[BEA @ ACL 2023] General-purpose tool for linguistic features extraction; Tested on readability assessment, essay scoring, fake news detection, hate speech detection, etc.

Simple synthetic audio feature extractor

We propose a novel targeted adversarial attack for multiple well-known handcrafted pipelines and datasets. Our attack is able to match an image with any given target image which can be completely different from the original image. Our approach provides a trade-off between effectiveness and imperceptibility, and outperforms the baselines on both …

Repository for my Master's thesis on the unsupervised early detection of fake news articles

🌲🧮 Eucalyptus counting using artisanal methods and computer vision.

Noise adding techniques in order to deceive the state of the art handcrafted features.

To preform image classification on Rice Leaf Disease images using CNN via various methods.

Cell clustering of tissue images using handcrafted intensity-based and textural features.

Implementing an effective combination of data preprocessing and handcrafted features along with Multinomial Naive Bayes classifier for Irony Detection in English Tweets

A custom lightweight neural network that incorporates a Bag Of Visual Words model alongside a custom shallow CNN to estimate the apparent age of a face.

Code and results for one-class autoencoder verification of historical sketches using handcrafted features (Fourier energy, Shannon entropy, contrast, GLCM homogeneity, fractal dimension) and deep feature baselines (ResNet50, EfficientNet-V2). Companion repository to Ugail et al., PLOS ONE (2026).

Implementation of a machine learning model to predict COVID-19 Informative Text.

Teste de Visão Computacional/Processamento de Imagens - Pixeon