2 code implementations • 28 Jun 2019 • Zhun Fan, Jiajie Mo, Benzhang Qiu, Wenji Li, Guijie Zhu, Chong Li, Jianye Hu, Yibiao Rong, Xinjian Chen
Compared with other convolution networks utilizing standard convolution for feature extraction, the proposed method utilizes octave convolutions and octave transposed convolutions for learning multiple-spatial-frequency features, thus can better capture retinal vasculatures with varying sizes and shapes.
1 code implementation • 3 Jun 2019 • Zhun Fan, Jiewei Lu, Benzhang Qiu, Tao Jiang, Kang An, Alex Noel Josephraj, Chuliang Wei
The proposed CNN-DC can achieve 99. 26% accuracy for steel bar counting and 4. 1% center offset for center localization on the established steel bar dataset, which demonstrates that the proposed CNN-DC can perform well on automated steel bar counting and center localization.
no code implementations • 4 Feb 2018 • Zhun Fan, Zhongxing Li, Benzhang Qiu, Wenji Li, Jianye Hu, Alex Noel Josephraj, Heping Chen
In this paper, we present a global texture-shape 3D feature descriptor which can be utilized in a system of object recognition and grasping, and can perform object sorting tasks well.