How a Robot System Inspects and Grades Objects for Flaws
This patent describes an automated system that uses cameras, special lighting, and deep learning AI to find and measure tiny flaws on an object's surface, then assigns a quality grade and sorts it.
Original patent title: “Inspection and cosmetic grading through image processing system and method”
This patent describes an automated system that uses cameras, special lighting, and deep learning AI to find and measure tiny flaws on an object's surface, then assigns a quality grade and sorts it. Granted to Griffyn Robotech Pvt in 2020 with 13 claims and 25 forward citations, and it is expected to expire in 2039.
Coverage
What does this patent actually cover?
The system first uses an "image capture subsystem" to take pictures of an object, adjusting a "lighting subsystem" for optimal viewing conditions (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1). An "image processing module" then employs "deep learning algorithms" to detect, segment, and classify surface defects, also measuring their length and width. For each identified defect, an "optical spot sensor subsystem" precisely measures its depth or height, providing a 3D understanding of the flaw (Claim 1). Finally, a "cosmetic grading module" determines the object's quality grade based on the number, type, and severity (length, width, and depth) of defects, and directs the item to the appropriate bin for shipment (Claim 3). For example, it could automatically inspect newly manufactured smartphone screens for scratches or dust particles.
The gap
What does this patent NOT cover?
- Does not cover systems that rely solely on human visual inspection for grading objects.
- Does not cover systems that only detect 2D surface defects without measuring their 3D depth or protrusion (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1).
- Does not cover systems that grade objects without using deep learning algorithms for defect detection and classification (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1, 2).
- Does not cover systems that do not use an automated control system to align the object for 3D defect measurement (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1).
- Does not cover systems that do not recommend an optimal path of disposition based on the cosmetic grade (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 3).
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
The noveltynoveltyThe requirement that an invention be different from anything publicly known before its priority date.Read more → lies in combining 2D image processing with deep learning for initial defect detection and classification, then precisely measuring the 3D depth of those specific defects using an "optical spot sensor" guided by the 2D analysis. This allows for a comprehensive and automated cosmetic grade.
The Patent Drawing
Schematic visualization of the patent's claim structure. Hand-drawn diagrams in progress for each landmark patent.
Where you've seen this
Real-world examples
Automated inspection of smartphone displays for scratches
Quality control for painted car body panels
Sorting of pharmaceutical pills for surface imperfections
Grading of fruit and vegetables for blemishes
Inspection of semiconductor wafers for defects
Why it matters
The bigger picture
This technology is important for quality control in manufacturing, especially for products where even small cosmetic flaws can impact value or customer satisfaction. It allows for consistent, objective, and high-speed inspection, reducing human error and labor costs. Industries producing electronics, automotive parts, or consumer goods can benefit from such automation to maintain high product standards.
Filed
June 19, 2019
Granted
August 25, 2020
Market context
Who's building on this
Companies in this space
Companies like Cognex, Keyence, and Basler are major players in industrial machine vision and automated inspection, developing advanced camera systems, lighting, and software that incorporate AI for defect detection. Robotics companies like Fanuc and KUKA integrate such vision systems into robotic arms for automated handling and inspection tasks. Griffyn Robotech, the assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →, is active in this space.
Market impact
This type of technology has driven a shift from manual, subjective quality control to automated, objective, and high-throughput inspection in manufacturing. It enables higher product quality, reduces waste from undetected defects, and allows for faster production lines. The integration of deep learning has significantly improved the accuracy and adaptability of these systems to various defect types and materials.
Claim 1 — Plain English
What this patent covers
The system first uses an "image capture subsystem" to take pictures of an object, adjusting a "lighting subsystem" for optimal viewing conditions (Claim 1). An "image processing module" then employs "deep learning algorithms" to detect, segment, and classify surface defects, also measuring their length and width. For each identified defect, an "optical spot sensor subsystem" precisely measures its depth or height, providing a 3D understanding of the flaw (Claim 1). Finally, a "cosmetic grading module" determines the object's quality grade based on the number, type, and severity (length, width, and depth) of defects, and directs the item to the appropriate bin for shipment (Claim 3). For example, it could automatically inspect newly manufactured smartphone screens for scratches or dust particles.
The clever bit
The novelty lies in combining 2D image processing with deep learning for initial defect detection and classification, then precisely measuring the 3D depth of those specific defects using an "optical spot sensor" guided by the 2D analysis. This allows for a comprehensive and automated cosmetic grade.
What it does not cover
- Does not cover systems that rely solely on human visual inspection for grading objects.
- Does not cover systems that only detect 2D surface defects without measuring their 3D depth or protrusion (Claim 1).
- Does not cover systems that grade objects without using deep learning algorithms for defect detection and classification (Claim 1, 2).
- Does not cover systems that do not use an automated control system to align the object for 3D defect measurement (Claim 1).
- Does not cover systems that do not recommend an optimal path of disposition based on the cosmetic grade (Claim 3).
Patent timeline
Application submitted to the patent office
Application published, typically 18 months after filing
Patent officially issued
Patent enters public domain
PatentBrief Score
Impact Score
Moderate
Citation count
28/40
Moderately cited
Claim breadth
9/20
Moderate scope
Recency
10/20
Granted 5–10 years ago
Assignee scale
0/20
Independent or smaller assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →
PatentBrief Impact Score — based on citation count, claim breadth, recency, and assignee scale. Not a legal assessment.
Heuristic Value Estimate
What this patent might be worth
$216K – $691K
Midpoint $432K · 12.7 yr remaining · industry ×1.6
Heuristic only — blends forward/backward citation counts, claim scope, time remaining, litigation history, and CPC-derived industry baseline. Real valuations need a professional appraisal.
Claim text not yet imported for this patent
The original legal language
Original claims
13 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Warokar, N. S., Mahajan, A. A., Alhat, V. P., Bagalkote, S. S., Anand, D., & Jathar, A. A. (2020). How a Robot System Inspects and Grades Objects for Flaws (U.S. Patent No. 10,753,882). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/10753882/inspection-and-cosmetic-grading-through-image-processing-system-and-method
Auto-generated from the patent record. Double-check author order and the issue date against the official USPTO document before submitting.
Embed
Add this patent to your site
Drop this plain-English patent card into any blog post or article — free, no signup. It always links back to the full breakdown here.
<div data-patentlens-widget data-patent-number="US10753882"></div> <script src="https://patentbrief.org/embed.js" async></script>
Stay in the loop
Get a weekly digest of new patents.
One email per week. No spam. Unsubscribe anytime.
Keep exploring
Related patents you should know
US 4683195 · 1987
How to Make Billions of Copies of a DNA Segment
This patent describes the Polymerase Chain Reaction (PCR), a method to rapidly create many copies of a specific piece of DNA or RNA, enabling its detection and analysis.
Cetus Corp
US 8697359 · 2014
How to Edit Genes in Human Cells Using an Engineered CRISPR System
This patent describes an engineered CRISPR-Cas9 system for precisely cutting DNA in eukaryotic cells to change how genes work, opening the door for gene editing in complex organisms.
Massachusetts Institute of Technology
US 7657849 · 2010
How the iPhone's Slide-to-Unlock Gesture Works
Apple's 2010 patent describes unlocking a device by dragging a specific graphical image across the touchscreen along a predefined path, a gesture that became iconic with the original iPhone.
Apple Inc
US 4733665 · 1988
How Doctors Implant a Permanent Stent Using a Balloon
This patent describes the method for placing a permanent, expandable wire mesh tube inside a blood vessel or other body tube using a balloon-tipped catheter to widen it and keep it open.
Expandable Grafts Partnership
US 4965188 · 1990
How to Make Many Copies of a DNA Piece with Heat
This patent describes the Polymerase Chain Reaction (PCR) method, a technique to make millions of copies of a specific DNA segment using a heat-resistant enzyme and repeated temperature changes.
Cetus Corp
US 4235871 · 1980
How to Encapsulate Active Materials in Lipid Bubbles Efficiently
This patent describes a method for trapping biologically active substances inside tiny, multi-layered fat bubbles called liposomes, using a specific water-in-oil emulsion and gel-forming process to improve how much material gets captured.
Individual
Semantically similar
You might also find these interesting
US 12243216 · 2025 · Musashi Auto Parts Canada
How AI Cameras Check Factory Parts for Flaws
US 10942133 · 2021 · Hong Kong Research Institute of Textiles and Apparel
How Machines Automatically Spot Flaws in Fabric During Manufacturing
US 20250377309 · Isra Vision
How to Inspect Moving Objects on a Production Line with a Moving Camera
US 12211234 · 2025 · Nippon Telegraph and Telephone Corp
How Computers Track the Position and Angle of Multiple Objects
More to explore
More in Consumer Electronics
US 7657849 · 2010 · Apple Inc
How the iPhone's Slide-to-Unlock Gesture Works
US 7479949 · 2009 · Apple Inc
How Touchscreens Understand Your Finger Swipes and Scrolls
US 4528643 · 1985 · FPDC Inc
How Stores Make Custom Products On-Demand with Remote Approval
US 7469381 · 2008 · Apple Inc
How Touchscreens Show and Snap Back When You Scroll Past an Edge
New to patents?
Common Questions
Frequently Asked Questions
What does How a Robot System Inspects and Grades Objects for Flaws cover?
This patent describes an automated system that uses cameras, special lighting, and deep learning AI to find and measure tiny flaws on an object's surface, then assigns a quality grade and sorts it.
Who owns patent US 10753882?
Griffyn Robotech Pvt owns this patent, granted in 2020.
When does this patent expire?
This patent is expected to expire on June 19, 2039, when the invention enters the public domain.
What is patent US 10753882 cited by?
This patent has been cited by 25 later patents that build on its ideas.
What problem does this patent solve?
This technology is important for quality control in manufacturing, especially for products where even small cosmetic flaws can impact value or customer satisfaction. It allows for consistent, objective, and high-speed inspection, reducing human error and labor costs. Industries producing electronics, automotive parts, or consumer goods can benefit from such automation to maintain high product standards.
What does this patent NOT cover?
Does not cover systems that rely solely on human visual inspection for grading objects.
Patent monitoring