Sang-Yong Rhee

Recognition of Natural Hand Gesture by Using HMM

In this paper, we propose a method that gives motion command to a mobile robot to recognize human being`s hand gesture. Former way of the robot-controlling system with the movement of hand used several kinds of pre-arranged gesture, therefore the ordering motion was unnatural. Also it forced people to study the pre-arranged gesture, making it more inconvenient. To solve this problem, there are many researches going on trying to figure out another way to make the machine to recognize the movement of the hand. In this paper, we used third-dimensional camera to obtain the color and depth data, which can be used to search the human hand and recognize its movement based on it. We used HMM method to make the proposed system to perceive the movement, then the observed data transfers to the robot making it to move at the direction where we want it to be.

Motion Control of a Mobile Robot Using Natural Hand Gesture

In this paper, we propose a method that gives motion command to a mobile robot to recognize human being`s hand gesture. Former way of the robot-controlling system with the movement of hand used several kinds of pre-arranged gesture, therefore the ordering motion was unnatural. Also it forced people to study the pre-arranged gesture, making it more inconvenient. To solve this problem, there are many researches going on trying to figure out another way to make the machine to recognize the movement of the hand. In this paper, we used third-dimensional camera to obtain the color and depth data, which can be used to search the human hand and recognize its movement based on it. We used HMM method to make the proposed system to perceive the movement, then the observed data transfers to the robot making it to move at the direction where we want it to be.

Plant Leaf Recognition Using a Convolution Neural Network

There are hundreds of kinds of trees in the natural ecosystem, and it can be very difficult to distinguish between them. Botanists and those who study plants however, are able to identify the type of tree at a glance by using the characteristics of the leaf. Machine learning is used to automatically classify leaf types. Studied extensively in 2012, this is a rapidly growing field based on deep learning. Deep learning is itself a self-learning technique used on large amounts of data, and recent developments in hardware and big data have made this technique more practical. We propose a method to classify leaves using the CNN model, which is often used when applying deep learning to image processing.

Implementation of a personal riding robot with a magnetic compass sensor using a smartphone interface

In the paper, a smartphone-controlled riding robot based on a compass sensor is developed. A smartphone-controlled riding robot system using a magnetic compass sensor makes a riding robot move with heading direction of a smartphone is controlled by a rider. The smartphone-controlled riding robot system gives an interface that is more intuitive than controlled by pushing a button through using a compass sensor. As well, a magnetic compass sensor is used to compensate for the mechanical characteristics of motors mounted on the riding robot. We propose absolute direction method for controlling a riding robot. Experimental results show that the riding robot is conveniently and effectively controlled by the proposed two methods based on magnetic compass sensor.

A Surveillance System for a Farm

This paper proposes a smart surveillance system to be able to identify person concerned or animal in order to prevent the crops stolen. Until now most of surveillance system use a method that records images by surveillance camera or sensor network. This kind of surveillance system has limitation not to identify person or not. The limitation bothers a farm supervisor. To overcome the problem, we detect moving object using codebook and distinguish whether to human or noise by using Adaboost algorithm. Also, this system transmits image information to the supervisor. But even though detected object is person, it is not easily distinguishable whether person concerned or dubious one. That is why because of low resolution of images. To make unnecessary emergency alarm not ring, we adopt smart card technology.

Lane Detection for Parking Violation Assessments

In this study, we propose a method to regulate parking violations using computer vision technology. A still color image of the parked vehicle under question is obtained by a camera mounted on enforcement vehicles. The acquired image is preprocessed through a morphological algorithm and binarized. The vehicle’s shadows are detected from the binarized image, and lanes are identified using the information from the yellow parking lines that are drawn on the load. Whether parking is illegal is determined by the conformity of the lanes and the vehicle’s shadow.

Development of Library Management System based on a Mobile Robot

According to an embodiment of the present invention, a method of a book management system based on mobile robots includes: a robot-based image obtaining step of recording the image of a library through robots moving between bookshelves having multiple books arranged thereon and recognizing the location of the books from the obtained images; a book boundary extracting step of recognizing the labels individually attached to the books obtained in the robot-based image obtaining step and extracting the boundaries of the books for obtaining the labels to compare book information with the database of the library; a class number recognition step of setting an area of interest to find the label area with reference to the boundaries of the books obtained in the book boundary extracting step, extracting color feature values by using a red, green, and blue (RGB) model and a hue, saturation, value (HSV) model in the area of interest, obtaining the area of a billing symbol by checking the location of the label by using the color recognition with the color feature value to recognize the billing symbol by using the optical character recognition through an optical character reading apparatus; and a library management step of comparing the billing symbol of the book recognized in the class number recognition step with the database of the library to detect books located incorrectly and store the result to the database.

Robot control by using multi-modes

In this paper, we propose a method that gives motion command to a mobile robot to recognize human beings hand gesture and speech. We get depth data by using a Kinect sensor, and detect a hand. After recognizing the hand motion by using HMM and speech by using Microsoft speech API, we give commands to the robot.

Web Contents Mining System for Real-Time Monitoring of Opinion Information based on Web 2.0

This paper focuses on the opinion information extraction and analysis system through Web mining that is based on statistics collected from Web contents. That is, users` opinion information which is scattered across several websites can be automatically analyzed and extracted. The system provides the opinion information search service that enables users to search for real-time positive and negative opinions and check their statistics. Also, users can do real-time search and monitoring about other opinion information by putting keywords in the system. Proposing technique proved that the actual performance is excellent by comparison experiment with other techniques. Performance evaluation of function extracting positive/negative opinion information, the performance evaluation applying dynamic window technique and tokenizer technique for multilingual information retrieval, and the performance evaluation of technique extracting exact multilingual phonetic translation are carried out. The experiment with typical movie review sentence and Wikipedia experiment data as object as that applying example is carried out and the result is analyzed.