Fastest
Eureka on the web
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →https://www.patsnap.com/resources/blog/rd-blog/automated-optical-and-x-ray-inspection-patent-landscape/ · Patsnap · data cut-off 2026-07-31 · downloaded from the live page
Patent Landscape · Industrial AutomationAutomated Optical and X-Ray Inspection Patents
- Concentrated at the top. The five leading assignees hold 21 of 36 records in scope (58.3%), and the leading ten hold 31 (86.1%) — a short list of names controls most of the documented claim space.
- Filing activity has cooled from its peak. Filings peaked at 4 in 2021 and fell to 1 by 2024, a 75% decline over that three-year span, though publication lag means 2025-2026 figures are still incomplete.
- Image processing rivals materials testing. G01N material analysis (41.7% of records) and G06T image data processing (36.1%) are the two largest classes, showing inspection patents split almost evenly between physical testing and computational defect detection.
36
Published Records
58%
Top-5 Share of All Records
-75%
Filing Growth 2021→2024
US
Leading Jurisdiction
Filing growth compares 2021 (4 records) with 2024 (1) — a three-year span. 2024 is the most recent year we treat as complete: publication lags filing by roughly 18 months, so 2025 onwards are still filling in and any growth rate that ends there would understate the field. Top-5 share is the combined record count of the five largest assignees divided by all 36 records in scope (CR5), not by the ranked leaders only.
Published byPatsnap Research··7 min readSourced from Patsnap Eureka
Overview
What this landscape covers
Automated optical inspection (AOI) and automated X-ray inspection (AXI) systems check solder joints, semiconductor packages and printed circuit assemblies for defects without manual review. This landscape draws on 36 published records filed between 2015 and mid-2026 that reference core inspection metrics directly in their text or claims — false call rate, programming effort, 3D solder joint inspection, hidden joint inspection, throughput and defect escape — rather than the broader universe of optical or X-ray patents generally.
That framing narrows the field to filings that engage with the practical trade-offs inspection engineers actually manage: how often a system flags a good joint as bad, how much setup time a new board requires, and whether defects hidden under packages get caught at all. The result is a smaller, more targeted corpus than a keyword search on 'optical inspection' alone would return.
Filing activity by year, 2015-2026
Source: Patsnap Eureka. Assignee ranking and totals. Derived from a Patsnap search on Automated Optical and X-Ray Inspection covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Let an AI agent run this analysis on your own technology
Pick a task. Every answer cites the patents behind it.
10,000 free credits to start
Data
Filing trends and technology composition
Two views of the same 36 records: how filing activity has moved year over year, and which IPC subclasses the claims sit in.
A peak in 2021, then a pullback
Filings rose from zero in 2017 to a peak of 4 in 2021, then declined to 1 by 2024 — a 75% drop over that span. 2025 and 2026 figures will fill in over the next 18 months as publication catches up with filing dates, so the apparent low recent count should not be read as the technology stalling.
Split between physical and computational inspection
G01N (material analysis & testing) and G06T (image data processing) each cover well over a third of the 36 records, with H01L (semiconductor devices) and H05K (printed circuits) trailing behind. G06N (AI-based computing) already appears in 8.3% of records, suggesting inspection claims are starting to fold in learned defect classification rather than rule-based image comparison alone.
Shares are the percentage of the 36 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Source: Patsnap Eureka. Filing trend and technology composition. Derived from a Patsnap search on Automated Optical and X-Ray Inspection covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.
Go deeper on Automated Optical and X-Ray Inspection with Eureka
This page is one run against one query. Ask Eureka your own question about automated optical and x-ray inspection and every answer comes back with the patent numbers behind it.
Try EurekaKey Patents
Representative and most-cited filings
Representative filing
US9659359B1 — Method of and device for quality control process optimization
BRIGHT MACHINES, INC.
Methods of and devices for quality control that can be used with automated optical inspection (AOI), solder paste inspection (SPI), and automated X-ray inspection (AXI) are disclosed. Plurality of threshold settings are entered in a testing process. Multiple testing results are obtained from the testing process. A graphic presentation is generated showing the numerical relationship among the data points, such that a quality control person is able to fine-tune the testing process to have a predetermined ratio of Defect Escaped % to False Call ppm.Filed by Bright Machines, Inc., published 2017-05-23. Claims a method for tuning the trade-off between false call rate and defect escape rather than a specific optical or X-ray sensing apparatus.
Most-cited records in this landscape
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US20230125477A1 | Defect detection using one or more neural networks | 55 |
| 2 | US6864498B2 | Optical inspection system employing a staring array scanner | 48 |
| 3 | US7084970B2 | Inspection of TFT LCD panels using on-demand automated optical inspection sub-system | 38 |
| 4 | US20050254045A1 | Inspection of TFT LCD panels using on-demand automated optical inspection sub-system | 35 |
| 5 | US5544338A | Apparatus and method for raster generation from sparse area array output | 27 |
| 6 | US20020166983A1 | Optical inspection system employing a staring array scanner | 20 |
| 7 | US20060170910A1 | Automatic optical inspection using multiple objectives | 16 |
| 8 | JP1987249040A | X-ray inspection device and inspection method | 14 |
| 9 | US20030043369A1 | Automated optical inspection and marking systems and methods | 13 |
| 10 | US5448650A | Thin-film latent open optical detection with template-based feature extraction | 13 |
Citation counts inside this corpus skew toward older filings that have had more time to accumulate citations — read them as a signal of influence on later work, not as a ranking of current technical relevance.
Each row carries its publication number; clicking a row searches Eureka by that number.
Source: Patsnap Eureka. Citation counts and representative records. Derived from a Patsnap search on Automated Optical and X-Ray Inspection covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Run it yourself
Put your own technology through the same analysis
Where to run it
For builders
MCP server & REST API
When it has to run inside your own pipeline.
Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.
Browse MCP servers →Insights
What the numbers mean for a filing decision
Reading the concentration and technology figures together points to where the field is settled and where a new filing still has room.
Concentration
58.3%
of 36 records held by top 5 assignees
A short list controls most of the claim space
Five assignees account for 21 of the 36 records in scope, and the top ten hold 31 — 86.1% of everything published. A new entrant is not filing into open ground; it is filing around a small number of established portfolios that already cover the core AOI/AXI methods.
Based on the 22-company ranked assignee list.
Momentum
-75%
filings, 2021 peak to 2024
Activity has pulled back from its 2021 peak
The field peaked at 4 filings in 2021 and had fallen to 1 by 2024. That is a real three-year decline, not an artefact of publication lag, since 2024 is the most recent year that can be treated as complete under the roughly 18-month publication delay.
2025-2026 counts will rise as later filings publish.
Technology mix
41.7% / 36.1%
G01N vs G06T share of 36 records
Physical testing and image computation are near-equal
G01N (material analysis & testing) narrowly leads G06T (image data processing) as the largest class. Their near-parity suggests neither pure sensor-hardware claims nor pure software-defect-classification claims dominate outright — both remain active claim territory.
Classes overlap; a record can carry both.
Filing geography
20 of 36
records with a US receiving office
Filing is heavily US-weighted
The United States receives more than half of all filings in scope, with Europe, WIPO/PCT, Australia, India and Taiwan each accounting for a handful. Anyone assessing freedom to operate elsewhere should not assume the US picture transfers directly to other jurisdictions.
Counts by receiving office, not by inventor origin.
Eureka AI Agent
Looking for what nobody has claimed yet?
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to automated optical and x-ray inspection, with the prior art for and against each one.
Source: Patsnap Eureka. Co-assignee relationships and derived observations. Derived from a Patsnap search on Automated Optical and X-Ray Inspection covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Players
Who holds the ground, and where it is still open
The ranked assignee list spans semiconductor manufacturers, equipment makers and test-system vendors — a mix that reflects how AOI/AXI sits at the intersection of fab tooling and dedicated inspection equipment.
Leader
5 records
held by the top-ranked assignee
The leading assignee sets the pace
The top-ranked assignee holds 5 of the 36 records in scope, ahead of the fifth-place holder at 4. That gap is narrow enough that the leading group functions more as a cluster of comparable portfolios than a single dominant player.
Ranked by patent family count.
Mid-field
4 → 1
records from 5th to 10th place
A steep drop after the top five
Filing counts fall quickly outside the leading group: by tenth place, an assignee holds just 1 record. That long tail of single- and few-filing entrants is where recent, more experimental approaches tend to sit.
22 companies appear in the full ranking.
Recent activity
0
latest-year filings across tracked leaders
No leader shows fresh momentum yet
None of the tracked leading assignees recorded a filing in the latest year, consistent with the broader pullback from the 2021 peak and with publication lag still working through the system. This is not evidence any of them have exited the space.
Momentum reflects publication dates, not R&D activity.
Recent-year filing momentum by assignee
| Assignee | Recent year | YoY |
|---|---|---|
| Taiwan Semiconductor Manufacturing Co., Ltd. (TSMC) | 0 | — |
| General Electric Co. | 0 | — |
| Siemens AG | 0 | — |
| Applied Materials Israel Ltd. | 0 | — |
| Teradyne Inc. | 0 | — |
| Photon Dynamics, Inc. | 0 | — |
| NVIDIA Corp. | 0 | — |
| Camtek Ltd. | 0 | — |
Source: Patsnap Eureka. Assignee-level momentum. Derived from a Patsnap search on Automated Optical and X-Ray Inspection covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
What's Next
Where to take this
The dataset points to a field with a settled leadership group and a technology mix still splitting between hardware and computation. Two directions follow from that.
Check freedom to operate against the leading cluster
With 58.3% of records held by five assignees, a new filing in core AOI/AXI methods needs a claim chart against that cluster specifically, not just a general prior-art search.
Run a freedom-to-operate check in Eureka →Scope claims around under-claimed branches
Hidden-joint inspection, programming-effort reduction and AI-assisted false-call suppression show thinner coverage than the core optical-comparison methods — a narrower, more specific claim may clear faster there.
Explore white space in Eureka →Source: Patsnap Eureka. Forward-looking reading of the same dataset. Derived from a Patsnap search on Automated Optical and X-Ray Inspection covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
FAQ
Common questions about this landscape
The dataset ranks 22 companies by patent family count, with the top five holding 21 of the 36 records in scope, or 58.3%. That leading group includes semiconductor manufacturers, general industrial equipment makers, and dedicated inspection-system vendors, reflecting how AOI/AXI technology sits at the intersection of fab process control and standalone test equipment. The gap between the leader and fifth place is narrow, which means no single company dominates the field outright.
Filings peaked at 4 in 2021 and had fallen to 1 by 2024, a 75% decline over that three-year window using the most recent year that can be treated as complete. Because publication typically lags actual filing by around 18 months, the 2025 and 2026 counts in any dataset will understate true activity and should not yet be read as a continued decline. The honest read is that visible filing activity cooled after 2021, with the true current trajectory still emerging.
Material analysis and testing (IPC class G01N) appears in 41.7% of the 36 records, closely followed by image data processing (G06T) at 36.1%. Semiconductor devices (H01L) and printed circuit assemblies (H05K) trail at 16.7% and 11.1% respectively. Since a single record can carry multiple IPC classes, these figures overlap rather than sum to 100%, and the near-parity between G01N and G06T shows the field splits fairly evenly between physical sensing methods and computational defect-detection approaches.
Several sub-areas show thin coverage relative to the core optical-comparison and solder-joint methods: hidden-joint X-ray inspection under packages, programming-effort reduction for AOI line setup, 3D solder joint reconstruction from limited viewing angles, and AI-assisted false-call suppression. These branches appear in the technology composition data at lower shares than the dominant material-analysis and image-processing classes, suggesting narrower, more specific claims in these areas may face less crowded prior art. A freedom-to-operate search focused specifically on these sub-areas is a reasonable next step before drafting.
US9659359B1, filed by Bright Machines and published in 2017, claims a method for tuning the trade-off between defect-escape percentage and false-call rate across AOI, solder-paste inspection and AXI systems using threshold settings and a graphical presentation of results. It is a process and calibration method rather than a claim on any specific optical or X-ray sensing hardware. New system designs using different calibration logic or that do not present the defect-escape-versus-false-call relationship graphically are likely to sit outside its literal claim scope, though a full claim chart is needed to confirm freedom to operate for any specific product.
Answers are grounded in the same dataset. Derived from a Patsnap search on Automated Optical and X-Ray Inspection covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Research Automated Optical and X-Ray Inspection in depth with Eureka
Go past this page: query the whole automated optical and x-ray inspection corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.
Patent data carries inherent limitations: recent filings (typically the most recent 18–24 months) are under-counted due to standard publication lag; counts may be reported at either a patent-family or a patent-record basis and are not always directly comparable; classification, applicant-name, and citation data may contain errors, duplicates, or omissions; and the underlying search query defines and constrains the scope shown. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, or validity search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. Any patent, commercial, or strategic decision should be verified independently and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.
Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company's registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.