CN113936000A - Injection molding wave flow mark identification method based on image processing - Google Patents
Injection molding wave flow mark identification method based on image processing Download PDFInfo
- Publication number
- CN113936000A CN113936000A CN202111541866.XA CN202111541866A CN113936000A CN 113936000 A CN113936000 A CN 113936000A CN 202111541866 A CN202111541866 A CN 202111541866A CN 113936000 A CN113936000 A CN 113936000A
- Authority
- CN
- China
- Prior art keywords
- injection molding
- wave flow
- suspected
- flow mark
- mark area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
-
- 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
- G06T7/11—Region-based segmentation
-
- 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
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
- G01N2021/8887—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 based on image processing techniques
-
- 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
- G06T2207/30164—Workpiece; Machine component
Abstract
The invention relates to the field of injection molding defect identification, in particular to an injection molding wave flow mark identification method based on image processing. The method comprises the following steps: obtaining initial reference points according to the stripe direction, and obtaining a segmentation area according to the gray level difference and the distance between each pixel point and each initial reference point; acquiring each vertical datum point pair and each horizontal datum point pair; obtaining each vertical segmentation boundary and each horizontal segmentation boundary according to the gray difference and the distance between each pixel point and each reference point pair; whether the wave flow marks exist in the injection molding part is judged according to the vertical segmentation boundaries and the horizontal segmentation boundaries, so that the wave flow marks are automatically identified, and the detection efficiency of the wave flow marks is improved.
Description
Technical Field
The invention relates to the field of injection molding defect identification, in particular to an injection molding wave flow mark identification method based on image processing.
Background
In the production process of injection molding parts, wave flow marks exist on the surfaces of the injection molding parts due to excessive plastic water, inconsistent resin temperature, low melt temperature in a cavity and the like. Injection molded part wave flow marks are a common injection molded part defect. Because the position of the wave flow mark area is unpredictable, people in the field mostly manually detect the wave flow marks of the injection molding parts, and the detection efficiency is low because a lot of work load is undoubtedly increased by a plurality of injection molding parts.
Disclosure of Invention
In order to solve the problem of low efficiency of detecting the wave flow marks of the injection molding part in the prior art, the invention aims to provide an injection molding part wave flow mark identification method based on image processing, and the adopted technical scheme is as follows:
the invention provides an injection molding wave flow mark identification method based on image processing, which comprises the following steps:
obtaining a suspected wave flow mark area of the injection molding;
obtaining the stripe direction of a suspected wave flow mark area of the injection molding part, obtaining two initial reference points according to the stripe direction of the suspected wave flow mark area of the injection molding part, and dividing the suspected wave flow mark area of the injection molding part according to the gray difference between each pixel point of the suspected wave flow mark area of the injection molding part and each initial reference point and the distance between each pixel point of the suspected wave flow mark area of the injection molding part and each initial reference point to obtain two division areas;
obtaining each vertical datum point pair and each horizontal datum point pair according to the position of the area center point of each partition area;
dividing the suspected wave flow mark area of the injection molding part according to the gray difference of each pixel point of the suspected wave flow mark area of the injection molding part and each vertical datum point pair and the distance from each pixel point of the suspected wave flow mark area of the injection molding part to each vertical datum point pair to obtain each vertical segmentation boundary; dividing the suspected wave flow mark area of the injection molding part according to the gray difference of each pixel point of the suspected wave flow mark area of the injection molding part and each horizontal datum point pair and the distance from each pixel point of the suspected wave flow mark area of the injection molding part to each horizontal datum point pair to obtain each horizontal segmentation boundary;
and judging whether the injection molding part has wave flow marks or not according to the vertical dividing boundaries and the horizontal dividing boundaries.
Preferably, the determining whether the injection-molded part has wave flow marks or not by each of the vertical dividing boundaries and each of the horizontal dividing boundaries includes:
obtaining a first arrangement entropy according to the distance from each vertical partition boundary to the central point of the area of the suspected wave flow mark area of the injection molding, and obtaining a second arrangement entropy according to the distance from each horizontal partition boundary to the central point of the area of the suspected wave flow mark area of the injection molding;
and judging whether the ratio of the first arrangement entropy to the second arrangement entropy is larger than a set threshold value, if so, judging that the wave flow mark exists in the injection molding piece, and if not, judging that the wave flow mark does not exist in the injection molding piece.
Preferably, the obtaining the direction of the striations of the suspected wave flow mark area of the injection molding part comprises:
obtaining the area central point of a suspected wave flow mark area of the injection molding, and drawing straight lines in all directions through the area central point of the suspected wave flow mark area of the injection molding;
acquiring the gray value of each pixel point on the straight line in each direction, and calculating the gray change degree of the straight line in each direction according to the gray value of each pixel point on the straight line in each direction;
and taking the direction corresponding to the straight line with the minimum gray scale change degree as the stripe direction of the suspected wave flow mark area of the injection molding.
Preferably, the dividing the suspected wave flow mark area of the injection molding according to the gray difference between each pixel point of the suspected wave flow mark area of the injection molding and each initial reference point and the distance between each pixel point of the suspected wave flow mark area of the injection molding and each initial reference point to obtain two divided areas includes:
normalizing the gray value of each pixel point in the suspected wave flow mark area of the injection molding by using the maximum gray value of the pixel point in the suspected wave flow mark area of the injection molding;
calculating the similarity between each pixel point of the suspected wave flow mark area of the injection molding part and each initial reference point;
and dividing the suspected wave flow mark area of the injection molding according to the similarity between each pixel point of the suspected wave flow mark area of the injection molding and each initial reference point to obtain two divided areas.
Preferably, the similarity between each pixel point of the suspected wave flow mark area of the injection molding part and each initial reference point is calculated by adopting the following formula:
wherein the content of the first and second substances,
the similarity between any pixel point of the suspected wave flow mark area of the injection molding piece and the initial reference point,
the distance between the pixel point and the initial reference point in the suspected wave flow mark area of the injection molding part,
the area of the suspected wave mark region of the injection molded part,
and (4) the gray level difference between the pixel point and the initial reference point is in the suspected wave flow mark area of the injection molding piece.
Preferably, the obtaining each vertical reference point pair and each horizontal reference point pair includes:
respectively making straight lines perpendicular to the stripe direction of the suspected wave flow mark area of the injection molding through the area center points of the segmentation areas, marking as vertical reference lines, respectively taking the area center of each segmentation area as a starting point, and taking a set number of reference points along the vertical reference lines towards the boundary direction of the suspected wave flow mark area of the injection molding to obtain each vertical reference point pair;
and respectively drawing straight lines parallel to the stripe direction of the suspected wave flow mark area of the injection molding through the area center points of the divided areas, marking the straight lines as horizontal datum lines, and respectively taking a set number of datum points along the horizontal datum line towards the boundary direction of the suspected wave flow mark area of the injection molding from the area center of each divided area as a starting point to obtain each horizontal datum point pair.
Preferably, the obtaining two initial reference points according to the stripe direction of the suspected wave flow mark area of the injection molding part includes:
acquiring a central point of a suspected wave flow mark area of the injection molding piece;
and (3) making a straight line perpendicular to the stripe direction of the suspected wave flow mark area of the injection molding by passing through the center point of the suspected wave flow mark area of the injection molding, and taking two intersection points of the straight line and the boundary of the suspected wave flow mark area of the injection molding as initial reference points.
Preferably, the obtaining the suspected wave flow mark area of the injection molding piece comprises:
acquiring an injection molding image, and performing graying processing on the injection molding image to obtain a grayed image of the injection molding;
and carrying out edge detection on the gray image of the injection molding part, and marking the area corresponding to the minimum circumscribed rectangle including all edge lines in the image as a suspected wave flow mark area of the injection molding part.
The invention has the following beneficial effects: according to the method, the stripe direction of a suspected wave flow mark area of the injection molding part is obtained, and each vertical datum point pair and each horizontal datum point pair are obtained according to the position of the area center point of each partition area of the suspected wave flow mark area of the injection molding part; according to the method, the suspected wave flow mark area of the injection molding piece is divided according to the gray level difference and the distance, the injection molding piece area is divided with the position as the assistance, the gray level difference and the distance between each pixel point and each reference point pair in the suspected wave flow mark area of the injection molding piece are obtained, the suspected wave flow mark area of the injection molding piece is divided, and each vertical dividing boundary and each horizontal dividing boundary are obtained. According to the method, the gray values of the pixel points on each direction straight line perpendicular to the stripe direction of the suspected wave flow mark area of the injection molding part are complex, the obtained positions of all the segmentation boundaries are random, the gray values of the pixel points on each direction straight line parallel to the stripe direction of the suspected wave flow mark area of the injection molding part are single, and the obtained positions of all the segmentation boundaries are basically unchanged, so that whether the suspected wave flow mark area of the injection molding part is a wave flow mark can be judged based on the characteristics of all the vertical segmentation boundaries and all the horizontal segmentation boundaries, the automatic identification of the wave flow mark is realized, and the efficiency of the wave flow mark identification is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for identifying wave flow marks of an injection molded part based on image processing according to an embodiment of the invention;
FIG. 2 is a schematic representation of a suspected wave mark region of an injection molded part.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be made on a method for identifying wave flow marks of an injection molding part based on image processing according to the present invention with reference to the accompanying drawings and preferred embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the injection molding wave flow mark identification method based on image processing, which is provided by the invention, with reference to the accompanying drawings.
Injection molding wave flow mark identification method embodiment based on image processing
The prior art is lower in efficiency of detecting the wave flow mark area of the injection molding part. In order to solve the above problems, the present embodiment proposes an injection molding wave flow mark recognition method based on image processing, and as shown in fig. 1, the injection molding wave flow mark recognition method based on image processing of the present embodiment includes the following steps:
and step S1, acquiring a suspected wave flow mark area of the injection molding.
In the manufacturing process of the injection molding part, due to improper treatment of some links, the molten material does not properly flow in a mold cavity, so that the surface of the injection molding part has annual-ring-shaped and spiral wave flow mark defects. Firstly, the melt flow is poor, when the low-temperature melt is injected into a cavity in a solidification fluctuation state in a feeding port and a runner, the melt flows along the surface of the cavity and is extruded by the injected subsequent melt to form a backflow and a branch flow, and thus, annual ring-shaped wave flow marks centering on a sprue are generated on the surface of an injection molding piece. Secondly, the melt flows unsmoothly in the flow channel, when the melt flows into a cavity with a larger cross section from a narrow cross section of the flow channel or the flow channel of the mold is narrow and has poor finish, the flow can easily form turbulent flow, and a spiral wave flow mark is formed on the surface of the plastic part.
This embodiment sets up the camera directly over the conveyer belt, makes camera optical axis perpendicular to conveyer belt plane, utilizes the camera to gather the injection molding image. As most of injection molding parts are monochromatic, when wave flow marks exist in the injection molding parts, the gray values of pixel points in wave flow mark areas are different from the gray values of pixel points in non-wave flow mark areas. Therefore, in the embodiment, the acquired injection molding image is subjected to graying processing to obtain a grayscale map of the injection molding, the edge of the grayscale map of the injection molding is detected by using a Canny operator to obtain an edge map of a suspected wave flow mark area of the injection molding, and the minimum circumscribed rectangle including all edge lines in the image is marked as the suspected wave flow mark area of the injection molding. The suspected wave flow mark area of the injection molding piece is averagely divided into n × n areas, n is more than or equal to 2, in the embodiment, one suspected wave flow mark area of the divided injection molding piece is taken as an example, as shown in fig. 2, subsequent treatment is carried out, and other suspected wave flow mark areas of the injection molding piece can be treated by adopting the method. The Canny operator used in this embodiment is a well-known technique, and will not be described herein.
Step S2, obtaining the stripe direction of the suspected wave flow mark area of the injection molding piece, obtaining two initial reference points according to the stripe direction of the suspected wave flow mark area of the injection molding piece, and dividing the suspected wave flow mark area of the injection molding piece according to the gray difference between each pixel point of the suspected wave flow mark area of the injection molding piece and each initial reference point and the distance between each pixel point of the suspected wave flow mark area of the injection molding piece and each initial reference point to obtain two divided areas.
Specifically, the process of determining the streak direction of the suspected wave flow mark region of the injection molding part in the embodiment is as follows:
and obtaining the area central point of the suspected wave flow mark area of the injection molding part, making straight lines in all directions through the area central point of the suspected wave flow mark area of the injection molding part, and forming a sequence by all pixel points on the straight lines in all directions to obtain a sequence corresponding to the straight lines in all directions.
The gray level range difference refers to the difference value between the maximum gray level and the minimum gray level of a pixel point in a sequence, and reflects the variation range and the discrete amplitude of variable distribution, the difference between the standard values of any two units in the total cannot exceed the range difference, the gray level fluctuation range of the pixel point in the sequence can be reflected, and the larger the gray level range difference is, the larger the fluctuation degree of the pixel point on the straight line in the direction is; the ratio of the gray variance to the number of the pixels reflects the gray discrete degree of the pixels under the unit length, and the larger the gray discrete degree of the pixels under the unit length is, the larger the gray change degree corresponding to the direction straight line is. In this embodiment, the gray level variation degree of each direction line is represented by the gray level range and the gray level dispersion degree of the pixel point under the unit length, and the specific formula is as follows:
wherein the content of the first and second substances,
is as follows
The degree of change in the gray scale of the sequence,
is as follows
The gray scale of the sequence is very poor,
is as follows
The degree of gray scale dispersion of the pixel points per unit length in the sequence,
is as follows
The number of pixels in each sequence.
If a certain straight line is parallel to the stripe direction of the suspected wave flow mark area of the injection molding part, most pixel points contained on the straight line in the direction are on the same stripe or not, the gray value of the pixel points on the straight line in the direction is single, the gray range difference and the gray variance are small, and the gray variation degree is small; if a certain straight line is not parallel to the direction of the stripes of the suspected wave flow mark area of the injection molding part, the straight line in the direction comprises partial pixel points on the stripes and partial pixel points on the non-stripes, so that the gray values of the pixel points on the straight line in the direction have certain difference, the gray range difference and the gray variance are large, and the gray variation degree is large; therefore, when the direction straight line is approximately parallel to the stripe direction, the degree of gray scale change corresponding to the straight line is the smallest, and in the present embodiment, the direction corresponding to the straight line with the smallest degree of gray scale change is taken as the stripe direction of the suspected wave flow mark region of the injection molding, and the stripe direction is estimated according to the degree of gray scale change, so that the obtained stripe direction is the approximate direction with the greatest possibility.
In this embodiment, the central point of the suspected wave flow mark region of the injection molding is obtained, a straight line perpendicular to the direction of the stripe is made through the central point of the suspected wave flow mark region of the injection molding, and two intersection points of the straight line and the boundary of the suspected wave flow mark region of the injection molding are taken as initial reference points. In this embodiment, two intersection points of the straight line and the boundary of the suspected wave flow mark area of the injection molding are used as initial reference points to subsequently divide the suspected wave flow mark area of the injection molding into two areas to obtain a division boundary, the initial reference points are located on the boundary of the suspected wave flow mark area of the injection molding, and when gray differences between each pixel point of the suspected wave flow mark area of the injection molding and the initial reference points are consistent, the suspected wave flow mark area of the injection molding can be directly divided according to the distance from each pixel point to the initial reference points.
In this embodiment, the gray level difference between each pixel point in the suspected wave flow mark region of the injection molding piece and the initial reference point and the distance between each pixel point in the suspected wave flow mark region of the injection molding piece and the initial reference point are obtained, and for each pixel point in the suspected wave flow mark region of the injection molding piece, the gray level of each pixel point is normalized by using the maximum gray level value of all pixel points in the suspected wave flow mark region of the injection molding piece, that is, the order is as follows:
wherein the content of the first and second substances,
is the normalized gray value of any pixel point in the suspected wave flow mark area of the injection molding part,
is the gray value of the current pixel point before normalization,
the maximum value of the gray scale of the pixel points in the suspected wave flow mark area of the injection molding part is obtained.
According to the gray difference between each pixel point of the suspected wave flow mark area of the injection molding part and the initial reference point and the distance between each pixel point of the suspected wave flow mark area of the injection molding part and the initial reference point, the similarity between each pixel point in the current area and each initial reference point is calculated, and because the gray value and the distance are two different dimensions, the calculation is carried out by adopting a vector summation method, and the specific formula is as follows:
wherein the content of the first and second substances,
the similarity between any pixel point of the suspected wave flow mark area of the injection molding piece and the initial reference point,
the distance between the current pixel point of the suspected wave flow mark area of the injection molding part and the initial reference point,
the area of the suspected wave mark region of the injection molded part,
and (4) the gray difference between the current pixel point and the initial reference point in the suspected wave flow mark area of the injection molding piece. The smaller the gray difference between the current pixel point and the initial reference point is and the closer the current pixel point is to the initial reference point, the greater the similarity between the current pixel point and the initial reference point is.
And comparing the similarity of the current pixel point and the two initial reference points, wherein the similarity of the current pixel point and which initial reference point is large, dividing the current pixel point and which initial reference point into the same area, and extracting the initial segmentation boundary of the two areas to obtain two segmentation areas.
In step S3, vertical reference point pairs and horizontal reference point pairs are obtained from the position of the area center point of each divided area.
In this embodiment, the initial reference point is determined according to the position, the segmentation area is divided according to the gray difference and the distance between each pixel point of the suspected wave flow mark area of the injection molding and the initial reference point, the gray value of the initial reference point has a great influence on the segmentation boundary, and in order to eliminate the influence, the position of the reference point is changed, and the area is re-segmented in the suspected wave flow mark area of the injection molding.
Specifically, the region center points of the two divided regions are acquired, respectively, as shown in 1 and 2 in fig. 2. And calculating the minimum value of the distance from the center point of the two segmentation areas to the segmentation boundary, and recording the number of pixel points corresponding to the minimum value as n.
Respectively making straight lines perpendicular to the stripe direction of the suspected wave flow mark area of the injection molding part through the area center points of the two segmentation areas, marking the straight lines as vertical reference lines, respectively taking the area center points of the two segmentation areas as starting points, moving the straight lines along the vertical reference lines to the boundary direction of the suspected wave flow mark area of the injection molding part, moving the straight lines for n times for each time by the distance of one pixel, obtaining a pair of new reference points for each time, obtaining n pairs of new reference points for each time, and marking the reference points as vertical reference point pairs, as shown in 3 in fig. 2; respectively making straight lines parallel to the stripe direction of the suspected wave flow mark area of the injection molding through the area center points of the two divided areas, marking the straight lines as horizontal datum lines, respectively taking the area centers of the two divided areas as starting points, moving the straight lines along the horizontal datum lines to the boundary direction of the suspected wave flow mark area of the injection molding along the horizontal datum lines, moving the straight lines for n times for each time by a distance of one pixel, obtaining a pair of new datum points for each time, obtaining n pairs of new datum points, and marking the datum points as horizontal datum point pairs, as shown in 4 in fig. 2. In this embodiment, the two regions of the injection molding part are respectively moved to the suspected wave flow mark region of the injection molding part for n times along the region center points of the two divided regions, so that the obtained number of the reference point pairs is sufficient on the premise that all the reference point pairs are located in the suspected wave flow mark region of the injection molding part, and thus, the subsequent judgment result of whether the wave flow marks exist or not based on the position of the divided boundary can be accurate enough, and the identification precision of the wave flow marks of the injection molding part is improved.
Step S4, dividing the suspected wave flow mark area of the injection molding part according to the gray difference between each pixel point of the suspected wave flow mark area of the injection molding part and each vertical datum point pair and the distance between each pixel point of the suspected wave flow mark area of the injection molding part and each vertical datum point pair to obtain each vertical division boundary; and dividing the suspected wave flow mark area of the injection molding part according to the gray difference of each pixel point of the suspected wave flow mark area of the injection molding part and each horizontal datum point pair and the distance from each pixel point of the suspected wave flow mark area of the injection molding part to each horizontal datum point pair to obtain each horizontal segmentation boundary.
According to the method, the suspected wave flow mark area of the injection molding is divided according to the gray value and the distance, the injection molding area is divided by taking the position as an auxiliary, and the influence of the position on the divided area is eliminated by linearly changing the position of the reference point. Specifically, for each pair of reference points, the similarity between each pixel point and each pair of reference points in the suspected wave flow mark area of the injection molding is calculated by the method in step S2, and the suspected wave flow mark area of the injection molding is re-divided according to the similarity between each pixel point and each pair of reference points to obtain a new division boundary. In this embodiment, the divided boundary obtained from the vertical reference point pair is referred to as a vertical divided boundary, and the divided boundary obtained from the horizontal reference point pair is referred to as a horizontal divided boundary. Thus, a plurality of vertical division boundaries and a plurality of horizontal division boundaries are obtained.
And step S5, judging whether the injection molding piece has wave flow marks according to the vertical dividing boundaries and the horizontal dividing boundaries.
On each direction straight line perpendicular to the direction of the stripes, part of pixel points are on the stripes, part of pixel points are not on the stripes, and the gray values of the pixel points are complex, so that the suspected wave flow mark area of the injection molding piece is divided according to the gray difference between each pixel point and each vertical reference point pair and the distance between each pixel point and each vertical reference point pair, the obtained positions of each vertical segmentation boundary are random, and the distance between each vertical segmentation boundary and the area center point of the suspected wave flow mark area of the injection molding piece is variable; and on each direction straight line parallel to the stripe direction, most of the pixel points are positioned on the same stripe or not, and the gray value of the pixel points is single, so that the suspected wave flow mark area of the injection molding piece is divided according to the gray difference between each pixel point and each horizontal datum point pair and the distance from each pixel point to each horizontal datum point pair, the position of each obtained horizontal division boundary is almost unchanged, and the distance from each horizontal division boundary to the central point of the area of the suspected wave flow mark area of the injection molding piece is basically unchanged. In the embodiment, each vertical segmentation boundary and each horizontal segmentation boundary are respectively fitted into a straight line by adopting a least square method, the distance from the straight line corresponding to each vertical segmentation boundary to the central point of the suspected wave flow mark area of the injection molding piece and the distance from the straight line corresponding to each horizontal segmentation boundary to the central point of the suspected wave flow mark area of the injection molding piece are obtained, a first array entropy is obtained according to the distance from the straight line corresponding to each vertical segmentation boundary to the central point of the suspected wave flow mark area of the injection molding piece, and a second array entropy is obtained according to the distance from the straight line corresponding to each horizontal segmentation boundary to the central point of the suspected wave flow mark area of the injection molding piece. The method for obtaining the permutation entropy is a known method and is not described herein. In this embodiment, the wave flow mark rate of the suspected wave flow mark region of the injection molding is determined by using the ratio of the first arrangement entropy and the second arrangement entropy, and the specific formula is as follows:
wherein the content of the first and second substances,
is the ratio of the first permutation entropy to the second permutation entropy,
in order to be the first arrangement entropy,
in order to obtain the second permutation entropy,
the distance from each vertical dividing boundary to the central point of the area of the suspected wave flow mark area of the injection molding piece,
the distance from each horizontal segmentation boundary to the center point of the area of the suspected wave flow mark area of the injection molding piece is obtained.
And judging whether the suspected wave flow mark area of the injection molding part has the wave flow marks or not according to the ratio of the obtained first arrangement entropy to the obtained second arrangement entropy. Specifically, whether the ratio of the first arrangement entropy to the second arrangement entropy is larger than a set threshold value or not is judged, if so, the wave flow mark of the injection molding piece is judged, and if not, the wave flow mark of the injection molding piece is judged not to exist. The threshold is set to 1 in this embodiment, and in a specific application, the threshold is set to a certain value greater than 1 as needed.
In this embodiment, in order to determine whether the injection molding piece has the wave flow marks, the first arrangement entropy and the second arrangement entropy are calculated, and the magnitude of the distance between the dividing lines is reflected by the magnitude of the arrangement entropy, as another embodiment, it may also be determined whether the injection molding piece has the wave flow marks according to whether the distance mean value between the vertical dividing boundaries is greater than the distance mean value between the horizontal dividing boundaries, where the specific determination method is: and if the average distance value between the vertical dividing boundaries is larger than the average distance value between the horizontal dividing boundaries, judging that the injection molding part has wave flow marks.
The method comprises the steps of obtaining the stripe direction of a suspected wave flow mark area of the injection molding, and obtaining each vertical datum point pair and each horizontal datum point pair according to the position of the area center point of each partition area of the suspected wave flow mark area of the injection molding; in this embodiment, the suspected wave flow mark area of the injection molding is segmented according to the gray level difference and the distance, the injection molding area is segmented with the position as the assistance, the gray level difference and the distance between each pixel point and each reference point pair in the suspected wave flow mark area of the injection molding are obtained, and the suspected wave flow mark area of the injection molding is divided to obtain each vertical segmentation boundary and each horizontal segmentation boundary. In the embodiment, the gray values of the pixel points on each direction straight line perpendicular to the stripe direction of the suspected wave flow mark area of the injection molding part are complex, the obtained positions of all the segmentation boundaries are random, and the gray values of the pixel points on each direction straight line parallel to the stripe direction of the suspected wave flow mark area of the injection molding part are single, so that the obtained positions of all the segmentation boundaries are basically unchanged, therefore, whether the suspected wave flow mark area of the injection molding part is the wave flow mark can be judged based on the characteristics of all the vertical segmentation boundaries and all the longitudinal segmentation boundaries, the automatic identification of the wave flow mark is realized, and the efficiency of the wave flow mark identification is improved.
It should be noted that: the above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. An injection molding wave flow mark recognition method based on image processing is characterized by comprising the following steps:
obtaining a suspected wave flow mark area of the injection molding;
obtaining the stripe direction of a suspected wave flow mark area of the injection molding part, obtaining two initial reference points according to the stripe direction of the suspected wave flow mark area of the injection molding part, and dividing the suspected wave flow mark area of the injection molding part according to the gray difference between each pixel point of the suspected wave flow mark area of the injection molding part and each initial reference point and the distance between each pixel point of the suspected wave flow mark area of the injection molding part and each initial reference point to obtain two division areas;
obtaining each vertical datum point pair and each horizontal datum point pair according to the position of the area center point of each partition area;
dividing the suspected wave flow mark area of the injection molding part according to the gray difference of each pixel point of the suspected wave flow mark area of the injection molding part and each vertical datum point pair and the distance from each pixel point of the suspected wave flow mark area of the injection molding part to each vertical datum point pair to obtain each vertical segmentation boundary; dividing the suspected wave flow mark area of the injection molding part according to the gray difference of each pixel point of the suspected wave flow mark area of the injection molding part and each horizontal datum point pair and the distance from each pixel point of the suspected wave flow mark area of the injection molding part to each horizontal datum point pair to obtain each horizontal segmentation boundary;
and judging whether the injection molding part has wave flow marks or not according to the vertical dividing boundaries and the horizontal dividing boundaries.
2. The method for identifying the wave flow marks of the injection molding part based on the image processing as claimed in claim 1, wherein the step of judging whether the injection molding part has the wave flow marks or not according to the vertical segmentation boundaries and the horizontal segmentation boundaries comprises the following steps:
obtaining a first arrangement entropy according to the distance from each vertical partition boundary to the central point of the area of the suspected wave flow mark area of the injection molding, and obtaining a second arrangement entropy according to the distance from each horizontal partition boundary to the central point of the area of the suspected wave flow mark area of the injection molding;
and judging whether the ratio of the first arrangement entropy to the second arrangement entropy is larger than a set threshold value, if so, judging that the wave flow mark exists in the injection molding piece, and if not, judging that the wave flow mark does not exist in the injection molding piece.
3. The method for identifying the wave flow marks of the injection molding part based on the image processing as claimed in claim 1, wherein the obtaining of the stripe direction of the suspected wave flow mark area of the injection molding part comprises:
obtaining the area central point of a suspected wave flow mark area of the injection molding, and drawing straight lines in all directions through the area central point of the suspected wave flow mark area of the injection molding;
acquiring the gray value of each pixel point on the straight line in each direction, and calculating the gray change degree of the straight line in each direction according to the gray value of each pixel point on the straight line in each direction;
and taking the direction corresponding to the straight line with the minimum gray scale change degree as the stripe direction of the suspected wave flow mark area of the injection molding.
4. The method for identifying the wave flow marks of the injection molding part based on the image processing as claimed in claim 1, wherein the step of dividing the suspected wave flow mark region of the injection molding part according to the gray difference between each pixel point of the suspected wave flow mark region of the injection molding part and each initial reference point and the distance between each pixel point of the suspected wave flow mark region of the injection molding part and each initial reference point to obtain two divided regions comprises the steps of:
normalizing the gray value of each pixel point in the suspected wave flow mark area of the injection molding by using the maximum gray value of the pixel point in the suspected wave flow mark area of the injection molding;
calculating the similarity between each pixel point of the suspected wave flow mark area of the injection molding part and each initial reference point;
and dividing the suspected wave flow mark area of the injection molding according to the similarity between each pixel point of the suspected wave flow mark area of the injection molding and each initial reference point to obtain two divided areas.
5. The method for identifying the wave flow marks of the injection molding part based on the image processing as claimed in claim 4, wherein the similarity between each pixel point of the suspected wave flow mark area of the injection molding part and each initial reference point is calculated by adopting the following formula:
wherein the content of the first and second substances,
the similarity between any pixel point of the suspected wave flow mark area of the injection molding piece and the initial reference point,
the distance between the pixel point and the initial reference point in the suspected wave flow mark area of the injection molding part,
the area of the suspected wave mark region of the injection molded part,
and (4) the gray level difference between the pixel point and the initial reference point is in the suspected wave flow mark area of the injection molding piece.
6. The method for identifying the wave flow marks of the injection molded part based on the image processing as claimed in claim 1, wherein the obtaining of each vertical datum point pair and each horizontal datum point pair comprises:
respectively making straight lines perpendicular to the stripe direction of the suspected wave flow mark area of the injection molding through the area center points of the segmentation areas, marking as vertical reference lines, respectively taking the area center of each segmentation area as a starting point, and taking a set number of reference points along the vertical reference lines towards the boundary direction of the suspected wave flow mark area of the injection molding to obtain each vertical reference point pair;
and respectively drawing straight lines parallel to the stripe direction of the suspected wave flow mark area of the injection molding through the area center points of the divided areas, marking the straight lines as horizontal datum lines, and respectively taking a set number of datum points along the horizontal datum line towards the boundary direction of the suspected wave flow mark area of the injection molding from the area center of each divided area as a starting point to obtain each horizontal datum point pair.
7. The method for identifying the wave flow marks of the injection molding part based on the image processing as claimed in claim 1, wherein the obtaining of two initial reference points according to the stripe direction of the suspected wave flow mark area of the injection molding part comprises:
acquiring a central point of a suspected wave flow mark area of the injection molding piece;
and (3) making a straight line perpendicular to the stripe direction of the suspected wave flow mark area of the injection molding by passing through the center point of the suspected wave flow mark area of the injection molding, and taking two intersection points of the straight line and the boundary of the suspected wave flow mark area of the injection molding as initial reference points.
8. The method for identifying the wave flow mark of the injection molding part based on the image processing as claimed in claim 1, wherein the step of obtaining the suspected wave flow mark area of the injection molding part comprises the following steps:
acquiring an injection molding image, and performing graying processing on the injection molding image to obtain a grayed image of the injection molding;
and carrying out edge detection on the gray image of the injection molding part, and marking the area corresponding to the minimum circumscribed rectangle including all edge lines in the image as a suspected wave flow mark area of the injection molding part.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111541866.XA CN113936000B (en) | 2021-12-16 | 2021-12-16 | Injection molding wave flow mark identification method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111541866.XA CN113936000B (en) | 2021-12-16 | 2021-12-16 | Injection molding wave flow mark identification method based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113936000A true CN113936000A (en) | 2022-01-14 |
| CN113936000B CN113936000B (en) | 2022-03-15 |
Family
ID=79289052
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111541866.XA Active CN113936000B (en) | 2021-12-16 | 2021-12-16 | Injection molding wave flow mark identification method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113936000B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114445379A (en) * | 2022-01-28 | 2022-05-06 | 江苏海辉塑胶制品有限公司 | Injection molding part classification method and system based on image processing |
| CN114565614A (en) * | 2022-05-02 | 2022-05-31 | 武汉华塑亿美工贸有限公司 | Injection molding surface defect analysis method and system based on machine vision |
| CN114693651A (en) * | 2022-03-31 | 2022-07-01 | 南通三信塑胶装备科技股份有限公司 | Rubber ring flow mark detection method and device based on image processing |
| CN115187602A (en) * | 2022-09-13 | 2022-10-14 | 江苏骏利精密制造科技有限公司 | Injection molding part defect detection method and system based on image processing |
| CN116630304A (en) * | 2023-07-18 | 2023-08-22 | 东莞市京品精密模具有限公司 | Lithium battery mold processing detection method and system based on artificial intelligence |
| CN116721101A (en) * | 2023-08-09 | 2023-09-08 | 山东华航高分子材料有限公司 | Defect detection method for surface wave flow marks of plastic part |
| CN117455870A (en) * | 2023-10-30 | 2024-01-26 | 太康精密（中山）有限公司 | Connecting wire and connector quality visual detection method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104850858A (en) * | 2015-05-15 | 2015-08-19 | 华中科技大学 | Injection-molded product defect detection and recognition method |
| CN110148130A (en) * | 2019-05-27 | 2019-08-20 | 北京百度网讯科技有限公司 | Method and apparatus for detecting part defect |
| CN110264447A (en) * | 2019-05-30 | 2019-09-20 | 浙江省北大信息技术高等研究院 | A kind of detection method of surface flaw of moulding, device, equipment and storage medium |
| CN111223088A (en) * | 2020-01-16 | 2020-06-02 | 东南大学 | Casting surface defect identification method based on deep convolutional neural network |
| CN210999792U (en) * | 2019-11-11 | 2020-07-14 | 河北奥都汽车零部件有限公司 | Top mold push block device for preventing wave flow marks of injection molding products |
| CN113484329A (en) * | 2021-09-07 | 2021-10-08 | 南通三信塑胶装备科技股份有限公司 | Injection molding part defect detection method and system based on machine vision |
-
2021
- 2021-12-16 CN CN202111541866.XA patent/CN113936000B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104850858A (en) * | 2015-05-15 | 2015-08-19 | 华中科技大学 | Injection-molded product defect detection and recognition method |
| CN110148130A (en) * | 2019-05-27 | 2019-08-20 | 北京百度网讯科技有限公司 | Method and apparatus for detecting part defect |
| CN110264447A (en) * | 2019-05-30 | 2019-09-20 | 浙江省北大信息技术高等研究院 | A kind of detection method of surface flaw of moulding, device, equipment and storage medium |
| CN210999792U (en) * | 2019-11-11 | 2020-07-14 | 河北奥都汽车零部件有限公司 | Top mold push block device for preventing wave flow marks of injection molding products |
| CN111223088A (en) * | 2020-01-16 | 2020-06-02 | 东南大学 | Casting surface defect identification method based on deep convolutional neural network |
| CN113484329A (en) * | 2021-09-07 | 2021-10-08 | 南通三信塑胶装备科技股份有限公司 | Injection molding part defect detection method and system based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| 吴荣佳: "注塑制品表面流痕的成因分析与研究", 《CNKI优秀硕士学位论文全文库工程科技Ⅰ辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114445379A (en) * | 2022-01-28 | 2022-05-06 | 江苏海辉塑胶制品有限公司 | Injection molding part classification method and system based on image processing |
| CN114445379B (en) * | 2022-01-28 | 2023-04-07 | 江苏海辉塑胶制品有限公司 | Injection molding part classification method and system based on image processing |
| CN114693651A (en) * | 2022-03-31 | 2022-07-01 | 南通三信塑胶装备科技股份有限公司 | Rubber ring flow mark detection method and device based on image processing |
| CN114565614A (en) * | 2022-05-02 | 2022-05-31 | 武汉华塑亿美工贸有限公司 | Injection molding surface defect analysis method and system based on machine vision |
| CN115187602A (en) * | 2022-09-13 | 2022-10-14 | 江苏骏利精密制造科技有限公司 | Injection molding part defect detection method and system based on image processing |
| CN116630304A (en) * | 2023-07-18 | 2023-08-22 | 东莞市京品精密模具有限公司 | Lithium battery mold processing detection method and system based on artificial intelligence |
| CN116630304B (en) * | 2023-07-18 | 2023-09-19 | 东莞市京品精密模具有限公司 | Lithium battery mold processing detection method and system based on artificial intelligence |
| CN116721101A (en) * | 2023-08-09 | 2023-09-08 | 山东华航高分子材料有限公司 | Defect detection method for surface wave flow marks of plastic part |
| CN116721101B (en) * | 2023-08-09 | 2023-10-20 | 山东华航高分子材料有限公司 | Defect detection method for surface wave flow marks of plastic part |
| CN117455870A (en) * | 2023-10-30 | 2024-01-26 | 太康精密（中山）有限公司 | Connecting wire and connector quality visual detection method |
| CN117455870B (en) * | 2023-10-30 | 2024-04-16 | 太康精密（中山）有限公司 | Connecting wire and connector quality visual detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113936000B (en) | 2022-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113936000B (en) | Injection molding wave flow mark identification method based on image processing | |
| CN115082485B (en) | Method and system for detecting bubble defects on surface of injection molding product | |
| CN115861291B (en) | Chip circuit board production defect detection method based on machine vision | |
| CN115082419A (en) | Blow-molded luggage production defect detection method | |
| CN109658402A (en) | Industry profile geometric dimension automatic testing method based on computer vision imaging | |
| CN113935999B (en) | Injection molding defect detection method based on image processing | |
| CN114387233A (en) | Sand mold defect detection method and system based on machine vision | |
| CN115861317A (en) | Plastic mold production defect detection method based on machine vision | |
| CN114445379B (en) | Injection molding part classification method and system based on image processing | |
| CN103886597A (en) | Circle detection method based on edge detection and fitted curve clustering | |
| CN114187289B (en) | Plastic product shrinkage pit detection method and system based on computer vision | |
| CN115578389A (en) | Defect detection method of groove MOS device | |
| CN114882029B (en) | Identification method for floating fibers on surface of glass fiber reinforced material and electronic equipment | |
| CN114998198A (en) | Injection molding surface defect identification method | |
| CN115294410B (en) | Plastic product molding control method based on pattern recognition | |
| CN116563279B (en) | Measuring switch detection method based on computer vision | |
| CN114119603A (en) | Image processing-based snack box short shot defect detection method | |
| CN114022483B (en) | Injection molding flash area identification method based on edge characteristics | |
| CN115042401B (en) | Quality detection method of microcellular foam injection molding product | |
| CN114387438A (en) | Machine vision-based die casting machine parameter regulation and control method | |
| CN104614386A (en) | Lens defects type identification method | |
| CN116630304A (en) | Lithium battery mold processing detection method and system based on artificial intelligence | |
| CN114511531A (en) | Injection molding wave flow mark identification method based on image processing | |
| CN116945521B (en) | Injection molding defect detection method | |
| CN116167970A (en) | Sand mold detection system and detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |