This project uses mammograms for breast cancer detection using deep learning techniques.

A food image to recipe converter for Indian food.

Models Supported: DenseNet121, DenseNet161, DenseNet169, DenseNet201 and DenseNet264 (1D and 2D version with DEMO for Classification and Regression)

Ensemble based transfer learning approach for accurately classifying common thoracic diseases from Chest X-Rays

Transfer-Learning based Sugarcane Leaf Disease Detection Using DenseNet201 Architecture

Classification of Tuberculosis (X-ray imagery).

A web app to predict whether a person has COVID-19 from their Chest X-Ray (CXR) scan by image classification using Transfer Learning with the pre-trained models VGG-16 and DenseNet201 with ImageNet weights.

This project uses mammograms for breast cancer detection using deep learning techniques.

Thesis Project

We have proposed a multimodal approach. Where we first took the best unimodal for textual and visual data classification by testing and automation process. Then we fusion of the two models which can successfully classify the materials that have been damaged using the image and text data. EfficientNetB3+BERT multimodal better accuracy with 94.18%

Code repository for training multi-label classification models on the CheXpert Chest X-ray dataset.

Makerere Passion Fruit Disease Detection Challenge

Deep Learning Final Project

CNN to develop a system that can automatically classify these X-rays as either indicative of COVID-19 infection or negative for the virus.

'CNN_Sorghum_Weed_Classifier' is an artificial intelligence (AI) based software that can differentiate a sorghum sampling image from its associated weeds images.

A skin cancer detection web app which takes a dermoscopic image and classify it in benign and malignant Malanoma.

Skin Cancer Detection: Leveraging Hybrid Deep Learning Models and Traditional Machine Learning Classifiers

Comparitive analysis of various CNN models which includes, RapidNet (Custom Model), VGG16, VGG19, InceptionV3, and DenseNet201.

Autostereogram Classification. Foundational concept to begin understanding how to differentiate between the image of a known thing, and a hidden like image in an autostereogram.

A cutting-edge model leveraging the power of a pretrained DenseNet201 network for sophisticated feature extraction, combined with layers of LSTM architectures for robust caption generation.