CN111862135A - Shaking table ore belt image segmentation method - Google Patents
Shaking table ore belt image segmentation method Download PDFInfo
- Publication number
- CN111862135A CN111862135A CN202010766804.8A CN202010766804A CN111862135A CN 111862135 A CN111862135 A CN 111862135A CN 202010766804 A CN202010766804 A CN 202010766804A CN 111862135 A CN111862135 A CN 111862135A
- Authority
- CN
- China
- Prior art keywords
- image
- boundary
- pixel
- segmentation
- threshold
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000003709 image segmentation Methods 0.000 title claims description 15
- 230000011218 segmentation Effects 0.000 claims abstract description 20
- 239000012141 concentrate Substances 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 229910052500 inorganic mineral Inorganic materials 0.000 abstract description 4
- 239000011707 mineral Substances 0.000 abstract description 4
- 238000011084 recovery Methods 0.000 abstract description 3
- 239000002245 particle Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000009991 scouring Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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 OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20004—Adaptive image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for segmenting images of a shaking table ore belt, which comprises the following steps: collecting an ore belt image, and preprocessing the collected ore belt image; aiming at the pretreated ore belt image, acquiring a left boundary of the concentrate by adopting an OUST algorithm; roughly positioning a boundary between the mine and the tailings in the mine belt image through self-adaptive threshold segmentation and integral projection; and finely positioning the boundary between the middlings and the tailings in the ore belt image by adopting a region growing method. The invention can accurately obtain the boundary of the concentrate, the middlings and the tailings, has good real-time performance, improves the recovery rate of minerals and saves labor force.
Description
Technical Field
The invention relates to a table ore belt image segmentation method.
Background
The concentrating table is a common device for separating fine ore in the concentrating process, and can make ore particles move along different directions according to different densities and particle sizes by vertical vibration of the table and horizontal scouring of water flow, and the ore particles are spread in a fan shape along a diagonal line from an ore feeding groove, so that the effect of separating different minerals is achieved.
At present, most of ore dressing plants adopt a mode of judging ore belts by naked eyes and manually adjusting ore receiving plates to receive ore concentrate, middlings and tailings into different ore ponds. The receiving effect of the mode is influenced by the operation level of workers, and the problem that the ore receiving plate is not adjusted timely exists, so that the mineral recovery rate is low. In addition, this method is labor-consuming.
Due to the influence of ore quality, the tailing belt sometimes exists in the form of a plurality of ore belts, the gray value of the leftmost tailing belt is even similar to that of the middling belt, and at the moment, the boundary between the middling and the tailing is required to be identified accurately with certain difficulty.
Disclosure of Invention
In order to solve the technical problems, the invention provides the table ore belt image segmentation method which is simple in algorithm and high in accuracy.
The technical scheme for solving the problems is as follows: a table ore belt image segmentation method comprises the following steps:
the method comprises the following steps: collecting an ore belt image, and preprocessing the collected ore belt image;
step two: aiming at the pretreated ore belt image, acquiring a left boundary of the concentrate by adopting an OUST algorithm;
step three: roughly positioning a boundary between the mine and the tailings in the mine belt image through self-adaptive threshold segmentation and integral projection;
step four: and finely positioning the boundary between the middlings and the tailings in the ore belt image by adopting a region growing method.
In the table ore belt image segmentation method, in the first step, the preprocessing of the collected ore belt image includes: firstly, converting an image into a gray-scale image, then carrying out 3 x 3 neighborhood median filtering on the image, and finally carrying out pixel normalization processing on the filtered image, so that all pixel values after normalization are in a [0,1] interval.
In the second step, the step of obtaining the boundary of the left side of the concentrate by using the OUST algorithm comprises; first, a threshold value T is set1By means of a threshold value T1Performing threshold segmentation on the image to obtain a boundary L1,L1The right image is a tailing area, the segmented left image is segmented again by adopting an OTSU algorithm, and the segmentation line is a left boundary line L of the concentrate belt2。
In the table mine belt image segmentation method, in the second step, the OTSU algorithm is a self-adaptive global optimal threshold determination method, and the OTSU algorithm considers that the larger the inter-class variance between the background and the foreground obtained after segmentation is, the smaller the probability of wrong segmentation is, therefore, the algorithm obtains the threshold value which maximizes the inter-class variance in a traversal manner, that is, the method is required to be specifically:
if the image size is M × N, the number of pixels in the image whose gray-level value is less than the threshold is recorded as N1The number of pixels having a pixel gray level greater than the threshold is denoted by N2The background pixel ratio is denoted as ω1Average of itGray scale mu1(ii) a Foreground pixel ratio of omega2Average gray of μ2The total average gray level of the image is recorded as mu, and the inter-class variance is recorded as g; then there is the following equation:
Foreground pixel fraction omega2=1-ω1
Mean gray-scale value of pixel is mu-omega1×μ1+ω2×μ2
Between-class variance g ═ ω1×(μ-μ1)2+ω2×(μ-μ2)2
Simplified equivalent formula g ═ ω1×ω2×(μ1-μ2)2
And circularly traversing all the thresholds, so that the threshold with the maximum inter-class variance g is the required threshold.
In the third step, the step of roughly positioning the boundary between the mine and the tailings in the mine belt image through adaptive threshold segmentation and integral projection comprises the following steps; intercepting an image L2,L1Obtaining T by adopting a self-adaptive threshold value calculation method at the part between two boundary lines2Using a threshold value T2Carrying out binarization on the image, carrying out vertical integral projection on the image obtained by binarization, searching the integral projection image from the right side to the left side, and when detecting that the point with the projection value of continuously 0 exceeds a fixed value m, using the position as a rough positioning boundary line L of the boundary line of middlings and tailings3。
In the above table ore belt image segmentation method, in the third step, the adaptive threshold is obtained by using the following formula:
T2=min(I)+α×(max(I)-min(I))
where min (i) represents the minimum value of an image pixel, max (i) represents the maximum value of an image pixel, and α is the adjustment factor.
The table ore belt image segmentation methodThe fourth step, wherein the step of finely positioning the boundary of the mine and the tailings in the mine belt image by adopting a region growing method comprises the following steps; by a boundary line L3Further determining the position of a boundary by adopting a region growing method for a seed point to obtain an accurate boundary L of middlings and tailings4;
The growth criteria of the region growing method are as follows: judging whether the difference between the gray value of each pixel in the 8-neighborhood near the seed point L3 and the gray value of the pixel where the growing point is located is larger than a threshold value T, if so, including the pixel into the area where the seed point pixel is located; after the area growth is finished, the rightmost side of the growing area is taken as a boundary L4 between middlings and tailings.
The invention has the beneficial effects that: firstly, acquiring an ore belt image, and preprocessing the acquired ore belt image; then, aiming at the pretreated ore belt image, acquiring a left boundary of the concentrate by adopting an OUST algorithm; roughly positioning the boundary between the mine and the tailings in the mine belt image through self-adaptive threshold segmentation and integral projection; and finally, finely positioning the boundary between the middlings and the tailings in the image of the ore belt by adopting a region growing method, accurately obtaining the boundary between the concentrates, the middlings and the tailings, and having good real-time performance, so that the recovery rate of minerals is improved, and the labor force is saved.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention is further described below with reference to the figures and examples.
In this embodiment, the gold ore band is segmented, and the resolution of the image of the ore band is 1280 × 720P. As shown in fig. 1, a table mine belt image segmentation method includes the following steps:
the method comprises the following steps: and acquiring an ore belt image, and preprocessing the acquired ore belt image.
The pretreatment comprises the following steps: firstly, converting an image into a gray-scale image, then carrying out 3 x 3 neighborhood median filtering on the image, and finally carrying out pixel normalization processing on the filtered image, so that all pixel values after normalization are in a [0,1] interval.
Step two: and aiming at the pretreated ore belt image, acquiring a left boundary of the concentrate by adopting an OUST algorithm.
The step of obtaining the boundary of the left side of the concentrate by adopting the OUST algorithm comprises the following steps; first, a threshold value T is set10.85, using threshold T1Performing threshold segmentation on the image to obtain a boundary L1,L1The right image is a tailing area, the segmented left image is segmented again by adopting an OTSU algorithm, and the segmentation line is a left boundary line L of the concentrate belt2。
The OTSU algorithm is a self-adaptive global optimal threshold determination method, and considers that the larger the inter-class variance between the background and the foreground obtained after segmentation is, the smaller the probability of wrong segmentation is, therefore, the algorithm obtains the threshold which maximizes the inter-class variance in a traversal mode, namely, the threshold is obtained, and the specific process is as follows:
if the image size is M × N, the number of pixels in the image whose gray-level value is less than the threshold is recorded as N1The number of pixels having a pixel gray level greater than the threshold is denoted by N2The background pixel ratio is denoted as ω1Average gray level mu of1(ii) a Foreground pixel ratio of omega2Average gray of μ2The total average gray level of the image is recorded as mu, and the inter-class variance is recorded as g; then there is the following equation:
Foreground pixel fraction omega2=1-ω1
Mean gray-scale value of pixel is mu-omega1×μ1+ω2×μ2
Between-class variance g ═ ω1×(μ-μ1)2+ω2×(μ-μ2)2
Simplified equivalent formula g ═ ω1×ω2×(μ1-μ2)2
And circularly traversing all the thresholds, so that the threshold with the maximum inter-class variance g is the required threshold.
Step three: and roughly positioning the boundary between the mine and the tailings in the mine belt image through adaptive threshold segmentation and integral projection.
The step of coarse positioning comprises; intercepting an image L2,L1Obtaining T by adopting a self-adaptive threshold value calculation method at the part between two boundary lines2Using a threshold value T2Carrying out binarization on an image, carrying out vertical integral projection on the image obtained by binarization, searching an integral projection image from the right side to the left side, and when detecting that points with continuous projection values of 0 exceed a fixed value m which is 100, taking the position as a rough positioning boundary L of a boundary between middlings and tailings3。
The adaptive threshold is calculated using the following equation:
T2=min(I)+α×(max(I)-min(I))
where min (i) represents the minimum value of an image pixel, max (i) represents the maximum value of an image pixel, and α is the adjustment factor.
Step four: and finely positioning the boundary between the middlings and the tailings in the ore belt image by adopting a region growing method.
The fine positioning step comprises; by a boundary line L3Further determining the position of a boundary by adopting a region growing method for a seed point to obtain an accurate boundary L of middlings and tailings4;
The growth criteria of the region growing method are as follows: judging whether the difference between the gray value of each pixel in the 8-neighborhood adjacent to the seed point L3 and the gray value of the pixel where the growing point is located is greater than a threshold value T-12, and if so, including the pixel into the area where the seed point pixel is located; after the area growth is finished, the rightmost side of the growing area is taken as a boundary L4 between middlings and tailings.
Two positions L obtained in the above example2And L4The required mine band segmentation result is automatically accessed.
Claims (7)
1. A table ore belt image segmentation method is characterized by comprising the following steps:
the method comprises the following steps: collecting an ore belt image, and preprocessing the collected ore belt image;
step two: aiming at the pretreated ore belt image, acquiring a left boundary of the concentrate by adopting an OUST algorithm;
step three: roughly positioning a boundary between the mine and the tailings in the mine belt image through self-adaptive threshold segmentation and integral projection;
step four: and finely positioning the boundary between the middlings and the tailings in the ore belt image by adopting a region growing method.
2. The method according to claim 1, wherein the step one, preprocessing the acquired ore belt image comprises: firstly, converting an image into a gray-scale image, then carrying out 3 x 3 neighborhood median filtering on the image, and finally carrying out pixel normalization processing on the filtered image, so that all pixel values after normalization are in a [0,1] interval.
3. The method of table ore belt image segmentation according to claim 1, wherein in the second step, the step of obtaining the boundary line of the left side of the concentrate by using the OUST algorithm comprises; first, a threshold value T is set1By means of a threshold value T1Performing threshold segmentation on the image to obtain a boundary L1,L1The right image is a tailing area, the segmented left image is segmented again by adopting an OTSU algorithm, and the segmentation line is a left boundary line L of the concentrate belt2。
4. The table mine belt image segmentation method according to claim 3, wherein in the second step, the OTSU algorithm is a self-adaptive global optimal threshold determination method, and the OTSU algorithm considers that the larger the inter-class variance between the background and foreground obtained after segmentation, the smaller the probability of wrong segmentation, and therefore, the algorithm obtains the threshold value that maximizes the inter-class variance in a traversal manner, that is, the method is implemented by the following specific steps:
if the image size is M × N, the number of pixels in the image whose gray-level value is less than the threshold is recorded as N1The number of pixels having a pixel gray level greater than the threshold is denoted by N2Background of the inventionThe pixel ratio is denoted as ω1Average gray level mu of1(ii) a Foreground pixel ratio of omega2Average gray of μ2The total average gray level of the image is recorded as mu, and the inter-class variance is recorded as g; then there is the following equation:
Foreground pixel fraction omega2=1-ω1
Mean gray-scale value of pixel is mu-omega1×μ1+ω2×μ2
Between-class variance g ═ ω1×(μ-μ1)2+ω2×(μ-μ2)2
Simplified equivalent formula g ═ ω1×ω2×(μ1-μ2)2
And circularly traversing all the thresholds, so that the threshold with the maximum inter-class variance g is the required threshold.
5. The method of table belt image segmentation of claim 4, wherein in step three, the step of coarsely locating the boundary between the mine and the tailings in the belt image by adaptive threshold segmentation and integral projection comprises; intercepting an image L2,L1Obtaining T by adopting a self-adaptive threshold value calculation method at the part between two boundary lines2Using a threshold value T2Carrying out binarization on the image, carrying out vertical integral projection on the image obtained by binarization, searching the integral projection image from the right side to the left side, and when detecting that the point with the projection value of continuously 0 exceeds a fixed value m, using the position as a rough positioning boundary line L of the boundary line of middlings and tailings3。
6. The method according to claim 5, wherein the adaptive threshold is determined in step three by the following equation:
T2=min(I)+α×(max(I)-min(I))
where min (i) represents the minimum value of an image pixel, max (i) represents the maximum value of an image pixel, and α is the adjustment factor.
7. The method of table belt image segmentation according to claim 5, wherein in step four, the step of fine positioning the boundary between the ore and the tailings in the belt image by using the area growth method comprises; by a boundary line L3Further determining the position of a boundary by adopting a region growing method for a seed point to obtain an accurate boundary L of middlings and tailings4;
The growth criteria of the region growing method are as follows: judging whether the difference between the gray value of each pixel in the 8-neighborhood near the seed point L3 and the gray value of the pixel where the growing point is located is larger than a threshold value T, if so, including the pixel into the area where the seed point pixel is located; after the area growth is finished, taking the rightmost side of the growing area as a boundary L of middlings and tailings4。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010766804.8A CN111862135A (en) | 2020-08-03 | 2020-08-03 | Shaking table ore belt image segmentation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010766804.8A CN111862135A (en) | 2020-08-03 | 2020-08-03 | Shaking table ore belt image segmentation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111862135A true CN111862135A (en) | 2020-10-30 |
Family
ID=72952794
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010766804.8A Pending CN111862135A (en) | 2020-08-03 | 2020-08-03 | Shaking table ore belt image segmentation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111862135A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113304869A (en) * | 2021-06-03 | 2021-08-27 | 昆明理工大学 | Method and device for automatically identifying and receiving shaking table ore belt |
CN117409009A (en) * | 2023-12-15 | 2024-01-16 | 长沙矿冶研究院有限责任公司 | Real-time sorting method for dry magnetic separation particles based on UNet |
CN112434570B (en) * | 2020-11-09 | 2024-05-24 | 宜春钽铌矿有限公司 | Image recognition method for tantalum-niobium ore cradle ore belt |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070065009A1 (en) * | 2005-08-26 | 2007-03-22 | Shenzhen Mindray Bio-Medical Electronics Co., Ltd. | Ultrasound image enhancement and speckle mitigation method |
CN101710424A (en) * | 2009-12-22 | 2010-05-19 | 中国矿业大学(北京) | Method for segmenting ore image |
CN102527489A (en) * | 2012-01-16 | 2012-07-04 | 昆明理工大学 | Method for dynamically segmenting table ore belt by utilizing image grey level of ore belt |
CN103366362A (en) * | 2013-04-17 | 2013-10-23 | 昆明理工大学 | Glowworm optimization algorithm-based ore zone image segmentation method |
KR101363370B1 (en) * | 2012-11-29 | 2014-02-17 | 주식회사 포스코 | Apparatus and method for measuring size of ore using image patten recognition |
CN103871029A (en) * | 2014-01-28 | 2014-06-18 | 西安科技大学 | Image enhancement and partition method |
RU2012156290A (en) * | 2012-12-25 | 2014-06-27 | Общество с ограниченной ответственностью "НТЦ "Магнитные жидкости" | METHOD FOR DETERMINING THE CIRCUITS OF INDUSTRIAL ORE MINING OF GOLD DEPOSIT |
WO2017020723A1 (en) * | 2015-08-04 | 2017-02-09 | 阿里巴巴集团控股有限公司 | Character segmentation method and device and electronic device |
CN111047555A (en) * | 2019-11-13 | 2020-04-21 | 鞍钢集团矿业有限公司 | Ore image granularity detection algorithm based on image processing technology |
-
2020
- 2020-08-03 CN CN202010766804.8A patent/CN111862135A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070065009A1 (en) * | 2005-08-26 | 2007-03-22 | Shenzhen Mindray Bio-Medical Electronics Co., Ltd. | Ultrasound image enhancement and speckle mitigation method |
CN101710424A (en) * | 2009-12-22 | 2010-05-19 | 中国矿业大学(北京) | Method for segmenting ore image |
CN102527489A (en) * | 2012-01-16 | 2012-07-04 | 昆明理工大学 | Method for dynamically segmenting table ore belt by utilizing image grey level of ore belt |
KR101363370B1 (en) * | 2012-11-29 | 2014-02-17 | 주식회사 포스코 | Apparatus and method for measuring size of ore using image patten recognition |
RU2012156290A (en) * | 2012-12-25 | 2014-06-27 | Общество с ограниченной ответственностью "НТЦ "Магнитные жидкости" | METHOD FOR DETERMINING THE CIRCUITS OF INDUSTRIAL ORE MINING OF GOLD DEPOSIT |
CN103366362A (en) * | 2013-04-17 | 2013-10-23 | 昆明理工大学 | Glowworm optimization algorithm-based ore zone image segmentation method |
CN103871029A (en) * | 2014-01-28 | 2014-06-18 | 西安科技大学 | Image enhancement and partition method |
WO2017020723A1 (en) * | 2015-08-04 | 2017-02-09 | 阿里巴巴集团控股有限公司 | Character segmentation method and device and electronic device |
CN111047555A (en) * | 2019-11-13 | 2020-04-21 | 鞍钢集团矿业有限公司 | Ore image granularity detection algorithm based on image processing technology |
Non-Patent Citations (1)
Title |
---|
田隽;钱建生;厉丹;李世银;: "基于多摄像机的矿井危险区域目标匹配算法", 中国矿业大学学报, no. 01, 15 January 2010 (2010-01-15) * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112434570B (en) * | 2020-11-09 | 2024-05-24 | 宜春钽铌矿有限公司 | Image recognition method for tantalum-niobium ore cradle ore belt |
CN113304869A (en) * | 2021-06-03 | 2021-08-27 | 昆明理工大学 | Method and device for automatically identifying and receiving shaking table ore belt |
CN113304869B (en) * | 2021-06-03 | 2024-04-19 | 昆明理工大学 | Automatic identification and access method and device for shaking table ore belt |
CN117409009A (en) * | 2023-12-15 | 2024-01-16 | 长沙矿冶研究院有限责任公司 | Real-time sorting method for dry magnetic separation particles based on UNet |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111862135A (en) | Shaking table ore belt image segmentation method | |
Moolman et al. | Digital image processing as a tool for on-line monitoring of froth in flotation plants | |
WO2019196130A1 (en) | Classifier training method and device for vehicle-mounted thermal imaging pedestrian detection | |
WO2019196131A1 (en) | Method and apparatus for filtering regions of interest for vehicle-mounted thermal imaging pedestrian detection | |
CN110687904A (en) | Visual navigation routing inspection and obstacle avoidance method for inspection robot | |
CN109993099A (en) | A kind of lane line drawing recognition methods based on machine vision | |
CN105335743A (en) | Vehicle license plate recognition method | |
CN103258198A (en) | Extraction method for characters in form document image | |
CN105139391B (en) | A kind of haze weather traffic image edge detection method | |
CN108052904B (en) | Method and device for acquiring lane line | |
WO2021109697A1 (en) | Character segmentation method and apparatus, and computer-readable storage medium | |
CN107895151A (en) | Method for detecting lane lines based on machine vision under a kind of high light conditions | |
CN102831416A (en) | Character identification method and relevant device | |
CN110674812B (en) | Civil license plate positioning and character segmentation method facing complex background | |
CN111583193B (en) | Pistachio nut framework extraction device based on geometric contour template matching and algorithm thereof | |
CN106780437B (en) | A kind of quick QFN chip plastic packaging image obtains and amplification method | |
CN109886935A (en) | A kind of road face foreign matter detecting method based on deep learning | |
CN116168025B (en) | Oil curtain type fried peanut production system | |
CN110607405A (en) | Leather inner contour recognition cutting device and method based on machine vision industrial application | |
CN116452506A (en) | Underground gangue intelligent visual identification and separation method based on machine learning | |
CN112435235A (en) | Seed cotton impurity content detection method based on image analysis | |
CN107977608B (en) | Method for extracting road area of highway video image | |
CN113642570A (en) | Method for recognizing license plate of mine car in dark environment | |
CN113095283B (en) | Lane line extraction method based on dynamic ROI and improved firefly algorithm | |
CN108537815B (en) | Video image foreground segmentation method and device |
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 |