CN110096980A - Character machining identifying system - Google Patents
Character machining identifying system Download PDFInfo
- Publication number
- CN110096980A CN110096980A CN201910320804.2A CN201910320804A CN110096980A CN 110096980 A CN110096980 A CN 110096980A CN 201910320804 A CN201910320804 A CN 201910320804A CN 110096980 A CN110096980 A CN 110096980A
- Authority
- CN
- China
- Prior art keywords
- image
- character
- millimeters
- identifying
- workpiece
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003754 machining Methods 0.000 title claims abstract description 22
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 238000006243 chemical reaction Methods 0.000 claims abstract description 15
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 11
- 238000000926 separation method Methods 0.000 claims description 10
- 230000000875 corresponding Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 241000894007 species Species 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 210000003850 cellular structures Anatomy 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006011 modification reaction Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/418—Document matching, e.g. of document images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30176—Document
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
The present invention relates to technical field of vision detection, refer in particular to a kind of character machining identifying system, include the following steps, step A: acquisition image；Step B: binary conversion treatment is carried out to the image of acquisition；Step C: the topography in image after the completion of extraction binary conversion treatment obtains identification region image；Step D: Threshold segmentation is carried out to identification region image, obtains text image；Step E: minimum circumscribed rectangle calculating is carried out to text image, obtains rectangular text image；Step F: OCR character recognition calculating is carried out to rectangular text image, judges the correspondence character picture of rectangular text image.Specific filming apparatus and its arrangement parameter cooperate the identification step, reach identification precision well and character match accuracy is high, and compatibility can identify by force multirow character simultaneously.
Description
Technical field
The present invention relates to technical field of vision detection, refer in particular to a kind of character machining identifying system.
Background technique
The characteristics of Machine Vision Detection is the flexibility and the degree of automation for improving production.It is not suitable for manual work some
Dangerous work environment or artificial vision be difficult to the occasion met the requirements, machine in normal service vision substitutes artificial vision；Exist simultaneously
In high-volume industrial processes, manually visual inspection product quality low efficiency and precision is not high, with Machine Vision Detection side
Method can greatly improve the degree of automation of production efficiency and production.And machine vision is easily achieved information integration, is to realize
The basic technology of computer integrated manufacturing system.Vision-based detection is exactly to replace human eye with machine to measure and judge.Vision-based detection is
Refer to that, by machine vision product, image-pickup device is divided to CMOS and two kinds of CCD, will be ingested target and be converted into picture signal,
It sends dedicated image processing system to, according to the information such as pixel distribution and brightness, color, is transformed into digitized signal；Image
System carries out various operations to these signals to extract clarification of objective, and then the equipment at scene is controlled according to the result of differentiation
Movement.It is the valuable mechanism for producing, assembling or pack.It is in detection defect and prevents from faulty goods to be dispensed into disappearing
There is immeasurable value in terms of the function of the person of expense.
As above situation, vision-based detection has huge market value, most crucial in vision-based detection system not to be
Hardware device but algorithm steps, and algorithm steps can be because of testing result requirement, product shape, operating environment situation and design
The appearance of the factors such as the technical capability of personnel or group is multifarious, if core algorithm step design shortcoming, affects a whole set of view
Feel the operational efficiency and running quality of detection device, and in the algorithm steps of character machining identification, in the market most of technology
The use cost of scheme is high, while algorithm steps also grasp by complex conventional change parameter etc. for being unfavorable for those skilled in the art
It sets.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of specific filming apparatus of collocation, reach identification precision and character
Matching accuracy is high, and compatibility can identify by force the character machining identifying system of multirow character simultaneously.
In order to solve the above-mentioned technical problem, the present invention adopts the following technical scheme: a kind of character machining identifying system, including
Rack, the monitor station for being set to rack, the arc light source above monitor station and the Image Acquisition above annular light source
Device, the rack are installed with horizontal cross bar and the lifting mould group for driving horizontal cross bar to move up and down；Vision-based detection step
It is as follows, step A: acquisition image；
Step B: binary conversion treatment is carried out to the image of acquisition；
Step C: the topography in image after the completion of extraction binary conversion treatment obtains identification region image；
Step D: Threshold segmentation is carried out to identification region image, obtains text image；
Step E: minimum circumscribed rectangle calculating is carried out to text image, obtains rectangular text image；
Step F: OCR character recognition calculating is carried out to rectangular text image, judges the correspondence character information of rectangular text image.
Preferably, in the step F, specific step is as follows for OCR character recognition calculating:
Step F1: character picture is acquired in advance；
Step F2: binary conversion treatment and filtration treatment are carried out to character picture；
Step F3: template image is set by the character picture for completing processing and is stored to memory module；
Step F4: obtained rectangular text image is matched with the template image in memory module, obtains corresponding character letter
Breath.
Preferably, the acquisition image device includes being arranged in pairs or groups 25 to 45 millimeters using the black and white camera of 300 to 6,000,000 pixels
Tight shot carry out shooting and using arc light source from side be irradiated assistant images shoot.
Preferably, in acquisition image process, horizontal interval distance is 150 to 200 millimeters between tight shot and workpiece,
Vertical height separation distance between the horizontal plane that tight shot and workpiece are placed is 210 to 280 millimeters, while the tight shot
Angle between horizontal plane is 20 to 48 degree.
Preferably, in acquisition image process, the horizontal interval distance between arc light source and workpiece is 35 to 68 millimeters,
Vertical height separation distance between the horizontal plane that arc light source and workpiece are placed is 80 to 160 millimeters.
Preferably, the acquisition image device includes the fixed-focus mirror using 35 millimeters of the black and white camera collocation of 5,000,000 pixels
Head carries out shooting and is irradiated assistant images shooting from side using arc light source.
Preferably, in acquisition image process, horizontal interval distance is 175 millimeters between tight shot and workpiece, fixed-focus
Vertical height separation distance between the horizontal plane that camera lens and workpiece are placed is 240 millimeters, while the tight shot and horizontal plane
Between angle be 35 degree.
Preferably, in acquisition image process, the horizontal interval distance between arc light source and workpiece is 50 millimeters, arc
Vertical height separation distance between the horizontal plane that light source and workpiece are placed is 130 millimeters.
The beneficial effects of the present invention are: a kind of character machining identifying system is provided, in actual application, according to
Specific filming apparatus is that the camera of special parameter and tight shot is selected to cooperate specific light source, by the camera, tight shot
It is arranged with light source according to special parameter distance, just controls required figure well in the early period that acquisition image step is analysis image
The quality of picture, those parameter settings are that producer's long-time experience accumulation obtains, can collect good image using those parameters
For effect to cooperate subsequent character recognition, the character recognition in the present invention includes interpreting blueprints, and extraction needs identification region, text
Text Feature Extraction is come out by modes such as Threshold segmentation, morphology, the text extracted is calculated the minimum external of region
Rectangle individually cuts out each minimum circumscribed rectangle image, and progress OCR character of classifying by reading order sequence, by MLP
MLP analysis model is removed in identification, and specific filming apparatus and its arrangement parameter cooperate the identification step, reach identification well
Precision and character match accuracy are high, and compatibility can identify by force multirow character simultaneously.
Detailed description of the invention
Fig. 1 is the step functional block diagram of character machining identifying system of the present invention.
Fig. 2 is that OCR character recognition calculates step functional block diagram in the present invention.
Fig. 3 is the positional diagram of workpiece, camera, tight shot and arc light source in the present invention.
Specific embodiment
For the ease of the understanding of those skilled in the art, below with reference to embodiment, the present invention is further illustrated, real
The content that the mode of applying refers to not is limitation of the invention.
As shown in Figure 1 to Figure 3, a kind of character machining identifying system, including rack 5, the monitor station 6 for being set to rack 5, position
Arc light source above monitor station 6 and the image collecting device above annular light source, the rack 5 are installed with horizontal cross
Bar 7 and lifting mould group 8 for driving horizontal cross bar 7 to move up and down；Steps are as follows for vision-based detection, step A: acquisition image is adopted
Collection image device includes carrying out shooting and using arc using the tight shot 3 of 35 millimeters of the collocation of black and white camera 2 of 5,000,000 pixels
Shape light source 4 is irradiated assistant images shooting from side, in acquisition image process, between tight shot 3 and workpiece 1 between level
For gauge from being 175 millimeters, the vertical height separation distance between the horizontal plane that tight shot 3 and workpiece 1 are placed is 240 millimeters,
The angle between the tight shot 3 and horizontal plane is 35 degree simultaneously, and the horizontal interval distance between arc light source 4 and workpiece 1 is
50 millimeters, the vertical height separation distance between arc light source 4 and the horizontal plane of the placement of workpiece 1 is 130 millimeters；
Step B: binary conversion treatment is carried out to the image of acquisition；
Step C: the topography in image after the completion of extraction binary conversion treatment obtains identification region image；
Step D: Threshold segmentation is carried out to identification region image, obtains text image；
Step E: minimum circumscribed rectangle calculating is carried out to text image, obtains rectangular text image；
Step F: carrying out OCR character recognition calculating to rectangular text image, and the specific steps that wherein OCR character recognition calculates are such as
Under:
Step F1: character picture is acquired in advance；
Step F2: binary conversion treatment and filtration treatment are carried out to character picture；
Step F3: template image is set by the character picture for completing processing and is stored to memory module；
Step F4: obtained rectangular text image is matched with the template image in memory module, obtains corresponding character letter
Breath.
The character machining identifying system of the present embodiment selects special in actual application according to specific filming apparatus
The camera and tight shot 3 for determining parameter cooperate specific light source, by the camera, tight shot 3 and light source according to special parameter
Distance arrangement is just to analyze the quality for controlling required image early period well of image, those parameters in acquisition image step
Setting is that producer's long-time experience accumulation obtains, it is subsequent to cooperate to collect good image effect using those parameters
Character recognition, the character recognition in the present invention include interpreting blueprints, extraction needs identification region, text by Threshold segmentation, form
Learn etc. modes Text Feature Extraction is come out, the minimum circumscribed rectangle that the text extracted is calculated region, each minimum outer
It connects rectangle and individually cuts out image, and classify by reading order sequence, by MLP and carry out OCR character recognition, remove MLP analysis
Model, specific filming apparatus and its arrangement parameter cooperate the identification step, reach identification precision and character match well
Accuracy is high, and compatibility can identify by force multirow character simultaneously.
In the present embodiment, binary conversion treatment is carried out to obtained image first, is reached with this and filters out interference figure in image
As the information characteristics of letter.It is obtaining after the image of binary conversion treatment, OCR character recognition algorithm is used to image, is first carried out
Study, then identifies similar character.
Binary conversion treatment: binaryzation is exactly to set the gray value of the pixel on image to 0 or 255, that is, will be whole
A image shows the process of apparent black and white effect.It is 0 that the binary conversion treatment of image, which is exactly by the gray value of the point on image,
Or 255, that is, whole image is showed into apparent black and white effect.The gray level image of 256 brightness degrees is passed through suitable
When threshold value choose and obtain and still can reflect that image is whole and the binary image of local feature.In Digital Image Processing
In, bianry image plays a very important role, especially in practical image procossing, the structure with binary Images Processing realization
At system be it is very much, the processing and analysis of Yao Jinhang bianry image first have to a Binary Sketch of Grey Scale Image, obtain binaryzation
Image, so to be conducive to when being further processed to image, point that the set property of image is only 0 or 255 with pixel value
Position it is related, do not further relate to the multilevel values of pixel, processing made to become simple, and data processing and decrement it is small.In order to
Ideal bianry image is obtained, the region that the general boundary definition using closing, connection does not overlap.All gray scales are greater than or equal to
The pixel of threshold value is judged as belonging to certain objects, and gray value is 255 expressions, and otherwise these pixels are excluded in object areas
Other than domain, gray value 0 indicates the object area of background or exception.
The Threshold segmentation used in step D for used Otsu thresholding method Otsu maximum variance between clusters principle utilize
Original image is divided into prospect, two images of background by threshold value.Prospect: using n1, and csum, m1 indicate the prospect under present threshold value
Points, moment of mass, average gray.Background: using n2, and sum-csum, m2 indicate the points of the background under present threshold value, matter
Measure square, average gray.When taking optimal threshold, background should be maximum with prospect difference, and key is how to select to measure difference
Standard, and in otsu algorithm this measure difference standard be exactly maximum between-cluster variance, in this program inter-class variance use
Sb expression, maximum between-cluster variance fmax；
Otsu algorithm: taking an optimal threshold that original image is divided into foreground (part A) and background colour (part B), two-part
Inter-class variance is bigger, illustrates that two parts difference is bigger, just can effective segmented image.So the algorithm is it is crucial that find most
Excellent threshold value；
Variance: such as 1,2,3,4,5；First average: 1/5(1+2+3+4+5)=3；Variance=1/5 [(1-3) ^2+(2-3) ^2+
(3-3)^2+(4-3)^2+(5-3)^2]；(above formula can bring respectively multiplication into 1/5)；Inter-class variance: it is similar to variance, it asks not
With the variance between part；
Such as 1,2,3,4,5.Treat as a part A 1,2,3,4,5 treat as part B, by variance it is found that needing to obtain total equal
Value, part A all proportions, part B proportion, part A value (i.e. mean value), part B value (i.e. mean value), PA(A ratio)=3/5,
PB(B ratio)=2/5, ave_all(grand mean)=3, ave_A (A mean value)=1/3 (1+2+3), ave_B (B mean value)=1/2 (4+5)
, inter-class variance=PA* (ave_A-ave_all) ^2+PB* (ave_B-ave_all) ^2(Otsu algorithm).
Image has used edge enhancement algorithm, one kind of image enhancement processing.It is by image (or image) adjacent picture elements
The brightness value (or tone) in (or region) differs to be added at biggish edge (i.e. the boundary line of image tone mutation or type of ground objects)
With the technical method highlighted.The side of different species type or phenomenon can be more clearly shown through the enhanced image in edge
The trace of boundary or linear image, in order to the identification of different species types and its delineation of distribution；Sobel operator has two
A, one is detection level edge；The other is detecting vertical pingbian edge.Sobel operator another kind form is each to same
Property Sobel operator, also there are two, one is detection level edge, the other is detecting vertical pingbian edge.Isotropism
Sobel operator is more more accurate than the position weighting coefficient of common Sobel operator, detect different directions edge when gradient+-
Amplitude is consistent.Since Sobel operator is the form of filter operator, for extracting edge, fast convolution function can use, simply
Effectively, it therefore is widely used.Only drawback is that there is no strictly distinguish the main body of image with background to Sobel operator
Come, is in other words exactly that Sobel operator is not based on image grayscale and is handled, since Sobel operator does not have stringent simulation people
Vision physiological feature, so extract image outline it is sometimes not satisfactory.When observing piece image, we
Often it is first noted that be the image part different from background, exactly this part highlights main body, be based on the theory, I
Give following thresholding contours extract algorithm, which has mathematically proved required when pixel meets normal distribution
Solution is optimal.The convolution of Sobel boundary operator is as shown, each pixel in image does convolution with the two cores.This
Two cores respond maximum, output bit of the maximum value of two convolution as the point to vertical edge and horizontal edge respectively.Operation
The result is that a breadths edge magnitude image.
Character machining is called OCR or OCV detection, is specially to various electronic components, cell phone keyboard, computor-keyboard etc.
The character for printing or carving on article surface is identified and is detected, and common character includes number, English alphabet, symbol, the Chinese
Word etc.；It much studies the corresponding inspection software of the enterprise developments of machine vision both at home and abroad at present, carries out after simply setting
To detected character automatic identification, detection, if any abnormal generation, machine down of alarming or control can be prompted.It is wanted to not meeting
Exportable control signal after the workpiece 1 asked detects, rejects rejected product, and self energy degree is quite high；The skill of character machining system
Art feature mainly has: operation interface is clear, simple and easy, and only need to simply set can execute measurement automatically；Survey Software
And the entirely autonomous exploitation of algorithm, system are with strong points；It can flexible setting detection template, detection range；Part detection function may be selected
Can, improve measuring speed；Specialized light source design, imaging clearly are uniform, it is ensured that measurement task is completed；Support Multiple Type product
Measurement, have On-line Product and the functions such as search for automatically；Using high-speed industrial camera, examined suitable for either statically or dynamically production line
It surveys；Installation is simple, does not influence primary producing line work;It is compact-sized, easily operated, maintenance and expansion；High reliablity, operation are steady
It is fixed, it is suitble to various live service conditions；Image recognition is mainly that the following steps are rapid: step 1: interpreting blueprints, and extraction needs identification region；
Step 2: text comes out Text Feature Extraction by modes such as Threshold segmentation, morphology；Step 3: the text meter extracted
Calculate the minimum circumscribed rectangle in region；Step 4: each minimum circumscribed rectangle is individually cut out image, and is arranged by reading order
Sequence；Step 5: classified by MLP and carry out OCR character recognition；Step 6: MLP analysis model is removed；
OCR identification is mainly that the following steps are rapid: step 1: interpreting blueprints, extraction need identification region；Step 2: and then learning character will
The character of study is stored in character set；Step 3: character is carried out binaryzation first by learning character, then carries out frame word selection
Symbol is learnt, and filter area (filtering out the stain of a little interference character machining) is first arranged in the width and height of setting character
Degree, then merging character is set, there is partial character in centre fracture by binaryzation after polishing irradiates character to improve
The case where；Step 4: the learning template kept is placed into character repertoire, and as matching template, entire character repertoire need to arrive A
Z, 0 to 9, all learn on one side.Guarantee that the subsequent character on other products identifies.
In addition, being used for description purposes only if any term " first ", " second ", it is not understood to indicate or imply relatively heavy
The property wanted or the quantity for implicitly indicating technical characteristic." first " is defined as a result, " second " feature can be expressed or implicit include
One or more this feature, in the present description, " several " are meant that two or more, unless otherwise clearly having
The restriction of body.
In the present invention, except as otherwise clear stipulaties and restriction, should make if any term " assembling ", " connected ", " connection " term
Broad sense goes to understand, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It is also possible to mechanical connect
It connects；It can be directly connected, be also possible to be connected by intermediary, can be and be connected inside two elements.For ability
For the those of ordinary skill of domain, the concrete meaning of above-mentioned term in the present invention can be understood as the case may be.
Several embodiments of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (8)
1. character machining identifying system, including rack (5), the monitor station (6) that is set to rack (5), it is located above monitor station (6)
Arc light source (4) and be located at annular light source (4) above image collecting device, it is characterised in that: the rack (5) is installed with
Horizontal cross bar (7) and lifting mould group (8) for driving horizontal cross bar (7) to move up and down；Steps are as follows for vision-based detection,
Step A: acquisition image；
Step B: binary conversion treatment is carried out to the image of acquisition；
Step C: the topography in image after the completion of extraction binary conversion treatment obtains identification region image；
Step D: Threshold segmentation is carried out to identification region image, obtains text image；
Step E: minimum circumscribed rectangle calculating is carried out to text image, obtains rectangular text image；
Step F: OCR character recognition calculating is carried out to rectangular text image, judges the correspondence character information of rectangular text image.
2. character machining identifying system according to claim 1, it is characterised in that: in the step F, OCR character recognition
Specific step is as follows for calculating:
Step F1: character picture is acquired in advance；
Step F2: binary conversion treatment and filtration treatment are carried out to character picture；
Step F3: template image is set by the character picture for completing processing and is stored to memory module；
Step F4: obtained rectangular text image is matched with the template image in memory module, obtains corresponding character letter
Breath.
3. character machining identifying system according to claim 1, it is characterised in that: the acquisition image device includes using
The tight shot (3) of 25 to 45 millimeters of black and white camera (2) collocation of 300 to 6,000,000 pixels carries out shooting and using arc light
Source (4) is irradiated assistant images shooting from side.
4. character machining identifying system according to claim 3, it is characterised in that: in acquisition image process, fixed-focus mirror
Horizontal interval distance is 150 to 200 millimeters between head (3) and workpiece (1), the horizontal plane of tight shot (3) and workpiece (1) placement
Between vertical height separation distance be 210 to 280 millimeters, while the angle between the tight shot (3) and horizontal plane is 20
To 48 degree.
5. character machining identifying system according to claim 3, it is characterised in that: in acquisition image process, arc light
Horizontal interval distance between source (4) and workpiece (1) is 35 to 68 millimeters, the horizontal plane of arc light source (4) and workpiece (1) placement
Between vertical height separation distance be 80 to 160 millimeters.
6. character machining identifying system according to claim 1, it is characterised in that: the acquisition image device includes using
The tight shot (3) of 35 millimeters of black and white camera (2) collocation of 5000000 pixels shoot and uses arc light source (4) from side
Face is irradiated assistant images shooting.
7. character machining identifying system according to claim 6, it is characterised in that: in acquisition image process, fixed-focus mirror
Horizontal interval distance is 175 millimeters between head (3) and workpiece (1), between the horizontal plane that tight shot (3) and workpiece (1) are placed
Vertical height separation distance be 240 millimeters, while the angle between the tight shot (3) and horizontal plane is 35 degree.
8. character machining identifying system according to claim 6, it is characterised in that: in acquisition image process, arc light
Horizontal interval distance between source (4) and workpiece (1) is 50 millimeters, between the horizontal plane that arc light source (4) and workpiece (1) are placed
Vertical height separation distance be 130 millimeters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910320804.2A CN110096980A (en) | 2019-04-20 | 2019-04-20 | Character machining identifying system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910320804.2A CN110096980A (en) | 2019-04-20 | 2019-04-20 | Character machining identifying system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110096980A true CN110096980A (en) | 2019-08-06 |
Family
ID=67445416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910320804.2A Pending CN110096980A (en) | 2019-04-20 | 2019-04-20 | Character machining identifying system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110096980A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110532973A (en) * | 2019-09-03 | 2019-12-03 | 海南阿凡题科技有限公司 | The identification of pair of pages text image and locating segmentation method based on special anchor point |
| CN111325213A (en) * | 2020-02-20 | 2020-06-23 | 电子科技大学 | Digital character detection method of mobile target |
| CN112445450A (en) * | 2019-08-30 | 2021-03-05 | 比亚迪股份有限公司 | Method and device for controlling terminal based on voice, storage medium and electronic equipment |
| CN112991410A (en) * | 2021-04-29 | 2021-06-18 | 北京世纪好未来教育科技有限公司 | Text image registration method, electronic equipment and storage medium thereof |
-
2019
- 2019-04-20 CN CN201910320804.2A patent/CN110096980A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112445450A (en) * | 2019-08-30 | 2021-03-05 | 比亚迪股份有限公司 | Method and device for controlling terminal based on voice, storage medium and electronic equipment |
| CN110532973A (en) * | 2019-09-03 | 2019-12-03 | 海南阿凡题科技有限公司 | The identification of pair of pages text image and locating segmentation method based on special anchor point |
| CN110532973B (en) * | 2019-09-03 | 2022-02-01 | 海南阿凡题科技有限公司 | Double-page text image identification and positioning segmentation method based on special anchor points |
| CN111325213A (en) * | 2020-02-20 | 2020-06-23 | 电子科技大学 | Digital character detection method of mobile target |
| CN111325213B (en) * | 2020-02-20 | 2022-03-15 | 电子科技大学 | Digital character detection method of mobile target |
| CN112991410A (en) * | 2021-04-29 | 2021-06-18 | 北京世纪好未来教育科技有限公司 | Text image registration method, electronic equipment and storage medium thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110096980A (en) | Character machining identifying system | |
| AU2016250791B2 (en) | Colony contrast gathering | |
| CN102426649B (en) | Simple steel seal digital automatic identification method with high accuracy rate | |
| CN109490316B (en) | Surface defect detection algorithm based on machine vision | |
| CN105844621A (en) | Method for detecting quality of printed matter | |
| CN108355987B (en) | A kind of screen printing of battery quality determining method based on piecemeal template matching | |
| CN110414334B (en) | Intelligent water quality identification method based on unmanned aerial vehicle inspection | |
| CN108765402B (en) | Non-woven fabric defect detection and classification method | |
| CN106056597A (en) | Object visual detection method and device | |
| CN104198497A (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN111982916A (en) | Welding seam surface defect detection method and system based on machine vision | |
| CN109115775B (en) | Betel nut grade detection method based on machine vision | |
| CN110216080A (en) | A kind of Quality Monitoring Control System of the PCB processing producing line based on image comparison | |
| CN109307675A (en) | A kind of product appearance detection method and system | |
| CN111369516A (en) | Transformer bushing heating defect detection method based on infrared image recognition | |
| CN107016353B (en) | A kind of integrated method and system of variable resolution target detection and identification | |
| CN110108712A (en) | Multifunctional visual sense defect detecting system | |
| Wah et al. | Analysis on feature extraction and classification of rice kernels for Myanmar rice using image processing techniques | |
| CN113252568A (en) | Lens surface defect detection method, system, product and terminal based on machine vision | |
| CN108898584A (en) | A kind of full-automatic veneering capacitor welding equipment polarity discriminating method based on image analysis | |
| CN106504251B (en) | A kind of electric aluminum foil cubic texture detection method of content based on picture processing | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| CN110389127B (en) | System and method for identifying metal ceramic parts and detecting surface defects | |
| CN109622404B (en) | Automatic sorting system and method for micro-workpieces based on machine vision |
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 |