sketch.py

The whole point of this is convert a picture to look like a cartoon sketch and the results are pretty good I feel. First step is to take the input image and convert it to grey scale. Second step is to invert this greyscale. Then we use Gaussian blur to blur the inverted image. Fourth step would be to invert back the blurred inverted image. The final step is to divide the gray imaage with the Inverted blur image. dividing the grayscale image by the inverse of the blurred image, remains with the highlights the boldest edges. This results in the sketch of the uploaded image.

sketch_live.py

This file opens up the web camera and converts each frame into a sketch in real time.

bgremove.py

We are trying to build a background removal app and the modules used here are cvzone and mediapipe.

Import the SelfiSegmentation from cvzone.SelfiSegmentationModule.

The removeBG module removes the background of the image, not much to do here, will need to try how to do this from scratch some day.

Open CV - Convert a picture to look like a cartoon sketch in python

Related tags

Overview

sketch.py

sketch_live.py

bgremove.py

Owner

Sammith S Bharadwaj

PyTorch implementation of our paper: Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition

Fashion Entity Classification

Learning Open-World Object Proposals without Learning to Classify

A collection of differentiable SVD methods and also the official implementation of the ICCV21 paper "Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling?"

Elevation Mapping on GPU.

Luminaire is a python package that provides ML driven solutions for monitoring time series data.

CS583: Deep Learning

The official implementation of the research paper "DAG Amendment for Inverse Control of Parametric Shapes"

Near-Optimal Sparse Allreduce for Distributed Deep Learning (published in PPoPP'22)

A `Neural = Symbolic` framework for sound and complete weighted real-value logic

Project page for the paper Semi-Supervised Raw-to-Raw Mapping 2021.

An implementation of Deep Forest 2021.2.1.

Text Generation by Learning from Demonstrations

Official Implementation of CoSMo: Content-Style Modulation for Image Retrieval with Text Feedback

Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming

Simple transformer model for CIFAR10

[ICLR 2021] "CPT: Efficient Deep Neural Network Training via Cyclic Precision" by Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin

Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation

git《Investigating Loss Functions for Extreme Super-Resolution》(CVPR 2020) GitHub:

An excellent hash algorithm combining classical sponge structure and RNN.