AI Metal Assembly Image Comparator - 08/07/2026 09:42 EDT

Open

Prize:

$1,500 USD

Entries Received:

123

7 days, 13 hours remaining

Overview

Entries

Files

I need a small, accurate program that accepts two medium-resolution JPEG photographs of a finished metal assembly and automatically presents them side-by-side, with every visual difference clearly highlighted on the right-hand image. The purpose is simple: help our fabrication team spot mis-welds, missing brackets, or other subtle manufacturing deviations without having to inspect the parts manually. Here is what matters most to me: 1. The tool must read standard JPEGs shot between 720p and 1080p—you can assume consistent lighting but plenty of reflections and shiny edges typical of stainless steel. 2. Output should be a single composite image (or screen) that shows both originals next to each other; regions that differ are accented visually so a technician can locate them in seconds. Feel free to decide whether to use bounding boxes, semi-transparent color flashes, or other intuitive cues, as long as the comparison view remains uncluttered. 3. Speed is valuable on the shop floor, so an algorithmic approach built with OpenCV, scikit-image, Pillow, or comparable computer-vision libraries is preferred over heavyweight cloud inference. Python is ideal, but I’m open to C++, .NET, or a lightweight desktop executable if performance warrants it. 4. The detector should ignore irrelevant noise such as slight lighting variations but catch dimensional or component changes down to a few millimeters in scale. Deliverables: • Compiled application (or runnable script) with a straightforward interface: select Image A and Image B, press “Compare”, receive the highlighted side-by-side result. • Source code with clear comments so my in-house developer can tweak thresholds later. • A brief read-me describing dependencies, installation, and how to add sample images for testing. Acceptance will be based on a small test set of actual shop photos I’ll provide; all genuine mistakes must be marked, and no more than 5% false positives may appear. Let me know which libraries you plan to leverage and how you’ll tune for reflective metal surfaces, and we can get started right away.

Skills Required

.NET

AI (Artificial Intelligence) HW/SW

Computer Vision

Data Visualization

Desktop Application

Image Processing

OpenCV

Python

Software Development

Accepted File Formats

gif, jpeg, jpg, png

Clarification Board
No spam, self-promotion or advertisement is permitted.

Sammad Y.

@yassersammad1

7 hours ago

If I have your code ready, is it possible to make profit on top of it, if my submission did not match your expectation?

Yamen A.

@yamenrafat132

2 days ago

Hello contest holder can i get test pics to test my app? Please make sure the image is taken from a similar angle, it doesn't need to be exact, just roughly similar would be fine. Thank you!

Muhammad Samraan A.

@samraanWriter123

3 days ago

Beware of AI generated entries I am working since this requires time will send you working system

Shem O.

@Shemziller

3 days ago

Please check entry #113 Made the software using AI Vision runs locally

Hossam A.

@HOSSAMELSYAD

3 days ago

Dear Contest Holder, I have submitted my design entries to your contest. Please take a moment to review them. I truly hope the designs match your requirements 100% and meet your expectations. All designs will be delivered in fully editable vector format, so you can easily modify any element in the future. The files will be print-ready and can be resized to any size without losing quality. You will receive high-resolution files in the following formats: AI, EPS, SVG, PDF, PNG, JPEG, and PSD. I also offer unlimited revisions to ensure you are completely satisfied. Please feel free to let me know if you need any changes. Thank you very much for your time and consideration.

Shem O.

@Shemziller

3 days ago

Dear Contest Holder, Allow video submission so you can see full video demo and reject lazy AI generated images

Muhammad I.

@ikhan9985

3 days ago

#111 is a unique number with perfect symmetry.

David Yoga P.

@dvyoga14

3 days ago

Dear contest holder, could you please share another sample image to help train/test my app? Please make sure the image is taken from a similar angle, it doesn't need to be exact, just roughly similar would be fine. Thank you!

Faisal K.

@Faisal050

4 days ago

Hi contest holder! Thanks for the details. This is very helpful and confirms the approach I'm building (automatic comparison, adjustable sensitivity, web-based so it works on any browser/OS). Since every assembly is different, it would really help accuracy if you could share a broader set of test images, ideally a few different assembly types, plus a couple of "good vs. defective" pairs with known/marked defects (missing screws, shifted parts, etc.), so I can validate detection against real examples similar to what you'll actually test with. Thank You

Mahnoor K.

@mahnoorkhandurra

6 days ago

Before providing a final timeline and implementation plan, I would appreciate clarification on a few important points: Can you share a small sample set of images, including: Reference (correct) assemblies Assemblies containing actual defects Examples of the types of deviations you want detected Are the photos always captured from the same camera position and angle, or should the system handle slight rotation, scaling, and perspective changes? What is the typical physical size of the assemblies, and what is the smallest defect (in millimeters) that must be detected? Are all assemblies of the same product, or will the application need to support multiple assembly types? Would you like the comparison to be: Fully automatic, or Allow technicians to adjust sensitivity thresholds before running the comparison?