Y
Yap-Peng Tan
Researcher at Nanyang Technological University
Publications - 296
Citations - 9430
Yap-Peng Tan is an academic researcher from Nanyang Technological University. The author has contributed to research in topics: Facial recognition system & Feature extraction. The author has an hindex of 47, co-authored 290 publications receiving 8521 citations. Previous affiliations of Yap-Peng Tan include Fudan University & Intel.
Papers
More filters
Proceedings ArticleDOI
Adaptive binarization method for document image analysis
Mengling Feng,Yap-Peng Tan +1 more
TL;DR: The proposed adaptive binarization method has overcome, to a large extent, the general problems of poor quality document images, such as non-uniform illumination, undesirable shadows and random noise.
Journal ArticleDOI
A Doubly Weighted Approach for Appearance-Based Subspace Learning Methods
Jiwen Lu,Yap-Peng Tan +1 more
TL;DR: Experimental results show that the proposed doubly weighted subspace learning approach can effectively enhance the discriminant power of the extracted face features and outperform existing, nonweighted sub space learning algorithms.
Proceedings ArticleDOI
A robust sequential approach for the detection of defective pixels in an image sensor
Yap-Peng Tan,Tinku Acharya +1 more
TL;DR: This paper presents a robust sequential approach for detecting sensor defects from a sequence of images captured by the sensor with no extra non-volatile memory required in the sensor device to store the locations of sensor defects.
Journal ArticleDOI
Reversing Demosaicking and Compression in Color Filter Array Image Processing: Performance Analysis and Modeling
TL;DR: Analytical models for the reconstruction errors of the two processing chains of single-sensor digital still cameras are proposed to confirm the results of existing empirical studies and provide better understanding of DSC processing chains.
Patent
Method for removing ringing artifacts from locations near dominant edges of an image reconstructed after compression
TL;DR: In this paper, a method to remove ringing artifacts from locations near dominant edges of an image reconstructed after compression is proposed, where the image is decomposed into blocks small enough so that each would contain only one significant edge.