D
Dong Sun Park
Researcher at Chonbuk National University
Publications - 87
Citations - 2594
Dong Sun Park is an academic researcher from Chonbuk National University. The author has contributed to research in topics: Computer science & Fingerprint recognition. The author has an hindex of 20, co-authored 74 publications receiving 1698 citations. Previous affiliations of Dong Sun Park include Tianjin University of Science and Technology.
Papers
More filters
Book ChapterDOI
Deep Learning-Based Techniques for Plant Diseases Recognition in Real-Field Scenarios
TL;DR: This research proposes an efficient solution that provides farmers with a technology that facilitates proper management of crops and addresses the problem of class imbalance and false positives through the introduction of a refinement function called Filter Bank.
Journal ArticleDOI
Finger Vein Recognition based on Matching Score-Level Fusion of Gabor Features
Yu Lu,Sook Yoon,Dong Sun Park +2 more
TL;DR: Experimental results demonstrate the CLAHE method is effective to enhance the finger vein image quality and the proposed matching score-level fusion shows better recognition performance.
Journal ArticleDOI
Style-Consistent Image Translation: A Novel Data Augmentation Paradigm to Improve Plant Disease Recognition
TL;DR: This study proposes a novel data augmentation paradigm that can adapt variations from one class to another, and leverages a prior mask as input to tell the area the authors are interested in and reuse the original annotations.
Journal ArticleDOI
Pyramid Histogram of Double Competitive Pattern for Finger Vein Recognition
TL;DR: This paper proposes a new local descriptor, namely, pyramid histogram of double competitive pattern (PHDCP), and demonstrates that the proposed PHDCP performs much better than the existing local descriptors.
Proceedings ArticleDOI
An Optimal Orientation Certainty Level Approach for Fingerprint Quality Estimation
TL;DR: Experimental results show that the proposed OOCL method can improve the recognition rate than OCL method and uses the SVM classifier to determine whether an image should be accepted as an input to the recognition system.