Seungbin Moon

An Efficient Hybrid Face Recognition Algorithm Using PCA and GABOR Wavelets

With the rapid development of computers and the increasing, mass use of high-tech mobile devices, vision-based face recognition has advanced significantly. However, it is hard to conclude that the performance of computers surpasses that of humans, as humans have generally exhibited better performance in challenging situations involving occlusion or variations. Motivated by the recognition method of humans who utilize both holistic and local features, we present a computationally efficient hybrid face recognition method that employs dual-stage holistic and local feature-based recognition algorithms. In the first coarse recognition stage, the proposed algorithm utilizes Principal Component Analysis (PCA) to identify a test image. The recognition ends at this stage if the confidence level of the result turns out to be reliable. Otherwise, the algorithm uses this result for filtering out top candidate images with a high degree of similarity, and passes them to the next fine recognition stage where Gabor filters are employed. As is well known, recognizing a face image with Gabor filters is a computationally heavy task. The contribution of our work is in proposing a flexible dual-stage algorithm that enables fast, hybrid face recognition. Experimental tests were performed with the Extended Yale Face Database B to verify the effectiveness and validity of the research, and we obtained better recognition results under illumination variations not only in terms of computation time but also in terms of the recognition rate in comparison to PCA- and Gabor wavelet-based recognition algorithms.

Face and facial expression recognition with an embedded system for human-robot interaction

In this paper, we present an embedded system in which face recognition and facial expression recognition for Human-Robot Interaction are implemented. To detect face with a fast and reliable way, AdaBoost algorithm is used. Then, Principal Component Analysis is applied for recognizing the face. Gabor wavelets are combined with Enhanced Fisher Model for facial expression recognition. Performance of the facial expression recognition reaches to 93%. The embedded system runs on 150MHz and the processing speed is 0.6 frames / second. Experimental result demonstrates that face detection, recognition and facial expression can be implemented with an embedded system for the Human-Robot Interaction.

Summary of recent standardization activities in the field of robotics

This paper summarizes the recent standardization activities in the field of robotics by ISO International Organization for Standardization, IEC International Electrotechnical Commission, OMG Object Management Group, and other organizations. While the standards in industrial robots have been mainly developed by ISO, the standards on the emerging service robots are initiated by many organizations. One of the goals of this paper is to coordinate the efforts among these groups so that more effective standardization activity can be executed. Standardization in the emerging service robots will eventually promote the proliferation of service robot markets in the near future.

Angle measurements for mobile robots with filtering of short-term noise in MEMS gyroscopes

This paper presents a simple, yet very effective filtering method to suppress short-term broadband noise in micro-electro-mechanical system (MEMS) gyros for yaw angle measurement with minimized drift. This method is suitable for autonomous indoor mobile robots that use two low-cost sensors: an inertial one, which uses a gyroscope, and an odometric one, which uses encoders mounted on the vehicle’s wheels. The main idea of the proposed approach is consists of two phases: (1) a threshold filter for translational motions, and (2) a moving average filter for rotational motions to reject the broadband noise component that affects short-term performance. Experimental results with the proposed phased method applied to an Epson XV3500 MEMS gyro demonstrate that it effectively suppresses short-term broadband noise and yields accurate yaw angle with minimized drift.

Portable robotic system for steel H‐beam welding

Steel beam welding at a construction site is challenging due to the increasing thickness of steel members in todays buildings. In order to achieve high quality welding and resolve the problem caused by the shortage of skilled welders, robotic systems are in high demand. We have proposed a practical robotic system for steel beam welding, specifically designed for working on H‐shaped column structures that are known to be the most difficult structures for automation.

Security Techniques for Prevention of Rank Manipulation in Social Tagging Services including Robotic Domains

With smartphone distribution becoming common and robotic applications on the rise, social tagging services for various applications including robotic domains have advanced significantly. Though social tagging plays an important role when users are finding the exact information through web search, reliability and semantic relation between web contents and tags are not considered. Spams are making ill use of this aspect and put irrelevant tags deliberately on contents and induce users to advertise contents when they click items of search results. Therefore, this study proposes a detection method for tag-ranking manipulation to solve the problem of the existing methods which cannot guarantee the reliability of tagging. Similarity is measured for ranking the grade of registered tag on the contents, and weighted values of each tag are measured by means of synonym relevance, frequency, and semantic distances between tags. Lastly, experimental evaluation results are provided and its efficiency and accuracy are verified through them.

Performance evaluation method for environment recognition of mobile robot employing video database

It is needed to evaluate how well the robot recognizes its environments while it is moving along the path to perform intended tasks. In general, the behavioral patterns of robot when it encounters sudden obstacles in a given environment may depend upon the obstacle avoidance algorithms that are programmed into the robot. In order to evaluate the performance of the environment recognition, we constructed the video image database sets which are photographed by both color image and depth image. We showed that the proposed performance evaluation method could be utilized effectively in evaluating the recognition performance of a robot.

An Extended DCT Domain Watermarking for Robot Vision against Geometric Image Attacks

With the rapid development of the Internet and the mobile service robot, the digital services are becoming important factors for robots to recognize things in the real world. Advances in computer technology and the risk of copyright infringement have increased in the way that anyone replicates and copies digital media easily. Therefore, ways to prevent and suppress copyright infringement, digital watermarking technologies that insert copyrights information into the work, are being researched. Digital watermark, depending on the actual insert domain, can be categorized into the spatial domain and transform domain. In this paper, we propose an extended DCT domain watermarking for robot vision. The suggested method is by distributing and duplicating watermark images that are including copyright information on the original images. By doing this, it can be strong on geometric image attacks such as partial cutting, resizing, rotating, and so forth. For the success of watermark extraction, invertible process can be used to recover a disfigured image. Experimental results are provided to support these methods, through the process of recombination by complete image pieces.

Minimum-Time Algorithm For Intercepting An Object On The Conveyor Belt By Robot

This paper provides a minimum time algorithm to intercept an object on the conveyor belt by robotic manipulator. The goal is that the robot is able to intercept objects on a conveyor line moving at a given speed in minimum time. In order to formulate the problem, we introduce the robot and object arrival time functions, and conclude that the optimal point occurs at the intersection of these two functions. The search algorithm for finding the intersection point between the robot and object arrival time functions are also presented to find the optimal point in real-time.

Face representation method using pixel-to-vertex map (PVM) for 3d model based face recognition

3D model based approach for face recognition has been spotlighted as a robust solution under variant conditions of pose and illumination. Since a generative 3D face model consists of a large number of vertices, a 3D model based face recognition system is generally inefficient in computation time. In this paper, we propose a novel 3D face representation algorithm to reduce the number of vertices and optimize its computation time. Finally, we evaluate the performance of proposed algorithm with the Korean face database collected using a stereo-camera based 3D face capturing device.