Shape Recognition with Computer Vision
summary
The talk explains a concrete OpenCV-in-Python pipeline for shape recognition: image acquisition, preprocessing (grayscale and Gaussian blur), Canny edge detection, segmentation via contour extraction, and counting shapes demonstrated in a Colab notebook. The demo counts shapes but mislabels one yellow shape, and the presenter discusses limitations for deployment such as noisy/low-contrast images, need for parameter tuning, and hardware constraints for real-time use.
AI-written summary · about
chapters (8)
- 0:00Shape recognition intro
- 2:57Image processing in vision
- 9:20Demo: OpenCV & Colab
- 14:05Advanced AI vision apps
- 16:51Summary
- 19:31Q&A: libraries
- 20:17Q&A: hardware
- 21:24Q&A: filtering
related talks
01h 11mObject detection using OpenCV
22mHow to effectively extract image features – let’s play with...
26mIs This Your Card? Computer Vision for Playing Card Recognition
22mOCR, Recognition and Information Extraction from Images
01h 12mBuilding a live face recognition system
30mIntroduction to Computer Vision with OpenCV
21mRecognizing Human features using Deep Networks
01h 39mGoogle Colaboratory and Python: Deep Learning basics for CV tasks