CN115359022A - Power chip quality detection method and system - Google Patents
Power chip quality detection method and system Download PDFInfo
- Publication number
- CN115359022A CN115359022A CN202211051583.1A CN202211051583A CN115359022A CN 115359022 A CN115359022 A CN 115359022A CN 202211051583 A CN202211051583 A CN 202211051583A CN 115359022 A CN115359022 A CN 115359022A
- Authority
- CN
- China
- Prior art keywords
- image
- power supply
- supply chip
- module
- pixel
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 230000009467 reduction Effects 0.000 claims abstract description 41
- 238000003709 image segmentation Methods 0.000 claims abstract description 40
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 238000007499 fusion processing Methods 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims description 24
- 230000004927 fusion Effects 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 12
- 238000003708 edge detection Methods 0.000 claims description 9
- 150000001875 compounds Chemical class 0.000 claims description 8
- 230000002146 bilateral effect Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 230000007547 defect Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000009826 distribution Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000011946 reduction process Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- 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
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
-
- 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
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/30148—Semiconductor; IC; Wafer
Abstract
The invention discloses a power supply chip quality detection method and a system, comprising S1, obtaining an appearance image of a pin of a power supply chip; s2, acquiring an image imgR of a red component, an image imgG of a green component and an image imgB of a blue component of the appearance image in an RGB color space; s3, respectively carrying out noise reduction treatment on the imgR, the imgG and the imgB to obtain images lwnsimgR, lwnsimgG and lwnsimgB; s4, respectively carrying out image segmentation processing on the lwnsimgR, the lwnsimgG and the lwnsimgB to obtain images sggimgR, sggimgG and sggimgB; s5, carrying out image fusion processing on the sgtimgR, the sgtimgG and the sgtimgB to obtain an image trgimg; s6, performing feature extraction on the trgimg to obtain feature information; and S7, judging whether the pin of the power supply chip passes the quality detection or not based on the characteristic information. According to the invention, image graying processing is not carried out before image segmentation, more detail information can be reserved than graying processing, and the accuracy of the result of detecting the pin of the power management chip by using an image recognition technology is effectively improved.
Description
Technical Field
The invention relates to the field of detection, in particular to a power supply chip quality detection method and system.
Background
A power supply chip is a chip that plays roles in conversion, distribution, detection, and other power management of power in an electronic equipment system. The CPU power supply amplitude is mainly identified, corresponding short moment waves are generated, and a post-stage circuit is pushed to output power.
After the power supply chip is produced, various quality detection needs to be carried out, in the aspect of pin detection, the prior art generally adopts an image identification mode to carry out detection, but the existing image identification process generally carries out the identification steps such as remaining noise reduction after carrying out graying processing on an image, and the processing mode is not beneficial to the retention of detail information, so that the image identification result is not accurate enough, and the quality detection result is influenced.
Disclosure of Invention
The invention aims to disclose a power supply chip quality detection method and system, which solve the problems that in the prior art, when the quality of a pin of a power supply chip is detected by adopting an image recognition technology, an image is grayed firstly, and then other recognition steps are carried out, so that the detail information is not sufficiently reserved, and the accuracy of an image recognition result is influenced.
In order to achieve the purpose, the invention adopts the following technical scheme:
in one aspect, the present invention provides a method for detecting quality of a power chip, including:
s1, obtaining an appearance image of a pin of a power supply chip;
s2, acquiring an image imgR of a red component, an image imgG of a green component and an image imgB of a blue component of the appearance image in an RGB color space;
s3, respectively carrying out noise reduction treatment on the imgR, the imgG and the imgB to obtain images lwnsimgR, lwnsimgG and lwnsimgB;
s4, respectively carrying out image segmentation processing on the lwnsimgR, the lwnsimgG and the lwnsimgB to obtain images sgtimgR, sgtimgG and sgtimgB;
s5, carrying out image fusion processing on the sgtimgR, the sgtimgG and the sgtimgB to obtain an image trgimg;
s6, performing feature extraction on the trgimg to obtain feature information;
and S7, judging whether the pin of the power supply chip passes the quality detection or not based on the characteristic information.
Preferably, the S1 includes:
an appearance image of a pin of a power supply chip is acquired using an industrial camera.
Preferably, the S3 includes:
for image I, I e { imgR, imgG, imgB }, the noise reduction is as follows:
respectively carrying out noise reduction processing on each pixel point in the image I by using a median filtering algorithm to obtain an image midI;
acquiring a set U of pixels to be processed in an image midI according to a set acquisition algorithm;
and respectively carrying out noise reduction treatment on each pixel point in the set U by using an improved bilateral filtering algorithm to obtain a noise-reduced image lwnsI.
Preferably, the acquiring a set U of to-be-processed pixel points in the image midI according to the set acquisition algorithm includes:
the pixel value of the pixel point pix in the image I is recorded as
The pixel value of the pixel pix in the image midI is recorded as
；
The coefficient of variation of the prime point pix is calculated using the following formula:
in the formula (I), the compound is shown in the specification,
the coefficient of variation is represented by a coefficient of variation,
representing a preset pixel value change standard value;
judgment of
And if so, storing the pixel point pix as a pixel point to be processed in the set U.
Preferably, the S4 includes:
the image segmentation process for image J, J ∈ { lwnsimgR, lwnsimgG, lwnsimgB }, is as follows:
dividing the image J into a plurality of sub-images with the same area;
carrying out edge detection on the image J to obtain a set of edge pixel points
；
Will comprise
In the collection of subimages of the pixels
；
Using image segmentation algorithm to respectively pair
Each subimage in the image segmentation processing unit is used for carrying out image segmentation processing to obtain a set of foreground pixel points
；
Will be at
The pixel points in the area are connected into pixel points in the area and
and taking the image formed by the pixel points in the image J as an image obtained by performing image segmentation processing on the image J.
Preferably, the edge detection is performed on the image J,obtaining a set of edge pixels
The method comprises the following steps:
carrying out edge detection on the image J by using a Marr-Hildreth algorithm to obtain a set of edge pixel points
。
Preferably, the S5 includes:
respectively calculating the self-adaptive fusion weights of sgtimgR, sgtimgG and sgtimgB
；
Respectively storing pixel points in the sgtimgR, sgtimgG and sgtimgB into sets sgtimgRU, sgtimgGU and sgtimgBU,
acquiring intersection uniU of sgtmsgRU, sgtmsgU and sgtmsgBU;
for a pixel point appix in the uniU, a pixel value trgimg (appix) of the appix in the image trgimg is obtained by using the following formula:
in the formula (I), the compound is shown in the specification,
respectively, the pixel values of appix in sgimgr, sgimgg, sgimgb.
Preferably, the S6 includes:
and performing feature extraction on the trgimg by using a SUFR algorithm to obtain feature information.
Preferably, the S7 includes:
matching the characteristic information acquired from the image trgimg with the corresponding characteristic information of the preset defect type, and if the matching is successful, indicating that the pin of the power supply chip does not pass the quality detection; and if the matching fails, indicating that the pin of the power supply chip passes the quality detection.
On the other hand, the invention provides a power chip quality detection system, which comprises a shooting module, a component image acquisition module, a noise reduction module, an image segmentation module, an image fusion module, a feature extraction module and a quality detection module;
the shooting module is used for acquiring an appearance image of a pin of the power supply chip;
the component image acquisition module is used for acquiring an image imgR of a red component, an image imgG of a green component and an image imgB of a blue component of the appearance image in an RGB color space;
the noise reduction module is used for respectively carrying out noise reduction processing on imgR, imgG and imgB to obtain images lwnsimgR, lwnsimgG and lwnsimgB;
the image segmentation module is used for respectively carrying out image segmentation on lwnsimgR, lwnsimgG and lwnsimgB to obtain images sgtimgR, sgtimgG and sgtimgB;
the image fusion module is used for carrying out image fusion processing on the sgtimgR, the sgtimgG and the sgtimgB to obtain an image trgimg;
the characteristic extraction module is used for extracting characteristics of the trgimg to obtain characteristic information;
the quality detection module is used for judging whether the pins of the power supply chip pass quality detection or not based on the characteristic information.
When the pin of the power management chip is processed by using an image recognition technology, the component images of red, green and blue are obtained firstly, then the noise reduction and image segmentation processing are respectively carried out on the component images, then the three images obtained by the segmentation processing are subjected to fusion processing, finally the image obtained by the fusion processing is subjected to feature extraction, and the quality detection is carried out based on the obtained feature information. Compared with the prior art, the invention does not carry out image graying processing before image segmentation, and the graying processing is a dimension reduction process, so that more detail information can be reserved than the graying processing, and the accuracy of the result of detecting the pin of the power management chip by using the image identification technology is effectively improved.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
Fig. 1 is a diagram of an embodiment of a method for detecting quality of a power chip according to the present invention.
Fig. 2 is a diagram of a power chip quality detection system according to an embodiment of the invention.
Detailed Description
Embodiments of the present application will be further described below with reference to the accompanying drawings. The same or similar reference numbers in the drawings identify the same or similar elements or elements having the same or similar functionality throughout. In addition, the embodiments of the present application described below in conjunction with the accompanying drawings are exemplary and are only for the purpose of explaining the embodiments of the present application, and are not to be construed as limiting the present application.
In one aspect, as shown in an embodiment of fig. 1, the present invention provides a method for detecting quality of a power chip, including:
s1, obtaining an appearance image of a pin of a power supply chip;
s2, acquiring an image imgR of a red component, an image imgG of a green component and an image imgB of a blue component of the appearance image in an RGB color space;
s3, respectively carrying out noise reduction treatment on the imgR, the imgG and the imgB to obtain images lwnsimgR, lwnsimgG and lwnsimgB;
s4, respectively carrying out image segmentation processing on the lwnsimgR, the lwnsimgG and the lwnsimgB to obtain images sggimgR, sggimgG and sggimgB;
s5, carrying out image fusion processing on the sgtimgR, the sgtimgG and the sgtimgB to obtain an image trgimg;
s6, performing feature extraction on the trgimg to obtain feature information;
and S7, judging whether the pin of the power supply chip passes the quality detection or not based on the characteristic information.
When the pin of the power management chip is processed by using an image recognition technology, the component images of red, green and blue are obtained firstly, then the noise reduction and image segmentation processing are respectively carried out on the component images, then the three images obtained by the segmentation processing are subjected to fusion processing, finally the image obtained by the fusion processing is subjected to feature extraction, and the quality detection is carried out based on the obtained feature information. Compared with the prior art, the invention does not carry out image graying processing before image segmentation, and the graying processing is a dimension reduction process, so that more detail information can be reserved than the graying processing, and the accuracy of the result of detecting the pin of the power management chip by using the image identification technology is effectively improved.
Taking an RGB image as an example, after the image is grayed, the detail information contained in the image is reduced from 3 channels to 1 channel, which also enables the detail information to be greatly reduced. The detail information has an important influence on whether the image can be accurately segmented, so that the accuracy of image segmentation can be influenced after dimension reduction.
Preferably, the S1 includes:
an industrial camera is used to acquire an appearance image of the pins of the power supply chip.
Preferably, the S3 includes:
for image I, I ∈ { imgR, imgG, imgB }, the noise reduction mode is as follows:
respectively carrying out noise reduction processing on each pixel point in the image I by using a median filtering algorithm to obtain an image midI;
acquiring a set U of pixels to be processed in the image midI according to a set acquisition algorithm;
and respectively carrying out noise reduction treatment on each pixel point in the set U by using an improved bilateral filtering algorithm to obtain a noise-reduced image lwnsI.
Different from the existing one-step noise reduction mode, the invention carries out two-step noise reduction processing, firstly carries out rapid first-step noise reduction processing through a median filtering algorithm, then obtains the pixel points to be processed needing second-step noise reduction processing according to the image obtained by the first-step noise reduction processing, and then carries out noise reduction processing on the pixel points to be processed. The pixels to be processed are all noise pixels with greatly changed pixel values after the first step of noise reduction processing, so that the selected noise pixels are subjected to the second step of noise reduction processing again on the basis of the first step of noise reduction processing, and the accuracy of the noise reduction processing result is further improved. Because all the pixel points are not processed in the second step, compared with the noise reduction in one step, the method can greatly improve the accuracy of the noise reduction result on the premise of increasing smaller noise reduction time.
Preferably, the improved bilateral filtering algorithm comprises:
in the formula (I), the compound is shown in the specification,
representing the pixel value of the pixel point q after the noise reduction processing is carried out on the pixel point q by using an improved bilateral filtering algorithm; setq representing pixel point q
A collection of pixel points in a neighborhood of size,
representing the distance between pixel point r and pixel point q,
the standard deviation representing the distance between the pixel point in setq and the pixel point r,
and
respectively representing the pixel values of pixel points q and r,
a standard deviation representing the difference in pixel values between the pixel point in setq and the pixel point r,
、
which represents a preset weight coefficient for the weight of the image,
and
respectively representing the gradient amplitudes of the pixel points q and r,
the standard deviation representing the difference in gradient magnitude between the pixel point in setq and the pixel point r.
Compared with the existing bilateral filtering algorithm, the invention also considers the aspect of gradient amplitude, and carries out weighted fusion on the original filtering result and the filtering result in the aspect of increased gradient amplitude by setting the weight coefficient, thereby obtaining a more accurate noise reduction result.
Preferably, the acquiring a set U of to-be-processed pixel points in the image midI according to the set acquisition algorithm includes:
recording the pixel value of the pixel point pix in the image I
The pixel value of the pixel pix in the image midI is recorded as
；
The coefficient of variation of the prime point pix is calculated using the following formula:
in the formula (I), the compound is shown in the specification,
the coefficient of variation is represented by a coefficient of variation,
representing a preset pixel value change standard value;
judgment of
And if so, storing the pixel point pix as a pixel point to be processed in the set U.
Preferably, the S4 includes:
the image segmentation process for image J, J ∈ { lwnsimgR, lwnsimgG, lwnsimgB }, is as follows:
dividing the image J into a plurality of sub-images with the same area;
carrying out edge detection on the image J to obtain a set of edge pixel points
；
Will comprise
In the collection of subimages of the pixels
；
Using image segmentation algorithm to respectively pair
Each subimage in the image segmentation processing unit is used for carrying out image segmentation processing to obtain a set of foreground pixel points
；
Will be at
The pixel points in the area are connected into pixel points in the area and
and taking the image formed by the pixel points in the image J as an image obtained by performing image segmentation processing on the image J.
When the image is divided, the sub-images are firstly acquired, then the sub-images which need to be divided are divided, and finally the final overall division result is acquired based on the division results of the plurality of sub-images. Compared with the existing image segmentation algorithm, the method has the advantage that the number of pixel bands required to be subjected to image segmentation is greatly reduced, so that the efficiency of image segmentation processing is effectively improved. For the sub-images not containing the edge pixel points, the sub-images may belong to a background part or a foreground part, therefore, the sub-images are not subjected to image segmentation, and the image segmentation of the pixel points can obtain an error segmentation result, namely, the pixel points which are originally the background part are forcibly divided into parts to be used as the pixel points of the foreground part, or the pixel points which are originally the foreground part are forcibly divided into parts to be used as the pixel points of the background part. In addition, since the sub-image has a much smaller area than the entire image, a partial region of the entire image is divided at the time of image division, and there is no need to consider other parts, so that the result of division is more accurate.
In obtaining a collection
Then, since the image J also has the foreground pixel points, the invention firstly gathers the pixels
The pixel points in the image segmentation method are used as partial foreground to form a region with a hollow middle, and all the pixel points in the region are used as foreground pixel points.
Preferably, the edge detection is performed on the image J to obtain a set of edge pixel points
The method comprises the following steps:
carrying out edge detection on the image J by using a Marr-Hildreth algorithm to obtain a set of edge pixel points
。
Preferably, the S5 includes:
respectively calculating the self-adaptive fusion weights of sgtimgR, sgtimgG and sgtimgB
；
Respectively storing the pixel points in the sgtimgR, sgtimgG and sgtimgB into the sets sgtimgU, sgtimgGU and sgtimgBU,
acquiring intersection uniU of sgtmsgRU, sgtmsgU and sgtmsgBU;
for a pixel point appix in the uniU, a pixel value trgimg (appix) of the appix in the image trgimg is obtained by using the following formula:
in the formula (I), the compound is shown in the specification,
respectively, the pixel values of appix in sgimgr, sgimgg, sgimgb.
Preferably, the S6 includes:
when the image fusion is carried out, the self-adaptive fusion weight is adopted, so that compared with the conventional fusion mode set as a fixed weight, the pixel distribution histogram of the fusion result of the invention is closer to the original pixel distribution histogram, and the fusion is more accurate.
Preferably, the adaptive fusion weight is calculated by using the following formula:
in the formula (I), the compound is shown in the specification,
the distribution represents an average value of pixel values of pixel points in the images sgtimgR, sgtimgG, sgtimgB.
When the self-adaptive weight is calculated, starting from the pixel value mean value of the pixel points of the three images, the larger the mean value is, the higher the importance degree of the component in the original pixel value is, and therefore, the accuracy of the image fusion result can be effectively improved.
And performing feature extraction on the trgimg by using a SUFR algorithm to obtain feature information.
Preferably, the S7 includes:
matching the feature information acquired from the image trgimg with the feature information corresponding to the preset defect type, and if the matching is successful, indicating that the pin of the power supply chip does not pass the quality detection; and if the matching fails, indicating that the pin of the power supply chip passes the quality detection.
Specifically, the defect types of the pins include that the number of the pins does not meet the set number requirement, the length of the pins does not meet the set length requirement, and the like, and the bending degree of the pins is too large.
On the other hand, as shown in fig. 2, the invention provides a power chip quality detection system, which includes a shooting module, a component image obtaining module, a noise reduction module, an image segmentation module, an image fusion module, a feature extraction module and a quality detection module;
the shooting module is used for acquiring an appearance image of a pin of the power supply chip;
the component image acquisition module is used for acquiring an image imgR of a red component, an image imgG of a green component and an image imgB of a blue component of the appearance image in an RGB color space;
the noise reduction module is used for respectively carrying out noise reduction processing on imgR, imgG and imgB to obtain images lwnsimgR, lwnsimgG and lwnsimgB;
the image segmentation module is used for respectively carrying out image segmentation processing on the lwnsimgR, the lwnsimgG and the lwnsimgB to obtain images sggimgR, sggimgG and sggimgB;
the image fusion module is used for carrying out image fusion processing on the sgtimgR, the sgtimgG and the sgtimgB to obtain an image trgimg;
the characteristic extraction module is used for extracting characteristics of the trgimg to obtain characteristic information;
the quality detection module is used for judging whether the pins of the power supply chip pass quality detection or not based on the characteristic information.
In the description herein, references to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example" or "some examples" or the like 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 present application. In this specification, schematic representations of the above terms 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. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more program modules for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes additional implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
Although embodiments of the present application have been shown and described above, it is to be understood that the above embodiments are exemplary and not to be construed as limiting the present application, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A power supply chip quality detection method is characterized by comprising the following steps:
s1, obtaining an appearance image of a pin of a power supply chip;
s2, acquiring an image imgR of a red component, an image imgG of a green component and an image imgB of a blue component of the appearance image in an RGB color space;
s3, respectively carrying out noise reduction treatment on the imgR, the imgG and the imgB to obtain images lwnsimgR, lwnsimgG and lwnsimgB;
s4, respectively carrying out image segmentation processing on the lwnsimgR, the lwnsimgG and the lwnsimgB to obtain images sgtimgR, sgtimgG and sgtimgB;
s5, carrying out image fusion processing on the sgtimgR, the sgtimgG and the sgtimgB to obtain an image trgimg;
s6, performing feature extraction on the trgimg to obtain feature information;
and S7, judging whether the pin of the power supply chip passes the quality detection or not based on the characteristic information.
2. The method for detecting the quality of the power supply chip as claimed in claim 1, wherein the step S1 comprises:
an industrial camera is used to acquire an appearance image of the pins of the power supply chip.
3. The method for detecting the quality of the power supply chip as claimed in claim 2, wherein the step S3 comprises:
for image I, I ∈ { imgR, imgG, imgB }, the noise reduction mode is as follows:
respectively carrying out noise reduction processing on each pixel point in the image I by using a median filtering algorithm to obtain an image midI;
acquiring a set U of pixels to be processed in the image midI according to a set acquisition algorithm;
and respectively carrying out noise reduction treatment on each pixel point in the set U by using an improved bilateral filtering algorithm to obtain a noise-reduced image lwnsI.
4. The method for detecting the quality of the power supply chip according to claim 3, wherein the obtaining the set U of the pixels to be processed in the image midI according to the set obtaining algorithm includes:
the pixel value of the pixel point pix in the image I is recorded as
Recording the pixel value of the pixel pix in the image midI
；
The coefficient of variation of the prime point pix is calculated using the following formula:
in the formula (I), the compound is shown in the specification,
the coefficient of variation is represented by a coefficient of variation,
representing a preset pixel value change standard value;
judgment of
And if the pixel point pix is larger than the set change coefficient threshold, storing the pixel point pix as the pixel point to be processed into the set U.
5. The method for detecting the quality of the power supply chip as claimed in claim 1, wherein the step S4 comprises:
the image segmentation process for image J, J ∈ { lwnsimgR, lwnsimgG, lwnsimgB }, is as follows:
dividing the image J into a plurality of sub-images with the same area;
performing edge detection on the image J to obtain a set of edge pixel points
；
Will comprise
In the collection of subimages of the pixels
；
Using image segmentation algorithm to respectively pair
Each subimage in the image segmentation processing unit is used for carrying out image segmentation processing to obtain a set of foreground pixel points
；
Will be at
The pixel points in the area are connected into pixel points in the area and
and taking the image formed by the pixel points as an image obtained by performing image segmentation on the image J.
6. The method according to claim 5, wherein the image J is subjected to edge detection to obtain a set of edge pixels
The method comprises the following steps:
carrying out edge detection on the image J by using a Marr-Hildreth algorithm to obtain a set of edge pixel points
。
7. The method for detecting the quality of the power supply chip as claimed in claim 1, wherein the step S5 comprises:
respectively calculating the self-adaptive fusion weights of sgtimgR, sgtimgG and sgtimgB
；
Respectively storing the pixel points in the sgtimgR, sgtimgG and sgtimgB into the sets sgtimgU, sgtimgGU and sgtimgBU,
acquiring intersection uniU of sgtmmgU, sgtmmgGU and sgtmmgBU;
for a pixel point appix in the uniU, a pixel value trgimg (appix) of the appix in the image trgimg is obtained by using the following formula:
in the formula (I), the compound is shown in the specification,
respectively, the pixel values of appix in sgimgr, sgimgg, sgimgb.
8. The method for detecting the quality of the power supply chip as claimed in claim 1, wherein the step S6 comprises:
and performing feature extraction on the trgimg by using a SUFR algorithm to obtain feature information.
9. The method for detecting the quality of the power supply chip as claimed in claim 1, wherein the step S7 comprises:
matching the feature information acquired from the image trgimg with the feature information corresponding to the preset defect type, and if the matching is successful, indicating that the pin of the power supply chip does not pass the quality detection; and if the matching fails, indicating that the pin of the power supply chip passes the quality detection.
10. A power chip quality detection system is characterized by comprising a shooting module, a component image acquisition module, a noise reduction module, an image segmentation module, an image fusion module, a feature extraction module and a quality detection module;
the shooting module is used for acquiring an appearance image of a pin of the power supply chip;
the component image acquisition module is used for acquiring an image imgR of a red component, an image imgG of a green component and an image imgB of a blue component of the appearance image in an RGB color space;
the noise reduction module is used for respectively carrying out noise reduction processing on the imgR, the imgG and the imgB to obtain images lwnsimgR, lwnsimgG and lwnsimgB;
the image segmentation module is used for respectively carrying out image segmentation processing on the lwnsimgR, the lwnsimgG and the lwnsimgB to obtain images sggimgR, sggimgG and sggimgB;
the image fusion module is used for carrying out image fusion processing on the sgtimgR, the sgtimgG and the sgtimgB to obtain an image trgimg;
the characteristic extraction module is used for extracting characteristics of the trgimg to obtain characteristic information;
the quality detection module is used for judging whether the pins of the power supply chip pass quality detection or not based on the characteristic information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211051583.1A CN115359022A (en) | 2022-08-31 | 2022-08-31 | Power chip quality detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211051583.1A CN115359022A (en) | 2022-08-31 | 2022-08-31 | Power chip quality detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115359022A true CN115359022A (en) | 2022-11-18 |
Family
ID=84003867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211051583.1A Pending CN115359022A (en) | 2022-08-31 | 2022-08-31 | Power chip quality detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115359022A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117038494A (en) * | 2023-10-10 | 2023-11-10 | 天津芯成半导体有限公司 | Auxiliary intelligent detection system for chip processing industry |
-
2022
- 2022-08-31 CN CN202211051583.1A patent/CN115359022A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117038494A (en) * | 2023-10-10 | 2023-11-10 | 天津芯成半导体有限公司 | Auxiliary intelligent detection system for chip processing industry |
| CN117038494B (en) * | 2023-10-10 | 2023-12-15 | 天津芯成半导体有限公司 | Auxiliary intelligent detection system for chip processing industry |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8363123B2 (en) | Image pickup apparatus, color noise reduction method, and color noise reduction program | |
| US7903870B1 (en) | Digital camera and method | |
| CN110930301B (en) | Image processing method, device, storage medium and electronic equipment | |
| US8310566B2 (en) | Image pickup system and image processing method with an edge extraction section | |
| US8660350B2 (en) | Image segmentation devices and methods based on sequential frame image of static scene | |
| CN108665417B (en) | License plate image deblurring method, device and system | |
| CN112418087B (en) | Underwater video fish identification method based on neural network | |
| CN111784605A (en) | Image denoising method based on region guidance, computer device and computer readable storage medium | |
| CN113255706B (en) | Target identification method and system based on convolutional neural network algorithm | |
| CN107784660A (en) | Image processing method, image processing system and defect detecting device | |
| CN115359022A (en) | Power chip quality detection method and system | |
| CN115937186A (en) | Textile defect identification method and system | |
| CN107644437B (en) | Color cast detection system and method based on blocks | |
| CN117078678B (en) | Waste silicon wafer shape detection method based on image recognition | |
| US7542166B2 (en) | Method for automatically extracting image effect color and recovering original image color | |
| JP4331120B2 (en) | Defective pixel detection method | |
| CN115008255B (en) | Tool wear identification method and device for machine tool | |
| CN111611940A (en) | Rapid video face recognition method based on big data processing | |
| JP3480408B2 (en) | Object extraction system and method, and storage medium storing object extraction program | |
| JP4831941B2 (en) | Imaging processing system, program, and storage medium | |
| KR101175737B1 (en) | Defect pixel processing method and device | |
| CN114170153A (en) | Wafer defect detection method and device, electronic equipment and storage medium | |
| CN114554188A (en) | Mobile phone camera detection method and device based on image sensor pixel array | |
| CN116883370B (en) | Agricultural product appearance quality detecting system | |
| CN110782438B (en) | Image detection method based on maximum inter-class variance method of FPGA (field programmable Gate array) |
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 |