15,863 questions
Advice
0
votes
4
replies
153
views
What can I use stack overflow for?
I am wrapping up my B.S. in cognitive science late this year. My professor had us create a stack overflow account in our data analysis and optimization course. I unfortunately never looked into it ...
- reputation score 1
-3
votes
0
answers
75
views
computer vision iOS help for teenager [closed]
so im building an iOS calligraphy learning app that uses your phone camera to give you realtime feedback on how you're holding your pen and upstroke/downstroke feedback. the idea is it detects whether ...
- reputation score 9
-3
votes
1
answer
114
views
How to register a blurry IR image to a sharp RGB image when the scene has a repetitive grid structure? [closed]
I am a student working on a plant phenotyping project. I am trying to align RGB and infrared (IR) images of plant trays.
The setup:
RGB camera: sharp, 4112×3006
IR camera: blurry, 1024×768 (upscaled ...
- reputation score 9
Tooling
0
votes
0
replies
47
views
How should I process frames from an LWIR camera such that an image stitching algorithm can reliably identify matching features?
Before I get into the issue I'm having, I'd like to preface this by saying I'm largely clueless when it comes to computer vision and optics in general, so much so that the most reliable source I've ...
- reputation score 29
1
vote
1
answer
344
views
How to fix this python code to count different sized (length) samples in an image?
I am trying to answer this question:
How to fix this python code to count duplicate sample in the images?
using 'rods_input.png' as input:
where OP was asking for:
I want to count samples in the ...
- reputation score 3397
Tooling
1
vote
2
replies
95
views
Pixel-based Pathfinding for a Bot in a 2.5D Isometric Game
I am building a game automation bot for Royal Revolt 2 using Python (running on an Android emulator and controlled via ADB inputs). I am currently stuck on designing a robust, vision-based pathfinding ...
- reputation score 1
Advice
1
vote
3
replies
126
views
How can I improve OCR accuracy for low-quality scanned identity documents?
I am working on an OCR pipeline that extracts structured information from scanned identity documents. The system performs reasonably well on high-quality images, but accuracy drops significantly when ...
- reputation score 1
Tooling
0
votes
0
replies
70
views
What's the best "FreeTier" resource, Generative-ai, text-prompt/image-upload_to_video fullstack llmm application that's pipelined through HuggingFace?
As an academic in the field of computer science with advanced specialization in artificial intelligence and prompt engineering, I am currently exploring the most effective open-source generative AI ...
- reputation score 1
1
vote
0
answers
93
views
How to get counts from multiple cross lines using cv2 and Ultralytics' yolo26 model
I am trying to conduct traffic analysis of an intersection by counting the number of cars entering and exiting each "arm" of the intersection. I followed ultralytics' docs to create one ...
- reputation score 11
Advice
1
vote
0
replies
64
views
Tech stack recommendation
I’m currently building a production-grade crowd-based face recognition attendance system for a company. The system takes input from 3 CCTV cameras and needs to detect, align, recognize, and track ...
- reputation score 1
Advice
0
votes
2
replies
95
views
Advice on Dataset Choice for Two-Way Sign Language App in Flutter
I am developing a Flutter app called Talk to Deaf, which aims to enable real-time two-way communication between deaf and hearing users. The app will allow normal users to input text or voice and the ...
- reputation score 1
Best practices
0
votes
0
replies
69
views
Best practices for image annotation consistency in object detection projects
I am working on a computer vision dataset preparation workflow for object detection training.
The project involves image annotation using bounding boxes and polygon segmentation for AI model training.
...
- reputation score 1
Advice
0
votes
2
replies
83
views
Real Time Image Classification Task
I am trying to create a program that takes live camera output on my mac and classifies the gesture that the user is making. I currently have the gestures to be [wave, fist, thumbs up, peace sign, no ...
- reputation score 1
Advice
0
votes
3
replies
94
views
YOLO11m fine-tuned on SKU dataset hallucinating and missing DuoPack detections
I am working on a retail shelf product detection system using YOLO11m fine-tuned on a 110k SKU dataset with a single class `product`. The model performs well overall but I have two problems after ...
- reputation score 11
Advice
1
vote
1
replies
58
views
Do Apache 2.0 licensed segmentation models (e.g., SegNeXt, PP‑LiteSeg) include commercial‑free pretrained weights?
I’m evaluating semantic segmentation models like SegNeXt and PP‑LiteSeg, which are released under the Apache 2.0 license. The code is clearly permissive, but I’m unsure about the pretrained weights.
...
- reputation score 1
