CN112288747A - Intelligent detection method and device for steel billets - Google Patents
Intelligent detection method and device for steel billets Download PDFInfo
- Publication number
- CN112288747A CN112288747A CN202011572256.1A CN202011572256A CN112288747A CN 112288747 A CN112288747 A CN 112288747A CN 202011572256 A CN202011572256 A CN 202011572256A CN 112288747 A CN112288747 A CN 112288747A
- Authority
- CN
- China
- Prior art keywords
- billet
- detected
- pixel points
- identified
- preset
- 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
Classifications
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65C—LABELLING OR TAGGING MACHINES, APPARATUS, OR PROCESSES
- B65C9/00—Details of labelling machines or apparatus
- B65C9/40—Controls; Safety devices
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/30136—Metal
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The application provides an intelligent detection method and device for a steel billet, and the method comprises the following steps: converting the shot picture containing the billet to be detected into a picture to be identified, wherein the picture consists of pixel points; carrying out black setting processing on pixel points which accord with a preset threshold value in the picture to be identified; performing area selection on the image to be identified after black setting treatment to obtain an initial area to be identified containing all billet pixel points; determining an accurate region of the billet to be detected from the initial region to be identified according to the length of the billet to be detected and the width of the billet to be detected; determining marking pixel points which accord with a preset color threshold value in pixel points included in an accurate region of a billet to be detected, and counting the number of the marking pixel points; judging whether the ratio of the number of the pixel points exceeds a preset ratio or not; and if the ratio of the number of the pixel points exceeds a preset ratio, determining the steel billet to be detected as an unqualified steel billet. According to the method, the detection accuracy is improved through black setting and ratio determination processing.
Description
Technical Field
The application relates to the field of industry, in particular to an intelligent detection method and device for steel billets.
Background
The manufacturing process of the steel billet involves many processes and requires a severe industrial manufacturing environment, so that the defective steel billet inevitably occurs in the production process. Unqualified billets show cracks, unqualified billets, and appearance quality flaws such as substandard flatness and the like which can be directly found. In order to detect the unqualified steel billets, quality testing personnel mark the unqualified steel billets before the steel billets enter a cooling bed for transportation. Since the billet is gray black, the billet is generally marked with white marks at will in order to highlight the marks. And (3) observing whether the marks appear in the steel billets transported by the cooling bed by a detector, attaching qualified labels to the steel billets without the marks, detecting the steel billets with the marks, and treating the steel billets as unqualified products.
However, the method of manually determining whether or not a mark is present on a billet is not only inefficient, but also prone to erroneous determination. If the marks made by the quality testing personnel are not obvious enough, the quality testing personnel probably ignore the marks, and therefore the unqualified steel billet is taken as the qualified steel billet to be labeled.
Based on this, there is a need for an intelligent detection method for steel billets, which is used for solving the problem that in the prior art, the false judgment rate of manually detecting steel billets is high, which causes unqualified steel billets to leave a factory.
Disclosure of Invention
The application provides an intelligent detection method and device for a steel billet, which can be used for solving the technical problems in the prior art.
In a first aspect, the present application provides an intelligent detection method for a steel billet, the method including:
converting the shot picture containing the billet to be detected into a picture to be identified, wherein the picture consists of pixel points; the pixel points comprise billet pixel points forming the graph of the billet to be identified and irrelevant pixel points forming the surrounding environment of the billet to be identified;
carrying out black setting processing on pixel points which accord with a preset threshold value in the picture to be identified;
performing area selection on the image to be identified after black setting treatment to obtain an initial area to be identified containing all billet pixel points; the initial area to be identified consists of all billet pixel points and irrelevant pixel points around the billet pixel points;
determining an accurate region of the billet to be detected from the initial region to be identified according to the length of the billet to be detected and the width of the billet to be detected; the accurate region of the billet to be detected only comprises the billet pixel points; the length of the steel billet to be detected and the width of the steel billet to be detected are obtained from a production information system;
determining marking pixel points which accord with a preset color threshold value in pixel points included in the accurate region of the billet to be detected, and counting the number of the marking pixel points; the marked pixel points are pixel points forming unqualified marks; the unqualified mark is positioned on the surface of the billet to be detected; the preset color threshold comprises a plurality of preset color subchannel thresholds;
judging whether the ratio of the number of the pixel points exceeds a preset ratio or not; the pixel point number ratio is the ratio of the number of the marking pixel points to the number of the total pixel points contained in the accurate region of the billet to be detected;
and if the ratio of the number of the pixel points exceeds the preset ratio, determining the steel billet to be detected as an unqualified steel billet.
With reference to the first aspect, in an implementation manner of the first aspect, performing black setting processing on a pixel point meeting a preset threshold in the picture to be recognized includes:
determining black pixel points to be set with a preset threshold value from the pixel points contained in the picture to be identified;
adjusting the tone value of the black pixel point to be placed into the tone value of the black pixel point;
adjusting the saturation value of the black pixel point to be placed into the saturation value of the black pixel point;
and adjusting the brightness value of the black pixel point to be placed into the brightness value of the black pixel point.
With reference to the first aspect, in an implementation manner of the first aspect, determining an accurate region of the billet to be detected from the initial region to be identified according to a length of the billet to be detected and a width of the billet to be detected includes:
determining the area of the billet to be detected, the shape profile of the billet to be detected and a preset coefficient according to the length of the billet to be detected and the width of the billet to be detected; the preset coefficient is determined according to the ratio of the length of the billet to be detected to the width of the billet to be detected;
and determining the accurate region of the steel billet to be detected from the region to be identified according to the area of the steel billet to be detected, the shape profile of the steel billet to be detected and the preset coefficient.
With reference to the first aspect, in an implementation manner of the first aspect, determining, among the pixel points included in the accurate region of the to-be-detected billet, a marked pixel point that meets a preset color threshold includes:
sequentially judging whether any color subchannel threshold of the pixel points to be determined exceeds the corresponding preset color subchannel threshold or not; the pixel points to be determined are pixel points included in the accurate region of the billet to be detected;
and if any color subchannel threshold of the pixel point to be determined exceeds the corresponding preset color subchannel threshold, determining the pixel point to be determined as the marking pixel point.
With reference to the first aspect, in an implementation manner of the first aspect, if the ratio of the number of the pixels exceeds the preset ratio, after determining the to-be-detected steel billet as an unqualified steel billet, the method further includes:
acquiring a mark position coordinate value corresponding to the mark pixel point;
determining the actual position of the mark according to the coordinate value of the mark position and the corresponding relation between the coordinate value of the position and the actual position;
sending out a labeling instruction; and the labeling instruction is used for controlling a labeling machine to label unqualified labels in the areas except the actual labeling positions of the unqualified billets.
In a second aspect, the present application provides an intelligent detection device for a steel billet, the device comprising:
the conversion module is used for converting the shot picture containing the billet to be detected into a picture to be identified, wherein the picture to be identified consists of pixel points; the pixel points comprise billet pixel points forming the graph of the billet to be identified and irrelevant pixel points forming the surrounding environment of the billet to be identified;
the processing module is used for carrying out black setting processing on pixel points which accord with a preset threshold value in the picture to be identified;
the selection module is used for carrying out region selection on the image to be identified after the blackening treatment to obtain an initial region to be identified containing all the billet pixel points; the initial area to be identified consists of all billet pixel points and irrelevant pixel points around the billet pixel points;
the determining module is used for determining the accurate area of the steel billet to be detected from the initial area to be identified according to the length of the steel billet to be detected and the width of the steel billet to be detected; the accurate region of the billet to be detected only comprises the billet pixel points; the length of the steel billet to be detected and the width of the steel billet to be detected are obtained from a production information system;
the determining module is further configured to determine marking pixel points meeting a preset color threshold from among the pixel points included in the accurate region of the billet to be detected, and count the number of the marking pixel points; the marked pixel points are pixel points forming unqualified marks; the unqualified mark is positioned on the surface of the billet to be detected; the preset color threshold comprises a plurality of preset color subchannel thresholds;
the judging module is used for judging whether the ratio of the number of the pixel points exceeds a preset ratio or not; the pixel point number ratio is the ratio of the number of the marking pixel points to the number of the total pixel points contained in the accurate region of the billet to be detected;
the determining module is further configured to determine the to-be-detected steel billet as an unqualified steel billet if the ratio of the number of the pixels exceeds the preset ratio.
With reference to the second aspect, in an implementable manner of the second aspect, the processing module is specifically configured to:
determining black pixel points to be set with a preset threshold value from the pixel points contained in the picture to be identified;
adjusting the tone value of the black pixel point to be placed into the tone value of the black pixel point;
adjusting the saturation value of the black pixel point to be placed into the saturation value of the black pixel point;
and adjusting the brightness value of the black pixel point to be placed into the brightness value of the black pixel point.
With reference to the second aspect, in an implementation manner of the second aspect, the determining module is specifically configured to:
determining the area of the billet to be detected, the shape profile of the billet to be detected and a preset coefficient according to the length of the billet to be detected and the width of the billet to be detected; the preset coefficient is determined according to the ratio of the length of the billet to be detected to the width of the billet to be detected;
and determining the accurate region of the steel billet to be detected from the region to be identified according to the area of the steel billet to be detected, the shape profile of the steel billet to be detected and the preset coefficient.
With reference to the second aspect, in an implementation manner of the second aspect, the determining module is specifically configured to:
sequentially judging whether any color subchannel threshold of the pixel points to be determined exceeds the corresponding preset color subchannel threshold or not; the pixel points to be determined are pixel points included in the accurate region of the billet to be detected;
and if any color subchannel threshold of the pixel point to be determined exceeds the corresponding preset color subchannel threshold, determining the pixel point to be determined as the marking pixel point.
With reference to the second aspect, in an implementation manner of the second aspect, the method further includes:
the acquisition module is used for acquiring a mark position coordinate value corresponding to the mark pixel point;
the determining module is further configured to determine an actual position of the mark according to the mark position coordinate value and a corresponding relationship between the position coordinate value and the actual position;
the instruction module is used for sending out a labeling instruction; and the labeling instruction is used for controlling a labeling machine to label unqualified labels in the areas except the actual labeling positions of the unqualified billets.
According to the method, the influence of the red part of the billet to be detected on the identification of the billet to be detected is avoided through black processing. And the accurate positioning of the steel billet to be detected is realized according to the length of the steel billet to be detected and the width of the steel billet to be detected, so that the positioning accuracy of the steel billet to be detected is improved. The method for determining the ratio of the number of the unqualified mark pixel points to the total pixel points in the accurate region of the billet to be detected avoids the problem of inaccurate judgment caused by different positions of the shooting equipment and the billet to be detected, and further improves the detection accuracy of the method.
Drawings
Fig. 1 is a schematic structural diagram of an intelligent detection system for a steel billet according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of an intelligent detection method for a steel billet according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of an initial region to be identified according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an intelligent detection device for a steel billet according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
Fig. 1 is a schematic structural diagram of an intelligent detection system for a steel billet according to an embodiment of the present application.
The intelligent detection system of steel billet includes: the cold bed 1, the blank separating device 2 and the detecting device 3. The steel billet 4 is transported to the detection device 3 through the cooling bed 1, and the detection device 3 executes the intelligent detection method of the steel billet provided by the embodiment of the application to determine the steel billet 4 as a qualified steel billet or an unqualified steel billet. The steel billet 4 shown in fig. 1 is the steel billet to be detected in the embodiment of the present application.
Fig. 2 is a schematic flow chart of an intelligent detection method for a steel billet according to an embodiment of the present application. The embodiment of the application comprises the following steps:
step S201, the shot picture containing the billet to be detected is converted into a picture to be identified, wherein the picture to be identified is composed of pixel points.
Step S202, carrying out black setting processing on pixel points which accord with a preset threshold value in the picture to be identified.
Step S203, area selection is carried out on the to-be-identified picture subjected to the blackening treatment, and an initial to-be-identified area containing all billet pixel points is obtained.
And S204, determining the accurate area of the billet to be detected from the initial area to be identified according to the length of the billet to be detected and the width of the billet to be detected.
Step S205, determining marking pixel points which accord with a preset color threshold value in pixel points included in the accurate region of the billet to be detected, and counting the number of the marking pixel points.
Step S206, judging whether the ratio of the number of the pixel points exceeds a preset ratio or not; if the ratio of the number of the pixels exceeds the preset ratio, step S207 is executed, otherwise step S208 is executed.
And step S207, determining the billet to be detected as the unqualified billet.
And step S208, determining the billet to be detected as a qualified billet.
According to the method, the influence of the red part of the billet to be detected on the identification of the billet to be detected is avoided through black processing. And the accurate positioning of the steel billet to be detected is realized according to the length of the steel billet to be detected and the width of the steel billet to be detected, so that the positioning accuracy of the steel billet to be detected is improved. The method for determining the ratio of the number of the unqualified mark pixel points to the total pixel points in the accurate region of the billet to be detected avoids the problem of inaccurate judgment caused by different positions of the shooting equipment and the billet to be detected, and further improves the detection accuracy of the method.
The method provided by the present application is specifically explained below with reference to the embodiments of the present application.
In step S201, the pixel points include billet pixel points constituting a billet graph to be recognized and irrelevant pixel points constituting an environment around the billet to be recognized. Through the preprocessing step of step S201, the photo is converted into a picture to be recognized that can be further processed.
In step S202, the side surface of the produced billet is red due to the scale adhered thereto. When the billet to be detected is photographed, the photographing device is not necessarily aligned with the billet cross section, and there is a possibility that the side faces of the billet are photographed together. In the embodiment of the application, the marks made by quality testing personnel are all on the end surface of the billet. In order to eliminate the influence of the side surface of the billet, the side surface of the billet needs to be subjected to blackening treatment.
Specifically, from the pixel points included in the picture to be recognized, the to-be-blacked pixel points with the preset threshold are determined. Firstly, adjusting a picture to be identified to a picture under a color model, then determining the hue value of a red pixel point as a preset hue threshold value, determining the saturation value of the red pixel point as a preset saturation threshold value, and determining the brightness value of the red pixel point as a preset brightness threshold value. And sequentially judging the hue value, the saturation value and the brightness value of each pixel point in the picture under the color model. If the hue value of any pixel exceeds the preset saturation threshold, the saturation value exceeds the preset saturation threshold and the brightness value exceeds the preset brightness threshold, the pixel is indicated to be a red pixel, and the corresponding pixel is determined to be a to-be-set black pixel.
It should be noted that the preset threshold is adjusted according to the actual production situation. If the side surface of the billet presents a specific color due to a specific manufacturing process, the preset threshold value is determined as a hue value, a saturation value and a brightness value of the specific color according to requirements.
Further, the tone value of the black pixel to be set is adjusted to the tone value of the black pixel.
And adjusting the saturation value of the black pixel point to be set to the saturation value of the black pixel point.
And adjusting the brightness value of the black pixel point to be placed into the brightness value of the black pixel point.
In the embodiment of the application, the side surface of the steel billet to be detected is black through black processing, and the side surface of the steel billet to be detected which originally presents red cannot be identified in the subsequent processing process, so that the interference on the subsequent steps is avoided.
In step S203, specifically, the initial to-be-identified area is composed of all billet pixel points and irrelevant pixel points around the billet pixel points.
There are various methods to implement step S203, for example, various methods such as a graying algorithm, a filtering algorithm, and a binarization algorithm are used to select the initial region to be identified. However, these methods have the same problem that the precise area of the billet to be detected cannot be precisely selected. In general, after the foregoing method is adopted to perform step S203, a schematic diagram of an initial region to be identified provided in the embodiment of the present application is obtained as shown in fig. 3.
In the picture 33 to be recognized in fig. 3, the actual area of the billet to be recognized is the area indicated by 31, and the initial area to be recognized is the area indicated by 32. In the prior art, the initial area to be identified 32 does not completely coincide with the actual area 31 of the billet to be detected.
The embodiment of the present application provides a method for accurate positioning, and the specific method is elaborated in step S204.
In step S204, the precise area of the billet to be detected only includes billet pixel points. The length of the billet to be detected and the width of the billet to be detected are obtained from a production information system. In the production process of the steel billet, the length of the steel billet to be detected and the width of the steel billet to be detected can be obtained at any time.
Specifically, step S204 includes the following steps:
firstly, determining the area of the billet to be detected, the shape profile of the billet to be detected and a preset coefficient according to the length of the billet to be detected and the width of the billet to be detected. The preset coefficient is determined according to the ratio of the length of the billet to be detected to the width of the billet to be detected.
And determining the area of the billet to be detected by multiplying the length of the billet to be detected by the width of the billet to be detected. According to the length of the billet to be detected and the width of the billet to be detected, the shape and the outline of the billet to be detected can be directly determined, namely the shape and the outline are rectangular.
And then, determining the accurate region of the steel billet to be detected from the region to be identified according to the area of the steel billet to be detected, the shape profile of the steel billet to be detected and a preset coefficient.
Specifically, the areas which do not satisfy the area of the billet to be detected and the shape profile of the billet to be detected in the areas to be identified are excluded, and the areas to be selected, the length-width ratio of which accords with the preset coefficient, in the remaining areas are the accurate areas of the billet to be detected.
With reference to fig. 3, after step S204 is executed, it is determined that the precise area of the billet to be detected is the area 31 shown in fig. 3, and irrelevant pixel points around the billet pixel points are eliminated.
According to the embodiment of the application, the accurate region of the billet to be detected is accurately positioned through the step S204, and the identification accuracy of the billet to be detected is improved.
In step S205, marking the pixel points as pixel points constituting the unqualified mark; and the unqualified mark is positioned on the surface of the billet to be detected. Therefore, the marking pixel points are located in the accurate area of the billet to be detected.
The preset color threshold comprises a plurality of preset color subchannel thresholds.
Specifically, step S205 includes the following steps:
and sequentially judging whether any color subchannel threshold of the pixel points to be determined exceeds a corresponding preset color subchannel threshold. And the pixel points to be determined are pixel points included in the accurate region of the billet to be detected. The preset color threshold comprises a plurality of preset color subchannel thresholds.
In the embodiment of the present application, the unqualified mark is displayed in white. Therefore, the preset color threshold is the color value of the white pixel point in the red subchannel, the color value of the white pixel point in the green subchannel and the color value of the white pixel point in the blue subchannel.
And if any color subchannel threshold of the pixel point to be determined exceeds the corresponding preset color subchannel threshold, determining the pixel point to be determined as a marking pixel point.
Specifically, if the color value of the pixel point to be determined in the red subchannel exceeds the color value of the white pixel point in the red subchannel; the color value of the pixel point to be determined in the green subchannel exceeds the color value of the white pixel point in the green subchannel; the color value of the pixel point to be determined in the blue subchannel exceeds the color value of the white pixel point in the blue subchannel; the pixel point to be determined is white, namely the marking pixel point.
It should be noted that, in the embodiment of the present application, any color that is easily distinguished from the billet to be detected, for example, red, may be used as the non-qualified mark. The specific preset color threshold is determined according to actual conditions.
In step S206, the ratio of the number of the pixels is a ratio of the number of the marked pixels to the number of the total pixels included in the accurate region of the billet to be detected.
After the number of the pixels is determined, the ratio of the number of the pixels is further determined.
In step S207, the surface of the billet to be detected is not pure gray black, and inevitably includes white impurities. If the white pixel points appear, the unqualified mark on the surface of the billet to be detected is judged, and the possibility of misjudgment exists.
The distance between the billet to be detected and the shooting equipment is not a fixed distance, if the billet to be detected is closer to the shooting equipment, the unqualified mark obtained by shooting is larger, and correspondingly, the number of mark pixel points is more; if the distance between the billet to be detected and the shooting equipment is far, the unqualified marks obtained by shooting are small, and the number of corresponding mark pixel points is small.
If step S207 directly determines whether the number of marked pixels exceeds the preset number value, there is a possibility of misdetermination. According to the embodiment of the application, the pixel point ratio is adopted for judgment, so that the problem that the number difference of the marked pixel points is caused due to the fact that the distance between the shooting equipment and the billet to be detected is different is solved.
And step S207 is executed, namely after the steel billet to be detected is determined to be an unqualified steel billet, an unqualified label can be attached to the unqualified steel billet, wherein the coordinate value of the marking position corresponding to the marking pixel point is obtained.
The method for sticking the unqualified label on the unqualified steel billet comprises the following steps:
firstly, the actual position of the mark is determined according to the coordinate value of the mark position and the corresponding relation between the coordinate value of the position and the actual position.
And then, a labeling instruction is sent. The labeling command is used for controlling the labeling machine to label the unqualified billet in the area except the actual labeling position. According to the embodiment of the application, the unqualified labels are attached to the areas outside the actual marking positions of the unqualified billets, so that the unqualified labels are prevented from shielding the unqualified marks.
It should be noted that in another method for distinguishing a qualified steel billet from an unqualified steel billet provided in the embodiment of the present application, a qualified label is attached to the qualified steel billet, and no labeling is performed on the unqualified steel billet.
The following are embodiments of the apparatus of the present application that may be used to perform embodiments of the method of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the embodiments of the method of the present application.
Fig. 4 shows a schematic structural diagram of an intelligent detection device for a steel billet according to an embodiment of the present application. The device has the function of realizing the intelligent detection method of the steel billet, and the function can be realized by hardware or by hardware executing corresponding software. The apparatus may include: a conversion module 401, a processing module 402, a selection module 403, a determination module 404, a judgment module 405, an acquisition module 406, and an instruction module 407.
The conversion module 401 is configured to convert the shot picture containing the billet to be detected into a picture to be identified, which is composed of pixel points; the pixel points comprise billet pixel points forming a billet figure to be identified and irrelevant pixel points forming the surrounding environment of the billet to be identified.
The processing module 402 is configured to perform black setting processing on pixel points in the picture to be recognized, where the pixel points meet a preset threshold.
A selecting module 403, configured to perform region selection on the image to be identified after the black setting process, to obtain an initial region to be identified that includes all the billet pixel points; the initial to-be-identified area consists of all billet pixel points and irrelevant pixel points around the billet pixel points.
A determining module 404, configured to determine, according to the length of the billet to be detected and the width of the billet to be detected, an accurate region of the billet to be detected from the initial region to be identified; the accurate region of the billet to be detected only comprises billet pixel points; the length of the billet to be detected and the width of the billet to be detected are obtained from a production information system.
The determining module 404 is further configured to determine, among the pixel points included in the accurate region of the billet to be detected, a marked pixel point meeting a preset color threshold, and count the number of the marked pixel points; marking the pixel points as the pixel points forming the unqualified mark; the unqualified mark is positioned on the surface of the billet to be detected; the preset color threshold comprises a plurality of preset color subchannel thresholds.
A judging module 405, configured to judge whether the ratio of the number of the pixel points exceeds a preset ratio; and the pixel point number ratio is the ratio of the number of the marking pixel points to the number of the total pixel points contained in the accurate region of the billet to be detected.
The determining module 404 is further configured to determine the steel billet to be detected as an unqualified steel billet if the ratio of the number of the pixels exceeds a preset ratio.
The processing module 402 is specifically configured to:
and determining black pixel points to be set of a preset threshold value from the pixel points contained in the picture to be identified.
And adjusting the tone value of the black pixel point to be placed into the tone value of the black pixel point.
And adjusting the saturation value of the black pixel point to be set to the saturation value of the black pixel point.
And adjusting the brightness value of the black pixel point to be placed into the brightness value of the black pixel point.
The determining module 404 is specifically configured to:
determining the area of the billet to be detected, the shape profile of the billet to be detected and a preset coefficient according to the length of the billet to be detected and the width of the billet to be detected; the preset coefficient is determined according to the ratio of the length of the billet to be detected to the width of the billet to be detected.
And determining the accurate region of the steel billet to be detected from the region to be identified according to the area of the steel billet to be detected, the shape profile of the steel billet to be detected and a preset coefficient.
The determining module 404 is specifically configured to:
sequentially judging whether any color subchannel threshold of the pixel points to be determined exceeds a corresponding preset color subchannel threshold or not; and the pixel points to be determined are pixel points included in the accurate region of the billet to be detected.
And if any color subchannel threshold of the pixel point to be determined exceeds the corresponding preset color subchannel threshold, determining the pixel point to be determined as a marking pixel point.
Further included is an acquisition module 406:
the obtaining module 406 is configured to obtain a mark position coordinate value corresponding to the mark pixel point.
The determining module 404 is further configured to determine an actual position of the mark according to the coordinate value of the position of the mark and the corresponding relationship between the coordinate value of the position and the actual position.
The instruction module 407 is configured to issue a labeling instruction; the labeling command is used for controlling the labeling machine to label the unqualified billet in the area except the actual labeling position.
The device provided by the application avoids the influence of the red part of the billet to be detected on the identification of the billet to be detected through black setting treatment. And the accurate positioning of the steel billet to be detected is realized according to the length of the steel billet to be detected and the width of the steel billet to be detected, so that the positioning accuracy of the steel billet to be detected is improved. The method for determining the ratio of the number of the unqualified mark pixel points to the total pixel points in the accurate region of the billet to be detected avoids the problem of inaccurate judgment caused by different positions of the shooting equipment and the billet to be detected, and further improves the detection accuracy of the method.
The invention is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. An intelligent detection method for a steel billet is characterized by comprising the following steps:
converting the shot picture containing the billet to be detected into a picture to be identified, wherein the picture consists of pixel points; the pixel points comprise billet pixel points forming the graph of the billet to be identified and irrelevant pixel points forming the surrounding environment of the billet to be identified;
carrying out black setting processing on pixel points which accord with a preset threshold value in the picture to be identified;
performing area selection on the image to be identified after black setting treatment to obtain an initial area to be identified containing all billet pixel points; the initial area to be identified consists of all billet pixel points and irrelevant pixel points around the billet pixel points;
determining an accurate region of the billet to be detected from the initial region to be identified according to the length of the billet to be detected and the width of the billet to be detected; the accurate region of the billet to be detected only comprises the billet pixel points; the length of the steel billet to be detected and the width of the steel billet to be detected are obtained from a production information system;
determining marking pixel points which accord with a preset color threshold value in pixel points included in the accurate region of the billet to be detected, and counting the number of the marking pixel points; the marked pixel points are pixel points forming unqualified marks; the unqualified mark is positioned on the surface of the billet to be detected; the preset color threshold comprises a plurality of preset color subchannel thresholds;
judging whether the ratio of the number of the pixel points exceeds a preset ratio or not; the pixel point number ratio is the ratio of the number of the marking pixel points to the number of the total pixel points contained in the accurate region of the billet to be detected;
and if the ratio of the number of the pixel points exceeds the preset ratio, determining the steel billet to be detected as an unqualified steel billet.
2. The method according to claim 1, wherein performing black-out processing on pixel points meeting a preset threshold in the picture to be recognized comprises:
determining black pixel points to be set with a preset threshold value from the pixel points contained in the picture to be identified;
adjusting the tone value of the black pixel point to be placed into the tone value of the black pixel point;
adjusting the saturation value of the black pixel point to be placed into the saturation value of the black pixel point;
and adjusting the brightness value of the black pixel point to be placed into the brightness value of the black pixel point.
3. The method of claim 1, wherein determining the precise area of the billet to be detected from the initial area to be identified based on the length of the billet to be detected and the width of the billet to be detected comprises:
determining the area of the billet to be detected, the shape profile of the billet to be detected and a preset coefficient according to the length of the billet to be detected and the width of the billet to be detected; the preset coefficient is determined according to the ratio of the length of the billet to be detected to the width of the billet to be detected;
and determining the accurate region of the steel billet to be detected from the region to be identified according to the area of the steel billet to be detected, the shape profile of the steel billet to be detected and the preset coefficient.
4. The method of claim 1, wherein determining the marked pixel points meeting a preset color threshold from the pixel points included in the precise region of the billet to be detected comprises:
sequentially judging whether any color subchannel threshold of the pixel points to be determined exceeds the corresponding preset color subchannel threshold or not; the pixel points to be determined are pixel points included in the accurate region of the billet to be detected;
and if any color subchannel threshold of the pixel point to be determined exceeds the corresponding preset color subchannel threshold, determining the pixel point to be determined as the marking pixel point.
5. The method of claim 1, wherein if the ratio of the number of pixels exceeds the preset ratio, the method further comprises, after determining the billet to be detected as an unqualified billet:
acquiring a mark position coordinate value corresponding to the mark pixel point;
determining the actual position of the mark according to the coordinate value of the mark position and the corresponding relation between the coordinate value of the position and the actual position;
sending out a labeling instruction; and the labeling instruction is used for controlling a labeling machine to label unqualified labels in the areas except the actual labeling positions of the unqualified billets.
6. An intelligent detection device for steel billets, characterized in that the device comprises:
the conversion module is used for converting the shot picture containing the billet to be detected into a picture to be identified, wherein the picture to be identified consists of pixel points; the pixel points comprise billet pixel points forming the graph of the billet to be identified and irrelevant pixel points forming the surrounding environment of the billet to be identified;
the processing module is used for carrying out black setting processing on pixel points which accord with a preset threshold value in the picture to be identified;
the selection module is used for carrying out region selection on the image to be identified after the blackening treatment to obtain an initial region to be identified containing all the billet pixel points; the initial area to be identified consists of all billet pixel points and irrelevant pixel points around the billet pixel points;
the determining module is used for determining the accurate area of the steel billet to be detected from the initial area to be identified according to the length of the steel billet to be detected and the width of the steel billet to be detected; the accurate region of the billet to be detected only comprises the billet pixel points; the length of the steel billet to be detected and the width of the steel billet to be detected are obtained from a production information system;
the determining module is further configured to determine marking pixel points meeting a preset color threshold from among the pixel points included in the accurate region of the billet to be detected, and count the number of the marking pixel points; the marked pixel points are pixel points forming unqualified marks; the unqualified mark is positioned on the surface of the billet to be detected; the preset color threshold comprises a plurality of preset color subchannel thresholds;
the judging module is used for judging whether the ratio of the number of the pixel points exceeds a preset ratio or not; the pixel point number ratio is the ratio of the number of the marking pixel points to the number of the total pixel points contained in the accurate region of the billet to be detected;
the determining module is further configured to determine the to-be-detected steel billet as an unqualified steel billet if the ratio of the number of the pixels exceeds the preset ratio.
7. The apparatus of claim 6, wherein the processing module is specifically configured to:
determining black pixel points to be set with a preset threshold value from the pixel points contained in the picture to be identified;
adjusting the tone value of the black pixel point to be placed into the tone value of the black pixel point;
adjusting the saturation value of the black pixel point to be placed into the saturation value of the black pixel point;
and adjusting the brightness value of the black pixel point to be placed into the brightness value of the black pixel point.
8. The apparatus of claim 6, wherein the determining module is specifically configured to:
determining the area of the billet to be detected, the shape profile of the billet to be detected and a preset coefficient according to the length of the billet to be detected and the width of the billet to be detected; the preset coefficient is determined according to the ratio of the length of the billet to be detected to the width of the billet to be detected;
and determining the accurate region of the steel billet to be detected from the region to be identified according to the area of the steel billet to be detected, the shape profile of the steel billet to be detected and the preset coefficient.
9. The apparatus of claim 6, wherein the determining module is specifically configured to:
sequentially judging whether any color subchannel threshold of the pixel points to be determined exceeds the corresponding preset color subchannel threshold or not; the pixel points to be determined are pixel points included in the accurate region of the billet to be detected;
and if any color subchannel threshold of the pixel point to be determined exceeds the corresponding preset color subchannel threshold, determining the pixel point to be determined as the marking pixel point.
10. The apparatus of claim 6, further comprising an acquisition module:
the acquisition module is used for acquiring a mark position coordinate value corresponding to the mark pixel point;
the determining module is further configured to determine an actual position of the mark according to the mark position coordinate value and a corresponding relationship between the position coordinate value and the actual position;
the instruction module is used for sending out a labeling instruction; and the labeling instruction is used for controlling a labeling machine to label unqualified labels in the areas except the actual labeling positions of the unqualified billets.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011572256.1A CN112288747A (en) | 2020-12-28 | 2020-12-28 | Intelligent detection method and device for steel billets |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011572256.1A CN112288747A (en) | 2020-12-28 | 2020-12-28 | Intelligent detection method and device for steel billets |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112288747A true CN112288747A (en) | 2021-01-29 |
Family
ID=74426302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011572256.1A Pending CN112288747A (en) | 2020-12-28 | 2020-12-28 | Intelligent detection method and device for steel billets |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112288747A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114046729A (en) * | 2021-10-27 | 2022-02-15 | 新兴铸管股份有限公司 | Rapid bearing disassembly detection method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105692122A (en) * | 2016-04-19 | 2016-06-22 | 南京工程学院 | Laser-ray-based longitudinal tear detecting method for conveying belt |
| CN106846304A (en) * | 2017-01-03 | 2017-06-13 | 中国特种设备检测研究院 | Electrical equipment detection method and device based on infrared detection |
| CN111693778A (en) * | 2020-05-25 | 2020-09-22 | 珠海格力电器股份有限公司 | Patch resistor abnormality detection method, device, system, equipment and storage medium |
-
2020
- 2020-12-28 CN CN202011572256.1A patent/CN112288747A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105692122A (en) * | 2016-04-19 | 2016-06-22 | 南京工程学院 | Laser-ray-based longitudinal tear detecting method for conveying belt |
| CN106846304A (en) * | 2017-01-03 | 2017-06-13 | 中国特种设备检测研究院 | Electrical equipment detection method and device based on infrared detection |
| CN111693778A (en) * | 2020-05-25 | 2020-09-22 | 珠海格力电器股份有限公司 | Patch resistor abnormality detection method, device, system, equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114046729A (en) * | 2021-10-27 | 2022-02-15 | 新兴铸管股份有限公司 | Rapid bearing disassembly detection method |
| CN114046729B (en) * | 2021-10-27 | 2023-07-04 | 新兴铸管股份有限公司 | Bearing quick disassembly detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114937055B (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| CN109472271B (en) | Printed circuit board image contour extraction method and device | |
| CN105865329B (en) | The acquisition system and method for the bundled round steel end face center coordinate of view-based access control model | |
| CN110018172B (en) | Product detection system and method | |
| CN111062934B (en) | Fabric image defect real-time detection method | |
| CN110766095A (en) | Defect detection method based on image gray level features | |
| CN111539927B (en) | Detection method of automobile plastic assembly fastening buckle missing detection device | |
| CN113034488B (en) | Visual inspection method for ink-jet printed matter | |
| CN113034624A (en) | Temperature early warning image identification method, system, equipment and storage medium based on temperature sensing color-changing adhesive tape | |
| CN114581760B (en) | Equipment fault detection method and system for machine room inspection | |
| CN113269769A (en) | Defect detection method, system and equipment based on image registration | |
| CN116993725B (en) | Intelligent patch information processing system of flexible circuit board | |
| TW201931308A (en) | Video type water ruler scale detecting and identifying system and method | |
| CN112288747A (en) | Intelligent detection method and device for steel billets | |
| CN112561875A (en) | Photovoltaic cell panel coarse grid detection method based on artificial intelligence | |
| CN111968082A (en) | Product packaging defect detection and identification method based on machine vision | |
| CN112329770B (en) | Instrument scale identification method and device | |
| CN116259008A (en) | Water level real-time monitoring method based on computer vision | |
| CN115909151A (en) | Method for identifying serial number of motion container under complex working condition | |
| CN115170551A (en) | Product detection and tracing method and system based on visual technology calibration | |
| CN114708234B (en) | Method and device for identifying number of detonators on automatic bayonet coding all-in-one machine | |
| CN111445458B (en) | Method for detecting printing quality of mobile phone battery label | |
| CN112730427B (en) | Product surface defect detection method and system based on machine vision | |
| CN115713758B (en) | Carriage identification method, system, device and storage medium | |
| CN111539933B (en) | Direct-insert element detection method and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210129 |