Xê-mi-na khoa học
06/04/2021: ThS. Qiuchen Zhu (Univ. Technology Sydney, Australia), Hierarchically Residual Network for feature extraction
In machine vision, the key to object detection rests with robust and accurate algorithms for feature extraction. To this end, this paper proposes a deep learning approach using hierarchical convolutional neural networks with feature preservation (HCNNFP) and an intercontrast iterative thresholding algorithm for image binarization. First, a set of branch networks is proposed, wherein the output of previous convolutional blocks is half-sizedly concatenated to the current ones to reduce the obscuration in the down-sampling stage taking into account the overall information loss. Next, to extract the feature map generated from the enhanced HCNN, a binary contrast- based autotuned thresholding (CBAT) approach is developed at the post-processing step, where patterns of interest are clustered within the probability map of the identified features. To overcome the impact of the imbedded uncertainty, our framework is probabilistically reformed using Bayesian modeling. The proposed technique is then applied to various image processing tasks.
Speaker: ThS. Qiuchen Zhu, Univ. Technology Sydney
Time: 15:30, Tuesday, April 06, 2021
Venue: G2-315, 144 Xuan Thuy, Cau Giay, Hanoi
Qiuchen Zhu received the M.Eng. degree from Huazhong University of Science and Technology, Wuhan, China, in 2017. He is currently pursuing a Ph.D. degree at the School of Electrical and Data Engineering, University of Technology Sydney, Australia. His research interests include machine vision, image processing, probabilistic representation, and uncertainty of deep learning.