CN110717889A - Defect detection method and device based on digital printing, terminal and readable medium - Google Patents
Defect detection method and device based on digital printing, terminal and readable medium Download PDFInfo
- Publication number
- CN110717889A CN110717889A CN201910842757.8A CN201910842757A CN110717889A CN 110717889 A CN110717889 A CN 110717889A CN 201910842757 A CN201910842757 A CN 201910842757A CN 110717889 A CN110717889 A CN 110717889A
- Authority
- CN
- China
- Prior art keywords
- value
- pixel
- target
- extreme
- defect
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a defect detection method based on digital printing, which comprises the following steps: acquiring a target image of a product to be detected; calculating an extreme value sequence corresponding to the target image according to a preset extreme value calculation algorithm and the gray value of each pixel point of the target image, wherein the extreme value sequence is used for representing the gray characteristic of the target image; and performing characteristic screening on the extreme sequence according to preset defect characteristics to determine the position of the target defect, wherein the characteristics comprise at least one of width characteristics, height characteristics and/or energy characteristics. The invention can detect whether the digital printing product has defects in time, so that workers can repair the printing terminal in time when the digital printing product has the defects, defective products in digital printing are reduced, and the yield and the production efficiency are improved.
Description
Technical Field
The invention relates to the technical field of computer networks and control, in particular to a defect detection method, a defect detection device, a defect detection terminal and a readable medium based on digital printing.
Background
With the development of printing technology, digital printing technology is used in more and more fields. Usually, the ink nozzles of the digital printing device are controlled by a computer to print the template picture on the reference material, and C, M, Y, K four groups of nozzles are generally configured to print in CMYK color format, and each pixel point of the jet printing is formed by combining four colors.
However, if ink cannot be ejected due to clogging or lack of ink in one of the heads or other reasons during printing, ink-jet printing cannot be performed as desired, and a single line consisting of numerous dots is missing on the printed product. In industrial application, due to the high precision and high printing speed of digital printing, human eyes cannot timely detect printing defects, so that the number of printed products for completing digital printing is already in a certain scale when the defects are discovered afterwards, and due to the defects, the corresponding printed products cannot be normally circulated or used and only can be discarded, thereby causing a great amount of waste.
That is, in the related digital printing technology, the printing defects caused by the inkjet printing cannot be detected in time, so that the yield of the printed products cannot be controlled.
Disclosure of Invention
In view of the above, it is necessary to provide a defect detection method, apparatus, computer terminal and readable medium based on digital printing.
A defect detection method based on digital printing is characterized by comprising the following steps:
acquiring a target image of a product to be detected;
calculating an extreme value sequence corresponding to the target image according to a preset extreme value calculation algorithm and the gray value of each pixel point of the target image, wherein the extreme value sequence is used for representing the gray characteristic of the target image;
and performing characteristic screening on the extreme sequence according to preset defect characteristics to determine the position of the target defect, wherein the characteristics comprise at least one of width characteristics, height characteristics and/or energy characteristics.
A defect detection apparatus based on digital printing, the apparatus comprising:
an acquisition unit: the system comprises a detection unit, a processing unit and a display unit, wherein the detection unit is used for acquiring a target image of a product to be detected;
a calculation unit: the extreme value sequence is used for calculating an extreme value sequence corresponding to the target image according to a preset extreme value calculation algorithm and the gray value of each pixel point of the target image, and the extreme value sequence is used for representing the gray characteristic of the target image;
a determination unit: the system is used for carrying out feature screening on the extreme sequence according to preset defect features and determining the position of a target defect, wherein the features comprise at least one of width features, height features and/or energy features.
A computer terminal comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of:
acquiring a target image of a product to be detected;
calculating an extreme value sequence corresponding to the target image according to a preset extreme value calculation algorithm and the gray value of each pixel point of the target image, wherein the extreme value sequence is used for representing the gray characteristic of the target image;
and performing characteristic screening on the extreme sequence according to preset defect characteristics to determine the position of the target defect, wherein the characteristics comprise at least one of width characteristics, height characteristics and/or energy characteristics.
A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of:
acquiring a target image of a product to be detected;
calculating an extreme value sequence corresponding to the target image according to a preset extreme value calculation algorithm and the gray value of each pixel point of the target image, wherein the extreme value sequence is used for representing the gray characteristic of the target image;
and performing characteristic screening on the extreme sequence according to preset defect characteristics to determine the position of the target defect, wherein the characteristics comprise at least one of width characteristics, height characteristics and/or energy characteristics.
In the embodiment of the invention, the target image of the product to be detected is obtained, the extreme value sequence corresponding to the whole target image is determined according to the gray value of each pixel point contained in the target image, and then the extreme value sequence corresponding to the target image is screened according to the preset characteristics including the height characteristic, the width characteristic, the energy characteristic and the like so as to detect the position of the target defect.
Compared with the prior art that the defects in the printed products cannot be detected in time, the product can be checked out afterwards, and once the defects are found, a certain number of defective products can be produced and only scrapped, so that the waste of production resources can be caused, and the production efficiency of digital printing is reduced when the product qualification rate of digital printing is reduced. The invention extracts the corresponding extreme value sequence aiming at the target image of the product to be detected and screens the extreme value sequence according to the preset characteristics so as to determine the target defect position, thereby realizing the defect detection of the quality of the printed product in time and improving the product qualification rate and the production efficiency of digital printing.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in 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 for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Wherein:
FIG. 1 shows a flow diagram of a digital print based defect detection method in one embodiment;
FIG. 2 illustrates a flow diagram for determining a sequence of extrema corresponding to a target image in one embodiment;
FIG. 3 illustrates a flow diagram according to one embodiment for determining a probability matrix corresponding to a target image;
FIG. 4 is a flow diagram that illustrates feature screening of extreme sequences by width features in one embodiment;
FIG. 5 is a flow diagram that illustrates feature screening of extremum sequences by height features in one embodiment;
FIG. 6 is a flow diagram that illustrates feature screening of extreme sequences by energy features in one embodiment;
FIG. 7 is a block diagram of a defect detection apparatus based on digital printing according to an embodiment;
fig. 8 shows an internal structural diagram of the computer terminal in one embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a defect detection method based on digital printing, and in one embodiment, the invention can be based on a terminal, and the terminal can be a device for collecting images and detecting defects based on the images.
Before describing a specific defect detection method, a digital printing process is described first: printing is generally performed by controlling an ink jet head to print a template picture on a reference material (such as paper, fiber, plastic, etc.) by a computer device. In a conventional digital printing, a CMYK color format (i.e., a four-color mode: a color register mode adopted in color printing, which utilizes the principle of color mixture of three primary colors of color materials and adds black ink to mix and superimpose four colors in total to present "full-color printing") is adopted for printing, so that the apparatus is provided with C, M, Y, K four groups of nozzles (corresponding to the four colors of blue, red, yellow and black, respectively), and each pixel point of the jet printing is formed by respectively jet printing the four color nozzles according to a preset time sequence and ink amount.
Based on the introduction of the digital printing process, when the four nozzles are blocked, the parts are in failure and the like, so that ink cannot be ejected, the pattern printed at the position corresponding to the failed nozzle will present a line consisting of discontinuous points instead of a normally printed uniformly-distributed dense pattern due to the absence of a certain layer of preset ink.
However, since the precision of the nozzle is high, the printing speed is fast, and the precision and the speed of the defect which can be identified by human eyes are much higher, the possible defect position in the target image needs to be timely and automatically detected according to the following steps, and further adjustment and maintenance measures need to be taken in time.
Referring to fig. 1, an embodiment of the present invention provides a defect detection method based on digital printing.
FIG. 1 shows a flow diagram of a digital print-based defect detection method in one embodiment. The defect detection method based on digital printing in the invention at least comprises steps S1022-S1026 shown in fig. 1, which are described in detail as follows:
in step S1022, a target image of the product to be detected is acquired.
In this embodiment, the product to be detected is a printed product, and it is necessary to detect whether there is a defect in the printing of the printed product. In an alternative embodiment, the product to be detected may be a printed product such as a paper poster, a poster album, or the like. And the acquisition of the target image can be completed in real time by the industrial camera arranged at the preset position.
In step S1024, an extreme value sequence corresponding to the target image is calculated according to a preset extreme value calculation algorithm and a gray value of each pixel of the target image, where the extreme value sequence is used to represent a gray characteristic of the target image.
Specifically, the process of determining the extremum sequence corresponding to the target image may include steps S1032-S1036 as shown in fig. 2. FIG. 2 illustrates a flow diagram for determining a sequence of extrema corresponding to a target image in one embodiment.
In step S1032, each pixel of the target image is traversed, and a first probability value is calculated according to a gray value of each pixel included in a row where the traversed pixel is located, so as to obtain a probability matrix corresponding to the target image.
It should be noted that after the target image of the product to be detected is obtained, a graying process may be performed on the target image to obtain a grayscale image of the target image so as to obtain grayscale information of each pixel point. In an optional embodiment, the grayscale image of the product to be detected can also be directly acquired as the target image through a preset device.
In the digital printing, a preset pattern is printed in a mode that each row or each column of nozzles are controlled and moved in sequence to spray ink with corresponding colors, when the ink jet abnormal condition of the nozzles causes the image quality of a printed product to be not in accordance with a preset standard, the difference degree between the corresponding defect position and the image part which is normally printed by ink jet at other parts is often larger (the difference is shown that the variance of the area around the defect point is larger than the average level), the variance in the local area of the defect is larger, and the gray scale distribution in the horizontal direction has certain symmetry.
Therefore, whether each pixel has defects or not can be detected from two angles of local gray variance and gray distribution symmetry. Alternatively, the defect probability may be measured according to the two angles based on the local area of each row of the target image, and accordingly, step S1032 may further include steps S1042-S1048 as shown in fig. 3. FIG. 3 illustrates a flow diagram according to one embodiment for determining a probability matrix corresponding to a target image.
In step S1042, for the traversed pixel, a local image region centered on the traversed pixel is determined, and a radius of the local image region satisfies a preset radius threshold.
In a specific embodiment, for a pixel point whose coordinate position in the traversed target image is (x, y), the gray level thereof may be denoted as I (x, y). A local transverse region with a radius R centered on the current point (x, y) may be further determined as the local image region.
In step S1044, a first pixel point and a second pixel point which are in the same pixel row as the traversed pixel point and have the same distance with the traversed pixel point in the local image region are obtained as a target pixel point pair, a difference value between the gray values of the first pixel point and the second pixel point is obtained as a first gray difference value, and an absolute value of the first gray difference value and a second gray difference value of each target pixel point pair are obtained as second gray difference values.
In an alternative embodiment, two pixel points that are respectively distant from the pixel point (x, y) by I in the same row (i.e., the x coordinate value is the same) may be taken as a first pixel point (x, y + I) and a second pixel point (x, y-I) to form a target pixel point pair, so that the first gray scale difference value is I (x, y + I) -I (x, y-I). And the sum of the absolute values of the first gray scale differences of each target pixel point pair isAs a second gray scale difference.
In step S1046, a gray variance of the local image area is calculated according to the gray value of each pixel point included in the local image area.
The gray variance corresponding to the R region can be determined as σ according to the definition of variance and a standard calculation formula.
In step S1048, the first probability value is calculated according to the second gray scale difference value, the gray scale variance, and a preset first constant.
Specifically, the probability P that a certain pixel (x, y) is a defect can be expressed as:
where R is the radius of the local image area, and γ is a predetermined first constant added to avoid the denominator being 0. From the above equation, the response of P of the defective pixel is larger than that of the non-defective pixel (refer to the above description of the characteristics of the defect region with large variance and symmetric distribution).
Returning to the description of the determination process of the extremum sequence, in step S1034, for each pixel column of the probability matrix, a column mean of the pixel column is calculated as a pixel extremum.
After the defect probability P (x, y) of the pixel point with the coordinate position (x, y) is obtained, the corresponding probability matrix can be obtained according to the defect probability of each pixel point contained in the target image.
Next, the corresponding column average probability value (denoted as column average value P) in the probability matrix for the pixel column (denoted as column c) at which point (x, y) is located is determinedc) As the extreme pixel value corresponding to the pixel column.
It should be noted that, in order to reduce the influence of background noise on subsequent defect detection, in an optional embodiment, before calculating the column mean of each pixel column and determining the corresponding pixel extremum according to the column mean, a zero-averaging processing procedure may be performed on each column mean, that is, the mean value of the defect probabilities of all the pixels of the pixel column is subtracted from each column mean value to be used as the column mean value after zero-averaging.
In step S1036, the extremum sequence is generated according to the second probability values corresponding to the pixel columns.
In particular, according to PcObtaining a second probability value P corresponding to the column c after zero equalization operationmcThis can be shown as follows:
in an alternative embodiment, the process of determining the extremum sequence may be: for each column c, by comparing Pmc(c-1)、Pmc(c) And PmcThe value of (c +1) (i.e. the second probability values corresponding to the pixel column c and the two adjacent pixel columns at the left and right sides thereof, respectively) can obtain the extremum sequence { x (n) } corresponding to the column c.
In step S1026, feature screening is performed on the extreme sequence according to preset defect features, and a target defect position is determined, where the features include at least one of a width feature, a height feature, and/or an energy feature.
First, in an alternative embodiment, the width feature of the extremum sequence may be screened to determine the target defect location, which may specifically include steps S1052-S1056 shown in fig. 4. FIG. 4 shows a flow diagram for feature screening of extreme sequences by width features in one embodiment.
It can be known from the signal characteristics of the one-dimensional signals such as the pixel points, the signal intensity of each pixel point position is determined only by the gray value of the point, so that the maximum value and the minimum value of the signal respectively correspond to the bright defect (the gray value is too large) and the dark defect (the gray value is too small), and therefore, the extremum sequence { x (n) } obtained through the above process correspondingly indicates the position where the defect (corresponding to the gray value is too large or too small) may exist.
However, due to the influence of noise in the acquired target image and the influence of false defects caused by the characteristics of the image, the extremum sequence { x (n) } may also correspond to some non-defect points. For a bright (dark) defect point, the pixel distance between the adjacent valleys (peaks) corresponding to the defect point can be used to characterize the width of the defect point.
Meanwhile, since the defect in the image usually has a certain width range, the pixel distance between the suspected defect point to be screened and its adjacent peak (valley) can be used for further defect determination.
Specifically, in step S1052, for each pixel extremum in the extremum sequence, a pixel distance between the pixel extremum and an adjacent pixel extremum is obtained as the width characteristic value.
Each element x (i) in the extremum sequence { x (n) } may be considered, and the pixel distance between it and the adjacent peak (valley) value x (i +1), x (i-1) may be obtained as the width eigenvalue corresponding to x (i).
In step S1054, it is determined whether the width feature value satisfies a preset width threshold.
In an alternative embodiment, the preset width threshold may be set to [ w ]min,wmax]In this interval range, the specific maximum/minimum value of w can be adjusted based on the distribution of the extremum sequence as a whole.
In step S1056, when the width characteristic value satisfies the preset width threshold, it is determined that the pixel point corresponding to the pixel extremum is the target defect position.
Combining the above steps, if adjacent peaks (valleys)The pixel distance between the values x (i +1), x (i-1) satisfies a specific range [ w [ w ] ]min,wmax]The current element x (i) is considered to correspond to a defect.
Further, the noise signal in the image corresponds to a small amplitude fluctuation, while the defect signal generally corresponds to a large amplitude fluctuation. Therefore, in an optional embodiment, in addition to the defect screening based on the width feature of the signal, the height feature of the signal may be correspondingly screened to further remove noise in the image, and then the defect position may be determined more accurately. The process of screening the extremum sequence for the height features may include steps S1062-S1066 as shown in fig. 5. FIG. 5 is a flow diagram that illustrates feature screening of extremum sequences by height features in one embodiment.
In step S1062, for each extremum of the pixel in the extremum sequence, an absolute value of a difference between the extremum of the pixel and two adjacent extremums of the pixel is obtained, and a height feature value is determined according to the absolute value.
In particular, at signal position cpHeight H (c) ofp) The following can be determined:
wherein bp is an extremum (maximum or minimum) of a certain pixel in the extremum sequence, alAnd arTwo extreme pixels adjacent to bp, respectively, thus al、bp、arThe positions of the three points correspond to form a signal fluctuation. And sequentially calculating the height value of each pixel extreme value contained in the extreme value sequence according to the formula.
In step S1064, it is determined whether the height feature value satisfies a preset height threshold.
In an alternative embodiment, an average of the height values of the pixel extremum included in the entire extremum sequence may be further calculated as the height threshold preset herein.
In step S1066, when the height characteristic value satisfies a preset height threshold, it is determined that the pixel point corresponding to the pixel extremum is the target defect position.
Specifically, when in the extremum sequence { x (n) }w) The height value corresponding to one or more pixel extremum in the pixel is larger than the extremum sequence x (n)w) Mean height of the rows, the row-extreme elements are considered to correspond to defect locations, and the elements satisfying the height constraint (i.e., greater than the mean height) constitute a new sequence { x (n) }h)}。
In an alternative embodiment, in addition to the defect signal screening based on the width feature (refer to fig. 4) and the height feature (refer to fig. 5) in the defect feature, an energy value feature screening may be performed on the extremum sequence to avoid the influence of noise therein and determine the defect position.
This particular optional signal screening for energy signature process may include steps S1072-S1078 as shown in fig. 6. FIG. 6 shows a flow diagram for feature screening of extreme sequences according to energy features in one embodiment.
In step S1072, at least one maximum/minimum value of the extremum sequence is determined as a target extremum.
In an alternative embodiment, one minimum bp in one extremum sequence may be determined as the target extremum.
In step S1074, each target extreme value is traversed, an energy feature value corresponding to the traversed target extreme value is calculated according to a preset energy calculation formula, and a first offset difference value and a second offset difference value are calculated according to the target extreme value adjacent to the traversed target extreme value.
First, in an alternative embodiment, according to the definition of energy, the energy feature value corresponding to the target extremum bp can be calculated as follows:
Er(bp)=|bp-a|m
the further determination process of each parameter in the above formula:
wherein m islAnd mrRespectively corresponding to a valley point bpThe adjacent maximum positions of the left side and the right side.
In the energy screening process, the selection of the optimal threshold value can be completed through the Weber's law. According to weber's law (i.e., the perception difference threshold varies with the stimulus intensity during the perception of the signal, and the ratio of the perception difference threshold to the stimulus intensity is a constant, which is set to 0.98 in one embodiment), the minimum energy threshold may be:wherein, E [ bp]Is the average of all minima (corresponding to dark defects) in x (n).
Specifically, the first deviation value may be a current point deviation value, and the calculation process is as follows:
the second deviation value may specifically be a threshold deviation, and the calculation process is as follows:
the parameters in the above formula are explained: gamma in the first deviation value calculation formula is a value [0,1]V is a preset parameter betweenlAnd vrRespectively represent the current (screened) point cpThe maximum signal variation value within the left and right specific ranges. Meanwhile, the offset value in the second offset value calculation formulaAndthe definition is as follows:
in step S1076, it is determined whether the traversed target extremum satisfies a preset energy relationship according to the energy characteristic value, the first offset difference value, and the second offset difference value.
In an alternative embodiment, n is calculated for all candidate pointshThe following equation can be taken as the preset energy relationship:
i.e. the energy value of the current point minus half of the deviation value of the current point, i.e. the first deviation value, needs to be not less than the sum of the energy value of the average minimum threshold and half of the threshold deviation, i.e. the second deviation value.
In step S1078, when the traversed target extreme value satisfies the preset energy relationship, it is determined that the pixel point corresponding to the target extreme value is the target defect position.
For all candidate points nhAnd may be determined as a defect point when the preset constraint relationship in step S1076 is satisfied.
In addition, in an optional embodiment, after the defect position is detected and determined, an alarm signal can be sent out through a preset sounding or ringing device, so that relevant personnel can classify and correspond to the failed (such as blocked) spray head according to the color corresponding to the determined defect position, adjustment and maintenance are carried out, and production of unqualified products is reduced to the greatest extent in time.
FIG. 7 is a block diagram of a defect detection apparatus based on digital printing according to an embodiment.
Referring to fig. 7, a defect detection apparatus 1080 based on digital printing according to an embodiment of the present invention includes: an acquisition unit 1082, a calculation unit 1084, a determination unit 1086.
Wherein the obtaining unit 1082: the method is used for acquiring a target image of a product to be detected.
Calculation unit 1084: the image processing method is used for calculating an extreme value sequence corresponding to the target image according to a preset extreme value calculation algorithm and the gray value of each pixel point of the target image, and the extreme value sequence is used for representing the gray characteristic of the target image.
Determination unit 1086: the system is used for carrying out feature screening on the extreme sequence according to preset defect features and determining the position of a target defect, wherein the features comprise at least one of width features, height features and/or energy features.
Fig. 8 shows an internal structural diagram of the computer terminal in one embodiment. The computer terminal may be a terminal or a server. As shown in fig. 8, the computer terminal includes a processor, a memory, and a detection module, a communication module, which are connected through a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer terminal stores an operating system and also stores a computer program, and when the computer program is executed by a processor, the computer program can enable the processor to realize the defect detection method based on digital printing. The internal memory may also have a computer program stored therein, which when executed by the processor, causes the processor to perform the digital printing based defect detection method. Those skilled in the art will appreciate that the architecture shown in fig. 8 is a block diagram of only a portion of the architecture associated with the subject application, and is not intended to limit the computer terminal to which the subject application may be applied, as a particular computer terminal may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer terminal is proposed, comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of:
acquiring a target image of a product to be detected;
calculating an extreme value sequence corresponding to the target image according to a preset extreme value calculation algorithm and the gray value of each pixel point of the target image, wherein the extreme value sequence is used for representing the gray characteristic of the target image;
and performing characteristic screening on the extreme sequence according to preset defect characteristics to determine the position of the target defect, wherein the characteristics comprise at least one of width characteristics, height characteristics and/or energy characteristics.
In one embodiment, a computer-readable storage medium is proposed, in which a computer program is stored which, when executed by a processor, causes the processor to carry out the steps of:
acquiring a target image of a product to be detected;
calculating an extreme value sequence corresponding to the target image according to a preset extreme value calculation algorithm and the gray value of each pixel point of the target image, wherein the extreme value sequence is used for representing the gray characteristic of the target image;
and performing characteristic screening on the extreme sequence according to preset defect characteristics to determine the position of the target defect, wherein the characteristics comprise at least one of width characteristics, height characteristics and/or energy characteristics.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, databases, or other media used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A defect detection method based on digital printing is characterized by comprising the following steps:
acquiring a target image of a product to be detected;
calculating an extreme value sequence corresponding to the target image according to a preset extreme value calculation algorithm and the gray value of each pixel point of the target image, wherein the extreme value sequence is used for representing the gray characteristic of the target image;
and performing characteristic screening on the extreme sequence according to preset defect characteristics to determine the position of the target defect, wherein the characteristics comprise at least one of width characteristics, height characteristics and/or energy characteristics.
2. The method according to claim 1, wherein the step of calculating an extremum sequence corresponding to the target image according to a preset extremum calculation algorithm and a gray value of each pixel point of the target image further comprises:
traversing each pixel point of a target image, calculating a first probability value through the gray value of each pixel point included in the row where the traversed pixel point is located, and acquiring a probability matrix corresponding to the target image;
calculating a column mean value of each pixel column of the probability matrix as a pixel extreme value;
and generating the extreme value sequence according to the second probability value corresponding to each pixel column.
3. The method of claim 2, wherein the step of calculating the column mean of the pixel column as the pixel extremum further comprises:
and carrying out zero equalization processing on each pixel extreme value.
4. The method according to claim 2 or 3, wherein said step of calculating, for each pixel of said traversed target image, a first probability value from the gray values of the pixels comprised in the row in which said traversed pixel is located, further comprises:
for the traversed pixel points, determining a local image area taking the traversed pixel points as a center, wherein the radius of the local image area meets a preset radius threshold;
acquiring a first pixel point and a second pixel point which are in the same pixel row with the traversed pixel point and have the same distance with the traversed pixel point in a local image area as a target pixel point pair, acquiring a difference value of gray values of the first pixel point and the second pixel point as a first gray difference value, and acquiring an absolute value of the first gray difference value of each target pixel point pair and the second gray difference value;
calculating the gray variance of the local image area according to the gray value of each pixel point contained in the local image area;
and calculating the first probability value according to the second gray difference value, the gray variance and a preset first constant.
5. The method of claim 1, wherein the step of feature-screening the extreme sequence according to a predetermined defect feature to determine the target defect location further comprises:
for each pixel extreme value in the extreme value sequence, acquiring a pixel distance between the pixel extreme value and an adjacent pixel extreme value as a width characteristic value;
judging whether the width characteristic value meets a preset width threshold value or not;
and when the width characteristic value meets a preset width threshold value, determining that the pixel point position corresponding to the pixel extreme value is a target defect position.
6. The method of claim 1, wherein the step of feature-screening the extreme sequence according to a predetermined defect feature to determine the target defect location further comprises:
for each pixel extreme value in the extreme value sequence, acquiring an absolute value of the difference between the pixel extreme value and two adjacent pixel extreme values, and determining a height characteristic value according to the absolute value;
judging whether the height characteristic value meets a preset height threshold value or not;
and when the height characteristic value meets a preset height threshold value, determining that the pixel point position corresponding to the pixel extreme value is a target defect position.
7. The method of claim 1, wherein the step of feature-screening the extreme sequence according to a predetermined defect feature to determine the target defect location further comprises:
determining at least one maximum/minimum of the extremum sequence as a target extremum;
traversing each target extreme value, calculating an energy characteristic value corresponding to the traversed target extreme value according to a preset energy calculation formula, and calculating a first offset difference value and a second offset difference value according to the target extreme value adjacent to the traversed target extreme value;
judging whether the traversed target extreme value meets a preset energy relation or not according to the energy characteristic value, the first offset difference value and the second offset difference value;
and when the traversed target extreme value meets the preset energy relation, determining that the pixel point position corresponding to the target extreme value is the target defect position.
8. A defect detection apparatus based on digital printing, the apparatus comprising:
an acquisition unit: the system comprises a detection unit, a processing unit and a display unit, wherein the detection unit is used for acquiring a target image of a product to be detected;
a calculation unit: the extreme value sequence is used for calculating an extreme value sequence corresponding to the target image according to a preset extreme value calculation algorithm and the gray value of each pixel point of the target image, and the extreme value sequence is used for representing the gray characteristic of the target image;
a determination unit: the system is used for carrying out feature screening on the extreme sequence according to preset defect features and determining the position of a target defect, wherein the features comprise at least one of width features, height features and/or energy features.
9. A readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the method according to any one of claims 1 to 7.
10. A computer terminal comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910842757.8A CN110717889A (en) | 2019-09-06 | 2019-09-06 | Defect detection method and device based on digital printing, terminal and readable medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910842757.8A CN110717889A (en) | 2019-09-06 | 2019-09-06 | Defect detection method and device based on digital printing, terminal and readable medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110717889A true CN110717889A (en) | 2020-01-21 |
Family
ID=69210341
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910842757.8A Pending CN110717889A (en) | 2019-09-06 | 2019-09-06 | Defect detection method and device based on digital printing, terminal and readable medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110717889A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113592831A (en) * | 2021-08-05 | 2021-11-02 | 北京方正印捷数码技术有限公司 | Method and device for detecting printing error and storage medium |
CN116373477A (en) * | 2023-06-06 | 2023-07-04 | 山东力乐新材料研究院有限公司 | Fault prediction method and system based on printing equipment operation parameter analysis |
CN117541585A (en) * | 2024-01-09 | 2024-02-09 | 浙江双元科技股份有限公司 | Method and device for detecting exposed foil defect of lithium battery pole piece |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101799434A (en) * | 2010-03-15 | 2010-08-11 | 深圳市中钞科信金融科技有限公司 | Printing image defect detection method |
CN106803244A (en) * | 2016-11-24 | 2017-06-06 | 深圳市华汉伟业科技有限公司 | Defect identification method and system |
DE112015004303T5 (en) * | 2014-09-22 | 2017-06-14 | Fujifilm Corporation | Image capture device, image defect detection device, and image defect detection method |
CN108230321A (en) * | 2018-01-19 | 2018-06-29 | 深圳市亿图视觉自动化技术有限公司 | Defect inspection method and device |
CN109377485A (en) * | 2018-10-12 | 2019-02-22 | 龙口味美思环保科技有限公司 | A kind of instant noodles packaging defect machine vision detection method |
-
2019
- 2019-09-06 CN CN201910842757.8A patent/CN110717889A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101799434A (en) * | 2010-03-15 | 2010-08-11 | 深圳市中钞科信金融科技有限公司 | Printing image defect detection method |
DE112015004303T5 (en) * | 2014-09-22 | 2017-06-14 | Fujifilm Corporation | Image capture device, image defect detection device, and image defect detection method |
CN106803244A (en) * | 2016-11-24 | 2017-06-06 | 深圳市华汉伟业科技有限公司 | Defect identification method and system |
CN108230321A (en) * | 2018-01-19 | 2018-06-29 | 深圳市亿图视觉自动化技术有限公司 | Defect inspection method and device |
CN109377485A (en) * | 2018-10-12 | 2019-02-22 | 龙口味美思环保科技有限公司 | A kind of instant noodles packaging defect machine vision detection method |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113592831A (en) * | 2021-08-05 | 2021-11-02 | 北京方正印捷数码技术有限公司 | Method and device for detecting printing error and storage medium |
CN113592831B (en) * | 2021-08-05 | 2024-03-19 | 北京方正印捷数码技术有限公司 | Printing error detection method, device and storage medium |
CN116373477A (en) * | 2023-06-06 | 2023-07-04 | 山东力乐新材料研究院有限公司 | Fault prediction method and system based on printing equipment operation parameter analysis |
CN116373477B (en) * | 2023-06-06 | 2023-08-15 | 山东力乐新材料研究院有限公司 | Fault prediction method and system based on printing equipment operation parameter analysis |
CN117541585A (en) * | 2024-01-09 | 2024-02-09 | 浙江双元科技股份有限公司 | Method and device for detecting exposed foil defect of lithium battery pole piece |
CN117541585B (en) * | 2024-01-09 | 2024-04-16 | 浙江双元科技股份有限公司 | Method and device for detecting exposed foil defect of lithium battery pole piece |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10214017B2 (en) | Method for detecting and compensating for failed printing nozzles in an inkjet printing machine | |
CN110717889A (en) | Defect detection method and device based on digital printing, terminal and readable medium | |
US8326079B2 (en) | Image defect detection | |
US10657640B2 (en) | System and method for generating images for inspection | |
US9213894B2 (en) | Image evaluation device, image evaluation method and program storage medium | |
CN110667254B (en) | Nozzle health detection method by means of neural network | |
US8867796B2 (en) | Automated inspection of a printed image | |
CN102529445B (en) | System and method for detecting missing inkjets in an inkjet printer using image data of printed documents without a priori knowledge of the documents | |
US10576751B2 (en) | System and methods for detecting malfunctioning nozzles in a digital printing press | |
JP6494847B1 (en) | Determining the threshold for detecting faulty print nozzles | |
US20210031507A1 (en) | Identifying differences between images | |
US11001077B2 (en) | System and methods for detecting malfunctioning nozzles in a digital printing press | |
JP2020100064A (en) | Image processing device, image processing method, and program | |
US20180082115A1 (en) | Methods of detecting moire artifacts | |
JP2019137048A (en) | Method for detecting defective printing nozzles in inkjet printing machine | |
JP5881576B2 (en) | Image evaluation apparatus, image evaluation method, image evaluation system, and program | |
JP2016034754A (en) | Image processing apparatus, image processing method, and program | |
US20220222803A1 (en) | Labeling pixels having defects | |
JP6667679B2 (en) | Calibrating a printer with multiple modules | |
US9098795B2 (en) | Image processing method and image processing apparatus | |
US20230088442A1 (en) | Image inspection device, printing device including the same, and image inspection method | |
US20180246041A1 (en) | Print data processing method, print data processing device, and recording medium having recorded therein print data processing program | |
JP2010042634A (en) | Printed image inspecting device and printing method | |
CN107533444A (en) | Print saturation degree calibration | |
JPH04255076A (en) | Method for inspecting printing and method for printing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200121 |