Match!
Yih-Cherng Lee
National Taiwan University
Pattern recognitionComputer visionComputer scienceFace detectionConvolutional neural network
14Publications
2H-index
10Citations
What is this?
Publications 14
Newest
#1Hung-Wei Hsu (NTU: National Taiwan University)H-Index: 1
#2Yih-Cherng Lee (NTU: National Taiwan University)H-Index: 2
Last. Ronald Y. Chang (CIT: Center for Information Technology)H-Index: 12
view all 4 authors...
Marine mammal detection is helpful for ecological conservation. In this paper, we proposed a novel automatic method in real-time to detect and recognize the dolphin that is underwater and just reveals some characteristics of the body. The proposed method is based on the convolutional neural network with an extra masking layer to approximate various filter without knowing the normal neural network, which explore a discriminative criterion to enhance the image segmentation performance. We evaluate...
Source
#1Chien-Yu Chen (NTU: National Taiwan University)
#2Jian-Jiun Ding (NTU: National Taiwan University)H-Index: 21
Last. Yih-Cherng Lee (NTU: National Taiwan University)H-Index: 2
view all 4 authors...
Face detection is one of the most popular topics in computer vision. There are several well-known techniques for face detection, such as the Viola-Jones detector. However, the performance of the Viola-Jones detector is limited since it mainly applies the simple Haar-based features. Many advanced methods, especially the convolutional neural network (CNN) based method, have very good performance in face detection. However, they require huge amount of training data. Moreover, most of existing algor...
Source
Oct 1, 2018 in APCCAS (Asia Pacific Conference on Circuits and Systems)
#1Hung-Wei Hsu (NTU: National Taiwan University)H-Index: 1
#2Yih-Cherng Lee (NTU: National Taiwan University)H-Index: 2
Last. Ronald Y. Chang (CIT: Center for Information Technology)H-Index: 12
view all 4 authors...
Dolphin identification is important for wildlife conservation. Since identifying dolphins from thousands of images manually takes tremendous time, it is important to develop an automatic dolphin identification algorithm. In this paper, a high accurate deep learning based dolphin identification algorithm is proposed. We presented an advanced approach, called hybrid saliency method, for feature extraction and efficiently integrate several well-known techniques to make dolphins distinguishable. Wit...
Source
#1Yu-Hsuan Tsai (NTU: National Taiwan University)H-Index: 1
#2Yih-Cherng Lee (NTU: National Taiwan University)H-Index: 2
Last. Ming-Chen Hsu (NTU: National Taiwan University)H-Index: 1
view all 5 authors...
Abstract Face detection plays an important role in many computer vision applications. In recent years, much research has focused on extending the well-established Adaboost face detector algorithm for multi-view face detection. However, detecting in-plane and out-of-plane rotated faces simultaneously is still a challenging task today. In this paper, a very robust multi-view face detection algorithm, with its core functionality based on frontal face detection, is proposed to simultaneously detect ...
2 CitationsSource
Oct 1, 2018 in APCCAS (Asia Pacific Conference on Circuits and Systems)
#1Hung-Yi Chen (NTU: National Taiwan University)H-Index: 1
#2Jian-Jiun Ding (NTU: National Taiwan University)H-Index: 21
Last. Yih-Cherng Lee (NTU: National Taiwan University)H-Index: 2
view all 3 authors...
Block matching based motion estimation (BMME) is widely used in video compression and stereoscopic image processing. Given that the full search algorithm is not efficient enough, many fast motion estimation algorithms are based on BMME. Adaptive rood path search (ARPS), which is an important process of the BMME method, exploits the inter-block correlation and zero-motion prejudgment to reduce the search cost. Although ARPS is very efficient, there is a gap between ARPS and full search in accurac...
Source
Oct 1, 2018 in APCCAS (Asia Pacific Conference on Circuits and Systems)
#1Alexandre Constantin (NTU: National Taiwan University)
#2Jian-Jiun Ding (NTU: National Taiwan University)H-Index: 21
Last. Yih-Cherng Lee (NTU: National Taiwan University)H-Index: 2
view all 3 authors...
In this paper, we present an accurate neural network algorithm to detect roads in satellite images. Based on convolutional neural networks, from a 6-channel image, this model is able to transfer the road structure to the output using both the U-net and the atrous convolution architecture. To train this model, we introduce a new combination of existing loss functions including the binary cross-entropy and the Jaccard distance to avoid false positive detection and increase binary classification ac...
3 CitationsSource
Oct 1, 2018 in APCCAS (Asia Pacific Conference on Circuits and Systems)
#1Kai-Yuan Tsai (NTU: National Taiwan University)
#2Jian-Jiun Ding (NTU: National Taiwan University)H-Index: 21
Last. Yih-Cherng Lee (NTU: National Taiwan University)H-Index: 2
view all 3 authors...
Automatic Facial Expression Recognition (FER) is an important technique in human-computer interfaces and surveillance systems. It classifies the input facial images into one of the basic expressions (e.g., anger, sad, surprise, happy, disgust, fear, and neutral) and has attracted significant attention in pattern recognition and computer vision. In this paper, we proposed an advanced convolutional neural networks based FER system. It applies the techniques of face frontalization and feature posit...
Source
#1Pin-Xuan Lee (NTU: National Taiwan University)H-Index: 2
#2Jian-Jiun Ding (NTU: National Taiwan University)H-Index: 21
Last. Yih-Cherng Lee (NTU: National Taiwan University)H-Index: 2
view all 4 authors...
Writer verification is to identify whether the script was written by a person himself. However, although there are many advanced machine learning methods now, automatic writer verification is still a very challenging work since the training data in the false case (forged case) is usually very hard to acquire. In practice, to avoid being convicted, a criminal may write scripts that are fully different from what he wrote on the forged document. In this manuscript, we adopt global and semi-global i...
3 CitationsSource
#1Chia-Chun Hsu (NTU: National Taiwan University)
#2Jian-Jiun Ding (NTU: National Taiwan University)H-Index: 21
Last. Yih-Cherng Lee (NTU: National Taiwan University)H-Index: 2
view all 3 authors...
Though image interpolation has been developed for many years, most of state-of-the-art methods, including machine learning based methods, can only zoom the image with the scaling factor of 2, 3, 2k, or other integer values. Hence, the bicubic interpolation method is still a popular method for the non-integer scaling problem. In this paper, we propose a novel interpolation algorithm for image zooming with non-integer scaling factors based on the gradient direction. The proposed method first estim...
Source
#1Jian-Jiun Ding (NTU: National Taiwan University)H-Index: 21
#2Shiang-Chih Hua (NTU: National Taiwan University)
Last. Yih-Cherng Lee (NTU: National Taiwan University)H-Index: 2
view all 4 authors...
Compressive sensing is to apply the sparsity of a signal in some domain to compress a signal. Its performance highly depends on the dictionary and the atoms one applies in the matching pursuit or the basis pursuit processes. In this paper, we generalize the atoms used in the dictionary by converting the phase into the higher order form, using Hermite-Gaussian functions instead of Gaussian functions, and applying harmonic combination. We call them higher-order atoms. This generalization can maxim...
Source
12