Automatic Produce Classification from Images Using Color, Texture and Appearance Cues

We propose a system to solve a multi-class produce categorization problem. For that, we use statistical color, texture, and structural appearance descriptors (bag-of-features). As the best combination setup is not known for our problem, we combine several individual features from the state-of-the-art in many different ways to assess how they interact to improve the overall accuracy of the system. We validate the system using an image data set collected on our local fruits and vegetables distribution center.