TWI722017B - Method and inspection system for inspecting an object, and non-transitory computer readable medium - Google Patents

Abstract

A method for inspecting an object, wherein the method may include acquiring an image of an object; wherein the object comprises a base layer that is not conductive, first conductors of a first conductive layer and second conductors of a second conductive layer, wherein the first conductors are positioned between the base layer and the second conductors, wherein the first conductors contact the second conductors; calculating a first registration transform; calculating a second registration transform; detecting first conductors defects based on the image and the second registration transformation; and detecting second conductors defects based on the image and the second registration transformation.

Description

Method and inspection system for inspecting objects, and non-transitory computer readable media

The present invention relates to an automated optical inspection technology including misaligned IBUMP and through hole process defects under the trace.

In the process of minimizing PCB layout, PCB manufacturers have developed a production process that allows denser copper signal layout.

iBump refers to an additional copper signal layer that resides directly on top of another copper layer; via under trace (VUT) refers to a via between layers, which is contrary to a typical laser via, which does not need to be drilled through The connected signal layers or gaps among them usually have approximately the same size as the connection pads above it.

These technologies pose challenges for production and automatic inspection. In production, strict tolerances for alignment between process layers are critical. In the inspection, the alignment and differentiation between the independent shifted signal and the iBump layer in the inspection image are not supported by current AOI solutions. VUT shift estimation is challenging because the via is partially hidden under the signal layer.

A method for inspecting an object, wherein the method may include acquiring an image of an object; wherein the object may include a non-conductive base layer, a first conductor of a first conductive layer, and a first conductor of a second conductive layer Two conductors, where the first conductors can be placed between the base layer and the second conductors, where the first conductors contact the second conductors Body; calculate a first alignment transformation which represents a first spatial relationship between (a) the imaged shape and position of the first conductors and (b) the designed shape and position of the first conductors Calculate a second alignment transformation which represents a second spatial relationship between (a) the imaged shapes and positions of the second conductors and (b) the designed shapes and positions of the second conductors; The first conductor defect is detected based on the image and the second alignment transformation; and the second conductor defect is detected based on the image and the second alignment transformation.

The detection of the first conductor defects can be performed separately from the detection of the second conductor defects.

The object can be a printed circuit board and the second conductors can be iBumps.

The object can be a printed circuit board and the first conductors can be under-trace vias.

The detection of the first conductor defects may include finding a portion of a via under a given trace that extends over a given second conductor that may be positioned above the via under the given trace, and Calculate an offset between the via hole and the second conductor under the given test.

The method may include calculating a center of the through hole under the given trace and a center of the given second conductor.

The calculation of the first alignment transformation may include masking the object part according to the designed shapes and positions of the second conductors.

The calculation of the second alignment transformation may include masking the object part according to the designed shapes and positions of the first conductors.

The method may include performing multiple iterations of the steps of calculating the first alignment transformation and calculating the second alignment transformation; wherein each iteration produces a repeated result that can be fed to a subsequent iteration.

The method may include multiple repetitions of the steps of calculating the first alignment transformation and calculating the second alignment transformation; wherein each repetition may be based on the second derivative The designed shapes and positions of the body are used to mask the object part to calculate the first alignment transformation; wherein each repetition produces a repetitive result that can be fed to a subsequent repetition.

The method may include multiple iterations of the steps of calculating the first alignment transformation and calculating the second alignment transformation; wherein each iteration may be masked according to the designed shapes and positions of the first conductors Part of the object to calculate the second alignment transformation; where each repetition produces a repetitive result that can be fed to a subsequent repetition.

An inspection system for inspecting an object, wherein the inspection system may include an image capturing module for acquiring an image of an object; wherein the object may include a base layer that may be non-conductive, and a first conductive Layer of the first conductor and a second conductor of the second conductive layer, wherein the first conductors can be placed between the base layer and the second conductors, wherein the first conductors contact the second conductors Conductor; a first alignment processor is used to calculate a first alignment transformation which is expressed in (a) the imaged shape and position of the first conductors and (b) the designed shape and position of the first conductors A first spatial relationship between; a second alignment processor is used to calculate a second alignment transformation which is expressed in (a) the imaged shapes and positions of the second conductors and (b) the second conductors A second spatial relationship between the designed shape and position; and an inspection processor for detecting the first conductor defect based on the image and the second alignment transformation, and for detecting the first conductor defect based on the image and the second alignment transformation Detect defects in the second conductor.

In the inspection system, the inspection processor can be configured to detect the first conductor defects separately from the detection of the second conductor defects.

The object can be a printed circuit board and the second conductors can be iBumps.

The object can be a printed circuit board and the first conductors can be under-trace vias.

The inspection processor can be configured to detect the first conductor defects by looking for a part of the via under a given trace, which extends over the via that may be positioned under the given trace Outside of a given second conductor, and calculate the through hole under the given test An offset from the second conductor.

The inspection processor can be configured to calculate a center of the through hole under the given trace and a center of the given second conductor.

The first alignment processor can be configured to mask the object part according to the designed shapes and positions of the second conductors to calculate the first alignment transformation.

The second alignment processor may be configured to calculate the second alignment transformation may include masking the object part according to the designed shapes and positions of the first conductors.

The inspection system can be configured to perform multiple repetitions of the steps of calculating the first alignment transformation and calculating the second alignment transformation; wherein each repetition produces a repetitive result that can be fed to a subsequent repetition.

The inspection system can be configured to perform multiple repetitions of the steps of calculating the first alignment transformation and calculating the second alignment transformation; wherein each repetition can be based on the designed shapes and the second conductors The position is used to mask the object part to calculate the first alignment transformation; where each iteration produces a iteration result that can be fed to a subsequent iteration.

The inspection system can be configured to perform multiple repetitions of the steps of calculating the first alignment transformation and calculating the second alignment transformation; wherein each repetition can be based on the designed shapes and the first conductors The position is used to mask the object part to calculate the second alignment transformation; where each repetition produces a repetitive result that can be fed to a subsequent repetition.

A non-transitory computer-readable medium that stores instructions. Once executed by an inspection system, it will cause the inspection system to perform the following steps: acquiring an image of an object; wherein the object may include It is a non-conductive base layer, a first conductor of a first conductive layer and a second conductor of a second conductive layer, wherein the first conductors can be placed between the base layer and the second conductors , Where the first conductors contact the second conductors; calculate a first alignment transformation which is expressed in (a) the imaged shape and position of the first conductors and (b) the design of the first conductors Between the shape and position A first spatial relationship of; calculating a second alignment transformation which represents the difference between (a) the imaged shape and position of the second conductors and (b) the designed shape and position of the second conductors A second spatial relationship; detecting a first conductor defect based on the image and the second alignment transformation, and detecting a second conductor defect based on the image and the second alignment transformation.

100: workbench

101: Items to be inspected

103: control and processing module

104: Storage

105: User Interface

106: Network interface, remote network, network

107: Processing Subsystem

200: Inspection image provider

102: Optical, lighting, and camera components; camera

201: Reference Material Provider

202: signal alignment processor

203a: iBump alignment processor

203b: VUT shift estimator

204: Inspection processor

205: Inspection result processor

300: method

301-320: steps

From the following detailed description in conjunction with the accompanying drawings, in which Figures 1-4 show an embodiment of the system and method according to the present invention, the present invention will be more fully understood and experienced.

Because in most cases, the device implementing the present invention is composed of electronic components and circuits known to those skilled in the art, in order to understand and appreciate the potential concepts of the present invention and in order not to obscure or deviate. The teachings and circuit details of the present invention will not be explained to any greater extent than necessary as shown above.

In the following description, the present invention will be described with reference to specific examples of embodiments of the present invention. However, it is clear that various modifications and changes can be made without breaking away It is away from the broader spirit and scope of the present invention as set forth in the scope of the appended invention application.

Any reference to a method in this manual shall apply mutatis mutandis to a system capable of executing the method, and shall be mutatis mutandis to a non-transitory computer-readable medium storing instructions, once it is executed by a computer Will lead to the execution of the method.

Any reference to a system in this manual shall apply mutatis mutandis to a method that can be executed by the system, and shall be mutatis mutandis to a non-transitory computer-readable medium that stores instructions that can be used by the system To execute.

Any reference to a non-transitory computer readable medium in this manual shall apply mutatis mutandis to a system capable of executing the instructions stored in the non-transitory computer readable medium, and shall apply mutatis mutandis to A method that can be executed by a computer that can read the instructions stored in the non-transitory computer-readable medium.

The following table illustrates some of these problems that can be overcome by the proposed system.

The present invention provides a method for inspecting and reporting "via under trace" (VUT) and "iBump" production defects for generation and process control. The VUT belongs to a VUT layer and the iBump belongs to a bump layer.

This method will enable PCB manufacturers using these advanced technologies to inspect production batches and help process quality control to achieve better yields.

This method is an additional part of the currently available inspection capabilities.

The AOI system includes a workbench 100 on which the inspected item 101 is placed; optical, lighting, and camera components 102 that capture an image of the item (using these components and/or workbenches to move relative to each other ); Various control and processing modules 103 which provide communication and control with these components and workbenches, camera images and CAD and other data storage 104, user interface 105 and/or network interface 106, etc.; And, in particular, a processing sub-module composed of analyzing and inspecting images and other data, and outputting measurements, discovered defects, and other data to the user interface, network, and/or memory module System 107. A schematic diagram is shown in Figure 1. All these components can be located in a physical enclosure, or can be scattered in several cabinets or even several locations, for example, the workbench and camera device can be placed away from the processing units, and the user interface is also It can be remote, all of which interact through the Internet. Some or all of these processing and control units can be implemented by software or dedicated hardware, etc.

Referring to FIG. 2, the inspection image provider 200 provides an image of the inspected article or a part of it, which comes from the camera 102, the remote network 106, or the storage 104. The reference data provider 201 provides all data related to the operation, including CAD data, working parameters, detection specifications, and so on. The signal alignment processor 202 receives the inspection image from 200 and the signal layer CAD data from 201 and other data, and calculates the best alignment transformation (alignment) between the signal layer and the CAD coordinates in the image ).

The iBump alignment processor 203a receives inspection images from the 200 and iBump layer CAD and other data from 201, and calculates the iBump layer and the The best alignment transformation (alignment) between CAD coordinates. Optionally, it calculates the alignment of each iBump object independently. Optionally, each of 202 and 203a also receives another layer (iBump or signal, respectively) of the CAD data, and uses it to identify or mask the image parts belonging to another image to help Isolate the related image parts and estimate the independent alignment transformation for each layer. More optionally, 202 and 203a exchange their calculated transformations to further help and improve their accuracy, optionally in an iterative manner.

The inspection processor 204 receives the reference and image data from 200 and 201, and the calculated alignment results from the processors 202 and 203a.

Each of the processors mentioned in the current application can be a hardware processor such as an image processor, a general-purpose processor, a graphics processor, an ASIC, an FPGA, and the like-which are grouped together It is equipped with a program that can cause the processor to work.

The independent alignment results enable the inspection processor to accurately locate and separate the visible image parts of the signal layer and the visible image parts of the iBump. Then, it performs the respective inspections of these components independently, finds defects in both the signal and the iBump layer, uses inspection parameters and optionally according to the inspection specifications received from 201. The inspection processor also performs other measurements, including calculating the relative displacement or misalignment between the iBump object and the signal object, based on the results from the processors 202 and 203a.

The inspection result processor 205 receives all the defects, measurements, and other results from the inspection processor 204, and distributes them to other appropriate components of the AOI system, including the user interface 105, network 106, and Storage 104.

For PCBs with VUTs, a similar sub-processing system is used, with a similar structure as shown in Figure 3. The main difference from the solution discussed above for iBump is as follows: a VUT displacement estimator 203b simultaneously receives the signal and the VUT layer CAD data from 201, and separately estimates the value of each VUT object (via) Should move Bit. Here, the through holes are usually hidden under the signal layer and therefore are not visible in the image unless they are significantly shifted so as to be displayed as a protrusion on the side of a signal object. Therefore, the VUT displacement estimator 203b uses the data from the two CAD layers and compares them with the visible shape of the signal object covering the via. Then, it uses a geometric estimation module that finds the best fit between the visible protrusion and the possible dislocation of the through hole.

Local alignment: As described above, the alignment processor processes the image and finds the best alignment (transformation) for each layer. In practice, a single matrix cannot describe an appropriate transformation for the entire inspection panel, because the layers may be deformed non-uniformly or produced with multiple exposures, due to nonlinear optical distortions, etc. Therefore, the alignment processors can process smaller image blocks separately, resulting in a mapping corresponding to the transformation of each image block. Providing an overview of the transformation mapping has an additional advantage that it can easily point out global issues such as layer stretching, rotation, and displacement of the entire unit or array. The information can be fed back to the AOI operator (for better positioning of the panel) and production quality control. An image block may include, for example, 1000×1000 pixels. This is quite small, considering that a typical PCB board scanned at a moderate magnification may contain about 50000x40000 pixels.

In addition, in some manufacturing processes, individual bumps or VUT vias may be shifted differently. In this case, the bump layer alignment processor independently performs the alignment of each individual bump/VUT. The user or operator can decide when to use a zone transformation and when to use a separate transformation.

Image analysis: The image processing methods used by the alignment processor simultaneously depend on the lighting quality and the surface characteristics of the product. In some manufacturing processes, the iBump layer is usually shiny and brighter than the trace copper layer. Therefore, there is a visible edge on the boundary between the bump copper and the trace copper, so that they can be distinguished during the alignment process. In addition, an appropriate strength threshold can further distinguish the bumps from the trace copper. However, in some other manufacturing processes, these two layers have similar characteristics. degree. In this case, it may be advantageous to use a narrow angle range of illumination, so that the "walls" of the bumps will appear darker in the image, providing a visible light around the bumps Dark border.

It should be noted that under an automatic optical inspection, the user often performs specific calibrations and adjustments and other preparations to set up the system for scanning a specific type of panel. In particular, these actions include calibration or group configuration of the lighting block.

The alignment processors can use the dark contours to combine the bumps and the stitches, and calculate their transformations.

Repeated two-layer alignment: The main challenge in two-layer alignment is that they all appear together in an image, with bump objects and stitch objects appearing side by side and/or stitch objects are partially or completely hidden Below the bumpy object. This makes conventional alignment methods (such as the interactive correlation between the reference image and the test image) unsuitable. The bump objects will confuse the signal layer alignment processor, and the signal objects will confuse the bump layer alignment processor.

A possible solution is to provide two CAD layers per processor, and use another layer as a mask. In other words, the signal layer aligns the processor mask to the areas occupied by bumps (according to the CAD), ignoring the edges found there, and the same bump layer aligns the processor mask to the traces For the occupied areas (according to the CAD), the edges found there are ignored. However, the alignment transformation is initially unknown, so the mask is usually inaccurate, and the alignment results may be sub-optimal. Therefore, the process can be repeated iteratively, where in each iteration the processors recalculate the alignment transformations, using the updated transformations from the previous iteration to transform another layer of the mask when generating the mask. The CAD image. This procedure is illustrated in Figure 4.

FIG. 4 illustrates the method 300, which starts at step 301 receiving a verified image (image) and reference data including one of iBump design information and signal design information.

Step 301 is followed by a first sequence of steps 302-307 that can be executed by the signal layer alignment processor and a second sequence of steps that can be executed by the bump layer alignment processor. Sequence of steps 312-317.

Steps 302 and 312 are optional. Other steps can be optional.

The first sequence of steps starts at step 302, loading the bump layer (bump design information) as a mask-thereby ignoring the portion of the image filled by the bump (according to the bump design data).

Step 303 includes calculating a bump layer transformation (alignment) between the imaged shape and position of the signal conductors and the designed shape and position of the signal conductors. The signal conductor belongs to the signal layer-a layer that transmits signals.

Step 304 includes receiving the bump layer transformation.

Step 305 includes generating a transformed bump layer mask-adjusting the mask according to the bump layer transformation.

Step 306 includes calculating the signal layer transformation (using the transformed bump layer mask).

Step 307 is a control step of checking whether a predetermined number of iterations has been reached. If not-skip to step 304. Otherwise-skip to step 320. It is worth noting that other stopping criteria can be used. For example-the stopping criterion may be in response to the amount of correction and/or error found in an iterative process. The stopped state may indicate a convergence-more iterations will not change the result (for example, the bump mask will not be significantly changed) above a predetermined threshold.

The second sequence of steps begins at step 312, loading the signal layer (signal design information) as a mask-thereby ignoring the portion of the image filled by the signal conductor (according to the bump design data).

Step 313 includes calculating a bump layer transformation (alignment) between the imaged shape and location of the bumps and the designed shape and location of the bumps. Step 314 includes receiving the signal layer transformation.

Step 315 includes generating a transformed signal layer mask-according to the signal Change the number layer to adjust the mask.

Step 316 includes calculating the bump layer transform (using the transformed signal layer mask).

Step 317 is a control step of checking whether a predetermined number of iterations has been reached. If not-skip to step 314. Otherwise-skip to step 320. It is worth noting that other stopping criteria can be used. For example-the stopping criterion may be in response to the amount of correction and/or error found in an iterative process. The stopped state may indicate a convergence-more iterations will not change the result (for example, the bump mask will not be significantly changed) above a predetermined threshold.

Step 320 includes outputting the signal layer transformation and the bump layer transformation.

A same procedure can be applied to a VUT layer.

Defect types: The proposed system and method are suitable to be a supplement to the full inspection of PCB AOI, that is, they do not impair the full inspection capability of AOI, including finding and measuring critical and non-critical defects including open circuits, short circuits, gaps, protruding parts, Wiring and space width violations, pinholes, isolated areas, drill defects, etc. By enabling the identification and measurement of critical and non-critical defects related to the bump and/or VUT layer and their interaction with the signal layer, the proposed system and method also enhance the AOI system.

These include: ˙Measurement of the relative displacement between the two layers (and report the large displacement of the critical dimension); ˙By the space violation of the bump/VUT displacement relative to the signal layer (and report the critical dimension Violation); ˙Lack of bumps and extra bumps; ˙Bump size violation (and report the violation of critical size); ˙Bump surface defects (notches, protrusions, pinholes, oxidation on the bumps, etc.) ).

This rich inspection capability is possible due to the system's ability to perform independent alignment of each layer, allowing the inspection processor to generate accurate masks (taking into account all CAD data and the calculated Alignment transformation) which isolates the The visible parts of each layer in the image, and therefore provide independent defect analysis and report for each layer.

In addition, those skilled in the art will recognize that the boundaries between the functions of the above-mentioned operations are only illustrative. The function of multiple operations may be combined into a single operation, and/or the function of a single operation may be dispersed in additional operations. Also, alternative embodiments may include multiple instances of a specific operation, and the order of operations may be changed in various other embodiments.

Therefore, it will be understood that the architectures described herein are only exemplary, and in fact many other architectures can be implemented to achieve the same function. In an abstract but still clear sense, any arrangement of components to achieve the same function is effectively "associated" so that the desired function is realized. Therefore, in this document, any two components combined to achieve a specific function can be regarded as being "associated with" each other to enable the desired function to be realized, regardless of the structure or intermediate components. Similarly, any two components so related can also be regarded as being "operably connected" or "operably coupled" to each other to achieve the desired function.

The present invention can also be implemented in a computer program for execution on a computer system, including at least part of the program code for executing the steps of a method according to the present invention, when executed on a programmable device, such as a The computer system may enable a programmable device to perform the functions of a device or system according to the present invention. The computer program can cause the storage system to allocate disks to disk groups.

A computer program is a sequence of commands such as a specific application program and/or an operating system. The computer program may, for example, include one or more of the following: a subprogram, a function, a program, an object method, an object implementation method, an executable application, a small application, a servlet, a source code, and a purpose Code, a shared library/dynamically loaded library, and/or other instruction sequences designed to be executed on a computer system.

The computer program can be stored in a non-transitory computer readable medium. All or part of the computer program can be permanently provided on computer readable media Above, it can be removably or remotely coupled to an information processing system. The computer-readable media may include, for example, but not limited to, any number of magnetic storage media including magnetic disks and tape storage media; optical storage media such as a CD-ROM media (for example, CD-ROM, CD-R, etc.) Etc.) and digital video disc storage media; non-electrical storage storage media, including semiconductor-based memory units such as flash memory, EEPROM, EPROM, ROM; ferromagnetic digital memory; MRAM; electrical storage media including Register, buffer or cache, main memory, RAM, etc.

A computer program usually includes an executing (running) program or a part of a program, current program values and status information, and the resources used by the operating system to manage the execution of the program. An operating system (OS) is software that manages the sharing of the resources of a computer and provides an interface for programmers to access these resources. An operating system processes system data and user input, and responds by assigning and managing tasks and internal system resources as a service to users and programs of the system.

The computer system may, for example, include at least one processing unit, associated memory, and several input/output (I/O) devices. When the computer program is executed, the computer system processes information according to the computer program, and generates the resulting output information through the I/O device.

In the foregoing specification, the present invention has been described with reference to specific examples of embodiments of the present invention. However, it is obvious that various modifications and changes can be made without departing from the broader spirit and scope of the present invention as set forth in the appended patent application scope.

In addition, the terms "front", "rear", "top", "bottom", "above", "below" and similar terms in the description and the scope of the invention application, if any, are used For descriptive purposes, it is not necessarily used to describe permanent relative positions. It should be understood that the terms so used are interchangeable under appropriate circumstances, so that the embodiments of the present invention described herein, for example, can be described in other ways. Those other directions to operate.

Those skilled in the art will recognize that the boundaries between logic blocks are only illustrative and alternative embodiments may incorporate logic blocks or circuit elements or apply functionality to various logic blocks or circuit elements. An alternative decomposition. Therefore, it can be understood that the architecture described herein is only exemplary, and in fact many other structures can be implemented to achieve the same function.

Any arrangement of components to achieve the same function is effectively "associated" so that the desired function is realized. Therefore, in this document, any two components combined to achieve a specific function can be regarded as being "associated with" each other to enable the desired function to be realized, regardless of the structure or intermediate components. Similarly, any two components so related can also be regarded as being "operably connected" or "operably coupled" to each other to achieve the desired function.

Furthermore, those skilled in the art will recognize that the boundaries between the functions of the above-mentioned operations are only illustrative. The function of multiple operations may be combined into a single operation, and/or the function of a single operation may be distributed in additional operations and may at least partially overlap in time to perform operations. In addition, alternative embodiments may include multiple instances of a specific operation, and the order of operations may be changed in various other embodiments.

Also, for example, in one embodiment, the illustrated example may be implemented as a circuit located on a single integrated circuit or within the same device. Alternatively, the examples can be implemented as any number of separate integrated circuits or separate devices interconnected with each other in a suitable manner.

Moreover, for example, the examples, or parts thereof, can be implemented as physical circuits or can be converted into software or code presentations that can be converted into logical representations of physical circuits, such as using any suitable type of hardware description language.

Moreover, the present invention is not limited to physical devices or units implemented in non-programmable hardware, but can also be applied to programmable devices or units, which can be operated according to appropriate code to execute the desired device Functions, such as mainframes, minicomputers, Servers, workstations, personal computers, notebook computers, personal digital assistants, electronic game consoles, automobiles and other embedded systems, cellular phones and various other wireless devices are collectively referred to as "computer systems" in this application.

However, other modifications, variations, and replacements are also possible. Correspondingly, this specification and the drawings are also regarded as an explanatory rather than a restrictive meaning.

In the scope of the patent application for this invention, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "include" does not exclude the existence of other elements or steps besides those listed in a request item. In addition, terms such as "one" or "one", as used in this article, are defined as one or more than one. Moreover, the use of introductory phrases such as "at least one" and "one or more" in these claims should not be interpreted as implying that the indefinite articles "a" or "one" refer to elements of another claim. The introduction limits the invention to any specific claim that contains such an introduced claim element to include only one such element, even when the same claim includes the introductory phrases "one or more" or "at least one". "And indefinite articles such as "一" or "one".

This is also true for the use of definite articles. Unless otherwise indicated, terms such as "first" and "second" are used to arbitrarily distinguish between the elements described by such terms. Therefore, these terms are not necessarily intended to refer to the timing or other priorities of such elements. The simple fact that specific measures are stated in mutually different claims does not mean that a combination of these measures cannot be used to advantage.

Although the specific features of the present invention have been illustrated and described herein, those of ordinary skill in the art will now be able to think of many modifications, substitutions, changes, and equivalents. Therefore, it can be understood that the scope of the appended invention application is intended to cover all these modifications and changes that fall within the true spirit of the present invention.

100: workbench

101: Items to be inspected

102: Optical, lighting, and camera components; camera

103: control and processing module

104: Storage

105: User Interface

106: Network interface, remote network, network

107: Processing Subsystem

Claims (23)

A method for inspecting an object, wherein the method includes: acquiring an image of an object; wherein the object includes a non-conductive base layer, a first conductor of a first conductive layer, and a second conductor of a second conductive layer , Where the first conductors are arranged between the base layer and the second conductors, where the first conductors contact the second conductors; calculate a first alignment transformation, which is expressed in (a) the first conductors A first spatial relationship between the imaged shape and position of a conductor and (b) the designed shape and position of the first conductors; calculate a second alignment transformation, which is expressed in (a) the first conductors A second spatial relationship between the imaged shapes and positions of the two conductors and (b) the designed shapes and positions of the second conductors; detecting defects in the first conductor based on the image and the second alignment transformation And based on the image and the second alignment transformation to detect a second conductor defect. Such as the method of claim 1, wherein the detection of the first conductor defects and the detection of the second conductor defects are performed separately. Such as the method of claim 1, wherein the object is a printed circuit board, and the second leads are iBump. Such as the method of claim 1, wherein the object system is a printed circuit board, and the first conductive systems have through-holes under the traces. Such as the method of claim 4, wherein the detection of the first conductor defects includes finding a part of a via under a given trace, which extends over a given via placed under the given trace Outside the second conductor, and calculate an offset between the via hole and the second conductor under the given test. Such as the method of claim 5, which includes calculating a center of a through hole under the given trace and a center of the given second conductor. Such as the method of claim 1, wherein the calculation of the first alignment transformation includes masking the object part according to the designed shapes and positions of the second conductors. Such as the method of claim 1, wherein the calculation of the second alignment transformation includes masking the object part according to the designed shapes and positions of the first conductors. Such as the method of claim 1, which includes multiple repetitions of the steps of calculating the first alignment transformation and calculating the second alignment transformation; wherein each repetition produces a repetition result that is fed to a subsequent repetition. For example, the method of claim 1, which includes multiple repetitions of the steps of calculating the first alignment transformation and calculating the second alignment transformation; wherein each repetition includes the designed according to the second conductors The shape and position are used to mask the object part to calculate the first alignment transformation; where each repetition produces a repetitive result that is fed to a subsequent repetition. For example, the method of claim 1, which includes multiple repetitions of the steps of calculating the first alignment transformation and calculating the second alignment transformation; wherein each repetition includes the designed according to the first conductors The shape and position are used to mask the object part to calculate the second alignment transformation; where each repetition produces a repetitive result that is fed to a subsequent repetition. An inspection system for inspecting an object, wherein the inspection system includes: an image capturing module for acquiring an image of an object; wherein the object includes a non-conductive base layer and a first conductive layer. Conductor and a second conductor of a second conductive layer, wherein the first conductors are arranged between the base layer and the second conductors, wherein the first conductors contact the second conductors; a first alignment A processor for calculating a first alignment transformation, which represents the difference between (a) the imaged shape and position of the first conductors and (b) the designed shape and position of the first conductors A first spatial relationship; A second alignment processor for calculating a second alignment transformation, which is expressed in (a) the imaged shape and position of the second conductors and (b) the designed shape of the second conductors And a second spatial relationship between positions and positions; and an inspection processor for detecting a first conductor defect based on the image and the second alignment transformation, and for detecting a defect based on the image and the second alignment transformation Detect the second conductor defect. Such as the inspection system of claim 12, wherein the inspection processor is configured to separate the detection of the first conductor defects from the detection of the second conductor defects. For example, the inspection system of claim 12, wherein the object is a printed circuit board, and the second leads are iBump. For example, the inspection system of claim 12, wherein the object is a printed circuit board, and the first conductors are through holes under the traces. For example, the inspection system of claim 15, wherein the inspection processor is configured to detect the first conductor defects by finding a part of the through hole under a given trace, and the part extends to be placed on the given line Outside of a given second conductor above the under-track via; and calculate an offset between the via and the second conductor under the given test. For example, in the inspection system of claim 16, the inspection processor is configured to calculate a center of a through hole under the given trace and a center of the given second conductor. Such as the inspection system of claim 12, wherein the first alignment processor is configured to mask the object part according to the designed shapes and positions of the second conductors to calculate the first alignment transformation. Such as the inspection system of claim 12, wherein the configuration of the second alignment processor to calculate the second alignment transformation includes masking the object part according to the designed shapes and positions of the first conductors. For example, the inspection system of claim 12 is configured to perform multiple repetitions of the steps of calculating the first alignment transformation and calculating the second alignment transformation; wherein each repetition generates a repetition result that is fed to a subsequent repetition . For example, the inspection system of claim 12 is configured to perform multiple repetitions of the steps of calculating the first alignment transformation and calculating the second alignment transformation; wherein each repetition includes the calculations based on the second conductors The designed shape and position are used to mask the object part to calculate the first alignment transformation; where each repetition produces a repetitive result that is fed to a subsequent repetition. For example, the inspection system of claim 12 is configured to perform multiple repetitions of the steps of calculating the first alignment transformation and calculating the second alignment transformation; wherein each repetition includes the experience based on the first conductors The designed shape and position are used to mask the object part to calculate the second alignment transformation; where each repetition produces a repetitive result that is fed to a subsequent repetition. A non-transitory computer-readable medium storing instructions that, once executed by an inspection system, cause the inspection system to perform the following steps: obtain an image of an object; wherein the object includes a non-conductive base layer , A first conductor of a first conductive layer and a second conductor of a second conductive layer, wherein the first conductors are arranged between the base layer and the second conductors, and the first conductors contact the The second conductor; calculate a first alignment transformation, which represents a first between (a) the imaged shape and position of the first conductors and (b) the designed shape and position of the first conductors A spatial relationship; calculate a second alignment transformation, which represents a first between (a) the imaged shape and position of the second conductors and (b) the designed shape and position of the second conductors Two spatial relationships; detecting a first conductor defect based on the image and the second alignment transformation; and detecting a second conductor defect based on the image and the second alignment transformation.

Images