This Social Media Management project allow to classificate picture between food and non-food.
What we do:
- Extract feature splitted 70% for training and 30% test set.
- With deasy (step=8) extract local feature.
- To build aur dictionary of visual word, we have cluster all local feature with KMeans=500 (scikitlearn).
- Finally to classificate the picture we have used KNN.
Bag of visual word
In computer vision, the bag-of-words model (BoW model) can be applied to image classification, by treating image features as words. In document classification, a bag of words is a sparse vector of occurrence counts of words; that is, a sparse histogram over the vocabulary. In computer vision, a bag of visual words is a vector of occurrence counts of a vocabulary of local image features.
You need to have install on your system:
How to use
To use this script you need to clone this repo and download from release the dataset.7z file. Extract the file in the same folder of the repo and extract dataset/Food.7z & dataset/Non-Food.7z. Launch main.py and enojy the classificator.
Inspired by http://iplab.dmi.unict.it/madima2015