• Journal of the Korea Society of Computer and Information
• /
• v.13 no.4
• /
• pp.51-58
• /
• 2008

In this paper, we propose a place modeling based on the distribution of scale-invariant features, and a place recognition method that recognizes places by comparing the place model in a database with the extracted features from input data. The proposed method is based on the assumption that every place can be represented by unique feature distributions that are distinguishable from others. The proposed method uses global information of each place where one place is represented by one distribution model. Therefore, the main contribution of the proposed method is that the time cost corresponding to the increase of the number of places grows linearly without increasing exponentially. For the performance evaluation of the proposed method, the different number of frames and the different number of features are used, respectively. Empirical results illustrate that our approach achieves better performance in space and time cost comparing to other approaches. We expect that the Proposed method is applicable to many ubiquitous systems such as robot navigation, vision system for blind people, wearable computing, and so on.

• Journal of KIISE
• /
• v.41 no.11
• /
• pp.927-934
• /
• 2014

In this paper, we propose an effective method for recognizing daily human activities from a stream of three dimensional body poses, which can be obtained by using Kinect-like RGB-D sensors. The body pose data provided by Kinect SDK or OpenNI may suffer from both the view variance problem and the scale variance problem, since they are represented in the 3D Cartesian coordinate system, the origin of which is located on the center of Kinect. In order to resolve the problem and get the view-invariant and scale-invariant features, we transform the pose data into the spherical coordinate system of which the origin is placed on the center of the subject's hip, and then perform on them the scale normalization using the length of the subject's arm. In order to represent effectively complex internal structures of high-level daily activities, we utilize Hidden state Conditional Random Field (HCRF), which is one of probabilistic graphical models. Through various experiments using two different datasets, KAD-70 and CAD-60, we showed the high performance of our method and the implementation system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• pp.2881-2894
• /
• 2014

In complicated environment, context information plays an important role in image segmentation/labeling. The recently proposed auto-context algorithm is one of the effective context-based methods. However, the standard auto-context approach samples the context locations utilizing a fixed radius sequence, which is sensitive to large scale-change of objects. In this paper, we present a scale invariant auto-context (SIAC) algorithm which is an improved version of the auto-context algorithm. In order to achieve scale-invariance, we try to approximate the optimal scale for the image in an iterative way and adopt the corresponding optimal radius sequence for context location sampling, both in training and testing. In each iteration of the proposed SIAC algorithm, we use the current classification map to estimate the image scale, and the corresponding radius sequence is then used for choosing context locations. The algorithm iteratively updates the classification maps, as well as the image scales, until convergence. We demonstrate the SIAC algorithm on several image segmentation/labeling tasks. The results demonstrate improvement over the standard auto-context algorithm when large scale-change of objects exists.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.7B
• /
• pp.1361-1369
• /
• 1999

A hit-miss transform(HMT) using modified synthetic structuring elements(SEs) for distortion-invariant recognition of multiple objects is proposed. A fundamental problem in an HMT is the determination of the optimal SE needed to improve the false alarm rate, and detect distorted objects with various shapes. The proposed synthetic methods of SE provide good solutions against this problem. One is the multistage synthesis of each true class SE using only set theory, and the other is the multistage synthesis of each true class and false class SE using set theory and SDF(synthetic discriminant function) synthesis method. Simulation results show the proposed methods can be used for the recognition of distorted intraclass objects and the discrimination of similar interclass objects.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.1
• /
• pp.132-144
• /
• 1997

The rotation-invariant pattern recognition filter using circular harmonic function of the wavelet transforme dsreference image by morlet, mexican-hat, and haar wavelt function is proposed. The rotated reference images, the images sililar to the reference image, and the images which are added by random noise are used for the inpt images, and in case of the input images with random noise, they are applied to the recognition after removing the random noise by the transformed moving average method with proper thresholding value and window size. The proposed optical wavelet circular harmonic matched filter (WCHMF) is a type of the matche dfilter, so that it can be applied to the 4f vander lugt optical correlation system. SNR and discrimination capability of the proposed filter are compared with those of the conventional HF, the POCHF, and the BPOCHF. The proper wavelet function for the reference image used in this paper is achieved by applying morlet, mexican-hat, and harr wavelet function ot the proposed filter, and the proposed filter has good SNR and discrimination capability with rotation-invariance in case of the morlet wavelet function.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.35D no.3
• /
• pp.63-69
• /
• 1998

In this paper, a new input method is proposed to improve shift-invariant property of a photorefractive correlator andwe implemented real-time optical pattern recognition system using it. In the conventional photorefractive correlator, it is vrey difficult to satisfy the Bragg condition in the pattern recognition process. So, correlation peak is decreased heavily for the shift of input image. If a liquid crystal television(LCTV) without an anlyzer is used as input device, we can get the correlation result regardless of shift of input image because beam path is not changed during storage of holographic filter and correlation process. Also recording time of a holographic matched filter in photorefractive crystal is reduced and the correlation peak is increased because incident beam on the LCTV is transmitted completely. Therefore total optical efficiency is improved. We compared and analyzed the correlation results of proposed photorefractive correlator by computer simulation and optical experiment. We used a BaTiO$_{3}$ single crystal which has high diffraction efficiency in optical experiment.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.11
• /
• pp.1393-1404
• /
• 1995

For the factory automation(FA) of production or assembly lines, computer vision techniques have been widely used for the recognition and position-control of objects. In this application, it is very important to analyze characteristic features of each object and to find an efficient matching algorithm using the selected features. If the object has regular or homogeneous patterns, the problem is relatively simple. However, If the object is shifted or rotated, and if the depth of the input visual system is not fixed, the problem becomes very complicated. Also, in order to understand and recognize objects with concentric noise patterns, it is more effective to use feature-information represented in polar coordinates than in cartesian coordinates. In this paper, an algorithm for the recognition of objects with concentric circular noise-patterns is proposed. And position-conrtol information is calculated with the matching result. First, a filtering algorithm for eliminating concentric noise patterns is proposed to obtain concentric-feature patterns. Then a shift, rotation and scale invariant alogrithm is proposed for the recognition and position-control of objects uusing invariant feature information. Experimental results indicate the effectiveness of the proposed alogrithm.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1147-1155
• /
• 2005

This paper deals with Iris recognition as one of biometric techniques which is applied to identify a person using his/her behavior or congenital characteristics. The Iris of a human eye has a texture that is unique and time invariant for each individual. First, we obtain the feature vector from the 2D Iris pattern having a property of size invariant and using the fuzzy LDA which is further through four types of 2D Gabor wavelet. At the recognition process, we compute the similarity measure based on the correlation values. Here, since we use four different matching values obtained from four different directional Gabor wavelet and select the maximum value, it is possible to minimize the recognition error rate. To show the usefulness of the proposed algorithm, we applied it to a biometric database consisting of 300 Iris Patterns extracted from 50 subjects and finally got more higher than $90\%$ recognition rate.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.31-39
• /
• 2006

This paper presents a novel approach to real-time recognition of 3D environment and objects for various applications such as intelligent robots, intelligent vehicles, intelligent buildings,..etc. First, we establish the three fundamental principles that humans use for recognizing and interacting with the environment. These principles have led to the development of an integrated approach to real-time 3D recognition and modeling, as follows: 1) It starts with a rapid but approximate characterization of the geometric configuration of workspace by identifying global plane features. 2) It quickly recognizes known objects in environment and replaces them by their models in database based on 3D registration. 3) It models the geometric details the geometric details on the fly adaptively to the need of the given task based on a multi-resolution octree representation. SIFT features with their 3D position data, referred to here as stereo-sis SIFT, are used extensively, together with point clouds, for fast extraction of global plane features, for fast recognition of objects, for fast registration of scenes, as well as for overcoming incomplete and noisy nature of point clouds.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.639-642
• /
• 1999

There exist geometrically invariant relations in single-view images under a specific geometrical structure. This invariance may be utilized for 3D object recognition. Two types of invariants are compared in terms of the robustness to the variation of the feature points. Deviation of the invariant relations are measured by adding random noise to the feature point location. Zhu’s invariant requires six points on adjacent planes having two sets of four coplanar points, whereas the Kaist method requires four coplanar points and two non-coplanar points. Experimental results show that the latter method has the advantage in choosing feature points while suffering from weak robustness to the noise.