fdcb228294
* colors expression by KMean algorithm * object detection by imageai * object detection by cvlib * add encapsulation of object detection * remove encapsulation of objdetect v0 * objects expression to dict * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * added imageai to requirements * add objects to dictionary * update for AnalysisMethod baseline * add objects dection support explore_analysis display * extend python version of misinf to allow imageai * account for older python * use global functionality for dict to csv convert * update for docker build * docker will build now but ipywidgets still not working * test code * include test data folder in repo * add some sample images * load cvs labels to dict * add test data * retrigger checks * add map to human coding * get orders from dict, missing dep * add module to test accuracy * retrigger checks * retrigger checks * now removing imageai * removed imageai * move labelmanager to analyse * multiple faces in mydict * fix pre-commit issues * map mydict * hide imageai * objects default using cvlib, isolate and disable imageai * correct python version * refactor faces tests * refactor objects tests * sonarcloud issues * refactor utils tests * address code smells * update readme * update notebook without imageai Co-authored-by: Ma Xianghe <825074348@qq.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: iulusoy <inga.ulusoy@uni-heidelberg.de>
Misinformation campaign analysis
Extract data from from social media images and texts in disinformation campaigns.
This project is currently under development!
Use the pre-processed social media posts (image files) and process to collect information:
- Text extraction from the images
- Improving the preparation of the text for the data analysis (e.g., text cleaning)
- Performing person and face recognition in images, facial expressions recognition, as well as the extraction of any other available individual characteristics (e.g., gender, clothes)
- Extraction of other non-human objects in the image
- 5-Color analysis of the images
This development will serve the fight to combat misinformation, by providing more comprehensive data about its content and techniques. The ultimate goal of this project is to develop a computer-assisted toolset to investigate the content of disinformation campaigns worldwide.
Installation
The misinformation package can be installed using pip: Navigate into your package folder misinformation/ and execute
pip install .
This will install the package and its dependencies locally.
Usage
There are sample notebooks in the misinformation/notebooks folder for you to explore the package usage:
- Facial analysis: Use the notebook
facial_expressions.ipynbto identify if there are faces on the image, if they are wearing masks, and if they are not wearing masks also the race, gender and dominant emotion. - Object analysis: Use the notebook
ojects_expression.ipynbto identify certain objects in the image. Currently, the following objects are being identified: person, bicycle, car, motorcycle, airplane, bus, train, truck, boat, traffic light, cell phone.
There are further notebooks that are currently of exploratory nature (colors_expression to identify certain colors on the image, get-text-from-image to extract text that is contained in an image.)