Deep edge-color invariant features for 2D/3D car fine-grained classification

Florian Chabot, Mohamed Chaouch, Jaonary Rabarisoa, Céline Teulière, Thierry Chateau

Abstract: Given an untextured 3D car models dataset, are we able to learn a robust make and model classifier which will be applied on real color images? One solution consists in finding a common representation between synthetic edge images and real color images. To address this issue, we introduce novel edge-color invariant features for 2D/3D car fine-grained classification. These features are learned simultaneously on real color and edge images of cars using a deep architecture. Using these accurate features, we propose to learn on edges synthetic images a fine-grained classifier which will be afterwards applied to real color images. The 3D car models dataset allows to automatically generate multi-views synthetic images using non-photorealistic edge rendering. Experimentally, we show efficiency of our learned edge-color invariant features for make and model recognition.