion light quantity correlative value is less than or equal to the correlation data that the 7th threshold value meets simultaneously, and the matching result of the correlation data got as file ink sample is exported.
In one embodiment, the first step, the spectral reflectivity of spectrophotometric spectra data characteristics item in the spectral reflectivity of spectrophotometric spectra data characteristics item in K correlation data filtering out and characteristic to be imported in formula (3), calculate the spectrophotometric spectra Data Comparison value that K correlation data and characteristic are formed respectively;
In formula (3), D0
kfor a kth spectrophotometric spectra Data Comparison value; Fgi0 (i=1, n) is the spectral reflectivity of spectrophotometric spectra data characteristics item in characteristic; Fgik (i=1, n) is the spectral reflectivity of spectrophotometric spectra data characteristics item item in a kth correlation data; 1≤k≤K, and be natural number;
Second step, the numerical value associating corresponding crest value characteristic item with spectrophotometric spectra data item of the numerical value and characteristic that associate corresponding crest value characteristic item with spectrophotometric spectra data item of the K a filtered out correlation data to be imported in formula (4), calculate the crest correlative value that K correlation data and characteristic are formed respectively;
In formula (4), D1
kfor a kth crest correlative value; X0 (p=1, m) is for associating the numerical value of corresponding crest value characteristic item with spectrophotometric spectra data item in characteristic; Xk (p=1, m) is for associating the numerical value of corresponding crest value characteristic item with spectrophotometric spectra data item in a kth correlation data;
The numerical value that in 3rd step, numerical value fluorescence in K correlation data filtering out being quantized data characteristics item and characteristic, fluorescence quantizes data characteristics item imports in formula (5), calculates the fluorescence volume correlative value that K correlation data and characteristic are formed respectively;
In formula (5), D2
kfor a kth fluorescence volume correlative value; Yg0 is the numerical value that in characteristic, fluorescence quantizes data characteristics item; Ygk is the numerical value that in a kth correlation data, fluorescence quantizes data characteristics item;
4th step, K correlation data mid-infrared light quantized data filtering out and characteristic mid-infrared light quantized data to be imported in formula (6), calculate the amount of infrared light correlative value that K correlation data and characteristic are formed respectively;
In formula (6), D3
kfor a kth amount of infrared light correlative value; Hwg0 is characteristic mid-infrared light quantized data; Hwgk is a kth correlation data mid-infrared light quantized data;
5th step, the numerical value of the numerical value of K correlation data medium ultraviolet light quantization data characteristics item filtered out and characteristic medium ultraviolet light quantization data characteristics item to be imported in formula (7), calculate the ultraviolet light quantity correlative value that K correlation data and characteristic are formed respectively;
In formula (7), D4
kfor a kth ultraviolet light quantity correlative value; Zwg0 is the numerical value of characteristic medium ultraviolet light quantization data characteristics item; Zwgk is the numerical value of a kth correlation data medium ultraviolet light quantization data characteristics item;
5th step, to import expanding the numerical value expanding light quantization data characteristics item in the numerical value of light quantization data characteristics item and characteristic in the K a filtered out correlation data in formula (8), calculating the expansion light quantity correlative value that K correlation data and characteristic are formed respectively;
In formula (8), D5
kfor a kth expansion light quantity correlative value; Qtg0 is the numerical value expanding light quantization data characteristics item in characteristic; Qtgk is the numerical value expanding light quantization data characteristics item in a kth correlation data;
6th step, in K correlation data, obtain that the spectrophotometric spectra Data Comparison value calculated in same correlation data is less than or equal to Second Threshold, crest correlative value is less than or equal to the 3rd threshold value, fluorescence volume correlative value is less than or equal to the 4th threshold value, amount of infrared light correlative value is less than or equal to the 5th threshold value, ultraviolet light quantity correlative value is less than or equal to the 6th threshold value and expansion light quantity correlative value is less than or equal to the correlation data that the 7th threshold value meets simultaneously, and the matching result of the correlation data got as file ink sample to be checked is exported.
Wherein, the span of Second Threshold is [0,0.2]; The span of the 3rd threshold value, the 4th threshold value, the 5th threshold value, the 6th threshold value and the 7th threshold value is [0,0.1].
Be understandable that, in embodiments of the present invention, the condition preset can be condition one: there is the Color pair ratio C that at least one calculates in correlation data
j≤ first threshold; Also can be the combination of condition one and condition two; Namely there is the Color pair ratio C that at least one calculates
jthe correlation data of≤first threshold, and this correlation data meets the spectrophotometric spectra Data Comparison value D0 calculated simultaneously
k≤ Second Threshold, the crest correlative value D1 calculated
k≤ the three threshold value, fluorescence volume correlative value D2
k≤ the four threshold value, the amount of infrared light correlative value D3 calculated
k≤ the five threshold value, the ultraviolet light quantity correlative value D4 calculated
k≤ the six threshold value, and the expansion light quantity correlative value D5 calculated
k≤ the seven threshold value.
Once occur comparing result do not meet pre-conditioned in arbitrary condition, using this characteristic as new data preserve in a database, therefore described method further comprises:
After the multiple correlation data obtained and described characteristic contrast one by one, when the comparing result of acquisition does not meet pre-conditioned, characteristic is saved in default database.
As shown in Figure 2, in the embodiment of the present invention, a kind of file ink data provided realizes the system of contrast automatically, and described system comprises:
Acquiring unit 210, for obtaining the characteristic that file ink sample to be checked is formed; Wherein, described characteristic is comprised spectrophotometric spectra data by characteristic item, with the crest value of described spectrophotometric spectra data correlation, fluorescence quantized data, infrared light quantized data, ultraviolet light quantized data, expanded the data that light quantization data, color, type and creation-time formed;
Matching result output unit 220, for selecting certain hour scope in the database preset, obtain multiple correlation datas identical with value in the type feature item of described characteristic in described time range, and according to the way of contrast preset, described multiple correlation data of obtaining and described characteristic are contrasted one by one, filters out comparing result and meet pre-conditioned correlation data and export as the matching result of described file ink sample to be checked.
Wherein, described matching result output unit 220 comprises:
Type matching module 2201, for selecting certain hour scope in the database preset, obtains multiple correlation datas identical with value in the type feature item of described characteristic in described time range;
Dithering module 2202, for the value of R, G, B in the value of R, G, B in the color characteristic item of multiple correlation datas that obtains described in basis and the color characteristic item of described characteristic, the Color pair ratio that the multiple correlation datas obtained described in calculating are formed with described characteristic respectively, and in the described multiple correlation datas obtained, filter out the correlation data that Color pair ratio is less than or equal to first threshold further;
Matching result output module 2203, for exporting the matching result of the described correlation data filtered out as described file ink sample to be checked.
Wherein, first threshold span is [0,100]; The span of Second Threshold is [0,0.2]; The span of the 3rd threshold value, the 4th threshold value, the 5th threshold value, the 6th threshold value and the 7th threshold value is [0,0.1].
Wherein, described system also comprises:
Preset unit 230, for building database in advance, and in described database each data with all for being comprised spectrophotometric spectra data by characteristic item, and the crest value of described spectrophotometric spectra data correlation, fluorescence quantized data, infrared light quantized data, ultraviolet light quantized data, expanding the data that light quantization data, color, type and creation-time formed, and to be saved in a storer in time ascending order mode.
Wherein, described system also comprises:
Updating block 240, for when described in after multiple correlation data of obtaining and described characteristic contrast one by one, the comparing result of acquisition do not meet described pre-conditioned time, described characteristic is saved in described default database.
Implement the embodiment of the present invention, there is following beneficial effect:
In embodiments of the present invention, because file ink sample forms the characteristic with special characteristic item after treatment, this characteristic can be carried out rapid comparison with the data in database and mate, thus correctly identified, therefore there is quick, efficient and accuracy, manually-operated error can be reduced, save screening time.
It should be noted that in said system embodiment, each included system unit is carry out dividing according to function logic, but is not limited to above-mentioned division, as long as can realize corresponding function; In addition, the concrete title of each functional unit, also just for the ease of mutual differentiation, is not limited to protection scope of the present invention.
One of ordinary skill in the art will appreciate that all or part of step realized in above-described embodiment method is that the hardware that can carry out instruction relevant by program has come, described program can be stored in a computer read/write memory medium, described storage medium, as ROM/RAM, disk, CD etc.
Above disclosedly be only present pre-ferred embodiments, certainly can not limit the interest field of the present invention with this, therefore according to the equivalent variations that the claims in the present invention are done, still belong to the scope that the present invention is contained.
Claims (10)
1. file ink data realizes a method for contrast automatically, and it is characterized in that, described method comprises:
A, obtain file ink sample to be checked formed characteristic; Wherein, described characteristic is comprised spectrophotometric spectra data by characteristic item, with the crest value of described spectrophotometric spectra data correlation, fluorescence quantized data, infrared light quantized data, ultraviolet light quantized data, expanded the data that light quantization data, color, type and creation-time formed;
B, preset database in select certain hour scope, obtain multiple correlation datas identical with value in the type feature item of described characteristic in described time range, and according to the way of contrast preset, described multiple correlation data of obtaining and described characteristic are contrasted one by one, filters out comparing result and meet pre-conditioned correlation data and export as the matching result of described file ink sample to be checked.
2. the method for claim 1, is characterized in that, described step b specifically comprises:
In the database preset, select certain hour scope, obtain multiple correlation datas identical with value in the type feature item of described characteristic in described time range;
According to the value of R, G, B in the value of R, G, B in the color characteristic item of the described multiple correlation datas obtained and the color characteristic item of described characteristic, the Color pair ratio that the multiple correlation datas obtained described in calculating are formed with described characteristic respectively, and in the described multiple correlation datas obtained, filter out the correlation data that Color pair ratio is less than or equal to first threshold further;
The matching result of the described correlation data filtered out as described file ink sample to be checked is exported.
3. method as claimed in claim 2, is characterized in that, describedly the step that the described correlation data filtered out exports as the matching result of described file ink sample to be checked is comprised further:
According to the spectral reflectivity of spectrophotometric spectra data characteristics item in the spectral reflectivity of spectrophotometric spectra data characteristics item in the described correlation data filtered out and described characteristic, the spectrophotometric spectra Data Comparison value that the correlation data filtered out described in calculating is formed with described characteristic respectively;
According to associating the numerical value associating corresponding crest value characteristic item in the numerical value of corresponding crest value characteristic item and described characteristic with spectrophotometric spectra data item in the described correlation data filtered out with spectrophotometric spectra data item, the crest correlative value that the correlation data filtered out described in calculating is formed with described characteristic respectively;
Quantize fluorescence in the numerical value of data characteristics item and described characteristic according to fluorescence in the described correlation data filtered out and quantize the numerical value of data characteristics item, the fluorescence volume correlative value that the correlation data filtered out described in calculating is formed with described characteristic respectively;
According to the numerical value of the described correlation data mid-infrared light quantized data characteristic item filtered out and the numerical value of described characteristic mid-infrared light quantized data characteristic item, the amount of infrared light correlative value that the correlation data filtered out described in calculating is formed with described characteristic respectively;
According to the numerical value of the described correlation data medium ultraviolet light quantization data characteristics item filtered out and the numerical value of described characteristic medium ultraviolet light quantization data characteristics item, the ultraviolet light quantity correlative value that the correlation data filtered out described in calculating is formed with described characteristic respectively;
According to expanding the numerical value expanding light quantization data characteristics item in the numerical value of light quantization data characteristics item and described characteristic in the described correlation data filtered out, the expansion light quantity correlative value that the correlation data filtered out described in calculating is formed with described characteristic respectively;
In the described correlation data filtered out, obtain that the spectrophotometric spectra Data Comparison value calculated in same correlation data is less than or equal to Second Threshold, crest correlative value is less than or equal to the 3rd threshold value, fluorescence volume correlative value is less than or equal to the 4th threshold value, amount of infrared light correlative value is less than or equal to the 5th threshold value, ultraviolet light quantity correlative value is less than or equal to the 6th threshold value and expansion light quantity correlative value is less than or equal to the correlation data that the 7th threshold value meets simultaneously, and the matching result of the described correlation data got as described file ink sample is exported.
4. method as claimed in claim 3, it is characterized in that, described first threshold span is [0,100]; The span of described Second Threshold is [0,0.2]; The span of described 3rd threshold value, the 4th threshold value, the 5th threshold value, the 6th threshold value and the 7th threshold value is [0,0.1].
5. the method for claim 1, is characterized in that, before described step a, described method comprises further:
Build database in advance, and each data, all for being comprised spectrophotometric spectra data by characteristic item, with the crest value of described spectrophotometric spectra data correlation, fluorescence quantized data, infrared light quantized data, ultraviolet light quantized data, expanding the data that light quantization data, color, type and creation-time formed, and to be saved in a storer in time ascending order mode in described database.
6. the method for claim 1, is characterized in that, described method further comprises:
After described multiple correlation data of obtaining and described characteristic contrast one by one, the comparing result of acquisition do not meet described pre-conditioned time, described characteristic is saved in described default database.
7. file ink data realizes a system for contrast automatically, and it is characterized in that, described system comprises:
Acquiring unit, for obtaining the characteristic that file ink marks sample to be checked is formed; Wherein, described characteristic is comprised spectrophotometric spectra data by characteristic item, with the crest value of described spectrophotometric spectra data correlation, fluorescence quantized data, infrared light quantized data, ultraviolet light quantized data, expanded the data that light quantization data, color, type and creation-time formed;
Matching result output unit, for selecting certain hour scope in the database preset, obtain multiple correlation datas identical with value in the type feature item of described characteristic in described time range, and according to the way of contrast preset, described multiple correlation data of obtaining and described characteristic are contrasted one by one, filters out comparing result and meet pre-conditioned correlation data and export as the matching result of described file ink sample to be checked.
8. system as claimed in claim 7, it is characterized in that, described matching result output unit comprises:
Type matching module, for selecting certain hour scope in the database preset, obtains multiple correlation datas identical with the type feature item of described characteristic in described time range;
Dithering module, for the value of R, G, B in the value of R, G, B in the color characteristic item of multiple correlation datas that obtains described in basis and the color characteristic item of described characteristic, the Color pair ratio that the multiple correlation datas obtained described in calculating are formed with described characteristic respectively, and in the described multiple correlation datas obtained, filter out the correlation data that Color pair ratio is less than or equal to first threshold further;
Matching result output module, for exporting the matching result of the described correlation data filtered out as described file ink sample to be checked.
9. system as claimed in claim 7, it is characterized in that, described system also comprises:
Preset unit, for building database in advance, and each data, all for being comprised spectrophotometric spectra data by characteristic item, with the crest value of described spectrophotometric spectra data correlation, fluorescence quantized data, infrared light quantized data, ultraviolet light quantized data, expanding the data that light quantization data, color, type and creation-time formed, and to be saved in a storer in time ascending order mode in described database.
10. system as claimed in claim 7, it is characterized in that, described system also comprises:
Updating block, for when described in after multiple correlation data of obtaining and described characteristic contrast one by one, the comparing result of acquisition do not meet described pre-conditioned time, described characteristic is saved in described default database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510791503.XA CN105447513B (en) | 2015-11-17 | 2015-11-17 | A kind of file ink data realizes the method and system of automatic contrast |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510791503.XA CN105447513B (en) | 2015-11-17 | 2015-11-17 | A kind of file ink data realizes the method and system of automatic contrast |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105447513A true CN105447513A (en) | 2016-03-30 |
| CN105447513B CN105447513B (en) | 2017-06-16 |
Family
ID=55557672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510791503.XA Active CN105447513B (en) | 2015-11-17 | 2015-11-17 | A kind of file ink data realizes the method and system of automatic contrast |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105447513B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239826A (en) * | 2017-06-06 | 2017-10-10 | 上海兆芯集成电路有限公司 | Computational methods and device in convolutional neural networks |
| CN107256422A (en) * | 2017-06-06 | 2017-10-17 | 上海兆芯集成电路有限公司 | Data quantization methods and device |
| CN112834507A (en) * | 2020-12-31 | 2021-05-25 | 易旻 | Uniqueness identification system and method based on image registration and spectrum identification |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101162508A (en) * | 2006-10-09 | 2008-04-16 | 柯惟中 | Raman optical spectrum method for identifying blackness handwriting |
| CN101587540A (en) * | 2009-04-16 | 2009-11-25 | 大连理工大学 | Printer verification method for detecting document source by means of geometric distortion of page document |
| CN102289665A (en) * | 2011-09-01 | 2011-12-21 | 华中师范大学 | Printed file identifying method based on powdered ink stack texture analysis |
| CN103969198A (en) * | 2013-02-06 | 2014-08-06 | 上海帆声图像科技有限公司 | Artwork identification method |
| CN104422667A (en) * | 2013-08-30 | 2015-03-18 | 首都师范大学 | Method and device for authenticating industrial art imitation |
-
2015
- 2015-11-17 CN CN201510791503.XA patent/CN105447513B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101162508A (en) * | 2006-10-09 | 2008-04-16 | 柯惟中 | Raman optical spectrum method for identifying blackness handwriting |
| CN101587540A (en) * | 2009-04-16 | 2009-11-25 | 大连理工大学 | Printer verification method for detecting document source by means of geometric distortion of page document |
| CN102289665A (en) * | 2011-09-01 | 2011-12-21 | 华中师范大学 | Printed file identifying method based on powdered ink stack texture analysis |
| CN103969198A (en) * | 2013-02-06 | 2014-08-06 | 上海帆声图像科技有限公司 | Artwork identification method |
| CN104422667A (en) * | 2013-08-30 | 2015-03-18 | 首都师范大学 | Method and device for authenticating industrial art imitation |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239826A (en) * | 2017-06-06 | 2017-10-10 | 上海兆芯集成电路有限公司 | Computational methods and device in convolutional neural networks |
| CN107256422A (en) * | 2017-06-06 | 2017-10-17 | 上海兆芯集成电路有限公司 | Data quantization methods and device |
| CN112834507A (en) * | 2020-12-31 | 2021-05-25 | 易旻 | Uniqueness identification system and method based on image registration and spectrum identification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105447513B (en) | 2017-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Valencia-Hernández et al. | SAP algorithm for citation analysis: An improvement to tree of science | |
| CN107462535B (en) | A kind of resolutions of spectra based on Gaussian rough surface | |
| CN109299501B (en) | Vibration spectrum analysis model optimization method based on workflow | |
| CN105447513A (en) | File ink mark data automation contrast realization method and system thereof | |
| CN105975589A (en) | Feature selection method and device of high-dimension data | |
| CN105528288A (en) | Software testing method and apparatus | |
| CN105334186A (en) | Infrared spectral analysis method | |
| CN111351757A (en) | Method and system for predicting quantitative measure of oil adulteration of edible oil sample | |
| CN105277498A (en) | Method and system for detecting types of file writings | |
| CN101943658B (en) | Method for continuously monitoring water quality by combining principal component analysis theory and spectrum analysis technology | |
| CN105069153A (en) | Patent analysis system | |
| CN108844898A (en) | A kind of landwaste kind identification method and system | |
| Ruan et al. | A novel hybrid filter/wrapper method for feature selection in archaeological ceramics classification by laser-induced breakdown spectroscopy | |
| CN103868858B (en) | A kind ofly determine the method that saliferous clay dominates salinity spectral response best band | |
| GB2594187A (en) | Determining reservoir fluid properties from downhole fluid analysis data using machine learning | |
| CN114216877A (en) | Automatic detection and reconstruction method and system for spectral peak in tea near infrared spectral analysis | |
| CN112200252A (en) | Joint dimension reduction method based on probability box global sensitivity analysis and active subspace | |
| CN107153046A (en) | Near infrared spectrum based on concentration residual information detects the method and system of fruit quality | |
| CN105843891A (en) | Incremental online characteristic extraction and analysis method and system | |
| CN105227333B (en) | The method and apparatus of network element device data maintenance | |
| CN113297722A (en) | Coastal soil salinity assessment method and system | |
| CN114235715B (en) | Full phosphorus content nondestructive monitoring method for karst plant leaves | |
| Chen | An extensional micmac method to identify the key factors | |
| CN117250183B (en) | Gas component analysis method, apparatus, device, and storage medium | |
| CN117076454B (en) | Engineering quality acceptance form data structured storage method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20170503 Address after: 518000 Guangdong province Futian District Shenzhen City Binhe Road, No. 5003 building, 17 floor, West Wing of love Applicant after: Xu Qilin Address before: 518000 Guangdong province Futian District Shenzhen City Binhe Road, No. 5003 building, 17 floor, West Wing of love Applicant before: Guangdong Nantian Mingjian Expert Testimony |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant |