CN108830314A - A kind of sxemiquantitative recognition methods of external diagnosis reagent and device - Google Patents
A kind of sxemiquantitative recognition methods of external diagnosis reagent and device Download PDFInfo
- Publication number
- CN108830314A CN108830314A CN201810574939.7A CN201810574939A CN108830314A CN 108830314 A CN108830314 A CN 108830314A CN 201810574939 A CN201810574939 A CN 201810574939A CN 108830314 A CN108830314 A CN 108830314A
- Authority
- CN
- China
- Prior art keywords
- line
- longitudinal edge
- edge
- external diagnosis
- diagnosis reagent
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Investigating Or Analysing Materials By The Use Of Chemical Reactions (AREA)
Abstract
The embodiment of the present invention provides sxemiquantitative recognition methods and the device of a kind of external diagnosis reagent, the method includes：Acquisition includes the image of external diagnosis reagent；Extract the transverse edge in described image；According to the length of the transverse edge and position, the T line and the position range where C line that determine the external diagnosis reagent；Extract the longitudinal edge in described image；Target longitudinal edge is obtained in the position range；And calculate the color concentration in the corresponding region of the target longitudinal edge；The target longitudinal edge is the T line and the corresponding longitudinal edge of the C line；The comparison result that the corresponding T line color concentration of T line C line color concentration corresponding with the C line is compared is as the sxemiquantitative recognition result of the external diagnosis reagent.Described device executes the above method.Method and device provided in an embodiment of the present invention can be improved popularization of the vitro diagnostic techniques in general population.
Description
Technical field
The present embodiments relate to image identification technical fields, and in particular to a kind of sxemiquantitative identification of external diagnosis reagent
Method and device.
Background technique
External diagnosis reagent can be used alone or use with instrument, utensil, equipment or system in combination, can specifically include body
Reagent, kit, calibration object (object), quality-control product (object) of outer detection etc., are widely applied.
Existing external diagnosis reagent needs in certain circumstances and relies on professional and professional equipment just get
The recognition result of external diagnosis reagent, such as：Detection device is all based on greatly single point detector, need to completely cut off extraneous light environment with
Ensure to judge by accident, a small number of detection devices based on camera also must could be under particular optical lighting environment in darkroom
Row identification.This recognition methods is seriously limited by professional, professional equipment and specific environment, hinders vitro diagnostic techniques and exists
Universal and application in general population.
Therefore, how to avoid drawbacks described above, can carry out sxemiquantitative identification to external diagnosis reagent, to improve external
Popularization of the diagnostic techniques in general population, becoming need solve the problems, such as.
Summary of the invention
In view of the problems of the existing technology, the embodiment of the present invention provides a kind of sxemiquantitative identification side of external diagnosis reagent
Method and device.
In a first aspect, the embodiment of the present invention provides a kind of sxemiquantitative recognition methods of external diagnosis reagent, the method packet
It includes：
Acquisition includes the image of external diagnosis reagent；
Extract the transverse edge in described image；The transverse edge is prolonged along the axial direction of the external diagnosis reagent
It stretches；
According to the length of the transverse edge and position, the T line for determining the external diagnosis reagent and the position where C line
Range；
Extract the longitudinal edge in described image；The longitudinal edge is prolonged along the radial direction of the external diagnosis reagent
It stretches；
Target longitudinal edge is obtained in the position range；And calculate the corresponding region of the target longitudinal edge
Color concentration；The target longitudinal edge is the T line and the corresponding longitudinal edge of the C line；
The comparison result that the corresponding T line color concentration of T line C line color concentration corresponding with the C line is compared
Sxemiquantitative recognition result as the external diagnosis reagent.
Second aspect, the embodiment of the present invention provide a kind of sxemiquantitative identification device of external diagnosis reagent, described device packet
It includes：
Acquiring unit, for obtain include external diagnosis reagent image；
First extraction unit, for extracting the transverse edge in described image；The transverse edge is examined in vitro along described
What the axial direction of disconnected reagent extended；
Determination unit, for according to the transverse edge length and position, determine the external diagnosis reagent T line and
Position range where C line；
Second extraction unit, for extracting the longitudinal edge in described image；The longitudinal edge is examined in vitro along described
What the radial direction of disconnected reagent extended；
Computing unit, for obtaining target longitudinal edge in the position range；And calculate the target longitudinal edge
The color concentration in corresponding region；The target longitudinal edge is the T line and the corresponding longitudinal edge of the C line
Edge；
Recognition unit, for comparing the corresponding T line color concentration of T line C line color concentration corresponding with the C line
Compared with sxemiquantitative recognition result of the comparison result as the external diagnosis reagent.
The third aspect, the embodiment of the present invention provide a kind of electronic equipment, including：Processor, memory and bus, wherein
The processor and the memory complete mutual communication by the bus；
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to refer to
Order is able to carry out following method：
Acquisition includes the image of external diagnosis reagent；
Extract the transverse edge in described image；The transverse edge is prolonged along the axial direction of the external diagnosis reagent
It stretches；
According to the length of the transverse edge and position, the T line for determining the external diagnosis reagent and the position where C line
Range；
Extract the longitudinal edge in described image；The longitudinal edge is prolonged along the radial direction of the external diagnosis reagent
It stretches；
Target longitudinal edge is obtained in the position range；And calculate the corresponding region of the target longitudinal edge
Color concentration；The target longitudinal edge is the T line and the corresponding longitudinal edge of the C line；
The comparison result that the corresponding T line color concentration of T line C line color concentration corresponding with the C line is compared
Sxemiquantitative recognition result as the external diagnosis reagent.
Fourth aspect, the embodiment of the present invention provide a kind of non-transient computer readable storage medium, including：
The non-transient computer readable storage medium stores computer instruction, and the computer instruction makes the computer
Execute following method：
Acquisition includes the image of external diagnosis reagent；
Extract the transverse edge in described image；The transverse edge is prolonged along the axial direction of the external diagnosis reagent
It stretches；
According to the length of the transverse edge and position, the T line for determining the external diagnosis reagent and the position where C line
Range；
Extract the longitudinal edge in described image；The longitudinal edge is prolonged along the radial direction of the external diagnosis reagent
It stretches；
Target longitudinal edge is obtained in the position range；And calculate the corresponding region of the target longitudinal edge
Color concentration；The target longitudinal edge is the T line and the corresponding longitudinal edge of the C line；
The comparison result that the corresponding T line color concentration of T line C line color concentration corresponding with the C line is compared
Sxemiquantitative recognition result as the external diagnosis reagent.
The sxemiquantitative recognition methods of external diagnosis reagent provided in an embodiment of the present invention and device, by determining in-vitro diagnosis
The T line and the position range where C line of reagent, obtain T line and the corresponding longitudinal edge of C line in position range, and by T
Sxemiquantitative recognition result of the comparison result of line color concentration and C line color concentration as external diagnosis reagent, can be to external
Diagnostic reagent carries out sxemiquantitative identification, to improve popularization of the vitro diagnostic techniques in general population.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the sxemiquantitative recognition methods flow diagram of external diagnosis reagent of the embodiment of the present invention；
Fig. 2 is the screenshot for the transverse edge that the embodiment of the present invention extracts；
Fig. 3 is the T line of external diagnosis reagent of the embodiment of the present invention and the screenshot of the position range where C line；
Fig. 4 is the screenshot for the longitudinal edge that the embodiment of the present invention extracts；
Fig. 5 is the screenshot of T of embodiment of the present invention line and C line；
Fig. 6 is the sxemiquantitative identification device structural schematic diagram of external diagnosis reagent of the embodiment of the present invention；
Fig. 7 is electronic equipment entity structure schematic diagram provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 is the sxemiquantitative recognition methods flow diagram of external diagnosis reagent of the embodiment of the present invention, as shown in Figure 1, this
A kind of sxemiquantitative recognition methods for external diagnosis reagent that inventive embodiments provide, includes the following steps：
S101：Acquisition includes the image of external diagnosis reagent.
Specifically, device acquisition includes the image of external diagnosis reagent.Image can by mobile phone photograph or other
Mode obtains, and is not especially limited.External diagnosis reagent can be using the acquisition of colloidal gold method, be not especially limited.
S102：Extract the transverse edge in described image；The transverse edge is the axial direction along the external diagnosis reagent
What direction extended.
Specifically, device extracts the transverse edge in described image；The transverse edge is along the external diagnosis reagent
Axial direction extend.The transverse edge can be extracted using Boundary extracting algorithm.Fig. 2 extracts for the embodiment of the present invention
Transverse edge screenshot, as shown in Fig. 2, the transverse edge in Fig. 2 is extended along the axial direction of external diagnosis reagent,
It should be noted that：Before this step, image can also be pre-processed, to eliminate noise jamming etc..
S103：According to the length of the transverse edge and position, T line and the C line place of the external diagnosis reagent are determined
Position range.
Specifically, length and position of the device according to the transverse edge, determine the T line and C of the external diagnosis reagent
Position range where line.Fig. 3 be external diagnosis reagent of the embodiment of the present invention T line and the position range where C line screenshot,
As shown in figure 3, the box mark in Fig. 3 is the position range, position range specifically determines that method can be as follows：
According to the position, the fore-and-aft distance between parallel transverse edge is calculated；If the fore-and-aft distance is corresponding
First ratio of the equal length of transverse edge and any equal length and the fore-and-aft distance is greater than preset ratio, then really
Determining the corresponding transverse edge of any equal length is the position range.Preset ratio can independently be set according to the actual situation
It sets, is described as follows referring to Fig. 2：Transverse edge 1~5 be all it is parallel, parallel transverse edge is calculated according to position
Between fore-and-aft distance be specially fore-and-aft distance L12, transverse edge 2 and transverse edge between transverse edge 1 and transverse edge 2
Fore-and-aft distance L23, transverse edge 4 between 3 and the fore-and-aft distance L45 between transverse edge 5, due to the corresponding widthwise edge of L12
The length of edge 1 and transverse edge 2 differs, and therefore, transverse edge 1 and transverse edge 2 all cannot function as the position range；Although
The equal length of L23 corresponding transverse edge 2 and transverse edge 3, but the first ratio of transverse edge 2 or transverse edge 3 and L23
Value is less than preset ratio, and therefore, transverse edge 2 and transverse edge 3 all cannot function as the position range, and transverse edge 4 and cross
All meet above-mentioned condition to edge 5, therefore, transverse edge 4 or transverse edge 5 can be used as the position range, be referring to Fig. 3, Fig. 3
It regard transverse edge 4 as the position range.
S104：Extract the longitudinal edge in described image；The longitudinal edge is the radial direction along the external diagnosis reagent
What direction extended.
Specifically, device extracts the longitudinal edge in described image；The longitudinal edge is along the external diagnosis reagent
Radial direction extend.The longitudinal edge is extracted using Boundary extracting algorithm.Fig. 4 extracts vertical for the embodiment of the present invention
Extrorse screenshot, as shown in figure 4, the longitudinal edge in Fig. 4 is extended along the radial direction of external diagnosis reagent.
S105：Target longitudinal edge is obtained in the position range；And it calculates the target longitudinal edge and respectively corresponds
Region color concentration；The target longitudinal edge is the T line and the corresponding longitudinal edge of the C line.
Specifically, device obtains target longitudinal edge in the position range；And calculate the target longitudinal edge fate
The color concentration in not corresponding region；The target longitudinal edge is the T line and the corresponding longitudinal edge of the C line.
Fig. 5 is the screenshot of T of embodiment of the present invention line and C line, as shown in figure 5, the box in Fig. 5 is labeled as T line and C line, box label
Region respectively correspond C line color concentration and T line color concentration, it should be noted that：The embodiment of the present invention does not need area
Separate C line and T line.The color concentration in the corresponding region of target longitudinal edge can be calculated using k-means clustering method,
I.e. above-mentioned C line color concentration and T line color concentration.The specific method for obtaining target longitudinal edge can be as follows：
The corresponding shape feature of all longitudinal edges is obtained in the position range；Obtain the complete of the shape feature
Degree will be greater than the corresponding longitudinal edge of integrated degree of threshold value as longitudinal edge to be selected；It obtains in the position range
Two-end-point position；The longitudinal edge to be selected the distance between closer end point into the two-end-point position is obtained, in institute
The longitudinal edge to be selected rejected in distance and be less than pre-determined distance is stated, and longitudinal using remaining longitudinal edge to be selected as the target
Edge.Threshold value and pre-determined distance can be independently arranged according to the actual situation.Referring to the example above and Fig. 4, for longitudinal edge 1~
4 corresponding shape features, since the integrated degree of the shape feature of longitudinal edge 4 is less than threshold value, longitudinal edge 1~3
The integrated degree of shape feature is greater than threshold value, and therefore, longitudinal edge 1~3 is used as longitudinal edge to be selected, referring to Fig. 3, in Fig. 3
It is 1 endpoint and 2 endpoints in two-end-point, the distance of 1 to 1 endpoint of longitudinal edge to be selected in Fig. 4 is more compared to the distance to 2 endpoints
Closely, since the distance of 1 to 1 endpoint of longitudinal edge to be selected is less than pre-determined distance (Fig. 3 and Fig. 4 are not shown), it rejects to be selected vertical
To edge 1, since the distance of 2 to 1 endpoint of longitudinal edge to be selected is closer compared to the distance to 2 endpoints, due to longitudinal edge to be selected
The distance of 2 to 1 endpoint of edge is greater than pre-determined distance, therefore does not reject；Similarly, due to the distance of 3 to 1 endpoint of longitudinal edge to be selected
It is farther compared to the distance to 2 endpoints, since the distance of 3 to 2 endpoint of longitudinal edge to be selected is greater than pre-determined distance, do not pick
It removes.To regard longitudinal edge 2 to be selected and longitudinal edge to be selected 3 as target longitudinal edge.
S106：The comparison that the corresponding T line color concentration of T line C line color concentration corresponding with the C line is compared
As a result as the sxemiquantitative recognition result of the external diagnosis reagent.
Specifically, device compares the corresponding T line color concentration of T line C line color concentration corresponding with the C line
Sxemiquantitative recognition result of the comparison result as the external diagnosis reagent.The comparison result includes that the T line color is dense
The second ratio between degree and the C line color concentration；Correspondingly, acquisition sxemiquantitative recognition result is specially：
The first recognition result that comparison result using second ratio greater than 1 is identified as sxemiquantitative；By described second
The second recognition result that comparison result of the ratio less than 1 is identified as sxemiquantitative；Second ratio is equal to 1 comparison result
Third recognition result as sxemiquantitative identification.
The sxemiquantitative recognition methods of external diagnosis reagent provided in an embodiment of the present invention, by determining external diagnosis reagent
Position range where T line and C line, obtains T line and the corresponding longitudinal edge of C line in position range, and by T line color
Sxemiquantitative recognition result of the comparison result of concentration and C line color concentration as external diagnosis reagent, can try in-vitro diagnosis
Agent carries out sxemiquantitative identification, to improve popularization of the vitro diagnostic techniques in general population.
The present invention has the advantage that as follows：
The range that T line and C line are first determined using transverse edge, is recycled longitudinal edge to carry out last optimizing, determines T line
With C line, do not influenced by T line and the C line color depth and evolution.In various ambient lights, different colours T line and C line, no
Equal energy robust control policy T line and C line and its position, are counted respectively using the T line and C line that recognize in the case where with depth T line and C line
Its color concentration is calculated, to achieve the purpose that vitro detection agent (colloidal gold) half-quantitative detection, carries out color using clustering algorithm
Concentration calculation can effectively remove variegated influence, improve the accuracy that color concentration calculates.
On the basis of the above embodiments, the length and position according to the transverse edge is determined and described is examined in vitro
The T line and the position range where C line of disconnected reagent, including：
According to the position, the fore-and-aft distance between parallel transverse edge is calculated.
Specifically, device calculates the fore-and-aft distance between parallel transverse edge according to the position.It can refer to above-mentioned
Embodiment repeats no more.
If the equal length and any equal length of the corresponding transverse edge of the fore-and-aft distance and the fore-and-aft distance
The first ratio be greater than preset ratio, it is determined that the corresponding transverse edge of any equal length is the position range.
Specifically, if the equal length of the corresponding transverse edge of the fore-and-aft distance and any equal is known in device judgement
Length and the first ratio of the fore-and-aft distance be greater than preset ratio, it is determined that the corresponding transverse edge of any equal length
For the position range.It can refer to above-described embodiment, repeat no more.
The sxemiquantitative recognition methods of external diagnosis reagent provided in an embodiment of the present invention can rationally determine that in-vitro diagnosis is tried
The T line and the position range where C line of agent.
On the basis of the above embodiments, the acquisition target longitudinal edge in the position range, including：
The corresponding shape feature of all longitudinal edges is obtained in the position range.
Specifically, device obtains the corresponding shape feature of all longitudinal edges in the position range.It can refer to above-mentioned
Embodiment repeats no more.
The integrated degree for obtaining the shape feature will be greater than the corresponding longitudinal edge of integrated degree of threshold value as to be selected
Longitudinal edge.
Specifically, device obtains the integrated degree of the shape feature, the corresponding longitudinal direction of integrated degree of threshold value will be greater than
Edge is as longitudinal edge to be selected.It can refer to above-described embodiment, repeat no more.
Obtain the two-end-point position in the position range.
Specifically, device obtains the two-end-point position in the position range.It can refer to above-described embodiment, repeat no more.
Obtain the longitudinal edge to be selected the distance between closer end point into the two-end-point position, it is described away from
From the middle longitudinal edge to be selected rejected less than pre-determined distance, and using remaining longitudinal edge to be selected as the target longitudinal edge
Edge.
Specifically, device obtain the longitudinal edge to be selected into the two-end-point position between closer end point away from
From rejecting is less than the longitudinal edge to be selected of pre-determined distance in the distance, and using remaining longitudinal edge to be selected as described in
Target longitudinal edge.It can refer to above-described embodiment, repeat no more.
The sxemiquantitative recognition methods of external diagnosis reagent provided in an embodiment of the present invention can rationally obtain target longitudinal edge
Edge.
On the basis of the above embodiments, the comparison result includes the T line color concentration and the C line color concentration
Between the second ratio；Correspondingly, described that the corresponding T line color concentration of the T line and the corresponding C line color of the C line is dense
Sxemiquantitative recognition result of the comparison result to compare as the external diagnosis reagent is spent, including：
The first recognition result that comparison result using second ratio greater than 1 is identified as sxemiquantitative.
Specifically, the first recognition result that comparison result of the device using second ratio greater than 1 is identified as sxemiquantitative.
It can refer to above-described embodiment, repeat no more.
The second recognition result that comparison result using second ratio less than 1 is identified as sxemiquantitative.
Specifically, the second recognition result that comparison result of the device using second ratio less than 1 is identified as sxemiquantitative.
It can refer to above-described embodiment, repeat no more.
The third recognition result that comparison result using second ratio equal to 1 is identified as sxemiquantitative.
Specifically, the third recognition result that comparison result of the device using second ratio equal to 1 is identified as sxemiquantitative.
It can refer to above-described embodiment, repeat no more.
The sxemiquantitative recognition methods of external diagnosis reagent provided in an embodiment of the present invention being capable of semidefinite by ratio calculation
Amount identifies the recognition result of external diagnosis reagent.
On the basis of the above embodiments, described to calculate the dark of the corresponding region of the target longitudinal edge
Degree, including：
The color concentration in the corresponding region of the target longitudinal edge is calculated using k-means clustering method.
Specifically, device calculates the face in the corresponding region of the target longitudinal edge using k-means clustering method
Colour saturation.It can refer to above-described embodiment, repeat no more.
The sxemiquantitative recognition methods of external diagnosis reagent provided in an embodiment of the present invention, by using the cluster side k-means
Method calculates the color concentration in the corresponding region of target longitudinal edge, can effectively get color concentration.
On the basis of the above embodiments, the transverse edge extracted in described image, including：It is calculated using edge extracting
Method extracts the transverse edge；Longitudinal edge in the extraction described image, including：Described in being extracted using Boundary extracting algorithm
Longitudinal edge.
Specifically, the transverse edge in the extraction described image in device, including：It is extracted using Boundary extracting algorithm
The transverse edge；Longitudinal edge in the extraction described image, including：The longitudinal edge is extracted using Boundary extracting algorithm
Edge.It can refer to above-described embodiment, repeat no more.
The sxemiquantitative recognition methods of external diagnosis reagent provided in an embodiment of the present invention, mentions by using Boundary extracting algorithm
Transverse direction/longitudinal edge is taken, transverse direction/longitudinal edge can be effectively extracted.
On the basis of the above embodiments, the external diagnosis reagent is obtained using colloidal gold method.
Specifically, the external diagnosis reagent in device is obtained using colloidal gold method.It can refer to above-mentioned implementation
Example, repeats no more.
The sxemiquantitative recognition methods of external diagnosis reagent provided in an embodiment of the present invention can be obtained to using colloidal gold method
The external diagnosis reagent obtained carries out sxemiquantitative identification.
Fig. 6 is the sxemiquantitative identification device structural schematic diagram of external diagnosis reagent of the embodiment of the present invention, as shown in fig. 6, this
Inventive embodiments provide a kind of sxemiquantitative identification device of external diagnosis reagent, including acquiring unit 601, the first extraction unit
602, determination unit 603, the second extraction unit 604, computing unit 605 and recognition unit 606, wherein：
Acquiring unit 601 be used for obtain include external diagnosis reagent image；First extraction unit 602 is for extracting institute
State the transverse edge in image；The transverse edge is extended along the axial direction of the external diagnosis reagent；Determination unit
603 are used for length and position, the T line for determining the external diagnosis reagent and the position where C line according to the transverse edge
Range；Second extraction unit 604 is used to extract the longitudinal edge in described image；The longitudinal edge is along the in-vitro diagnosis
What the radial direction of reagent extended；Computing unit 605 is used to obtain target longitudinal edge in the position range；And calculate institute
State the color concentration in the corresponding region of target longitudinal edge；The target longitudinal edge is that the T line and the C line are distinguished
Corresponding longitudinal edge；Recognition unit 606 is used for the corresponding T line color concentration of the T line and the corresponding C line face of the C line
Sxemiquantitative recognition result of the comparison result that colour saturation compares as the external diagnosis reagent.
Specifically, acquiring unit 601 be used for obtain include external diagnosis reagent image；First extraction unit 602 is used
Transverse edge in extraction described image；The transverse edge is extended along the axial direction of the external diagnosis reagent；
Determination unit 603 is used for length and position according to the transverse edge, determines T line and the C line institute of the external diagnosis reagent
Position range；Second extraction unit 604 is used to extract the longitudinal edge in described image；The longitudinal edge is along described
What the radial direction of external diagnosis reagent extended；Computing unit 605 is used to obtain target longitudinal edge in the position range；
And calculate the color concentration in the corresponding region of the target longitudinal edge；The target longitudinal edge is the T line and institute
State the corresponding longitudinal edge of C line；Recognition unit 606 is used for the corresponding T line color concentration of the T line and the C line pair
Sxemiquantitative recognition result of the comparison result that the C line color concentration answered compares as the external diagnosis reagent.
The sxemiquantitative identification device of external diagnosis reagent provided in an embodiment of the present invention, by determining external diagnosis reagent
Position range where T line and C line, obtains T line and the corresponding longitudinal edge of C line in position range, and by T line color
Sxemiquantitative recognition result of the comparison result of concentration and C line color concentration as external diagnosis reagent, can try in-vitro diagnosis
Agent carries out sxemiquantitative identification, to improve popularization of the vitro diagnostic techniques in general population.
The sxemiquantitative identification device of external diagnosis reagent provided in an embodiment of the present invention specifically can be used for executing above-mentioned each
The process flow of embodiment of the method, details are not described herein for function, is referred to the detailed description of above method embodiment.
Fig. 7 is electronic equipment entity structure schematic diagram provided in an embodiment of the present invention, as shown in fig. 7, the electronic equipment
Including：Processor (processor) 701, memory (memory) 702 and bus 703；
Wherein, the processor 701, memory 702 complete mutual communication by bus 703；
The processor 701 is used to call the program instruction in the memory 702, to execute above-mentioned each method embodiment
Provided method, for example including：Acquisition includes the image of external diagnosis reagent；Extract the transverse edge in described image；
The transverse edge is extended along the axial direction of the external diagnosis reagent；According to the length of the transverse edge and position
It sets, the T line and the position range where C line for determining the external diagnosis reagent；Extract the longitudinal edge in described image；It is described
Longitudinal edge is extended along the radial direction of the external diagnosis reagent；Target longitudinal edge is obtained in the position range
Edge；And calculate the color concentration in the corresponding region of the target longitudinal edge；The target longitudinal edge be the T line and
The corresponding longitudinal edge of the C line；The corresponding T line color concentration of the T line and the corresponding C line color of the C line is dense
Spend sxemiquantitative recognition result of the comparison result to compare as the external diagnosis reagent.
The present embodiment discloses a kind of computer program product, and the computer program product includes being stored in non-transient calculating
Computer program on machine readable storage medium storing program for executing, the computer program include program instruction, when described program instruction is calculated
When machine executes, computer is able to carry out method provided by above-mentioned each method embodiment, for example including：Acquisition includes to examine in vitro
The image of disconnected reagent；Extract the transverse edge in described image；The transverse edge is the axial direction along the external diagnosis reagent
What direction extended；According to the length of the transverse edge and position, where determining the T line and C line of the external diagnosis reagent
Position range；Extract the longitudinal edge in described image；The longitudinal edge is the radial direction along the external diagnosis reagent
Extend；Target longitudinal edge is obtained in the position range；And calculate the corresponding region of the target longitudinal edge
Color concentration；The target longitudinal edge is the T line and the corresponding longitudinal edge of the C line；The T line is corresponding
The comparison result that compares of T line color concentration C line color concentration corresponding with the C line as the external diagnosis reagent
Sxemiquantitative recognition result.
The present embodiment provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage medium
Computer instruction is stored, the computer instruction makes the computer execute method provided by above-mentioned each method embodiment, example
Such as include：Acquisition includes the image of external diagnosis reagent；Extract the transverse edge in described image；The transverse edge is edge
What the axial direction of the external diagnosis reagent extended；According to the length of the transverse edge and position, determines and described examine in vitro
The T line and the position range where C line of disconnected reagent；Extract the longitudinal edge in described image；The longitudinal edge is along described
What the radial direction of external diagnosis reagent extended；Target longitudinal edge is obtained in the position range；And calculate the target
The color concentration in the corresponding region of longitudinal edge；The target longitudinal edge is that the T line and the C line are corresponding
Longitudinal edge；The comparison result that the corresponding T line color concentration of T line C line color concentration corresponding with the C line is compared
Sxemiquantitative recognition result as the external diagnosis reagent.
Those of ordinary skill in the art will appreciate that：Realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer readable storage medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed；And storage medium above-mentioned includes：ROM, RAM, magnetic disk or light
The various media that can store program code such as disk.
The embodiments such as electronic equipment described above are only schematical, wherein it is described as illustrated by the separation member
Unit may or may not be physically separated, and component shown as a unit may or may not be object
Manage unit, it can it is in one place, or may be distributed over multiple network units.It can select according to the actual needs
Some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying wound
In the case where the labour for the property made, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally it should be noted that：The above various embodiments is only to illustrate the technical solution of the embodiment of the present invention, rather than right
It is limited；Although the embodiment of the present invention is described in detail referring to foregoing embodiments, the ordinary skill of this field
Personnel should understand that：It is still possible to modify the technical solutions described in the foregoing embodiments, or to part
Or all technical features are equivalently replaced；And these are modified or replaceed, it does not separate the essence of the corresponding technical solution
The range of various embodiments of the present invention technical solution.
Claims (10)
1. a kind of sxemiquantitative recognition methods of external diagnosis reagent, which is characterized in that including：
Acquisition includes the image of external diagnosis reagent；
Extract the transverse edge in described image；The transverse edge is the axial direction extension along the external diagnosis reagent
's；
According to the length of the transverse edge and position, the T line and the position model where C line that determine the external diagnosis reagent
It encloses；
Extract the longitudinal edge in described image；The longitudinal edge is the radial direction extension along the external diagnosis reagent
's；
Target longitudinal edge is obtained in the position range；And calculate the face in the corresponding region of the target longitudinal edge
Colour saturation；The target longitudinal edge is the T line and the corresponding longitudinal edge of the C line；
The comparison result that the corresponding T line color concentration of T line C line color concentration corresponding with the C line is compared as
The sxemiquantitative recognition result of the external diagnosis reagent.
2. the method according to claim 1, wherein the length and position according to the transverse edge, really
The T line and the position range where C line of the fixed external diagnosis reagent, including：
According to the position, the fore-and-aft distance between parallel transverse edge is calculated；
If the of the equal length and any equal length of the corresponding transverse edge of the fore-and-aft distance and the fore-and-aft distance
One ratio is greater than preset ratio, it is determined that the corresponding transverse edge of any equal length is the position range.
3. the method according to claim 1, wherein described obtain target longitudinal edge in the position range
Edge, including：
The corresponding shape feature of all longitudinal edges is obtained in the position range；
The integrated degree for obtaining the shape feature will be greater than the corresponding longitudinal edge of integrated degree of threshold value as longitudinal direction to be selected
Edge；
Obtain the two-end-point position in the position range；
The longitudinal edge to be selected the distance between closer end point into the two-end-point position is obtained, in the distance
The longitudinal edge to be selected for being less than pre-determined distance is rejected, and using remaining longitudinal edge to be selected as the target longitudinal edge.
4. the method according to claim 1, wherein the comparison result includes the T line color concentration and institute
State the second ratio between C line color concentration；Correspondingly, described by the corresponding T line color concentration of the T line and the C line pair
Sxemiquantitative recognition result of the comparison result that the C line color concentration answered compares as the external diagnosis reagent, including：
The first recognition result that comparison result using second ratio greater than 1 is identified as sxemiquantitative；
The second recognition result that comparison result using second ratio less than 1 is identified as sxemiquantitative；
The third recognition result that comparison result using second ratio equal to 1 is identified as sxemiquantitative.
5. the method according to claim 1, wherein described calculate the corresponding area of the target longitudinal edge
The color concentration in domain, including：
The color concentration in the corresponding region of the target longitudinal edge is calculated using k-means clustering method.
6. the method according to claim 1, wherein it is described extract described image in transverse edge, including：
The transverse edge is extracted using Boundary extracting algorithm；
Longitudinal edge in the extraction described image, including：
The longitudinal edge is extracted using Boundary extracting algorithm.
7. the method according to claim 1, wherein the external diagnosis reagent is obtained using colloidal gold method
's.
8. a kind of sxemiquantitative identification device of external diagnosis reagent, which is characterized in that including：
Acquiring unit, for obtain include external diagnosis reagent image；
First extraction unit, for extracting the transverse edge in described image；The transverse edge is tried along the in-vitro diagnosis
What the axial direction of agent extended；
Determination unit, for according to the transverse edge length and position, determine the T line and C line of the external diagnosis reagent
The position range at place；
Second extraction unit, for extracting the longitudinal edge in described image；The longitudinal edge is tried along the in-vitro diagnosis
What the radial direction of agent extended；
Computing unit, for obtaining target longitudinal edge in the position range；And calculate the target longitudinal edge difference
The color concentration in corresponding region；The target longitudinal edge is the T line and the corresponding longitudinal edge of the C line；
Recognition unit, for what the corresponding T line color concentration of T line C line color concentration corresponding with the C line compared
Sxemiquantitative recognition result of the comparison result as the external diagnosis reagent.
9. a kind of electronic equipment, which is characterized in that including：Processor, memory and bus, wherein
The processor and the memory complete mutual communication by the bus；
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to instruct energy
Enough methods executed as described in claim 1 to 7 is any.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute the method as described in claim 1 to 7 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810574939.7A CN108830314B (en) | 2018-06-06 | 2018-06-06 | Semi-quantitative identification method and device for in-vitro diagnostic reagent |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810574939.7A CN108830314B (en) | 2018-06-06 | 2018-06-06 | Semi-quantitative identification method and device for in-vitro diagnostic reagent |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108830314A true CN108830314A (en) | 2018-11-16 |
| CN108830314B CN108830314B (en) | 2020-12-15 |
Family
ID=64144059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810574939.7A Active CN108830314B (en) | 2018-06-06 | 2018-06-06 | Semi-quantitative identification method and device for in-vitro diagnostic reagent |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108830314B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112453A (en) * | 2021-03-22 | 2021-07-13 | 深圳市华启生物科技有限公司 | Colloidal gold detection card identification method and system, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101789005A (en) * | 2010-01-22 | 2010-07-28 | 深圳创维数字技术股份有限公司 | Image searching method based on region of interest (ROI) |
| CN103116751A (en) * | 2013-01-24 | 2013-05-22 | 河海大学 | Automatic license plate character recognition method |
| CN104964973A (en) * | 2015-07-08 | 2015-10-07 | 邓双胜 | Test paper reading and analyzing method and system based on mobile terminal camera |
| CN105844615A (en) * | 2016-03-17 | 2016-08-10 | 网易（杭州）网络有限公司 | Method of identifying regular rectangular area and apparatus thereof |
| CN106404783A (en) * | 2016-09-29 | 2017-02-15 | 网易（杭州）网络有限公司 | Test paper detection method and device |
| CN106771169A (en) * | 2017-01-19 | 2017-05-31 | 厦门海荭兴仪器股份有限公司 | A kind of collaurum detection method and system based on image procossing |
-
2018
- 2018-06-06 CN CN201810574939.7A patent/CN108830314B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101789005A (en) * | 2010-01-22 | 2010-07-28 | 深圳创维数字技术股份有限公司 | Image searching method based on region of interest (ROI) |
| CN103116751A (en) * | 2013-01-24 | 2013-05-22 | 河海大学 | Automatic license plate character recognition method |
| CN104964973A (en) * | 2015-07-08 | 2015-10-07 | 邓双胜 | Test paper reading and analyzing method and system based on mobile terminal camera |
| CN105844615A (en) * | 2016-03-17 | 2016-08-10 | 网易（杭州）网络有限公司 | Method of identifying regular rectangular area and apparatus thereof |
| CN106404783A (en) * | 2016-09-29 | 2017-02-15 | 网易（杭州）网络有限公司 | Test paper detection method and device |
| CN106771169A (en) * | 2017-01-19 | 2017-05-31 | 厦门海荭兴仪器股份有限公司 | A kind of collaurum detection method and system based on image procossing |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112453A (en) * | 2021-03-22 | 2021-07-13 | 深圳市华启生物科技有限公司 | Colloidal gold detection card identification method and system, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108830314B (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chang et al. | Gold-standard and improved framework for sperm head segmentation | |
| CN110120056B (en) | Blood leukocyte segmentation method based on adaptive histogram threshold and contour detection | |
| US10234442B2 (en) | Device and method for finding cell nucleus of target cell from cell image | |
| WO2014031086A1 (en) | Methods and systems for automatic location of optic structures in an image of an eye, and for automatic retina cup-to-disc ratio computation | |
| CN113344894B (en) | Method and device for extracting features of fundus leopard spots and determining feature indexes | |
| US20220047159A1 (en) | Glaucoma image recognition method and device and diagnosis system | |
| US20150356342A1 (en) | Image processing apparatus, image processing method, and storage medium | |
| Shaikh et al. | A novel approach for automatic number plate recognition | |
| CN111639598A (en) | License plate recognition method, license plate recognition device, license plate recognition equipment and storage medium | |
| CN108601509B (en) | Image processing apparatus, image processing method, and program-recorded medium | |
| CN108802024A (en) | A kind of sxemiquantitative recognition methods of external diagnosis reagent and device | |
| Nisha et al. | A computer-aided diagnosis system for plus disease in retinopathy of prematurity with structure adaptive segmentation and vessel based features | |
| CN108663382A (en) | The method and device of the paper surface defects detection of view-based access control model conspicuousness | |
| CN117392733B (en) | Acne grading detection method and device, electronic equipment and storage medium | |
| CN111582045A (en) | Living body detection method and device and electronic equipment | |
| Tomari et al. | Red blood cell counting analysis by considering an overlapping constraint | |
| WO2012121488A2 (en) | Method for processing medical blood vessel image | |
| CN108830314A (en) | A kind of sxemiquantitative recognition methods of external diagnosis reagent and device | |
| CN114332058A (en) | Serum quality identification method, device, equipment and medium based on neural network | |
| CN112288697B (en) | Method, apparatus, electronic device and readable storage medium for quantifying degree of abnormality | |
| CN113724235A (en) | Semi-automated Ki67/ER/PR negative and positive cell counting system and method under changed conditions of environment under mirror | |
| Moallem et al. | Detecting and segmenting white blood cells in microscopy images of thin blood smears | |
| Angkoso et al. | Automatic white blood cell segmentation based on color segmentation and active contour model | |
| CN104050455B (en) | A kind of skin color detection method and system | |
| Cao et al. | Leaf vein extraction and angle measurement using hue information and line detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |