CN111311537A - Defect detection device and detection method - Google Patents
Defect detection device and detection method Download PDFInfo
- Publication number
- CN111311537A CN111311537A CN201911194843.9A CN201911194843A CN111311537A CN 111311537 A CN111311537 A CN 111311537A CN 201911194843 A CN201911194843 A CN 201911194843A CN 111311537 A CN111311537 A CN 111311537A
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- paper
- light source
- roller
- 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
-
- 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
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8901—Optical details; Scanning details
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8914—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
- G01N21/898—Irregularities in textured or patterned surfaces, e.g. textiles, wood
-
- 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
- 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
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8901—Optical details; Scanning details
- G01N2021/8908—Strip illuminator, e.g. light tube
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8914—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined
- G01N2021/8917—Paper, also ondulated
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/30124—Fabrics; Textile; Paper
Abstract
A defect detection device and a detection method are provided, the detection device comprises a flattening device, a light source device and an image acquisition device which are connected with the flattening device, and an online detection device which is connected with the image acquisition device, the flattening device is used for being installed on a roller of a printing machine, the light source device comprises a substrate and a plurality of light source particles which are fixedly arranged on the substrate, when the defect device is installed on the roller, the light source particles are arranged in a mode of being parallel to the central axis of the roller, the light of each light source particle is obliquely emitted onto the roller, the shooting line of the image acquisition device is perpendicular to the roller, and the online detection device is used for acquiring a paper image acquired by the image acquisition device and analyzing and processing the paper image to determine a defect area in the paper image and give an alarm. The device accessible machine is examined the defect on the mode short-term test paper product, solves the paper printing production in-process quality and controls the weak item, reduces the quality risk, satisfies the on-the-spot demand of industry mass production.
Description
Technical Field
The invention relates to the technical field of optical detection, in particular to a defect detection device and a defect detection method.
Background
In the paper printing process, due to the fact that the surface of paper is locally uneven or the gripping force of a printing roller gripper is uneven and the like, quality defects such as paper bow and wrinkles are often caused, the defects are slender in characteristic and complete in printed patterns on the surfaces of the wrinkles, and the quality control of printing products leaving factory is seriously influenced because the defects are difficult to find by the inspection of the straight surface of human eyes.
Currently, the product quality is a life line of each industry competing for the outside, and the quality target of zero defect, zero tolerance and casting fine products is the infinite pursuit of a printer. Aiming at the defects of bowed paper, folds and the like on paper, the folds of the paper are detected by people or by a mode of detecting pattern missing after the printed paper is stretched, the detection efficiency is low, and the method is not suitable for the requirement of industrial mass production. Therefore, a new device and method for detecting defects of paper is needed.
Disclosure of Invention
In view of the above, it is necessary to provide a defect detecting apparatus and a detecting method, which can solve the problem of low defect detecting efficiency in the conventional printed paper products.
A defect detection device comprises a flattening device, a light source device and an image acquisition device which are connected with the flattening device, and an online detection device which is electrically connected with the image acquisition device, wherein the flattening device is used for being installed on a roller of a printing machine so as to flatten a paper product to be tested on the roller, the light source device comprises a substrate and a plurality of light source particles which are fixedly arranged on the substrate, the light source particles are arranged in a linear manner, when the defect device is installed on the roller, the light source particles arranged in the linear manner are parallel to the central axis of the roller, an included angle is formed between each light source particle and the substrate so as to enable light rays of the light source particles to be obliquely irradiated on the roller, a shooting line of the image acquisition device is perpendicular to the roller, and the image acquisition device is used for acquiring paper images of the paper product, the online detection device is used for acquiring the paper image acquired by the image acquisition device, analyzing and processing the paper image to determine a defect area in the paper image and giving an alarm.
Further, above-mentioned defect detecting device, wherein, the exhibition paper-back edition is including scraping the cardboard and set firmly respectively scrape two connecting plates at cardboard both ends, the connecting plate is used for connecting the cylinder, the both ends of base plate respectively with two connecting plate fixed connection.
Further, the defect detecting device, wherein the image collecting device comprises a fixing plate and a plurality of cameras fixed on the fixing plate, the plurality of cameras are arranged in a linear manner, and two ends of the fixing plate are respectively fixedly connected with the two connecting plates.
Further, in the defect detection device, an included angle between the light source particles and the substrate is 30 to 60 °.
Further, in the defect detection device, the light source particles are infrared LED particles of 800-1000 nm.
An embodiment of the present invention further provides a defect detection method applied to any one of the defect detection apparatuses described above, where the defect detection method includes:
the online detection device acquires the paper image acquired by the image acquisition device;
the online detection device divides the paper image into a plurality of target subarea images according to the division rule of the standard image, and establishes the corresponding relation between the target subarea images and each standard subarea image in the standard image;
and the online detection device compares each target subarea image with the corresponding standard subarea image to determine a defect area in the paper image and give an alarm.
Further, in the defect detection method, the step of comparing each target subarea image with the corresponding standard subarea image to determine a defect area in the paper image includes:
calculating each target partition image through an edge detection algorithm to obtain gradient values of pixel points in the image;
comparing the gradient value of each pixel point with the gray value range set by the corresponding standard subarea image;
when the gradient value of the pixel point is within the gray value range, determining the pixel point as a defect point;
and carrying out clustering analysis on the defect points to obtain a defect area.
Further, in the defect detection method, the step of alarming includes:
comparing the energy of the defect region or the area of the defect point with a correspondingly set parameter value;
and when the energy or the area is larger than the corresponding parameter value, determining that the defect area reaches an error reporting condition, and alarming.
Further, in the defect detection method, the step of dividing the paper sheet image into a plurality of target subarea images according to the standard image segmentation rule includes:
positioning the paper image and the standard image based on a region positioning algorithm, and determining each region in the paper image which is respectively matched with each standard subarea image in the standard image;
and dividing the paper image according to the matched areas to obtain a plurality of target subarea images.
Further, in the above defect detection method, before the step of dividing the sheet image into a plurality of target partition images, the method further includes the steps of:
and performing Gaussian filtering on the paper image to eliminate image noise.
The defect detection device disclosed by the invention ingeniously utilizes the infrared oblique-ray and angle imaging technology, eliminates the interference of original patterns on paper, amplifies the surface flatness difference of the paper and effectively images the defects in different directions. The device accessible machine is examined the defect on the mode short-term test paper product, solves the paper printing production in-process quality and controls the weak item, improves printing product detection efficiency, reduces the quality risk, satisfies the on-the-spot demand of industry mass production.
Drawings
FIG. 1 is a schematic structural diagram of a defect detection apparatus according to a first embodiment of the present invention;
FIG. 2 is a schematic side view of a defect detection apparatus according to a first embodiment of the present invention;
FIG. 3 is a block diagram of a defect detection apparatus according to a first embodiment of the present invention;
FIG. 4 is an enlarged schematic view of the area A in FIG. 1;
FIG. 5 is a flowchart of a defect detection method according to a second embodiment of the present invention;
FIG. 6 is a flowchart of a defect detection method according to a third embodiment of the present invention;
fig. 7a and 7b show the original of the acquired paper image and the processed image, respectively.
Description of the main elements
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
These and other aspects of embodiments of the invention will be apparent with reference to the following description and attached drawings. In the description and drawings, particular embodiments of the invention have been disclosed in detail as being indicative of some of the ways in which the principles of the embodiments of the invention may be practiced, but it is understood that the scope of the embodiments of the invention is not limited correspondingly. On the contrary, the embodiments of the invention include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.
Referring to fig. 1 to 4, a defect detecting apparatus according to a first embodiment of the present invention is used for detecting a wrinkle defect on a paper product, and in particular, the defect detecting apparatus is installed on a roller 10 of a brushing machine and detects the paper product on the roller 10. The defect detection device comprises a flattening device 20, a light source device 30 and an image acquisition device 40 which are connected with the flattening device 20, and an online detection device 50 which is electrically connected with the image acquisition device 40.
The flattening device 20 is intended to be mounted on a cylinder 10 of a printing press in order to flatten a sheet product to be tested on the cylinder. Specifically, the flattening device 20 includes a paper scraping plate 21 and two connecting plates 22 fixed at two ends of the paper scraping plate 21, and the two connecting plates 22 can be fixed on the cylinder 10 of the printing machine by a fixing member such as a bolt. The paper product is closely attached to the surface of the cylinder 10 and rotates with the rotation of the cylinder 10. The paper scraping plate 21 is parallel to the surface of the roller 10, and performs leveling pretreatment on paper moving along with the roller 10, and the function of the paper scraping plate is to reduce local shadows on camera imaging caused by uneven paper so as not to influence later detection.
The cylinder 10 is provided with grippers for fixing paper, in order to avoid collision between the paper scraping plates 21 and the grippers in the movement process, vacancy with the same width as the grippers is reserved in the paper scraping plates 21 according to the positions of the grippers in design, and the grippers are effectively avoided while the paper is flattened. Generally, the width of the gripper is 2-3 sheets, so that a gap with the thickness of 2-3 sheets is reserved at the installation position of the paper scraping plate 21 and the roller 10.
The light source device 30 includes a substrate 31 and a plurality of light source particles 32, two ends of the substrate 31 are respectively fixed on the two connection plates 22, the plurality of light source particles 32 are fixed on the substrate 31 and arranged in a linear manner, when the defect detection device is installed on the drum 10, the plurality of light source particles 32 are in a linear array parallel to the central axis of the drum to form a linear light source to polish paper products, an included angle is formed between each light source particle 32 and the substrate 31 to enable light rays of the light source particles 32 to be obliquely incident on the surface of the drum 10 to polish printed paper clinging to the drum, the value range of the included angle α can be 30-60 degrees, preferably, the included angle is 45 degrees in the embodiment, and the purpose of using the oblique light source is to eliminate the original pattern interference of paper printing in later-stage imaging and amplify the defect imaging characteristics.
The infrared light is selected as irradiation light in consideration of different wavelength imaging characteristics of different lights, so that the light source particles select the infrared LED particles with the wavelength of 800-1000 nanometers, the original pattern interference of printing paper can be eliminated, and the surface smoothness difference of the paper is highlighted.
The image capturing device 40 includes a fixing plate 41 and a plurality of cameras 42 fixed on the fixing plate 41, and both ends of the fixing plate 41 are fixedly connected to the two connecting plates 22, respectively. The plurality of cameras 42 are arranged in a line to form a line camera to capture images of the paper products in real time.
The image acquisition device selects a color infrared linear array, and the shooting angle of the color infrared linear array is vertical to the surface of the roller 10, namely the shooting line of the linear array camera is vertical to the paper products on the surface of the roller 10. Because the light source particles irradiate on the roller 10 at an oblique incidence angle of 45 degrees, the shooting line of the camera 42 forms an included angle of 45 degrees with the light rays of the light source particles, the paper to be detected is vertically shot, the image obtained in the mode can eliminate the interference of the printed patterns and simultaneously amplify the defect characteristics in different directions, and the online detection of the defects such as the printed wrinkles of the paper is favorably realized.
As shown in fig. 4, the online detection device 50 is connected to the image capture device 40 via a data line, and performs information interaction. The online detection device 50 acquires the paper image acquired by the image acquisition device 40, and analyzes and processes the acquired paper image to determine a defect area in the paper image and alarm for the defect area.
The line detection device 50 mainly comprises an industrial personal computer, online detection software, an IO card, an acousto-optic alarm lamp and the like. The industrial personal computer is provided with online detection software, the online detection software is designed based on a feature extraction algorithm of edge detection and detection parameters of regions, defect analysis is directly carried out on a single product, the online detection of the defect of the printing wrinkle of the paper is realized, and the industrial personal computer sends an alarm to shut down through an IO card under the condition of abnormal quality.
The defect detection device in the embodiment ingeniously utilizes the infrared oblique incidence and angle imaging technology, eliminates the interference of original patterns on paper, amplifies the surface flatness difference of the paper, and effectively images defects in different directions. The device accessible machine is examined the defect on the mode short-term test paper product, solves the paper printing production in-process quality and controls the weak item, improves printing product detection efficiency, reduces the quality risk, satisfies the on-the-spot demand of industry mass production.
Referring to fig. 5, a defect detecting method applied to the defect detecting apparatus in the above embodiment is shown in a second embodiment of the present invention, and the method includes steps S11 to S13.
And step S11, the online detection device acquires the paper image acquired by the image acquisition device.
When the printed paper products are detected, the defect detection device is installed on the roller through the connecting plate, the paper products to be detected move close to the surface of the detection roller, and the paper to be detected is subjected to leveling pretreatment through the paper scraping plate of the paper flattening device. The light source particles of the oblique light source device are fixed on the substrate at a certain included angle (45 degrees in the embodiment), and the paper to be detected after being flattened is horizontally polished, so that the interference of the original printing patterns of the paper is eliminated in imaging, and the surface flatness difference of the paper is amplified. The camera shooting angle of the image acquisition device is perpendicular to the detection roller and forms an included angle of 45 degrees with the oblique light source, and the image acquisition line and the light beam of the image acquisition device are superposed on the surface of the paper to be detected, so that the defects generated after the paper is printed in different directions can be effectively imaged.
The on-line detection device is connected with the image acquisition device through a data line and is used for acquiring images acquired by the image acquisition device.
Step S12, the online detection device divides the paper sheet image into a plurality of target subarea images according to the dividing rule of the standard image, and establishes the corresponding relationship between the target subarea images and the standard subarea images in the standard image.
The standard image is the same image as the printing content of the paper product to be detected, and serves as a qualified reference product. The printed content in the paper image includes various kinds, such as pictures, characters, symbols, and the like, and the color is complex. If the paper product is compared as a whole, the detection difficulty and accuracy will be undoubtedly increased. Therefore, the standard image is divided into a plurality of regions, the division rule can be preset, and in specific implementation, a region with the same or similar pattern can be used as one target subarea image according to an image feature extraction algorithm, for example, the gray values of an eye region and a nearby cheek region are different, and the eye region and the nearby cheek region can be used as two different target subarea images.
Dividing the standard image into a plurality of target subarea images according to a segmentation rule, determining the positions of one or more pre-trained features in each target subarea image, and measuring the quality of each target subarea image. The quality can be measured by adopting a gray value method, for example, that is, each target partition image is correspondingly provided with a standard gray value range, and as long as the gray value of the area of the product to be tested is within the corresponding gray value range, the image of the area is normal.
When a paper image to be detected is acquired, the paper image is divided into a plurality of target subarea images according to the dividing rule of the standard image. The paper image can be divided into a plurality of target subarea images in an image positioning mode, and at present, the image positioning method based on template matching in digital image processing mainly comprises area positioning, edge positioning, geometric positioning and the like. According to the field matching efficiency of printed products and the characteristics of paper patterns, a region positioning method is generally selected, and the principle is that on the basis of image gray scale information, normalized correlation coefficients are used as similarity measurement indexes, and the positions of the characteristics consistent with standard images are searched in collected paper images in real time. And determining the one-to-one corresponding area of each standard subarea image in the paper sheet according to the positioning result to be used as a target subarea image. And meanwhile, establishing a corresponding relation between the target subarea image and each standard subarea image in the standard image.
And step S13, the online detection device compares each target subarea image with the corresponding standard subarea image to determine a defect area in the paper image and give an alarm.
And determining the standard subarea images corresponding to the target subarea images according to the corresponding relation between the target subarea images and the standard subarea images, respectively comparing the standard subarea images, and determining the defect areas in the target subarea images according to the comparison result.
In this embodiment, the target subarea image and the corresponding standard subarea image are compared by using a gray value as a measurement standard, when each pixel in the target subarea image is not within a gray value range correspondingly set by the standard image, the pixel is determined as a defect point, and a defect area is determined according to the result of the pixel one-to-one comparison, and an alarm is given.
In the embodiment, the light source with a certain included angle is arranged to eliminate the interference of the original printing patterns of the paper on the imaging, and meanwhile, the surface smoothness difference of the paper is amplified to obtain the paper image with the effective imaging defects. The paper image carries out defect analysis on a single product through a regional detection method and gives an alarm under the condition of abnormal quality.
Referring to fig. 6, a defect detecting method in a third embodiment of the present invention is applied to the defect detecting apparatus in the above embodiments, and the method is mainly implemented by an on-line detecting apparatus. The method comprises the following steps of S21-S27:
and step S21, acquiring the paper image acquired by the image acquisition device, and carrying out Gaussian filtering on the paper image to eliminate image noise.
Due to the influence of charge integration fluctuation and the like, the image acquired by the camera contains a large amount of noise, and has great interference on image quality detection. Therefore, after the image is acquired, considering the characteristics of the wrinkle defect and the processing speed of the detection system, in this embodiment, the online detection device first performs gaussian filtering on the image to remove the image noise, and this embodiment card adopts two-dimensional gaussian filtering.
The specific operation of gaussian filtering is: each pixel in the image is scanned using a specified template (or convolution, mask), and the weighted average gray value of the pixels in the neighborhood determined by the template is used to replace the value of the pixel in the center of the template.
Step S22, positioning the paper sheet image and the standard image based on an area positioning algorithm, and determining areas in the paper sheet image respectively matching with each subarea image in the standard image.
In this embodiment, the paper image and the standard image are positioned by an area positioning method. The principle is that based on image gray information, normalized correlation coefficients are used as similarity measurement indexes, and positions of features consistent with standard images are searched in paper images collected in real time. And determining the one-to-one corresponding area of each standard subarea image in the paper sheet according to the positioning result to be used as a target subarea image.
Step S23, the paper sheet image is divided according to each region determined by matching to obtain a plurality of divisional images, and a correspondence between the target divisional image and each standard divisional image in the standard image is established.
And step S24, calculating each target subarea image through an edge detection algorithm to obtain gradient values of pixel points in the image.
After the image is subjected to Gaussian filtering, a defect area in the paper image is obtained based on a quality detection algorithm of edge detection. There are many existing edge detection algorithms, such as first-order and second-order edge detection operators like sobel operator, Canny operator, Laplace operator, DOG operator, etc. According to the test results of various detection algorithms, the features extracted by the sobel operator are found to be the most complete, and the number of the mixed points is less. Therefore, the present embodiment selects the sobel edge detection algorithm as the core detection algorithm. As shown in fig. 7, the paper wrinkle area effect is obtained for the sobel operator.
The Sobel operator is a discrete first order difference operator for calculating the approximate value of the first order gradient of the image brightness function, and the operator comprises two groups of 3 x 3 matrixes which are respectively horizontal and vertical, and the horizontal and vertical brightness difference approximate values can be obtained by performing plane convolution on the horizontal and vertical matrixes and the image. If A represents the original image, GxAnd GyRepresents the images detected by the transverse and longitudinal edges respectively, and the formula is as follows:
the transverse and longitudinal gradient approximations for each pixel of the image are combined using the following formula to calculate the magnitude of the gradient G:
step S25, comparing the gradient value of each pixel with the gray value range set by the corresponding standard subarea image, and determining the pixel as a defect point when the gradient value of the pixel is in the gray value range.
And (3) correspondingly setting a gradient high value A and a gradient low value B for each standard subarea image, wherein the range [ B, A ] is a gray value range acceptable by the system, and if the gray value of the edge pixel point exceeds the acceptable range, the standard subarea image is regarded as a defect point.
And step S26, performing cluster analysis on the defect points to obtain defect areas.
And comparing the gradient value of each pixel point in the target partition image with the gray value range set by the corresponding standard partition image to obtain a residual point image for defect detection. The system adopts a Blob clustering algorithm to perform clustering analysis on the target image to obtain a defect area. The Blob clustering algorithm is used for extracting and classifying the in-out characteristics of the image, and the determination of the defect area is completed through defect combination and defect expansion. As shown in fig. 7a and 7b, the original of the collected paper image and the wrinkle feature map processed by the method are shown.
Step S27 compares the energy or the area of the defect region with a corresponding set parameter value, and when the energy or the area is greater than the corresponding parameter value, determines that the defect region meets an error reporting condition, and performs an alarm.
Due to the difference of paper and ink, the influence of factors such as the temperature and humidity of the environment and the like, certain errors exist between the image of the local area of the product and the standard image, and therefore all detected defect areas need to be alarmed. In this embodiment, an alarm is given when the defective area reaches the error reporting condition. Specifically, when the energy of the defect region is greater than the set energy parameter value or the area of the defect region is greater than the set area parameter value, it is determined that the defect region meets the error reporting condition. The energy is the sum of the gray value of the pixel point and the absolute value of the corresponding threshold difference in one region. The threshold value here may be an average value of end points of the gray value range corresponding to the region, and the energy is calculated as follows:
In this embodiment, gaussian filtering is performed on the acquired paper image to remove noise, then the paper image is divided into a plurality of target subarea images according to a division rule of a standard image, and then a wrinkle edge and an uneven paper inhibiting region are extracted through an edge detection algorithm to obtain a gradient value of each pixel point in the subarea image. And each target subarea image is correspondingly provided with a system acceptable gray value range, when the gradient value of a pixel point in one target subarea image exceeds the corresponding gray value range, the shop is determined as a defect point, finally the defect point is combined into the whole defect area through a Blob clustering algorithm, and an alarm is given when the defect area reaches an error reporting condition. The defect detection weak item in the printed product is solved to this embodiment, realizes that machine inspection replaces people to examine, has improved detection efficiency greatly.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A defect detection device is characterized by comprising a flattening device, a light source device and an image acquisition device which are connected with the flattening device, and an online detection device which is electrically connected with the image acquisition device, wherein the flattening device is used for being installed on a roller of a printing machine so as to flatten a paper product to be tested on the roller, the light source device comprises a substrate and a plurality of light source particles fixedly arranged on the substrate, the light source particles are arranged in a linear manner, when the defect device is installed on the roller, the light source particles arranged in the linear manner are parallel to the central axis of the roller, an included angle is formed between each light source particle and the substrate so as to enable light rays of the light source particles to be obliquely incident on the roller, a shooting line of the image acquisition device is perpendicular to the roller, and the image acquisition device is used for acquiring paper images of the paper product, the online detection device is used for acquiring the paper image acquired by the image acquisition device, analyzing and processing the paper image to determine a defect area in the paper image and giving an alarm.
2. The defect detecting device of claim 1, wherein the flattening device comprises a paper scraping plate and two connecting plates fixedly arranged at two ends of the paper scraping plate respectively, the connecting plates are used for connecting the roller, and two ends of the base plate are fixedly connected with the two connecting plates respectively.
3. The defect detecting device of claim 2, wherein the image capturing device comprises a fixing plate and a plurality of cameras fixed on the fixing plate, the plurality of cameras are arranged in a linear manner, and two ends of the fixing plate are respectively fixedly connected with the two connecting plates.
4. The defect inspection apparatus of claim 1, wherein an angle between the light source particles and the substrate is 30 to 60 °.
5. The defect detection device of claim 6, wherein the light source particles are infrared LED particles of 800-1000 nm.
6. A defect detection method applied to the defect detection apparatus according to any one of claims 1 to 5, the defect detection method comprising:
the online detection device acquires the paper image acquired by the image acquisition device;
the online detection device divides the paper image into a plurality of target subarea images according to the division rule of the standard image, and establishes the corresponding relation between the target subarea images and each standard subarea image in the standard image;
and the online detection device compares each target subarea image with the corresponding standard subarea image to determine a defect area in the paper image and give an alarm.
7. The method of claim 6, wherein the step of comparing each of the target subarea images with the corresponding standard subarea image to determine a defect area in the sheet image comprises:
calculating each target partition image through an edge detection algorithm to obtain gradient values of pixel points in the image;
comparing the gradient value of each pixel point with the gray value range set by the corresponding standard subarea image;
when the gradient value of the pixel point is within the gray value range, determining the pixel point as a defect point;
and carrying out clustering analysis on the defect points to obtain a defect area.
8. The defect detection method of claim 7, wherein said step of alerting comprises:
comparing the energy of the defect region or the area of the defect point with a correspondingly set parameter value;
and when the energy or the area is larger than the corresponding parameter value, determining that the defect area reaches an error reporting condition, and alarming.
9. The defect detection method of claim 6, wherein the step of dividing the sheet image into a plurality of target subarea images according to the standard image segmentation rule comprises:
positioning the paper image and the standard image based on a region positioning algorithm, and determining each region in the paper image which is respectively matched with each standard subarea image in the standard image;
and dividing the paper image according to the matched areas to obtain a plurality of target subarea images.
10. The defect detection method of claim 6, wherein said step of dividing said sheet image into a plurality of target section images is preceded by the step of:
and performing Gaussian filtering on the paper image to eliminate image noise.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911194843.9A CN111311537A (en) | 2019-11-28 | 2019-11-28 | Defect detection device and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911194843.9A CN111311537A (en) | 2019-11-28 | 2019-11-28 | Defect detection device and detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111311537A true CN111311537A (en) | 2020-06-19 |
Family
ID=71144708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911194843.9A Pending CN111311537A (en) | 2019-11-28 | 2019-11-28 | Defect detection device and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111311537A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113533372A (en) * | 2021-07-12 | 2021-10-22 | 浙江理工大学 | Paper defect detection method, system, device and computer storage medium |
| CN114418899A (en) * | 2022-03-28 | 2022-04-29 | 深圳市嘉年印务有限公司 | Self-adaptive repairing method and system for self-color printing and readable storage medium |
| CN115272341A (en) * | 2022-09-29 | 2022-11-01 | 华联机械集团有限公司 | Packaging machine defect product detection method based on machine vision |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6373964B1 (en) * | 1995-05-04 | 2002-04-16 | Heidelberger Druckmaschinen Ag | Method for image inspection and color guidance for printing products of a printing press |
| CN103342249A (en) * | 2013-07-16 | 2013-10-09 | 成都印钞有限公司 | Printing paper air-suction flattening device |
| CN107464336A (en) * | 2017-07-26 | 2017-12-12 | 南昌印钞有限公司 | A kind of colourless phosphorescence printing figure line quality online test method and device |
| CN107945152A (en) * | 2017-10-27 | 2018-04-20 | 深圳市创科自动化控制技术有限公司 | The defects of industrial camera detecting and controlling system and method |
-
2019
- 2019-11-28 CN CN201911194843.9A patent/CN111311537A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6373964B1 (en) * | 1995-05-04 | 2002-04-16 | Heidelberger Druckmaschinen Ag | Method for image inspection and color guidance for printing products of a printing press |
| CN103342249A (en) * | 2013-07-16 | 2013-10-09 | 成都印钞有限公司 | Printing paper air-suction flattening device |
| CN107464336A (en) * | 2017-07-26 | 2017-12-12 | 南昌印钞有限公司 | A kind of colourless phosphorescence printing figure line quality online test method and device |
| CN107945152A (en) * | 2017-10-27 | 2018-04-20 | 深圳市创科自动化控制技术有限公司 | The defects of industrial camera detecting and controlling system and method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113533372A (en) * | 2021-07-12 | 2021-10-22 | 浙江理工大学 | Paper defect detection method, system, device and computer storage medium |
| CN113533372B (en) * | 2021-07-12 | 2024-02-23 | 浙江理工大学 | Paper defect detection method, system, device and computer storage medium |
| CN114418899A (en) * | 2022-03-28 | 2022-04-29 | 深圳市嘉年印务有限公司 | Self-adaptive repairing method and system for self-color printing and readable storage medium |
| CN114418899B (en) * | 2022-03-28 | 2022-08-16 | 深圳市嘉年印务有限公司 | Self-adaptive repairing method and system for self-color printing and readable storage medium |
| CN115272341A (en) * | 2022-09-29 | 2022-11-01 | 华联机械集团有限公司 | Packaging machine defect product detection method based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7495758B2 (en) | Apparatus and methods for two-dimensional and three-dimensional inspection of a workpiece | |
| US8050486B2 (en) | System and method for identifying a feature of a workpiece | |
| CN111311537A (en) | Defect detection device and detection method | |
| EP1664749B1 (en) | Apparatus and method for automated web inspection | |
| CN108230324B (en) | Visual detection method for microdefect on surface of magnetic shoe | |
| WO2007062563A1 (en) | On-line automatic inspection method for detecting surface flaws of steel during the pretreatment of the ship steel | |
| US10607333B2 (en) | Real-time, full web image processing method and system for web manufacturing supervision | |
| CN109596530B (en) | Dark field polarization imaging method for classifying pockmarks and dust defects on optical surface | |
| WO2006028077A1 (en) | Ovd examination method and examination instrument | |
| CN104458764B (en) | Curved uneven surface defect identification method based on large-field-depth stripped image projection | |
| CN115100206B (en) | Printing defect identification method for textile with periodic pattern | |
| Medina et al. | Automated visual classification of frequent defects in flat steel coils | |
| CN114719749B (en) | Metal surface crack detection and real size measurement method and system based on machine vision | |
| Tolba et al. | Multiscale image quality measures for defect detection in thin films | |
| JP2015197396A (en) | Image inspection method and image inspection device | |
| JPH1163959A (en) | Surface-inspecting device | |
| CN110987954B (en) | Method and system for eliminating leather surface defect detection blind area | |
| WO2021109011A1 (en) | Intelligent capacitor internal defect detection method based on ultrasound image | |
| CN112950541A (en) | Synthetic leather gluing online monitoring method based on machine vision | |
| Boukouvalas et al. | An integrated system for quality inspection of tiles | |
| CN114166849B (en) | Method for detecting defects of printed carbon lines and moisture-sensitive film of humidity sensor | |
| JP4658779B2 (en) | Haze detection method, apparatus, and computer program | |
| WO2004034041A1 (en) | Method and apparatus for the optical evaluation of a paper surface | |
| Mishra et al. | Surface defects detection for ceramic tiles using image processing and morphological techniques | |
| JP2004125629A (en) | Defect detection apparatus |
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 | ||
| CB02 | Change of applicant information |
Address after: Kaixuan Building, No. 143 A, Xizhimenwai Street, Xicheng District, Beijing 100032 Applicant after: China Banknote Printing and Minting Group Co.,Ltd. Applicant after: NANCHANG BANKNOTE PRINTING CO.,LTD. Address before: 100044 Beijing city Xicheng District Xizhimen Street No. 143 Applicant before: CHINA BANKNOTE PRINTING AND MINTING Corp. Applicant before: NANCHANG BANKNOTE PRINTING CO.,LTD. |
|
| CB02 | Change of applicant information |