Datasets, Transforms and Models specific to Computer Vision

In this paper I introduce a new oral lesion database that I created by scraping Images from research papers and dentists online. Next, I showcase a novel method for generating NxN pixel samples from human lips by isolating the labial fissure via image segmentation induced via the Kmean algorithm. I experiment with a variety of convolutional neur…

Convolutional Neural Network

Detect Fire Smoke with vgg and cnn

Image Classification for a City Dog Show Project Goal Improving your programming skills using Python. In this project, I use a created image classifier to identify dog breeds. It is for one of the submission for the udacity nanodegree program

VGG model based on Tensorflow

Computer Vision models (include classification models and detection models) implemented by PyTorch

Image segmentation project. Two architectures implemented: VGG-16 + FCN-8 module and U-Net. For FCN-8, pre-trained weights are used from SSD300. Although it is designed for object detection, its feature extractor can be reused in another task involving similar classes. Linked article explains the full project.

A Two-Stage Deep Learning Approach for Mitosis Recognition

Pytorch implementation of some of the popular papers

Implement VGG family from scratch and train them on CIFAR-10, and ImageNet datasets

This repo implements a VGG model with SPP layer to make it receive images with different shapes, which is then used to classify images of culture relics and compare results under differnt images types - gray images with the same shape, gray images with different shapes, bgr images with the same shape, bgr images with different shapes

VGG Blog

Implementation on tensorflow fine tuning of generic CNN based model

A tensorflow tool for loading some pre-trained models from MatConvNet

Using VGG to predict images with 10 classes

We have developed a Image Caption Generator which is a challenging artificial intelligence problem where a text description is generated for a given photograph.

In this repository I explore the effect of applying Residual Connections to a VGG CNN Architecture, as well as applying Batch Normalisation. The networks are tested on the CIFAR100 benchmark dataset.

Google's Inceptionism algorithm implementation in Pytorch with ResNet-x, VGG-x using MIT Indoor Scene dataset

Image & Video Technology and Analysis [ECE NTUA]