CN103699896A - Scanning device, and device and method for judging scanning angle by using image brightness information - Google Patents
Scanning device, and device and method for judging scanning angle by using image brightness information Download PDFInfo
- Publication number
- CN103699896A CN103699896A CN201210366235.3A CN201210366235A CN103699896A CN 103699896 A CN103699896 A CN 103699896A CN 201210366235 A CN201210366235 A CN 201210366235A CN 103699896 A CN103699896 A CN 103699896A
- Authority
- CN
- China
- Prior art keywords
- field picture
- background pixel
- scanning
- brightness value
- scanning angle
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a scanning device. The scanning device comprises an image sensor and a controller, wherein the image sensor is connected with the controller and used for performing focusing imaging to characters on scanning medium, generating frame image data and sending the data to the controller, so as to process the data; the controller is used for receiving the frame image data generated through the image sensor, judging the scanning angle of the scanning device through the brightness distribution of all pixel points of a gray level image, and alerting a user to adjust the scanning angle according to judging results. The scanning angle is judged through the brightness distribution condition of a background image, the scanning angle can be automatically judged, when a certain scanning angle causes that the position of light shot on a frame image at right angle is close to the edge of the image, the brightness of the whole image is nonuniform, then the user can be alerted to adjust a pen holding angle, and good scanning recognition effect is achieved.
Description
Technical field
The invention belongs to image processing field, be specifically related to a kind of scanister, and utilize the apparatus and method of image luminance information judgement scanning angle.
Background technology
Electronic scanning pen (abbreviation wand) is one of important application of OCR.The optical camera of wand is taken pictures to scanned document continuously according to certain frequency, obtains the sequence of image frames of scanned document, carries out OCR processing after then sequence of image frames being spliced into a width panoramic picture, realizes the Rapid input of scanning data.
The patent of Granted publication CN201562284U describes the structure of wand in detail.Wand comprises: housing, triggers pin, function button, acquisition window, trigger switch, main circuit board, USB interface seat, light path illumination LED, camera lens, image sensor board, connection seat between plate, imageing sensor and spring.Main circuit board is assemblied in the upper end of housing.Between digital signal controller DSP, USB interface seat, function button, trigger switch, light path illumination LED and plate, connection seat is arranged on main circuit board.Imageing sensor is positioned at the lower end of housing.In this image sensor board, assembling is contacted the flip flop equipment of paper by the sensitive scanning pen that between imageing sensor, camera lens and plate, connection seat, triggering pin, spring form jointly with trigger switch.When wand contact paper scans, triggering pin is stressed and push spring and trigger switch, and trigger switch produces working signal, is transferred to the digital signal controller DSP in main circuit board.It is luminous that this digital signal controller is controlled light path illumination LED, and camera photographed frame image, delivers to processing module by imageing sensor.
In above-mentioned patent documentation, light path illumination LED is subject to the restriction of installation site, and at whole two field picture, lighting level is different everywhere, when direct projection is during to one jiao of two field picture, whole each pixel brightness value of two field picture differs larger, thereby affects binaryzation effect and the OCR recognition result of image.
Summary of the invention
In order to overcome the above-mentioned defect of prior art, the present invention proposes a kind of scanister and utilizes the apparatus and method of image luminance information judgement scanning angle.
The present invention proposes a kind of scanister, comprising: imageing sensor, be connected with controller, and for the character focal imaging on scanned medium, delta frame view data, sends into controller and processes; Controller, for receiving the frame image data being generated by imageing sensor, and utilizes the distribution of two field picture background pixel brightness value to judge the scanning angle of this scanister, according to judged result, comes reminding user to adjust scanning angle.
Wherein said controller further comprises: two field picture background extracting device, for extracting two field picture background according to described frame image data; Background pixel brightness value distributed acquisition device, distributes for obtaining described two field picture background pixel brightness value; Scanning angle judgment means, for distributing according to described two field picture background pixel brightness value, judgement scanning angle.
Wherein said two field picture background extracting device adopts binaryzation mode to extract two field picture background or adopts watershed segmentation mode to carry out Region Segmentation and extracts two field picture background.
Wherein background pixel brightness value distributed acquisition device obtains the two field picture background pixel brightness value distribution being parallel on direction of scanning, comprise: the mean flow rate of every row background pixel point in the described background pixel brightness value distributed acquisition device statistics direction vertical with direction of scanning, matching gray-scale value curve, obtaining two field picture background pixel brightness value distributes, or along direction of scanning, background pixel is divided into n part, calculate every part average brightness value normalization, obtaining two field picture background pixel brightness value distributes, wherein, n >=2; Described scanning angle judgment means judges scanning angle or tables look-up to recently judging scanning angle according to every part background pixel mean flow rate normalized value according to the gray-scale value slope of a curve of matching.
Wherein said watershed segmentation mode comprises: first adopt morphological reconstruction technology to carry out mark to specific target and background in image, and then use minimum calibration technique to revise gradient image, finally revised gradient image is carried out to watershed transform and obtain final segmentation result.
Wherein said scanister also comprises display screen, perforate, flip flop equipment, light path device and optical lens, and display screen wherein, when controller judgement need to be adjusted scanning angle, for to user's display reminding information; Perforate is arranged on the shell position corresponding with imageing sensor of scanister, makes imageing sensor see through perforate and obtains the image on scanned medium; Flip flop equipment is for when scanister contact scanning medium scans, produce working signal, control light path device and form light path, the light that light path produces, after scanned medium reflection, more directly converges in imageing sensor for imageing sensor imaging through optical lens.
The present invention proposes a kind of method of utilizing image luminance information judgement scanning angle in addition, and the method comprising the steps of: step 1, and the frame image data that scanning obtains according to scanister extracts two field picture background; Step 2, obtains described two field picture background pixel brightness value and distributes; Step 3, distributes according to described two field picture background pixel brightness value, the scanning angle of judgement scanister.
The present invention also proposes a kind of device that utilizes image luminance information judgement scanning angle, and it comprises: two field picture background extracting device, extracts two field picture background for the frame image data obtaining according to scanister; Background pixel brightness value distributed acquisition device, distributes for obtaining described two field picture background pixel brightness value; Scanning angle judgment means, for distributing according to described two field picture background pixel brightness value, the scanning angle of judgement scanister.
The present invention utilizes the scanning angle of each pixel Luminance Distribution judgement scanister of gray level image.For illumination path and the definite scanister of camera position relation, the position of illumination light paths of LEDs direct projection on two field picture changes with scanning angle is different.When background pixel point brightness skewness, can judge thus that scanning angle is improper, and user is pointed out, adjust scanning angle, thereby improve discrimination.
Accompanying drawing explanation
Fig. 1 is the structural representation of scanister of the present invention;
Fig. 2 is the functional block diagram of scanister of the present invention;
Fig. 3 is the pixel intensity curve that in the concrete example of the present invention one, wand obtains in different scanning angle;
Fig. 3 a is the brightness curve that scanning angle 90 obtains while spending, slope-0.494;
Fig. 3 b is the brightness curve that scanning angle 75 obtains while spending, slope-0.0209;
Fig. 3 c is the brightness curve that scanning angle 45 obtains while spending, slope 0.760;
Fig. 4 a is the two field picture that wand obtains while approximately becoming miter angle with scanned medium;
Fig. 4 b is for to obtain image to this two field picture binarization segmentation;
Fig. 4 c is for to cut apart based on this brightness curve that image obtains.
Fig. 5 a is that wand approximately becomes an angle of 90 degrees to scan the two field picture obtaining with scanned medium, the image of Fig. 5 b for these two field picture two watershed segmentation are obtained.
Fig. 6 is the process flow diagram that the present invention utilizes image luminance information judgement scanning angle method.
Embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in more detail.
The present invention proposes a kind of scanister, and the apparatus and method of utilizing image luminance information judgement scanning angle, its ultimate principle is to utilize each pixel Luminance Distribution judgement scanning angle of gray level image, when background pixel point brightness skewness, can judge thus that scanning angle is improper, and user is pointed out, adjust scanning angle, thereby improve discrimination.
Fig. 1 is the structural representation of scanister of the present invention.As shown in Figure 1.With reference to Fig. 1, this scanister comprises housing 1, controller 2, imageing sensor 3, display screen 4, optical lens 5, perforate 6, flip flop equipment 7, light path device 8.
In shell 1 position corresponding with imageing sensor 3, offer a perforate 6, make imageing sensor 3 see through perforate 6 and obtain the character picture in simulating keyboard or scanning data.
Flip flop equipment 7 is for when scanister contact scanning medium scans, produce working signal, control light path device 8 and form light paths, the light that light path produces, after scanned medium reflection, more directly converges in imageing sensor 3 for imageing sensor 3 imagings through optical lens 5.Light path device is preferably used light path illumination LED.
Two field picture background extracting device 201, for obtaining two field picture background.In the present invention, can adopt and extract in two ways two field picture background, the first is to adopt binarization method that prospect and background are separated, thereby extracts two field picture background, the second is to adopt watershed segmentation mode to carry out Region Segmentation, extracts two field picture background.
Described image binaryzation is exactly that the gray-scale value of the pixel on image is set to 0 or 1, namely whole image is presented to obvious black and white effect.The further processing that the binaryzation of image is conducive to highlight, becomes simply image, and data volume reduces, and can highlight the profile of specific target.
Described watershed areas domain splitting method, it is a kind of dividing method of the mathematical morphology based on topological theory, its basic thought is that image is regarded as to the topological landforms in geodesy, in image, the gray-scale value of every bit pixel represents the sea level elevation of this point, each local minimum and range of influence thereof become reception basin, and the border of reception basin forms watershed divide.The concept of watershed divide and formation can illustrate by simulation immersion process.On each local minimum surface, pierce through an aperture, then whole model is slowly immersed in the water, along with the intensification of immersing, the domain of influence of each local minimum, slowly to external expansion, is constructed dam at two reception basin meets, forms watershed divide.
The present invention improves traditional watershed segmentation mode, first adopt morphological reconstruction technology to carry out mark to specific target and background in image, and then use minimum calibration technique to revise gradient image, finally revised gradient image is carried out to watershed transform and obtain final segmentation result.
Background pixel brightness value distributed acquisition device 202, distributes for obtaining the two field picture background pixel brightness value being parallel on direction of scanning.In the present invention, also can obtain the distributed intelligence of background pixel brightness value by two kinds of modes, the first is the mean flow rate of every row background pixel point in the described background pixel brightness value distributed acquisition device 202 statistics direction vertical with direction of scanning, matching gray-scale value curve, obtaining two field picture background pixel brightness value distributes, the second is along direction of scanning, background pixel to be divided into n part, calculate every part average brightness value normalization, obtaining two field picture background pixel brightness value distributes, wherein, n >=2.
Scanning angle judgment means 203, for distributing according to background pixel brightness value, judgement scanning angle.The background pixel monochrome information that scanning angle judgment means need to be obtained in conjunction with background pixel brightness value distributed acquisition device judges the angle that holds a pen.Background pixel brightness value distributed acquisition device can adopt two kinds of background pixel brightness value distribution calculation methods, scanning angle judgment means also can correspondingly be adopted and judge in two ways scanning angle, the first can judge the angle that holds a pen according to the gray-scale value slope of a curve of matching, the second can be tabled look-up according to every part background pixel mean flow rate normalized value, judgement scanning angle.
Each several part two field picture background pixel mean flow rate normalized value corresponding to pre-stored each scanning angle in this table, the each several part background pixel mean flow rate normalized value comparison that scanning angle judgment means is corresponding with each angle in table according to the every a part of background pixel mean flow rate normalized value of two field picture, by the most approaching angle of comparative result, be judged as scanning angle.
Scanister of the present invention can be wand, wand obtains having the two field picture of certain number of scanning lines and scanning columns by optical lens, image size is relevant with perforate size, for example two field picture has 80 row pixels in the direction vertical with direction of scanning, has 120 row pixels in the direction parallel with direction of scanning.From wand scanning end, vertically look over, illumination light paths of LEDs is for example arranged on the camera upper right corner, and when wand scans perpendicular to scanned medium, light vertical irradiation is in the upper left corner of two field picture, and the gray-scale value of pixel is maximum herein.Illumination light paths of LEDs also can be arranged on other positions as required, if be installed on directly over camera, when wand scans perpendicular to scanned medium, light vertical irradiation is in the centre of two field picture, and grey scale pixel value is maximum herein.
Fig. 3 is all pixel average gray of the every row of the two field picture curve that wand obtains, wherein, Fig. 3 a is that wand vertical scanning is wand every row pixel grey scale mean value curve while becoming an angle of 90 degrees with scanned medium, now camera is directly over the two field picture upper left corner, thereby by left-to-right, light is dimmed gradually, and grey scale pixel value diminishes.Fig. 3 b is wand every row pixel grey scale mean value curve while becoming 75 degree angle with scanned medium, and Fig. 3 c is wand every row place pixel grey scale mean value curve while becoming miter angle with scanned medium.
When wand, take and trigger pin as axle is from rotating to paper perpendicular to scanned medium position, when pen diminishes gradually with scanned medium angle, the bright spot that illumination light paths of LEDs impinges upon on two field picture moves to right gradually, when wand approximately becomes 75 degree angle with scanned medium, two field picture intermediate pixel is the brightest, and both sides are dimmed gradually, when wand approximately becomes miter angle with scanned medium, bright spot is near the upper right corner on two field picture, and it is large that grey scale pixel value is become to a left side gradually by the right side.Wand and scanned medium angle recognition effect when 75 degree left and right is best.When angle too small or when excessive, can judge and user is pointed out according to image background pixel brightness contribution.
Below by further illustrating wand for two examples, how scanning angle is judged.The two field picture that Fig. 4 a approximately becomes miter angle scanning to obtain for this wand and scanned medium.At wand, get after this two field picture, first the two field picture background extracting device by controller obtains two field picture background.
Two field picture background extracting device adopts image binaryzation to process and extracts background.Image binaryzation is processed and is adopted otsu method, i.e. maximum variance between clusters.The method is pressed the gamma characteristic of image, and image is divided into background and prospect two parts.Inter-class variance between background and prospect is larger, illustrates that the two-part difference of composing images is larger, when part prospect mistake is divided into background or background mistake, is divided into prospect and all can causes two parts difference to diminish.Therefore, mean that misclassification probability is minimum cutting apart of inter-class variance maximum.Through binarization method, extract image background result as shown in Figure 4 b, display foreground pixel represents with 1, and background pixel represents with 0.
According to two field picture background extracting device, obtain two field picture background, the distributed intelligence of background pixel brightness value distributed acquisition device background extraction pixel brightness value.The mean flow rate of every row background pixel point carry out matching and obtain background pixel brightness variation tendency in the background pixel brightness value distributed acquisition device statistics direction vertical with direction of scanning, as shown in Fig. 4 c.If for example calculate the x vertical with direction of scanning
ithe mean flow rate of row background pixel point, needs x in calculating chart 4b background pixel (pixel that value is 0)
ithe mean value of all pixels gray-scale value in gray-scale map 4a of row.
After obtaining the distributed intelligence of background pixel brightness value, according to matched curve slope pre-stored in wand and scanning angle corresponding relation, scanning angle judgment means, according to brightness variation tendency, judges scanning angle.According to Fig. 4 c, matched curve slope is 0.781, with in Fig. 3 c 45 when scanning degree slope approach, thereby judgement scanning angle approximately 45 degree, controller sends message and shows to display screen, displaying contents " scanning angle approximately 45 degree, please adjust ".Except display screen, also can to user, carry out voice message by loudspeaker.
Be to take to become miter angle as example is illustrated between wand and scanned medium above, and Fig. 5 a is wand, approximately become an angle of 90 degrees to scan the two field picture obtaining with scanned medium.Two field picture background extracting device adopts watershed algorithm to extract two field picture background.Watershed algorithm, is a kind of dividing method of the mathematical morphology based on topological theory, but due to image dark noise and the secretly impact of grain details, has a large amount of pseudo-local minimums in image, and they produce corresponding pseudo-reception basin in image.Therefore, each pseudo-local minimum by be used as together with the local minimum real with those one independently region by watershed algorithm, split, finally cause serious over-segmentation problem.The present invention adopts Based On Method of Labeling Watershed Algorithm to improve traditional algorithm.First adopt morphological reconstruction technology to carry out mark to specific target and background in image, and then use minimum calibration technique to revise gradient image, finally revised gradient image is carried out to watershed transform and obtain final segmentation result.The two field picture background result of Fig. 5 b for adopting this dividing ridge method to extract.Wherein display foreground pixel represents with 1, and background pixel represents with 0.
This two field picture for example has 80 row background pixel points in the direction vertical with direction of scanning, this 80 row background pixel is divided into three parts along direction of scanning, first comprises the background pixel that columns is [127] scope, second portion comprises the background pixel that columns is [2857] scope, third part comprises the background pixel that columns is [5580] scope, background pixel brightness value distributed acquisition device calculates every part background pixel average brightness, mean1, mean2, mean3, wherein first's background pixel average brightness is mean1=145.08, second portion background pixel average brightness is mean2=138.46, third part background pixel average brightness is mean3=118.98.By way of example two field picture being divided into three parts herein along direction of scanning, can also be a plurality of parts such as 2,4,5.
Background pixel brightness value distributed acquisition device further calculates the maximal value Maxmean=145.08 of three mean values.The normalization result of calculating every part average brightness value, is respectively mean1/Maxmean=1, mean2/Maxmean=0.954, mean3/Maxmean=0.82.Scanning angle judgment means distributes according to brightness value, tables look-up and judges the angle that holds a pen.Three part background pixel average brightness normalization results are 1,0.954,0.82, table look-up 1 can draw, this two field picture scanning angle approaches 90 degree, and controller sends message and shows to display, displaying contents " angle approximately 90 degree, please adjust ".
Table 1
| |
30 | 45 | 60 | 75 | 80 | 90 |
| mean1/Maxmean | 0.479 | 0.614 | 0.787 | 0.968 | 1 | 1 |
| mean2/Maxmean | 0.711 | 0.853 | 0.948 | 1 | 0.983 | 0.957 |
| mean3/Maxmean | 1 | 1 | 1 | 0.957 | 0.897 | 0.83 |
Fig. 6 is the method flow diagram that the present invention utilizes image luminance information judgement scanning angle, and with reference to Fig. 6, the method specifically comprises the steps:
Step 1, extracts two field picture background.
In this step, two field picture based on obtaining in advance, can adopt and extract in two ways two field picture background the first is to adopt binarization method that prospect and background are separated, and extracts background image, the second is to adopt watershed segmentation mode to carry out Region Segmentation, extracts background image.
Described image binaryzation is exactly that the gray-scale value of the pixel on image is set to 0 or 1, namely whole image is presented to obvious black and white effect.The further processing that the binaryzation of image is conducive to highlight, becomes simply image, and data volume reduces, and can highlight the profile of specific target.
Described watershed areas domain splitting method, it is a kind of dividing method of the mathematical morphology based on topological theory, its basic thought is that image is regarded as to the topological landforms in geodesy, in image, the gray-scale value of every bit pixel represents the sea level elevation of this point, each local minimum and range of influence thereof become reception basin, and the border of reception basin forms watershed divide.The concept of watershed divide and formation can illustrate by simulation immersion process.On each local minimum surface, pierce through an aperture, then whole model is slowly immersed in the water, along with the intensification of immersing, the domain of influence of each local minimum, slowly to external expansion, is constructed dam at two reception basin meets, forms watershed divide.
The present invention adopts Based On Method of Labeling Watershed Algorithm to improve traditional algorithm.First adopt morphological reconstruction technology to carry out mark to specific target and background in image, and then use minimum calibration technique to revise gradient image, finally revised gradient image is carried out to watershed transform and obtain final segmentation result.
In this step, obtaining the two field picture background pixel brightness value being parallel on direction of scanning distributes, can obtain the distributed intelligence of background pixel brightness value by two kinds of modes, the first is the mean flow rate of every row background pixel point in the statistics direction vertical with direction of scanning, matching gray-scale value curve, obtaining two field picture background pixel brightness value distributes, the second is along direction of scanning, background pixel to be divided into n part, calculate every part average brightness value normalization, obtaining two field picture background pixel brightness value distributes, wherein, n >=2.
In this step, need the background pixel brightness value distributed intelligence obtaining in integrating step 2 to judge the angle that holds a pen.In step 2, can there be two kinds of background pixel brightness value distribution calculation methods, in step 3, also can correspondingly adopt and judge in two ways the angle that holds a pen, the first can judge the angle that holds a pen according to the gray-scale value slope of a curve of matching, the second can be tabled look-up according to every part background pixel mean flow rate normalized value, judgement scanning angle.
Scheme provided by the invention is by background image Luminance Distribution situation judgement scanning angle, energy automatic decision scanning angle, when certain scanning angle causes the position of light direct projection on two field picture to keep to the side, whole brightness of image inequality, now can point out user, the adjustment angle that holds a pen, obtains good scanning recognition effect.
Above-described specific embodiment; object of the present invention, technical scheme and beneficial effect are further described; institute is understood that; the foregoing is only specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any modification of making, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (13)
1. a scanister, it comprises:
Imageing sensor, is connected with controller, and for the character focal imaging on scanned medium, delta frame view data, sends into controller and process;
Controller, for receiving the frame image data being generated by imageing sensor, and utilizes the distribution of two field picture background pixel brightness value to judge the scanning angle of this scanister, according to judged result, comes reminding user to adjust scanning angle.
2. scanister as claimed in claim 1, is characterized in that, described controller further comprises:
Two field picture background extracting device, for extracting two field picture background according to described frame image data;
Background pixel brightness value distributed acquisition device, distributes for obtaining described two field picture background pixel brightness value;
Scanning angle judgment means, for distributing according to described two field picture background pixel brightness value, judgement scanning angle.
3. scanister as claimed in claim 2, is characterized in that, described two field picture background extracting device adopts binaryzation mode to extract two field picture background or adopts watershed segmentation mode to carry out Region Segmentation and extracts two field picture background.
4. scanister as claimed in claim 3, it is characterized in that, described background pixel brightness value distributed acquisition device obtains the two field picture background pixel brightness value being parallel on direction of scanning and distributes, comprise: the mean flow rate of every row background pixel point in the described background pixel brightness value distributed acquisition device statistics direction vertical with direction of scanning, matching gray-scale value curve, obtaining two field picture background pixel brightness value distributes, or along direction of scanning, background pixel is divided into n part, calculate every part average brightness value normalization, obtaining two field picture background pixel brightness value distributes, wherein, n >=2,
Described scanning angle judgment means is according to the gray-scale value slope of a curve judgement scanning angle of matching or table look-up to judge scanning angle according to every part background pixel mean flow rate normalized value.
5. scanister as claimed in claim 4, it is characterized in that, described watershed segmentation mode comprises: first adopt morphological reconstruction technology to carry out mark to specific target and background in image, and then use minimum calibration technique to revise gradient image, finally revised gradient image is carried out to watershed transform and obtain final segmentation result.
6. a method of utilizing image luminance information judgement scanning angle, the method comprising the steps of:
Step 1, the frame image data that scanning obtains according to scanister extracts two field picture background;
Step 2, obtains described two field picture background pixel brightness value and distributes;
Step 3, distributes according to described two field picture background pixel brightness value, the scanning angle of judgement scanister.
7. method as claimed in claim 6, it is characterized in that, step 1 further comprises that the frame image data to obtaining carries out binary conversion treatment and extracts two field picture background, or adopts watershed segmentation mode to carry out Region Segmentation extraction two field picture background to the frame image data obtaining.
8. method as claimed in claim 7, is characterized in that,
Step 2 further comprises that obtaining the two field picture background pixel brightness value being parallel on direction of scanning distributes, comprise: the mean flow rate of adding up every row background pixel point in the direction vertical with direction of scanning, matching gray-scale value curve, obtaining two field picture background pixel brightness value distributes, or along direction of scanning, background pixel is divided into n part, calculates every part average brightness value normalization, obtain two field picture background pixel brightness value and distribute, wherein, n >=2;
Step 3 further comprises the gray-scale value slope of a curve judgement scanning angle according to matching, or tables look-up according to every part background pixel mean flow rate normalized value, judgement scanning angle.
9. method as claimed in claim 8, it is characterized in that, described watershed segmentation mode comprises: first adopt morphological reconstruction technology to carry out mark to specific target and background in image, and then use minimum calibration technique to revise gradient image, finally revised gradient image is carried out to watershed transform and obtain final segmentation result.
10. a device that utilizes image luminance information judgement scanning angle, it comprises:
Two field picture background extracting device, extracts two field picture background for the frame image data obtaining according to scanister;
Background pixel brightness value distributed acquisition device, distributes for obtaining described two field picture background pixel brightness value;
Scanning angle judgment means, for distributing according to described two field picture background pixel brightness value, the scanning angle of judgement scanister.
11. devices as claimed in claim 10, is characterized in that, described two field picture background extracting device adopts binaryzation mode to extract two field picture background, or adopt watershed segmentation mode to carry out Region Segmentation to extract two field picture background.
12. devices as claimed in claim 11, it is characterized in that, described background pixel brightness value distributed acquisition device obtains the two field picture background pixel brightness value being parallel on direction of scanning and distributes, comprise: the mean flow rate of every row background pixel point in the described background pixel brightness value distributed acquisition device statistics direction vertical with direction of scanning, matching gray-scale value curve, obtaining two field picture background pixel brightness value distributes, or along direction of scanning, background pixel is divided into n part, calculate every part average brightness value normalization, obtaining two field picture background pixel brightness value distributes, wherein, n >=2, described scanning angle judgment means is according to the gray-scale value slope of a curve judgement scanning angle of matching, or scanning angle judgment means searches to judge scanning angle according to every part background pixel mean flow rate normalized value.
13. devices as described in claim 10-12, it is characterized in that, described watershed segmentation mode comprises: first adopt morphological reconstruction technology to carry out mark to specific target and background in image, and then use minimum calibration technique to revise gradient image, finally revised gradient image is carried out to watershed transform and obtain final segmentation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210366235.3A CN103699896A (en) | 2012-09-27 | 2012-09-27 | Scanning device, and device and method for judging scanning angle by using image brightness information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210366235.3A CN103699896A (en) | 2012-09-27 | 2012-09-27 | Scanning device, and device and method for judging scanning angle by using image brightness information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103699896A true CN103699896A (en) | 2014-04-02 |
Family
ID=50361418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210366235.3A Pending CN103699896A (en) | 2012-09-27 | 2012-09-27 | Scanning device, and device and method for judging scanning angle by using image brightness information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103699896A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108513040A (en) * | 2017-02-24 | 2018-09-07 | 株式会社东芝 | Image processing apparatus and image processing method |
| CN112577448A (en) * | 2020-12-04 | 2021-03-30 | 长飞光纤光缆股份有限公司 | Optical fiber end face inclination angle measurement method and system based on image gray value |
| CN113065542A (en) * | 2021-03-15 | 2021-07-02 | 读书郎教育科技有限公司 | Scanning control system and method of scanning pen |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1412712A (en) * | 2001-10-19 | 2003-04-23 | 讯宝科技公司 | Electro-optical assembly for image projection, in particular in a portable instrument |
| CN101763171A (en) * | 2008-12-26 | 2010-06-30 | 凌通科技股份有限公司 | Pen type optical device and method for improving uniformity degree of image and controlling indicator |
| CN102156868A (en) * | 2011-03-31 | 2011-08-17 | 汉王科技股份有限公司 | Image binaryzation method and device |
-
2012
- 2012-09-27 CN CN201210366235.3A patent/CN103699896A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1412712A (en) * | 2001-10-19 | 2003-04-23 | 讯宝科技公司 | Electro-optical assembly for image projection, in particular in a portable instrument |
| CN101763171A (en) * | 2008-12-26 | 2010-06-30 | 凌通科技股份有限公司 | Pen type optical device and method for improving uniformity degree of image and controlling indicator |
| CN102156868A (en) * | 2011-03-31 | 2011-08-17 | 汉王科技股份有限公司 | Image binaryzation method and device |
Non-Patent Citations (1)
| Title |
|---|
| 朱俊良等: "基于形态预处理和标记提取的分水岭分割算法", 《信息技术》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108513040A (en) * | 2017-02-24 | 2018-09-07 | 株式会社东芝 | Image processing apparatus and image processing method |
| CN112577448A (en) * | 2020-12-04 | 2021-03-30 | 长飞光纤光缆股份有限公司 | Optical fiber end face inclination angle measurement method and system based on image gray value |
| CN113065542A (en) * | 2021-03-15 | 2021-07-02 | 读书郎教育科技有限公司 | Scanning control system and method of scanning pen |
| CN113065542B (en) * | 2021-03-15 | 2022-03-29 | 读书郎教育科技有限公司 | Scanning control system and method of scanning pen |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111862195B (en) | Light spot detection method and device, terminal and storage medium | |
| US7936926B2 (en) | Apparatus, method, and program for face feature point detection | |
| US8818095B2 (en) | Image processing apparatus, image processing method, and computer-readable, non-transitory medium | |
| EP3272110B1 (en) | Apparatus and method for color calibration | |
| US12136266B2 (en) | Real-time glare detection inside a dynamic region of an image | |
| JP4309927B2 (en) | Eyelid detection device and program | |
| CN106537416B (en) | Image processing apparatus, character recognition apparatus, image processing method, and storage medium | |
| CN102156868A (en) | Image binaryzation method and device | |
| WO2019201184A1 (en) | License plate enhancement method, apparatus and electronic device | |
| CN112149476B (en) | Target detection method, device, equipment and storage medium | |
| JP5301694B2 (en) | Image processing apparatus, image processing method, program, and recording medium therefor | |
| CN114596620B (en) | Light supplement control method, device and equipment for face recognition equipment and storage medium | |
| KR101549495B1 (en) | An apparatus for extracting characters and the method thereof | |
| CN112633181A (en) | Data processing method, system, device, equipment and medium | |
| CN110910372B (en) | Deep convolutional neural network-based uniform light plate defect detection method | |
| CN103699896A (en) | Scanning device, and device and method for judging scanning angle by using image brightness information | |
| CN1822027A (en) | Precise dividing device and method for grayscale character | |
| CN115100104A (en) | Defect detection method, device and equipment for glass ink area and readable storage medium | |
| TWI648985B (en) | Video imaging method and electronic device using the same | |
| CN104240227A (en) | Image analysis system and method | |
| JP2014115979A (en) | Area extraction device, area extraction method, and program | |
| CN109612408B (en) | Method and device for testing emission angle of semiconductor laser and readable storage medium | |
| CN117745622A (en) | Garbage leachate membrane concentrate catalytic oxidation device | |
| JPWO2018011928A1 (en) | Image processing apparatus, operation method of image processing apparatus, and operation program of image processing apparatus | |
| CN115937324B (en) | Assembly quality evaluation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140402 |