SURF (Speeded Up Robust Features)
-
Updated
Feb 7, 2023 - Jupyter Notebook
SURF (Speeded Up Robust Features)
Generalized Time Series Decomposition (GTSD) is an experimental method of generating and using large recurrence plots to self identify and segment away features of an unknown time series.
Kialo Scraper used for "Argumentative-debates" project. Edited by @FedeSpu
FeatVIS: High dimensional feature space visualization
Using transfer learning to classify tools for a ColRobot application
Argument classification with BERT plus contextual and structural features as text for ICONIP 2022.
This sentiment analysis project extracts features such as content length, tokens, hashtags, bad words, and various emojis. It also includes word features. Preprocessing steps include removing stop words, non-Arabic characters, consecutive redundant characters, and stemming to improve the models' accuracy in classifying the tweets. Max accuracy 88%.
Developed an image search and retrieval system based on color, feature and shape.
Object Classification is one of the most significant tasks whose development is constantly growing in the field of deep learning research. The objective of this study is the development of neural architectures for the classification of images (of fruits and vegetables) contained within the Fruits-360 dataset. The methodological approach adopted …
machine learning
Project in the Durrant Lab at UPitt that wanted to re-use code from a previous neural network ligand-protein interaction software to extract features for ML
Ce projet a pour but de réaliser une extraction de features, suivie d'une PCA sur des données volumineuses à l'aide de Spark dans le cloud.
Similarity between faces: One person resembles another person to a large degree. This can lead to many problems facing security surveillance systems. Facial recognition systems have difficulty distinguishing between the main person and other people who are highly similar in terms of features.
tsfresh is a library that automatically extracts features.
Emotions recognition application that will be able to distinguish between seven basic facial expressions: joy, surprise, neutral, anger, fear, disgust and sadness.
Analysis of public audio datasets and audio datasets of my making
A solution for humor detection in binary data, using python and some classification algorithms such as Naive Bayes, KNN, SVM, Decision Trees.
Thesis: "Autocalibration of monocular cameras for autonomous driving scenarios", carried out in collaboration with Luxoft. This repository contains all the related code and the two implemented solution pipelines for Structure from Motion (SfM) implementation.
Add a description, image, and links to the features-extraction topic page so that developers can more easily learn about it.
To associate your repository with the features-extraction topic, visit your repo's landing page and select "manage topics."