• Stars
    star
    6
  • Rank 2,531,863 (Top 51 %)
  • Language
    C++
  • Created over 7 years ago
  • Updated over 7 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

This is a fast custom algorithm having O(n) linear time & O(n) memory complexity implemented on the CPU for solving the famous connected component labelling problem. The algorithm implemented here, takes the image and the label of the connected region and spits out the number of such regions in the image.

More Repositories

1

CUDA-Connected-Component-Labelling

Parallel GPU Implementation of Connected Component Labelling (CCL). Connected-component labeling is used in computer vision to detect connected regions in binary digital images
Cuda
50
star
2

RoomNet

A lightweight ConvNet (~700 KB) to classify pictures of different rooms of a house/apartment with 88.9 % accuracy
Java
26
star
3

SHM-Learn

A CUDA & cuDNN powered Deep Learning C++ Library with clean interface and faster training speed (6x more over Caffe)
C++
5
star
4

SHMatrix

A neat C++ custom Matrix class to perform super-fast GPU (or CPU) powered Matrix/Vector computations with minimal code, leveraging the power of cuBLAS where applicable.
C++
3
star
5

naive-dqn-maze

Maze Solver from scratch (under 260 lines) using Naive Reinforcement Learning with Q-Table construction
Python
3
star
6

Lens-Smear-Detection

Python implementation of a Computer Vision algorithm to automatically extract lens smear regions from a batch of input images.
Python
2
star
7

Link-State-Routing-Simulator-CS-542

A C++ simulator to simulate Link State Routing protocols used in Computer Networks
C++
2
star
8

park.ai

Codebase to perform real-time detection+tracking of cars across different camera sources
Python
1
star
9

high-vision

microsoft ai hackathon submission for cloud coverage segmentation
Python
1
star
10

Business-Expansion-Engine-CS579

A Python application which analyses the social network pertaining to a given twitter handle and gives recommendations on the people in the network most likely to embrace a given product or service.
Jupyter Notebook
1
star