Learning a discriminative region descriptor for fine-grained cultivar identification

Chengzhuan Yang, Wenkai Lyu, Qian Yu, Yunliang Jiang, Zhonglong Zheng

Abstract: Highlights•We propose a novel learning-based discriminative region descriptor framework for recognizing fine-grained cultivars.•We present an effective pixel feature representation of an image called a pixel feature map.•We present a local region covariance feature, which can effectively integrate various visual information of an image.•The experimental results show that our method outperforms the state-of-the-art plant species recognition approaches.