Name: Ihsan Ullah Khan
Type: User
Company: Daegu Gyeongbuk Institute of Science and Technology (DGIST)
Bio: Phd Research Scholar at DGIST.
Interested in Computer Vision and Deep Learning,
Location: Daegu South Korea
Blog: http://dgist.ac.kr
Ihsan Ullah Khan's Projects
Keras 3D U-Net Convolution Neural Network (CNN) designed for meidcal image segmentation
Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes, ICCV 2017
Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)
Artificial neural networks for brain networks
Face-recognition using Siamese network
AttentionGAN for Unpaired Image-to-Image Translation & Multi-Domain Image-to-Image Translation
A background subtraction library
Predicting neuro-development scores using deep convolutional neural networks on brain network graphs
Automatic catheter detection in pediatric X-ray images using a scale-recurrent network and synthetic data
Catheter segmentation in X-Ray fluoroscopy using convolutional neural networks.
color recognition (convolutional neural network implemented in Keras
Connectome-convolutional neural netvork for connectivity-based classificatin
See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks (CVPR19)
Connectome visualization utility
Keras implementation of CycleGAN
Comparing different similarity functions for reconstruction of image on CycleGAN. (https://tandon-a.github.io/CycleGAN_ssim/)
Domain Adaptive Pseudo-LiDAR
Keras implementation of Road Extraction by Deep Residual U-Net article
Keras tutorial for beginners (using TF backend)
Video Labeling software for detection and tracking in videos
Fast Symmetric Diffeomorphic Image Registration with Convolutional Neural Networks
Tensorflow implementation of our paper: Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning
Compute the likeliness of an image region to vessels or ridges
Header-only library for using Keras models in C++.
Real-time Tracking of Guidewire Robot Tips using Deep Convolutional Neural Networks on Successive Localized Frames
3D/2D vessel/catheter-based registration and 3D catheter tip tracking using hidden Markov model.