TWM621960U - Machine vision image storage and presentation system - Google Patents

Abstract

The present invention provides a storage and representation system for machine vision images, which is used to provide a user to detect an object to be tested, comprising: an image capture unit for capturing an image of the object to be tested of the object to be tested; a processing unit for connecting The image capturing unit is used for detecting the region of interest and the region of non-interest in the image of the object to be tested, and capturing the region of interest image of the region of interest; and a storage unit, connected to the processing unit, for to store the image of the region of interest; and an observation unit connected to the processing unit for viewing the region of interest of the object to be tested; wherein, when the user observes the object to be tested through the observation unit, the processing The unit displays the non-interested area on the observation unit in black, and displays the ROI image on the observation unit.

Description

Machine Vision Image Storage and Representation System

This creation is related to the technical field of artificial intelligence, especially a storage and representation system for machine vision images that separately stores images of regions of interest.

Machine vision detection technology is based on image processing algorithms, and is realized by digital image processing and pattern recognition. Compared with traditional manual detection technology, it improves the efficiency and accuracy of defect detection. Machine vision can cover all industrial and non-industrial applications, combining hardware and software to operatively guide devices to perform image capture and processing functions. Machine vision systems rely on digital sensors protected within industrial cameras, using specialized optics configurations to capture images for computer hardware and software to process, analyze, and measure a variety of different characteristics to make decisions. In industrial applications such as printed circuit board assembly applications, during the assembly process, it is necessary to check whether the component number, size and component position of the printed circuit board are correct. Poor solder paste printing or incorrect component placement can affect the performance and service life of the printed circuit board. PCB defect detection includes two parts: solder joint defect detection and component detection. The traditional detection method adopts manual detection method, which is easy to miss detection, slow detection speed, long detection time and high cost, and has gradually been unable to meet production needs. Therefore, it is of great practical significance to design an efficient and accurate machine vision PCB inspection system equipped with industrial cameras to replace human eyes.

To help printed circuit board manufacturers find defects in the early stages of production process implementation, more and more printed circuit board manufacturers are incorporating in-line machine vision technology in the printing units they manufacture. The operator can assist the machine in time to find defects and return to the production line for repairs in time.

In the technical field of artificial intelligence, in machine vision and image processing, the area to be processed is outlined from the processed image in the form of boxes, circles, ellipses, irregular polygons, etc., which is called the region of interest. interested, ROI). In the field of image processing, a region of interest is an image region selected from an image that is the focus of your image analysis. With the assistance of the machine, the operator can quickly find the area of interest in the printed circuit board, and assist in observing the defect image in the area of interest. Circle the area for further processing. Using regions of interest to delineate what you want to read can reduce processing time and increase accuracy. For the representation of the region of interest, there are traditionally two types:

(1) Frame the position of the region of interest directly on the original image: As shown in FIG. 1 , FIG. 1 is a schematic diagram of the image 100 of the object to be measured. The image 100 of the object to be tested is captured by the machine, and the image 102 of the region of interest and the image 104 of the non-interested region that do not include the region of interest are assisted in finding. The system stores the image of the region of interest 102 and the image of the non-interested region 104 other than the region of interest 102 at the same time, so it occupies the largest storage space of the system.

(2) As shown in Figure 2, Figure 2 is another schematic diagram. The object image 200 includes: a region of interest image 202 , an image of the non-region of interest 204 and a black background image 206 . The machine captures the ROI image 202 , and then pastes the ROI image 202 on a black background image 206 of the same size as the object image 200 . Although the storage space of the method (2) is smaller than that of the method (1), the method (2) also needs a storage space for storing the pixel data of the black background image. The two traditional representation methods cannot significantly reduce the storage space of the system.

In view of this, this creative department provides a storage and representation system for machine vision images to solve the lack of the prior art.

The first objective of this creation is to provide a method for storing and representing machine vision images, which includes: capturing an object image of the object to be measured; detecting the region of interest and non-interesting region of the object image; capturing Take a region of interest image of the region of interest; display the region of interest image, and display the non-interest region in black.

The second purpose of the present creation is based on the above-mentioned method for storing and representing machine vision images, wherein, in the steps of displaying the region of interest image and displaying the non-interest region in black, the steps include: storing the region of interest image; reading Take the region of interest image and display the region of interest image; and display the non-interest region in black.

The third object of this creation is based on the above-mentioned method for storing and representing machine vision images, wherein, in the steps of displaying the region of interest image and displaying the non-interest region in black, the steps include: storing the region of interest image; storing the region of interest image; The region of interest is displayed in black; and, the region of interest image is read, and the region of interest image is displayed.

The fourth object of the present invention is based on the above-mentioned method for storing and representing a machine vision image, wherein the image of the object to be tested includes information in an exchangeable image file format.

The fifth object of the present invention is based on the above-mentioned method for storing and representing machine vision images, wherein the exchangeable image file format information includes image information and manufacturer's comments.

The sixth object of the present creation is based on the above-mentioned method for storing and representing machine vision images, wherein the manufacturer's annotation includes image size information and image coordinate information.

In order to achieve the above-mentioned purpose or other purposes, the present invention provides a storage and representation system of machine vision images for providing a user to detect the object to be measured, including: an image capture unit for capturing the object to be measured. an object image; a processing unit, connected to the image capture unit, for detecting a region of interest and a region of non-interest in the image of the object to be measured, and capturing a region of interest image of the region of interest; and, storing a unit, connected to the processing unit, for storing the region of interest image; and, an observation unit, connected to the processing unit, for viewing the region of interest of the object to be tested; wherein, the user observes through the observation unit When the object is detected, the processing unit displays the non-interested area on the observation unit in black, and displays the ROI image on the observation unit.

The second object of this aspect of the present invention is based on the above-mentioned storage and representation system for machine vision images, wherein the object image contains information in an exchangeable image file format.

The third object of this aspect of the present invention is based on the above-mentioned storage and presentation system for machine vision images, wherein the exchangeable image file format information includes image information and manufacturer's comments.

The fourth object of this aspect of the present invention is based on the above-mentioned storage and representation system for machine vision images, wherein the manufacturer's annotation includes image size information and image coordinate information.

A fifth object of this aspect of the present invention is based on the above-mentioned storage and representation system for machine vision images, wherein the image information includes shooting information, and the shooting information includes an aperture value and a shutter value.

Compared with the conventional technology, this creation provides a storage and representation system for machine vision images. With the new concept of this creation, it can have the following advantages: it can mainly avoid many problems in the selection of training data for training in the conventional technology, For example, the model jitter in the training process is not conducive to the robustness of the model, unbalanced data, insufficient data, overfitting, etc.

In order to fully understand the purpose, features and effects of this creation, hereby use the following specific embodiments and cooperate with the attached drawings to give a detailed description of this creation, and the description is as follows:

In this work, the use of "a" or "an" is used to describe the elements, elements and components described herein. This is only for the convenience of explanation and to provide a general meaning to the scope of this creation. Thus, unless it is clear that it is meant otherwise, such descriptions should be read to include one, at least one, and the singular also includes the plural.

As used herein, the terms "comprising," "including," "having," "containing," or any other similar term are intended to encompass non-exclusive inclusions. For example, an element, structure, article or device containing a plurality of elements is not limited to those elements listed herein, but may include not explicitly listed but generally inherent to the element, structure, article or device other requirements. Otherwise, unless expressly stated to the contrary, the term "or" refers to an inclusive "or" and not an exclusive "or".

Please refer to FIG. 3 , FIG. 4A and FIG. 4B , wherein FIG. 3 is a flowchart of a method for storing and representing a machine vision image according to an embodiment of the creation. FIG. 4A is a schematic diagram of creating an object to be tested. FIG. 4B is a schematic diagram of creating an image of the object to be tested.

As shown in FIG. 4A , it is shown that the object to be tested O includes: a region of interest R ₁ , and a region of non-interest R ₂ .

As shown in FIG. 4B , the image V _{o of} the object to be tested includes an image of the region of interest _VR1 and an image of the non-region of interest _VR2 .

In an embodiment of the present invention, the method for storing and representing the region of interest image Vo includes: steps S31 to S38, as shown in FIG. 3 .

In step S31 , the object image V _{o of} the object O is captured. As shown in Figure 4A and Figure 4B. The object to be tested in this embodiment takes a wafer as an example, and a circuit is fabricated on the wafer. It should be noted that _{the storage and representation method of the region of interest image VR1} in this creation can be applied to various objects to be tested, and is not limited to the wafer in this embodiment, and the objects to be tested can also be printed circuit boards, three-dimensional The mechanical structure and circuit layout diagram.

Step S32 , detecting the region of interest R ₁ and the region of non-interest R _{2 in the image V o} of the object to be tested. The object image V _o includes exchangeable image file format information (Exif). The exchangeable image file format information is a file format specially set for the photos of the digital camera, which can record the attribute information and shooting data of the digital photos. The exchangeable image file format information is added to JPEG, TIFF, RIFF and other files to add content related to digital camera shooting information and index map or image processing software version information. The exchangeable image file format information includes, for example, image information, manufacturer's notes, exposure time, aperture value, and image resolution. It should be noted that the manufacturer's note includes image size information and image coordinate information.

According to the captured object image V _o and artificial intelligence technology, the edge of the defective region on the object O is detected, and the defective region is marked to become at least one region of interest R ₁ . Relative to the region of interest R _{1 of} the object to be tested O, other regions are defined as regions of non-interest R ₂ . It should be noted that, assuming that the yield rate is higher than the normal standard, that is, the number of defects is relatively small, the area of interest R ₁ is usually much smaller than the non-interest area R _{2 .} The number of regions of interest R _{1 in} this creation is at least one, and this embodiment is only described with one region of interest, and the scope of this creation is not limited to one region of interest in this embodiment.

Step S33, because we have more interest in the region of interest R ₁ that is defective area. Thus, capturing the region of interest of the _region of interest R image V _R1.

Step S34, the image storage region of interest V _R1.

Step S35, the image reading region of interest V _R1, the image display region of interest V _R1. .

In step S36 , the non-interesting region R ₂ is displayed in black to become a non-interesting region image _VR2 . Finally, the region- _{of-interest image VR1} and the black region-of-interest image _VR2 can be displayed simultaneously.

In another embodiment, after step S34, step S37 can also be executed in the present creation to display the non-interesting area in black. And a step S38, the image reading region of interest image region of interest V _R1, and displays. In the end, it is the same as displaying the region of interest image _VR1 and the black non-interesting region image _VR2 , as shown in FIG. 4B .

Because, what we need is that with the method of the present invention, only the image of the defect region (ie, the region of interest R ₁ ) needs to be displayed, instead of the region of interest R ₂ , and it is displayed in black if it is not needed. By displaying the result, the image of the defect region (ie, the region of interest R ₁ ) can be highlighted, and the image of the defect region can be viewed more conveniently.

In the present embodiment, since only one region of interest storage of _an image region of interest R V _R1. The area of interest R ₁ is much smaller than the object O to be tested. Therefore, compared to storing the object image V _{o of the entire object O to be tested, the file size of storing the image V o} of the object to be tested is greatly reduced compared to storing the image V _{R1 of the region of interest.} The storage and representation method of the region-of-interest image _VR1 of the present creation can reduce the storage space and the calculation amount of image processing.

FIG. 5 is a block diagram of a storage and presentation system of a region of interest image according to an embodiment of the invention. Referring to FIG. 5 , the system 500 for storing and representing region of interest images includes an image capturing unit 510 , a processing unit 520 , an observation unit 530 and a storage unit 540 . The user detects defects in the object O with the assistance of the storage and representation system 500 of the region of interest image.

As shown in Figure 4A and Figure 4B. The object to be tested in this embodiment takes a wafer as an example, and a circuit is fabricated on the wafer. It should be noted that the storage and representation method of the region of interest image Vo in this creation can be applied to various objects to be tested, and is not limited to the wafer in this embodiment. The object to be tested can also be a printed circuit board, a three-dimensional Mechanical structure, circuit layout diagram.

The image capturing unit 510 is used for capturing the object image Vo of the object O to be tested. The object image Vo includes exchangeable image file format information (Exif). The exchangeable image file format information is a file format specially set for the photos of the digital camera, which can record the attribute information and shooting data of the digital photos. The exchangeable image file format information is added to JPEG, TIFF, RIFF and other files to add content related to digital camera shooting information and index map or image processing software version information. Exchangeable image file format information includes, for example, image information, manufacturer's commented exposure time, aperture value, and image resolution. It should be noted that the manufacturer's note includes image size information and image coordinate information.

The image capturing unit 510 of the present invention captures the object image Vo of the object O to be measured. The processing unit 520 is connected to the image capturing unit 510 . Processing unit 520 to detect the analyte of interest in the image region Vo and the non-interest region R ₁ R _2, and capturing the region of interest of the _region of interest R image V _R1. Because, we are more interested in the region of interest R ₁ , that is, the defect region. Thus, the processing unit 520 to detect the analyte of interest in the image region Vo R _1, R capture the region of interest of the _region of interest image V _R1. The region of interest image _{VR1 is} stored in the storage unit 540 . The processing unit 520 reads the ROI image _VR1 and displays the ROI image _VR1 in the observation unit 530 . The processing unit 520 displays the non-interesting region R ₂ in black to become a non-interesting region image _VR2 . Finally, the observation unit 530 by the user to simultaneously see image display region of interest V _R1, and black non-image region of interest V _R2, shown in Figure 4B.

When observed by a user observing the analyte O unit 530, the processing unit 520 of unconcern displayed in black region R ₂ in the observation unit 530, and the region of interest V _R1 image displayed on the observation unit 530, i.e., the final At the same time, an image showing the region of interest image _VR1 in a black background is displayed, as shown in FIG. 4B . With the aid of the observation unit 530, the user can easily find the defective area (ie the area of interest R ₁ ) in the object to be tested O, and reduce the storage space, and additionally process the data calculation processing of the image of the non-interest area .

In another embodiment, the present invention can also capture the object image Vo of the object O by the image capturing unit 510 . The processing unit 520 is connected to the image capturing unit 510 . Processing unit 520 to detect the analyte of interest in the image region Vo and the non-interest region R ₁ R _2, and capturing the region of interest of the _region of interest R image V _R1. Because, we are more interested in the region of interest R ₁ , that is, the defect region. Thus, the processing unit 520 to detect the analyte of interest in the image region Vo R _1, R capture the region of interest of the _region of interest image V _R1. The region of interest image _{VR1 is} stored in the storage unit 540 . The processing unit 520 reads the ROI image _VR1 and displays the ROI image _VR1 in the observation unit 530 . The processing unit 520 displays the non-interesting region R ₂ in black to become a black non-interesting region image _VR2 . The non-interesting region image _{VR2 is} stored in the storage unit 540 . The processing unit 520 reads the storage unit 540 in the image region of interest V _R1, and a non-image region of interest V _R2, and displays the image region of interest. Finally, it can be the same as displaying the region of interest image _VR1 and the black non-interesting region image _VR2 , as shown in FIG. 4B .

The present creation has been disclosed above with preferred embodiments, but those skilled in the art should understand that the embodiments are only used to describe the present creation, and should not be construed as limiting the scope of the present creation. It should be noted that all changes and substitutions equivalent to this embodiment should be set to be included in the scope of the present creation. Therefore, the scope of protection of this creation shall be determined by the scope of the patent application.

S31, S32, S33, S34, S35, S36, S37, S38: step 100: object image 102: region of interest 104: non-interest region image 200: object image 202: region of interest image 204: non- ROI image 206: black background image 500: machine vision image storage and presentation system 510: image capture unit 520: processing unit 530: observation unit 540: storage unit O: object to be measured V _o : object image V to be measured _R1 : area of interest image V _R2 : non-interest area image R ₁ : area of interest R ₂ : area of non-interest

FIG. 1 is a schematic diagram of the image of the object to be tested; FIG. 2 is a schematic diagram of another image of the object to be tested; 3 is a flowchart of a method for storing and representing machine vision images according to an embodiment of the creation; 4A is a schematic diagram of the object to be tested for the creation; FIG. 4B is a schematic diagram of creating an image of the object to be tested; FIG. 5 is a block diagram of a system for storing and displaying machine vision images according to an embodiment of the invention.

500: Storage and Representation Systems for Machine Vision Images

510: Image capture unit

520: Processing Unit

530: Observation Unit

540: Storage Unit

O: analyte

R ₁ : Region of Interest

R ₂ : Region of no interest

Claims (4)

A storage and representation system for machine vision images, used to provide a user to detect an object to be measured, comprising: an image capture unit for capturing an image of the object to be measured of the object to be measured; a processing unit, connected to the image capture a unit for detecting a region of interest and a region of non-interest in the image of the object to be tested, and capturing a region of interest image of the region of interest; and a storage unit, connected to the processing unit, for storing the sense a region of interest image; and an observation unit connected to the processing unit for viewing the region of interest of the object to be tested; wherein, when the user observes the object to be tested through the observation unit, the processing unit will The region is displayed on the observation unit in black, and the ROI image is displayed on the observation unit. The storage and presentation system of a machine vision image as claimed in claim 1, wherein the image of the object to be tested includes information in an exchangeable image file format. The machine vision image storage and presentation system of claim 2, wherein the exchangeable image file format information includes image information and manufacturer's comments. The storage and representation system of machine vision images as claimed in claim 3, wherein the manufacturer's annotation includes image size information and image coordinate information.

Images