• Convergence Security Journal
• /
• v.14 no.5
• /
• pp.17-24
• /
• 2014

This study proposed LDP (Local Directional Pattern) as a new local micro pattern for facial expression recognition to solve noise sensitive problem of LBP (Local Binary Pattern). The proposed method extracts 8-directional components using $m{\times}m$ mask to solve LBP's problem and choose biggest k components, each chosen component marked with 1 as a bit, otherwise 0. Finally, generates a pattern code with bit sequence as 8-directional components. The result shows better performance of rotation and noise adaptation. Also, a new local facial feature can be developed to present both PFF (permanent Facial Feature) and TFF (Transient Facial Feature) based on the proposed method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.4
• /
• pp.316-320
• /
• 2016

In this paper, we presents a pattern recognition by considering the spatial co-occurrence among micro-patterns of texture images. The micro-patterns of texture image have been extracted by local binary pattern based on median(MLBP) of block image, and the recognition process is based on co-occurrence among MLBPs. The MLBP is applied not only to consider the local character but also analyze the pattern in order to be robust noise, and spatial co-occurrence is also applied to improve the recognition performance by considering the global space of image. The proposed method has been applied to recognized 17 RGB images of 120*120 pixels from Mayang texture image based on Euclidean distance. The experimental results show that the proposed method has a texture recognition performance.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.339-346
• /
• 2003

This paper proposes a multiple classifier system having massive micro classifiers. The micro classifiers are trained by using a local set of training patterns. The k nearest neighboring training patterns of one training pattern comprise the local region for training a micro classifier. Each training pattern is incorporated with one or more micro classifiers. Two types of micro classifiers are adapted in this paper. SVM with linear kernel and SVM with RBF kernel. Classification is done by selecting the best micro classifier among the micro classifiers in vicinity of incoming test pattern. To measure the goodness of each micro classifier, the weighted sum of correctly classified training patterns in vicinity of the test pattern is used. Experiments have been done on Elena database. Results show that the proposed method gives better classification accuracy than any conventional classifiers like SVM, k-NN and the conventional classifier combination/selection scheme.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.533-534
• /
• 2006

Micro pyramid pattern and its array are designed to enhance the brightness and its uniformity of LGP which is one of key parts in LCD. The designed micro pyramid patterns are fabricated on a Si-wafer first through MEMS process and then a Ni-stamper is electro-plated from the Si pattern master. Adopting the fabricated Ni-stamper, LGPs are injection molded at different mold temperatures and the fidelity of the pattern replication is estimated for each molding conditions and pattern locations. The replicated patterns are found to have some defect such as local short shot or micro weld line which are believed to have negative effect on the performance of the LGP.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.1537-1541
• /
• 2007

We injection molded a wedge type of plate with micro prizm patterns on its surface and investigated the fidelity of replication of the micro pattern depending on the process parameter such as mold temperature, melt temperature, injection rate or packing pressure. The size of the size of the $90^{\circ}$ prizm pattern is $50{\mu}m$ and the size of the plate is about 300㎜${\times}$200㎜. The thicknesses are 2.6㎜. and 0.7mm at each edge of the wedge type of plate. The fidelity of the replication turned out quite different according to the process parameters and location of the patterns on the plate. We measured the cavity pressure and temperature in real-time during the molding to analyze the effect of the local melt pressure and temperature on the micro pattern replication.

• Convergence Security Journal
• /
• v.14 no.7
• /
• pp.23-28
• /
• 2014

This study proposes the design and implementation of the system for a facial expression recognition system. LDP(Local Directional Pattern) feature computes the edge response in a different direction from a pixel with the relationship of neighbor pixels. It is necessary to be estimated that LDP code can represent facial features correctly under various conditions. In this respect, we build the system of facial expression recognition to test LDP performance quickly and the proposed evaluation system consists of six components. we experiment the recognition rate with local micro patterns (LDP, Gabor, LBP) in the proposed evaluation system.

• ETRI Journal
• /
• v.35 no.6
• /
• pp.1021-1028
• /
• 2013

Automatic facial expression recognition is a widely studied problem in computer vision and human-robot interaction. There has been a range of studies for representing facial descriptors for facial expression recognition. Some prominent descriptors were presented in the first facial expression recognition and analysis challenge (FERA2011). In that competition, the Local Gabor Binary Pattern Histogram Sequence descriptor showed the most powerful description capability. In this paper, we introduce hybrid facial representations for facial expression recognition, which have more powerful description capability with lower dimensionality. Our descriptors consist of a block-based descriptor and a pixel-based descriptor. The block-based descriptor represents the micro-orientation and micro-geometric structure information. The pixel-based descriptor represents texture information. We validate our descriptors on two public databases, and the results show that our descriptors perform well with a relatively low dimensionality.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.89-101
• /
• 2014

In this paper, we proposed a new local micro pattern, Signed Local Directional Pattern(SLDP). SLDP uses information of edges to represent the face's texture. This can produce a more discriminating and efficient code than other state-of-the-art methods. Each micro pattern of SLDP is encoded by sign and its major directions in which maximum edge responses exist-which allows it to distinguish among similar edge patterns that have different intensity transitions. In this paper, we divide the face image into several regions, each of which is used to calculate the distributions of the SLDP codes. Each distribution represents features of the region and these features are concatenated into a feature vector. We carried out facial expression recognition with feature vectors and SVM(Support Vector Machine) on Cohn-Kanade and JAFFE databases. SLDP shows better classification accuracy than other existing methods.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2007.05a
• /
• pp.205-208
• /
• 2007

We injection molded a thin plate with micro prism patterns on its surface and investigated the fidelity of replication of the micro pattern depending on the process parameter such as mold temperature, injection rate or packing pressure. The size of the $90^{\circ}$ prism pattern is $50{\mu}m$ and the size of the plate is $400mm{\times}400mm$. The thickness is 1mm. The fidelity of the replication turned out quite different according to the process parameters and location of the patterns of the plate. We measured the cavity pressure and temperature in real-time during the molding to analyze the effect of the local melt pressure and temperature on the micro pattern replication.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2013.02a
• /
• pp.272-273
• /
• 2013

Some living thingsuse micro- or nano- structures for living in nature. Scientists and engineers made efforts to mimic them, and they succeeded in making new types of applications. They used 'Namib desert beetle' to self-filling device by moisture harvesting and 'lotus leaf' to self-cleaning device by water repelling. 'Namib desert beetle' and lotus leaf have micro-patterns on their surface, which consists of hydrophobic or hydrophilic materials [1]. Moreover, micro-patterns on the surface make self-filling or self-cleaning property enhanced because of the surface roughness. Surface roughness enhances wettability [2]. Micro-pattern is a significant factor to make the surface be functional, so we want to make new types of functional surface by micro-patterning. In this work,we make several functional micro-patterns (radial, line, and dot arrays) using maskless lithography and analyze the characteristics of each micro-pattern. In order to analyze and understand surface characteristics, micro-patterns with varying sizes are investigated. All experiments are proceeded on mr-DWL5 photo resists coated on silicon wafers in same condition. All the experiments have demonstrated good performances about hydrophobic or hydrophilic property corresponding to their material and structural combinations. In radial micro-pattern, although the surface is flat, water drops on hydrophilic radial pattern can be convergent to a middle point and water drops on hydrophobic radial pattern can be divergent from the middle point. In line array micro-pattern, water drops can roll off along only one direction in parallel with the line arrays. Such phenomena might be mainly caused by the local change of surface roughness. From these results, controlling the movement and direction of water drops is made feasible without introducing a slope, which can potentially be used for new types of applications.