C
Ching Y. Suen
Researcher at Concordia University
Publications - 532
Citations - 25017
Ching Y. Suen is an academic researcher from Concordia University. The author has contributed to research in topics: Handwriting recognition & Feature extraction. The author has an hindex of 65, co-authored 511 publications receiving 23594 citations. Previous affiliations of Ching Y. Suen include École de technologie supérieure & Concordia University Wisconsin.
Papers
More filters
Journal ArticleDOI
Image Recognition Based on Nonlinear Wavelet Approximation
TL;DR: The mathematical theory on nonlinear wavelet approximation is introduced, which shows that nonlinear approximation contains much more information of the original image than linear approximation.
Book ChapterDOI
Facial Beauty Prediction Using Transfer and Multi-task Learning Techniques.
Elham Vahdati,Ching Y. Suen +1 more
TL;DR: In this paper, a multi-task learning scheme is employed by the model to learn optimal shared features for these correlated tasks in an end-to-end manner. And a deep residual network originally trained on massive face datasets is utilized which is capable of learning high-level and robust features from face images.
Proceedings ArticleDOI
Statistical Hypothesis Testing for Handwritten Word Segmentation Algorithms
TL;DR: The main idea behind the proposed approach is to learn the geometrical distribution of words within a sentence using a Markov chain or a Hidden Markov Model (HMM).
Proceedings ArticleDOI
Computer synthesis of Mandarin
TL;DR: Mandarin was synthesized using a computer-controlled speech synthesizer and it was shown that subjects could hear the synthesized passage with an encouraging intelligibility score of over 70% after less than an hour of exposure to the sounds.
Proceedings ArticleDOI
Multi-layer projections for the classification of similar Chinese characters
Wang Kai,Y.Y. Yang,Ching Y. Suen +2 more
TL;DR: Experimental results indicate that for any displacement and for rotations in the range of (-180 degrees, +180 degrees ), this method can separate without exception all similar Chinese characters including the complex ones.