• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.11
• /
• pp.2271-2283
• /
• 2015

In this paper, we propose a method which infers an accurate disparity map for radiometrically varying stereo images. For this end, firstly, we transform the input color images to the log-chromaticity color space from which a linear relationship can be established during constructing a joint pdf between input stereo images. Based on this linear property, we present a new stereo matching cost by combining weighted mutual information and the SIFT (Scale Invariant Feature Transform) descriptor with segment-based plane-fitting constraints to robustly find correspondences for stereo image pairs which undergo radiometric variations. Experimental results show that our method outperforms previous methods and produces accurate disparity maps even for stereo images with severe radiometric differences.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.1-8
• /
• 2005

Facial analysis is used in many applications like face recognition systems, human-computer interface through head movements or facial expressions, model based coding, or virtual reality. In all these applications a very precise extraction of facial feature points are necessary. In this paper we presents a method for automatic extraction of the facial features Points such as mouth corners, eye corners, eyebrow corners. First, face region is detected by AdaBoost-based object detection algorithm. Then a combination of three kinds of feature energy for facial features are computed; valley energy, intensity energy and edge energy. After feature area are detected by searching horizontal rectangles which has high feature energy. Finally, a corner detection algorithm is applied on the end region of each feature area. Because we integrate three feature energy and the suggested estimation method for valley energy and intensity energy are adaptive to the illumination change, the proposed feature extraction method is robust under various conditions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.10
• /
• pp.3490-3507
• /
• 2014

License plate detection (LPD) is one of the most important aspects of an automatic license plate recognition system. Although there have been some successful license plate recognition (LPR) methods in past decades, it is still a challenging problem because of the diversity of plate formats and outdoor illumination conditions in image acquisition. Because the accurate detection of license plates under different conditions directly affects overall recognition system accuracy, different methods have been developed for LPD systems. In this paper, we propose a license plate detection method that is rapid and robust against variation, especially variations in illumination conditions. Taking the aspects of accuracy and speed into consideration, the proposed system consists of two stages. For each stage, Haar-like features are used to compute and select features from license plate images and a cascade classifier based on the concatenation of classifiers where each classifier is trained by an AdaBoost algorithm is used to classify parts of an image within a search window as either license plate or non-license plate. And it is followed by connected component analysis (CCA) for eliminating false positives. The two stages use different image preprocessing blocks: image preprocessing without adaptive thresholding for the first stage and image preprocessing with adaptive thresholding for the second stage. The method is faster and more accurate than most existing methods used in LPD. Experimental results demonstrate that the LPD rate is 98.38% and the average computational time is 54.64 ms.

• Journal of KIISE:Software and Applications
• /
• v.36 no.10
• /
• pp.816-824
• /
• 2009

In the face space, face images due to illumination and pose variations have a nonlinear distribution. Active Appearance Models (AAM) based on the linear model have limits to the nonlinear distribution of face images. In this paper, we assume that a few clusters of face images are given; we build local AAMs according to the clusters of face images, and then select a proper AAM model during the fitting phase. To solve the problem of updating fitting parameters among the models due to the model changing, we propose to build in advance relationships among the clusters in the parameter space from the training images. In addition, we suggest a gradual model changing to reduce improper model selections due to serious fitting failures. In our experiment, we apply the proposed model to Yale Face Database B and compare it with the previous method. The proposed method demonstrated successful fitting results with strongly illuminated face images of deep shadows.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.6
• /
• pp.783-788
• /
• 2004

Many reported methods assume that the faces in an image or an image sequence have been identified and localization. Face detection from image is a challenging task because of the variability in scale, location, orientation and pose. The difficulties in visual detection and recognition are caused by the variations in viewpoint, viewing distance, illumination. In this paper, we present an efficient linear discriminant for multi-view face detection and face location. We define the training data by using the Fisher`s linear discriminant in an efficient learning method. Face detection is very difficult because it is influenced by the poses of the human face and changes in illumination. This idea can solve the multi-view and scale face detection problems. In this paper, we extract the face using the Fisher`s linear discriminant that has hierarchical models invariant size and background. The purpose of this paper is to classify face and non-face for efficient Fisher`s linear discriminant.

• 한국태양에너지학회:학술대회논문집
• /
• 2011.04a
• /
• pp.282-286
• /
• 2011

The artificial increase in the solar intensity incident on solar cells using lenses or mirrors can allow solar cells to generate equivalent power with a lower cost. In application areas of Fresnel lenses as solar concentrators, several variations of design were devised and tested. Some PV systems still use commercially available flat Fresnel lenses as concentrators. In this study, we designed and optimized flat Fresnel lens and the 'light pipe' to develop 500X concentrated solar PV system. We performed rigorous ray tracing simulation of the flat Fresnel lens and light-pipe. The light-pipe can play imporatant roles of redistributing solar energy at the solar cell and increase the mechanical tolerance so that it can increase the lifetime of the high-concentration solar PV system and decrease the cost of manufacturing. To investigate the sensitivity of the solar power generated by the concentrated solar PV according to the performance of lens and light pipe, we performed raytracing and executed a simulation of electrical performance of the solar cell when it is exposed to the non-uniform illumination. We could conclude that we can generate 95 % or more energy compared with the energy that can be generated by perfectly uniform illumination once the total energy is given the same.

• Journal of Korea Multimedia Society
• /
• v.6 no.2
• /
• pp.247-258
• /
• 2003

Principal component analysis (PCA) based algorithms form the basis of numerous algorithms and studies in the face recognition literature. PCA is a statistical technique and its incorporation into a face recognition system requires numerous design decisions. We explicitly take the design decisions by in-troducing a generic modular PCA-algorithm since some of these decision ate not documented in the literature We experiment with different implementations of each module, and evaluate the different im-plementations using the September 1996 FERET evaluation protocol (the do facto standard method for evaluating face recognition algorithms). We experiment with (1) changing the illumination normalization procedure; (2) studying effects on algorithm performance of compressing images using JPEG and wavelet compression algorithms; (3) varying the number of eigenvectors in the representation; and (4) changing the similarity measure in classification process. We perform two experiments. In the first experiment, we report performance results on the standard September 1996 FERET large gallery image sets. The result shows that empirical analysis of preprocessing, feature extraction, and matching performance is extremely important in order to produce optimized performance. In the second experiment, we examine variations in algorithm performance based on 100 randomly generated image sets (galleries) of the same size. The result shows that a reasonable threshold for measuring significant difference in performance for the classifiers is 0.10.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.3
• /
• pp.203-216
• /
• 2003

In this paper a new feature extraction and target classification method is proposed for the recognition part of FLIR(Forwar Looking Infrared)-image-based ATR system. Proposed feature extraction method is "cluster(=set of classes)-based"version of previous fisherfaces method that is known by its robustness to illumination changes in face recognition. Expecially introduced class clustering and cluster-based projection method maximizes the performance of fisherfaces method. Proposed target image classification method is based on the mixture of experts model which consists of RBF-type experts and MLP-type gating networks. Mixture of experts model is well-suited with ATR system because it should recognizee various targets in complexed feature space by variously mixed conditions. In proposed classification method, one expert takes charge of one cluster and the separated structure with experts reduces the complexity of feature space and achieves more accurate local discrimination between classes. Proposed feature extraction and classification method showed distinguished performances in recognition test with customized. FLIR-vehicle-image database. Expecially robustness to pixelwise sensor noise and un-wanted intensity variations was verified by simulation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.4
• /
• pp.302-306
• /
• 2001

Because face Images have many variations(expression, illumination, orientation of face, etc), there has been no popular method which has high recognition rate. To solve this difficulty, data fusion that fuses various information has been studied. But previous research for data fusion fused additional biological informationUingerplint, voice, del with face image. In this paper, cooperative results from several face image recognition modules are fused without using additional biological information. To fuse results from individual face image recognition modules, we use re-defined mass function based on Dempster-Shafer s fusion theory.Experimental results from fusing several face recognition modules are presented, to show that proposed fusion model has better performance than single face recognition module without using additional biological information.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.590-595
• /
• 2004

The shape and size variations of the nanopatterns produced on a positive photoresist using a near-field scanning optical microscope(NSOM) are investigated with respect to the process variables. A cantilever type nanoprobe having a 100nm aperture at the apex of the pyramidal tip is used with the NSOM and a He-Cd laser at a wavelength of 442nm as the illumination source. Patterning characteristics are examined for different laser beam power at the entrance side of the aperture( $P_{in}$ ), scan speed of the piezo stage(V), repeated scanning over the same pattern, and operation modes of the NSOM(DC and AC modes). The pattern size remained almost the same for equal linear energy density. Pattern size decreased for lower laser beam power and greater scan speed, leading to a minimum pattern width of around 50nm at $P_{in}$ =1.2$\mu$W and V=12$\mu$m/. Direct writing of an arbitrary pattern with a line width of about 150nm was demonstrated to verify the feasibility of this technique for nanomask fabrication. Application on high-density data storage using azopolymer is discussed at the end.