You will use computer vision and machine learning to predict for a product image (i.e. 2D images), its corresponding product category (e.g. italian dish) and confidence for your respective prediction. Therefore, you can use existing computer vision tools, e.g. Keras, PyTorch, Tensorflow.
**The Topic**
In our daily lives we often interact with grocery products: e.g. During shopping, or when we want to know the ingredients of a product. Today, such queries are usually triggered by scanning a product’s barcode – a process which requires a bright-light environment, visual contact, active high-resolution camera, close proximity between product and smartphone, and an active command from the user or app to scan the barcode. In the future, such interactions become much more natural – e.g. through smart glasses, which automatically detect a product, even without scanning its barcode. In our project “Image2Product”, you will use computer vision to automatically detect product features, e.g. its product category, size, or its identifier.
**The Thesis**
Our product database which is used as training and test data currently contains approx. 30 000 products including each product’s image, size, text description, nutrient and category data, and is constantly being extended. You will build a machine learning script that predicts for each of product image (i.e. 2D images), its corresponding product category (e.g. sweetened beverage) and confidence for the respective prediction. Therefore, you can use existing computer vision tools such as Keras, PyTorch or Tensorflow. You have the chance to become a co-author of a scientific paper in a conference or journal.
**You are**
• familiar with Java, Matlab, C/C++/C#, Python or R
• experienced with Machine Learning frameworks
• interested in Computer Vision
• capable of reading scientific articles
• motivated to participate on current research
**The Topic** In our daily lives we often interact with grocery products: e.g. During shopping, or when we want to know the ingredients of a product. Today, such queries are usually triggered by scanning a product’s barcode – a process which requires a bright-light environment, visual contact, active high-resolution camera, close proximity between product and smartphone, and an active command from the user or app to scan the barcode. In the future, such interactions become much more natural – e.g. through smart glasses, which automatically detect a product, even without scanning its barcode. In our project “Image2Product”, you will use computer vision to automatically detect product features, e.g. its product category, size, or its identifier.
**The Thesis** Our product database which is used as training and test data currently contains approx. 30 000 products including each product’s image, size, text description, nutrient and category data, and is constantly being extended. You will build a machine learning script that predicts for each of product image (i.e. 2D images), its corresponding product category (e.g. sweetened beverage) and confidence for the respective prediction. Therefore, you can use existing computer vision tools such as Keras, PyTorch or Tensorflow. You have the chance to become a co-author of a scientific paper in a conference or journal.
**You are**
• familiar with Java, Matlab, C/C++/C#, Python or R • experienced with Machine Learning frameworks • interested in Computer Vision • capable of reading scientific articles • motivated to participate on current research
You will build a machine learning script that predicts for each of product image (i.e. 2D images), its corresponding product category (e.g. sweetened beverages) and confidence for the respective prediction.
You will build a machine learning script that predicts for each of product image (i.e. 2D images), its corresponding product category (e.g. sweetened beverages) and confidence for the respective prediction.
Klaus Fuchs
ETH Zürich, D-MTEC
Weinbergstrasse 56/58
8092 Zürich
Phone: +41 44 633 89 15
fuchsk@ethz.ch
www.autoidlabs.ch
www.im.ethz.ch
Klaus Fuchs ETH Zürich, D-MTEC Weinbergstrasse 56/58 8092 Zürich