CN104899863A - Mold protector and implementation method thereof - Google Patents

Abstract

The invention discloses a mold protector and an implementation method thereof. The method comprises: using pre-collected multiple qualified template images as reference images; separately calculating a minimum value image and a maximum value image of the reference images; determining, when mold matching detection is performed, whether a color value of each pixel point of a to-be-detected template image is between a color value of a corresponding pixel point of the minimum value image and a color value of a corresponding pixel point of the maximum value image, and if yes, the pixel point of the to-be-detected template image is a qualified point, otherwise, the pixel point of the to-be-detected template image is an unqualified point; further excluding a single unqualified point; comparing a quantity of remaining unqualified points with a preset threshold, if the quantity of remaining unqualified points is greater than the preset threshold, a detection result is being unqualified, and if the quantity of remaining unqualified points is less than the preset threshold, the detection result is being qualified. The invention has the advantages that accuracy is higher, an algorithm is simpler, a processing speed is faster, and time required by detection is greatly shortened.

Description

A kind of mould protector and its implementation

Technical field

The present invention relates to mould monitoring technical field, particularly a kind of mould protector and its implementation.

Background technology

The implementation method of existing mould protector is all mainly the template matches based on benchmark image; namely; by gathering multiple qualified template images as benchmark image; current template image is obtained and all benchmark images contrast successively after each die sinking puts in place; as long as wherein a benchmark image is substantially similar; namely the difference of each pixel of current template image and benchmark image corresponding pixel points gray-scale value is greater than always counting of tolerance and is less than setting value; namely think that current template image is qualified, otherwise be then defective.The advantage of this method easily realizes and user's easy understand, but weak point is if die sinking position is slightly inaccurate, then image difference will cause wrong report comparatively greatly; And if template is more, then processing speed is slow, increases time production cycle.

Summary of the invention

The present invention, for solving the problem, provides a kind of mould protector and its implementation, makes template matches efficiency higher.

For achieving the above object, the technical solution used in the present invention is:

An implementation method for mould protector, is characterized in that, comprises the following steps:

10. gather several qualified template images, as benchmark image;

The minimum value image of the described benchmark image of 20. calculating and maximal value image;

30. judge that the color value of each pixel of template image to be detected is whether between the color value of the corresponding pixel points of described minimum value image and the color value of the corresponding pixel points of maximal value image, if, then the pixel of this template image to be detected is qualified point, otherwise for not conforming to lattice point;

40. analyze all consecutive point not conforming to lattice point, get rid of single not conform to lattice point, and statistics residue does not conform to the quantity of lattice point;

Described residue not to be conformed to the quantity of lattice point and predetermined threshold value contrasts by 50., be greater than predetermined threshold value then this testing result be defective, be less than predetermined threshold value then this testing result be qualified.

Preferably, in described step 20, calculate minimum value image and the maximal value image of described benchmark image, further comprising the steps:

Each pixel of the benchmark image described in 21. pairs calculates grey scale cumulative sum, mean value, standard deviation;

22. according to the size Lookup protocol amplification coefficient in region to be detected;

23. according to described grey scale cumulative sum, mean value, standard deviation and amplification coefficient, the minimum value image of Calculation Basis image and maximal value image.

Preferably, in described step 21, grey scale cumulative sum, mean value, standard deviation are calculated to each pixel of described benchmark image, further comprising the steps:

211. calculate grey scale cumulative sum:

$G(x,y)=\underset{i=1}{\overset{k}{\mathrm{\Σ}}}{G}_i(x,y);$

212. computation of mean values:

$\stackrel{\‾}{G}(x,y)=\frac{\underset{i=1}{\overset{k}{\mathrm{\Σ}}}{G}_i(x,y)}{k};$

213. calculate standard deviation:

$S_{(x,y)}=\sqrt{\frac{\underset{i=1}{\overset{k}{\mathrm{\Σ}}}{(G_i(x,y)-\stackrel{\‾}{G}(x,y))}^2}{k}};$

Wherein, G _i(x, y) is that on i-th benchmark image, coordinate is the gray-scale value of the pixel of (x, y), and k is the number of benchmark image.

Preferably, in described step 22, according to the size Lookup protocol amplification coefficient in region to be detected, computing method are as follows:

If length and the wide minimum value of the outsourcing rectangle in region to be detected are less than 40, then amplification coefficient T=1;

If length and the wide minimum value of the outsourcing rectangle in region to be detected equal 40, then amplification coefficient T=2;

If length and the wide minimum value of the outsourcing rectangle in region to be detected are greater than 40, then amplification coefficient T=3.

Preferably, in described step 23, according to described grey scale cumulative sum, mean value, standard deviation and amplification coefficient, the minimum value image of Calculation Basis image and maximal value image, computing method are as follows:

The color value of 231. each pixels of calculated minimum image:

$\mathrm{MIN}(x,y)=\stackrel{\‾}{G}(x,y)-S(x,y)\×T;$

The color value of 232. each pixels of calculated minimum image:

$\mathrm{MAX}(x,y)=\stackrel{\‾}{G}(x,y)+S(x,y)\×T;$

Wherein, for described mean value; S (x, y) is described standard deviation; T is described amplification coefficient.

In addition, present invention also offers a kind of mould protector, it is characterized in that, it at least comprises:

Image capture module, for gathering several qualified template images, as benchmark image;

Image computing module, for calculating minimum value image and the maximal value image of described benchmark image;

Analyze judge module, for judging that the color value of each pixel of template image to be detected is whether between the color value of the corresponding pixel points of described minimum value image and the color value of the corresponding pixel points of maximal value image, if, then the pixel of this template image to be detected is qualified point, otherwise for not conforming to lattice point;

Analytic statistics module, for analyzing all consecutive point not conforming to lattice point, gets rid of and single do not conform to lattice point, and statistics residue not conforming to the quantity of lattice point;

Threshold value judgment module, contrasts for the quantity and predetermined threshold value described residue not being conformed to lattice point, be greater than predetermined threshold value then this testing result be defective, be less than predetermined threshold value then this testing result be qualified.

The invention has the beneficial effects as follows:

A kind of mould protector of the present invention and its implementation, it is by gathering several qualified template images as benchmark image in advance, and calculate minimum value image and the maximal value image of described benchmark image respectively, then the color value of each pixel judging template image to be detected is carried out when carrying out mould matching detection whether between the color value of the corresponding pixel points of described minimum value image and the color value of the corresponding pixel points of maximal value image, if, then the pixel of this template image to be detected is qualified point, otherwise for not conforming to lattice point, and get rid of further and single do not conform to lattice point, the quantity and the predetermined threshold value that residue are not conformed to lattice point contrast, be greater than predetermined threshold value then this testing result be defective, be less than predetermined threshold value then this testing result be qualified, accuracy rate is higher, avoid because mould die sinking position changes the wrong report caused, and the maximal value image calculated with multiple benchmark images and minimum value image carry out the method for mating to replace traditional template one by one, algorithm is simpler, processing speed is faster, detection required time greatly reduces.

Accompanying drawing explanation

Accompanying drawing described herein is used to provide a further understanding of the present invention, forms a part of the present invention, and schematic description and description of the present invention, for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:

Fig. 1 is the general flow chart of the implementation method of a kind of mould protector of the present invention;

Fig. 2 is the structural representation of a kind of mould protector of the present invention.

Embodiment

In order to make technical matters to be solved by this invention, technical scheme and beneficial effect clearly, understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.

As shown in Figure 1, the implementation method of a kind of mould protector of the present invention, it comprises the following steps:

10. gather several qualified template images, as benchmark image;

The minimum value image of the described benchmark image of 20. calculating and maximal value image;

30. judge that the color value of each pixel of template image to be detected is whether between the color value of the corresponding pixel points of described minimum value image and the color value of the corresponding pixel points of maximal value image, if, then the pixel of this template image to be detected is qualified point, otherwise for not conforming to lattice point;

40. analyze all consecutive point not conforming to lattice point, get rid of single not conform to lattice point, and statistics residue does not conform to the quantity of lattice point;

Described residue not to be conformed to the quantity of lattice point and predetermined threshold value contrasts by 50., be greater than predetermined threshold value then this testing result be defective, be less than predetermined threshold value then this testing result be qualified.

In step 20 described in the present embodiment, calculate minimum value image and the maximal value image of described benchmark image, further comprising the steps:

Each pixel of the benchmark image described in 21. pairs calculates grey scale cumulative sum, mean value, standard deviation;

22. according to the size Lookup protocol amplification coefficient in region to be detected;

23. according to described grey scale cumulative sum, mean value, standard deviation and amplification coefficient, the minimum value image of Calculation Basis image and maximal value image.

In described step 21, grey scale cumulative sum, mean value, standard deviation are calculated to each pixel of described benchmark image, further comprising the steps:

211. calculate grey scale cumulative sum:

$G(x,y)=\underset{i=1}{\overset{k}{\mathrm{\Σ}}}{G}_i(x,y);$

212. computation of mean values:

$\stackrel{\‾}{G}(x,y)=\frac{\underset{i=1}{\overset{k}{\mathrm{\Σ}}}{G}_i(x,y)}{k};$

213. calculate standard deviation:

$S_{(x,y)}=\sqrt{\frac{\underset{i=1}{\overset{k}{\mathrm{\Σ}}}{(G_i(x,y)-\stackrel{\‾}{G}(x,y))}^2}{k}};$

Wherein, G _i(x, y) is that on i-th benchmark image, coordinate is the gray-scale value of the pixel of (x, y), and k is the number of benchmark image.

In described step 22, according to the size Lookup protocol amplification coefficient in region to be detected, computing method are as follows:

If length and the wide minimum value of the outsourcing rectangle in region to be detected are less than 40, then amplification coefficient T=1;

If length and the wide minimum value of the outsourcing rectangle in region to be detected equal 40, then amplification coefficient T=2;

If length and the wide minimum value of the outsourcing rectangle in region to be detected are greater than 40, then amplification coefficient T=3.

In described step 23, according to described grey scale cumulative sum, mean value, standard deviation and amplification coefficient, the minimum value image of Calculation Basis image and maximal value image, computing method are as follows:

The color value of 231. each pixels of calculated minimum image:

$\mathrm{MIN}(x,y)=\stackrel{\‾}{G}(x,y)-S(x,y)\×T;$

The color value of 232. each pixels of calculated minimum image:

$\mathrm{MAX}(x,y)=\stackrel{\‾}{G}(x,y)+S(x,y)\×T;$

Wherein, for described mean value; S (x, y) is described standard deviation; T is described amplification coefficient.

In described step 40, analyze all consecutive point not conforming to lattice point, get rid of and single do not conform to lattice point, mainly according to nine grids algorithm, do not conform to lattice point for each, analyze the current point do not conformed to around lattice point, there are at most 8 points in each surrounding not conforming to lattice point, if these 8 points are all qualified, then this current defective point is judged as single not conforming to lattice point, gets rid of; If have at least a point defective in these 8 points, then this current defective point is not single do not conform to lattice point, retains yet.

As shown in Figure 2, present invention also offers a kind of mould protector, it is characterized in that, it at least comprises:

Image capture module A, for gathering several qualified template images, as benchmark image;

Image computing module B, for calculating minimum value image and the maximal value image of described benchmark image;

Analyze judge module C, for judging that the color value of each pixel of template image to be detected is whether between the color value of the corresponding pixel points of described minimum value image and the color value of the corresponding pixel points of maximal value image, if, then the pixel of this template image to be detected is qualified point, otherwise for not conforming to lattice point;

Analytic statistics module D, for analyzing all consecutive point not conforming to lattice point, gets rid of and single do not conform to lattice point, and statistics residue not conforming to the quantity of lattice point;

Threshold value judgment module E, contrasts for the quantity and predetermined threshold value described residue not being conformed to lattice point, be greater than predetermined threshold value then this testing result be defective, be less than predetermined threshold value then this testing result be qualified.

It should be noted that, each embodiment in this instructions all adopts the mode of going forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, between each embodiment identical similar part mutually see.For device class embodiment, due to itself and embodiment of the method basic simlarity, so description is fairly simple, relevant part illustrates see the part of embodiment of the method.And, in this article, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, article or equipment and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, article or equipment.When not more restrictions, the key element limited by statement " comprising ... ", and be not precluded within process, method, article or the equipment comprising described key element and also there is other identical element.In addition, one of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can have been come by hardware, the hardware that also can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium mentioned can be ROM (read-only memory), disk or CD etc.

Above-mentioned explanation illustrate and describes the preferred embodiments of the present invention, be to be understood that the present invention is not limited to the form disclosed by this paper, should not regard the eliminating to other embodiments as, and can be used for other combinations various, amendment and environment, and can in invention contemplated scope herein, changed by the technology of above-mentioned instruction or association area or knowledge.And the change that those skilled in the art carry out and change do not depart from the spirit and scope of the present invention, then all should in the protection domain of claims of the present invention.

Claims (6)

1. an implementation method for mould protector, is characterized in that, comprises the following steps:

10. gather several qualified template images, as benchmark image;

The minimum value image of the described benchmark image of 20. calculating and maximal value image;

30. judge that the color value of each pixel of template image to be detected is whether between the color value of the corresponding pixel points of described minimum value image and the color value of the corresponding pixel points of maximal value image, if, then the pixel of this template image to be detected is qualified point, otherwise for not conforming to lattice point;

40. analyze all consecutive point not conforming to lattice point, get rid of single not conform to lattice point, and statistics residue does not conform to the quantity of lattice point;

Described residue not to be conformed to the quantity of lattice point and predetermined threshold value contrasts by 50., be greater than predetermined threshold value then this testing result be defective, be less than predetermined threshold value then this testing result be qualified.

2. the implementation method of a kind of mould protector according to claim 1, is characterized in that: in described step 20, calculates minimum value image and the maximal value image of described benchmark image, further comprising the steps:

Each pixel of the benchmark image described in 21. pairs calculates grey scale cumulative sum, mean value, standard deviation;

22. according to the size Lookup protocol amplification coefficient in region to be detected;

23. according to described grey scale cumulative sum, mean value, standard deviation and amplification coefficient, the minimum value image of Calculation Basis image and maximal value image.

3. the implementation method of a kind of mould protector according to claim 2, is characterized in that: in described step 21, calculates grey scale cumulative sum, mean value, standard deviation to each pixel of described benchmark image, further comprising the steps:

211. calculate grey scale cumulative sum:

$G(x,y)=\underset{i=1}{\overset{k}{\mathrm{\Σ}}}{G}_i(x,y);$

212. computation of mean values:

$\stackrel{\‾}{G}(x,y)=\frac{\underset{i=1}{\overset{k}{\mathrm{\Σ}}}{G}_i(x,y)}{k};$

213. calculate standard deviation:

$S_{(x,y)}=\sqrt{\frac{\underset{i=1}{\overset{k}{\mathrm{\Σ}}}{(G_i(x,y)-\stackrel{\‾}{G}(x,y))}^2}{k}};$

Wherein, G _i(x, y) is that on i-th benchmark image, coordinate is the gray-scale value of the pixel of (x, y), and k is the number of benchmark image.

4. the implementation method of a kind of mould protector according to claim 2, is characterized in that: in described step 22, and according to the size Lookup protocol amplification coefficient in region to be detected, computing method are as follows:

If length and the wide minimum value of the outsourcing rectangle in region to be detected are less than 40, then amplification coefficient T=1;

If length and the wide minimum value of the outsourcing rectangle in region to be detected equal 40, then amplification coefficient T=2;

If length and the wide minimum value of the outsourcing rectangle in region to be detected are greater than 40, then amplification coefficient T=3.

5. the implementation method of a kind of mould protector according to claim 2; it is characterized in that: in described step 23; according to described grey scale cumulative sum, mean value, standard deviation and amplification coefficient, the minimum value image of Calculation Basis image and maximal value image, computing method are as follows:

The color value of 231. each pixels of calculated minimum image:

$\mathrm{MIN}(x,y)=\stackrel{\‾}{G}(x,y)-S(x,y)\×T;$

The color value of 232. each pixels of calculated minimum image:

$\mathrm{MAX}(x,y)=\stackrel{\‾}{G}(x,y)+S(x,y)\×T;$

Wherein, for described mean value; S (x, y) is described standard deviation; T is described amplification coefficient.

6. a mould protector, is characterized in that, it at least comprises:

Image capture module, for gathering several qualified template images, as benchmark image;

Image computing module, for calculating minimum value image and the maximal value image of described benchmark image;

Analyze judge module, for judging that the color value of each pixel of template image to be detected is whether between the color value of the corresponding pixel points of described minimum value image and the color value of the corresponding pixel points of maximal value image, if, then the pixel of this template image to be detected is qualified point, otherwise for not conforming to lattice point;

Analytic statistics module, for analyzing all consecutive point not conforming to lattice point, gets rid of and single do not conform to lattice point, and statistics residue not conforming to the quantity of lattice point;

Threshold value judgment module, contrasts for the quantity and predetermined threshold value described residue not being conformed to lattice point, be greater than predetermined threshold value then this testing result be defective, be less than predetermined threshold value then this testing result be qualified.