• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.4
• /
• pp.494-499
• /
• 2007

In this paper we realized a system, if a user selects the area of the important parts or the arrangement parts when he reads the books or the papers, which amends, stores and readjusts the characters that are included in the selected area by outputting the characters to the word processor in sequence. If a user selects what he wishes lot with his finger, the system detects the movement of the finger by applying the hand recognition algorithm and recognizes the selected area. The system converts the distance of the width and the length of the selected area to the number of the pulse, and controls the motor to move the camera at the position. After the system scales up/down the zoom to be able to recognize the character and controls the focus to the regulated zoom closely, it controls the focus in detail to get more distinct image by using the difference of the light and darkness. We realize the recognition and editing support system of korean language that converts the obtained images to the document by applying the character recognition algorithm and arrange the important parts.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.610-616
• /
• 2023

In this paper, we implement an unmanned delivery robot system with Robot Operating System(ROS)-based mobile manipulator, and introduce the technologies employed for the system implementation. The robot consists of a mobile robot capable of autonomous navigation inside the building using an elevator and a Selective Compliance Assembly Robot Arm(SCARA)-Type manipulator equipped with a vacuum pump. The robot can determines the position and orientation for picking up a package through image segmentation and corner detection using the camera on the manipulator. The proposed system has a user interface implemented to check the delivery status and determine the real-time location of the robot through a web server linked to the application and ROS, and recognizes the shipment and address at the delivery station through You Only Look Once(YOLO) and Optical Character Recognition(OCR). The effectiveness of the system is validated through delivery experiments conducted within a 4-story building.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.1-25
• /
• 2020

In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2008.11a
• /
• pp.305-310
• /
• 2008

A lot of changes are required in a management method of a project because the character of construction projects gets bigger and higher gradually. Especially, for the efficiency of the management method the plans of various viewpoints focused on the construction supply chain field that the technical application of Ubiquitous Technologies such as RFID/USN is being advanced actively are presented. Recently, the introduction of the intelligent equipment which is developed for intelligence of construction site requires the new process model in the construction supply chain management on the construction site. Therefore, this study is to propose the intelligent construction supply chain reference model development in order to provide the guide that the numerous materials for construction could easily be applied in the changed process, as mentioned above, by overcoming the limit of the existing construction supply chain process which is proposed as bar codes and RFID/USN based individual material types and reflecting the change factors like the intelligent equipment of construction supply chain management.

• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.81-96
• /
• 2013

Video information retrieval has become a very important issue because of the explosive increase in video data from Web content development. Meanwhile, content-based video analysis using visual features has been the main source for video information retrieval and browsing. Content in video can be represented with content-based analysis techniques, which can extract various features from audio-visual data such as frames, shots, colors, texture, or shape. Moreover, similarity between videos can be measured through content-based analysis. However, a movie that is one of typical types of video data is organized by story as well as audio-visual data. This causes a semantic gap between significant information recognized by people and information resulting from content-based analysis, when content-based video analysis using only audio-visual data of low level is applied to information retrieval of movie. The reason for this semantic gap is that the story line for a movie is high level information, with relationships in the content that changes as the movie progresses. Information retrieval related to the story line of a movie cannot be executed by only content-based analysis techniques. A formal model is needed, which can determine relationships among movie contents, or track meaning changes, in order to accurately retrieve the story information. Recently, story-based video analysis techniques have emerged using a social network concept for story information retrieval. These approaches represent a story by using the relationships between characters in a movie, but these approaches have problems. First, they do not express dynamic changes in relationships between characters according to story development. Second, they miss profound information, such as emotions indicating the identities and psychological states of the characters. Emotion is essential to understanding a character's motivation, conflict, and resolution. Third, they do not take account of events and background that contribute to the story. As a result, this paper reviews the importance and weaknesses of previous video analysis methods ranging from content-based approaches to story analysis based on social network. Also, we suggest necessary elements, such as character, background, and events, based on narrative structures introduced in the literature. We extract characters' emotional words from the script of the movie Pretty Woman by using the hierarchical attribute of WordNet, which is an extensive English thesaurus. WordNet offers relationships between words (e.g., synonyms, hypernyms, hyponyms, antonyms). We present a method to visualize the emotional pattern of a character over time. Second, a character's inner nature must be predetermined in order to model a character arc that can depict the character's growth and development. To this end, we analyze the amount of the character's dialogue in the script and track the character's inner nature using social network concepts, such as in-degree (incoming links) and out-degree (outgoing links). Additionally, we propose a method that can track a character's inner nature by tracing indices such as degree, in-degree, and out-degree of the character network in a movie through its progression. Finally, the spatial background where characters meet and where events take place is an important element in the story. We take advantage of the movie script to extracting significant spatial background and suggest a scene map describing spatial arrangements and distances in the movie. Important places where main characters first meet or where they stay during long periods of time can be extracted through this scene map. In view of the aforementioned three elements (character, event, background), we extract a variety of information related to the story and evaluate the performance of the proposed method. We can track story information extracted over time and detect a change in the character's emotion or inner nature, spatial movement, and conflicts and resolutions in the story.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1191-1194
• /
• 2004

We describe the development of an interactive aerobic training system using vision-based motion capture and multimedia technology. Unlike the traditional one-way aerobic training on TV, the proposed system allows the virtual trainer to observe and interact with the user in real-time. The system is composed of a web camera connected to a PC watching the user moves. First, the animated character on the screen makes a move, and then instructs the user to follow its movement. The system applies a robust statistical background subtraction method to extract a silhouette of the moving user from the captured video. Subsequently, principal body parts of the extracted silhouette are located using model-based approach. The motion of these body parts is then analyzed and compared with the motion of the animated character. The system provides audio feedback to the user according to the result of the motion comparison. All the animation and video processing run in real-time on a PC-based system with consumer-type camera. This proposed system is a good example of applying vision algorithms and multimedia technology for intelligent interactive home entertainment systems.

• Journal of Korea Game Society
• /
• v.9 no.2
• /
• pp.125-133
• /
• 2009

Game artificial intelligence is usually used to provide intelligent and adjusted game environment for user. Previously, it was used for Non-player character(NPC) playing a role of a company or an enemy through collecting and analyzing a user's behaviour. However, it was just mimicking the user's behavior. This paper introduces a method to change game environment by analyzing a user's game behavior. Game behavior data has been used to understand user's game preference. Also, the user's preference was used to provide more active game environment by reflecting decision of geographical features, items and distribution of NPC. For experiment of the suggested method, we utilized a real 2D action game and confirmed the game environment which changing properly according to the user's game play.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3488-3500
• /
• 2020

At the present time, the economy continues to flourish, and private cars have become the means of choice for most people. Therefore, the license plate recognition technology has become an indispensable part of intelligent transportation, with research and application value. In recent years, the convolution neural network for image classification is an application of deep learning on image processing. This paper proposes a strategy to improve the YOLO model by studying the deep learning convolutional neural network (CNN) and related target detection methods, and combines the OpenCV and TensorFlow frameworks to achieve efficient recognition of license plate characters. The experimental results show that target detection method based on YOLO is beneficial to shorten the training process and achieve a good level of accuracy.

• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.65-77
• /
• 2004

This paper presents a priori and the local font classification method. The font classification uses ascenders, descenders, and serifs extracted from a word image. The gradient features of those sub-images are extracted, and used as an input to a neural network classifier to produce font classification results. The font classification determines 2 font styles (upright or slant), 3 font groups (serif sans-serif or typewriter), and 7-font names (Postscript fonts such as Avant Garde, Helvetica, Bookman, New Century Schoolbook, Palatine, Times, and Courier). The proposed a priori and local font classification method allows an OCR system consisting of various font-specific character segmentation tools and various mono-font character recognizers. Experiments have shown font classification accuracies reach high performance levels of about 95.4 percent even with severely touching characters. The technique developed for tile selected 7 fonts in this paper can be applied to any other fonts.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.3 s.303
• /
• pp.17-28
• /
• 2005

Recently intelligent characters in computer games have been an important element more and more because they continually stimulate gamers' interests. As a typical method for implementing such intelligent characters, neural networks have been used for training action patterns of opponent's characters and game rules. However, some of the game rules can be abruptly changed and action properties of garners in on-line game environments are quite different according to gamers. In this paper, we address how a neural network adapts to those environmental changes. Our adaptation solution includes two components: an individual adaptation mechanism and a group adaptation mechanism. With the individual adaptation algorithm, an intelligent character steadily checks its game score, assesses the environmental change with taking into consideration of the lastly earned scores, and initiates a new learning process when a change is detected. In multi-user games, including massively multiple on-line games, intelligent characters confront diverse opponents that have various action patterns and strategies depending on the gamers controlling the opponents. The group adaptation algorithm controls the birth of intelligent characters to conserve an equilibrium state of a game world by using a genetic algorithm. To show the performance of the proposed schemes, we implement a simple fighting action game and experiment on it with changing game rules and opponent characters' action patterns. The experimental results show that the proposed algorithms are able to make intelligent characters adapt themselves to the change.