---
title: "Reconstructed Slides: Harnesses in AI: A Deep Dive — Tejas Kumar, IBM"
category: "slides"
video_id: "C_GG5g38vLU"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Harnesses in AI: A Deep Dive — Tejas Kumar, IBM

## Source Video
[Harnesses in AI: A Deep Dive — Tejas Kumar, IBM](https://www.youtube.com/watch?v=C_GG5g38vLU)

## Method
This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck.

## Reconstructed Slides
![[assets/reconstructed-slides/C_GG5g38vLU/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.8`
![[assets/reconstructed-slides/C_GG5g38vLU/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.55`
![[assets/reconstructed-slides/C_GG5g38vLU/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.7`
![[assets/reconstructed-slides/C_GG5g38vLU/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `161.54`
![[assets/reconstructed-slides/C_GG5g38vLU/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `161.24`
![[assets/reconstructed-slides/C_GG5g38vLU/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `162.42`
![[assets/reconstructed-slides/C_GG5g38vLU/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `162.56`
![[assets/reconstructed-slides/C_GG5g38vLU/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.74`
![[assets/reconstructed-slides/C_GG5g38vLU/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.77`
![[assets/reconstructed-slides/C_GG5g38vLU/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `162.33`
## Dense Scene-Detected Slide Candidates
- [[youtube-C_GG5g38vLU-dense-slides]]