• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.2
• /
• pp.69-80
• /
• 1999

Recently, social requirements of personal identification techniques are rapidly expanding in a number of new application ares. Especially fingerprint recognition is the most important technology. Fingerprint recognition technologies are well established, proven, cost and legally accepted. Therefore, it has more spot lighted among the any other biometrics technologies. In this paper we propose a new on-line fingerprint recognition algorithm for non-inked type live scanner to fit their increasing of security level under the computing environment. Fingerprint recognition system consists of two distinct structural blocks: feature extraction and feature matching. The main topic in this paper focuses on the feature matching using the fingerprint minutiae (ridge ending and bifurcation). Minutiae matching is composed in the alignment stage and matching stage. Success of optimizing the alignment stage is the key of real-time (on-line) fingerprint recognition. Proposed alignment algorithm using clique shows the strength in the search space optimization and partially incomplete image. We make our own database to get the generality. Using the traditional statistical discriminant analysis, 0.05% false acceptance rate (FAR) at 8.83% false rejection rate (FRR) in 1.55 second average matching speed on a Pentium system have been achieved. This makes it possible to construct high performance fingerprint recognition system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.15-23
• /
• 2017

The person Re-identification is the most challenging part of computer vision due to the significant changes in human pose and background clutter with occlusions. The picture from non-overlapping cameras enhance the difficulty to distinguish some person from the other. To reach a better performance match, most methods use feature selection and distance metrics separately to get discriminative representations and proper distance to describe the similarity between person and kind of ignoring some significant features. This situation has encouraged us to consider a novel method to deal with this problem. In this paper, we proposed an enhanced recurrent neural network with three-tier hierarchical network for person re-identification. Specifically, the proposed recurrent neural network (RNN) model contain an iterative expectation maximum (EM) algorithm and three-tier Hierarchical network to jointly learn both the discriminative features and metrics distance. The iterative EM algorithm can fully use of the feature extraction ability of convolutional neural network (CNN) which is in series before the RNN. By unsupervised learning, the EM framework can change the labels of the patches and train larger datasets. Through the three-tier hierarchical network, the convolutional neural network, recurrent network and pooling layer can jointly be a feature extractor to better train the network. The experimental result shows that comparing with other researchers' approaches in this field, this method also can get a competitive accuracy. The influence of different component of this method will be analyzed and evaluated in the future research.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.375-382
• /
• 2002

Handwritten character recognition is classified into on-line handwritten character recognition and off-line handwritten character recognition. On-line handwritten character recognition has made a remarkable outcome compared to off-line hacdwritten character recognition. This method can acquire the dynamic written information such as the writing order and the position of a stroke by means of pen-based electronic input device such as a tablet board. On the contrary, Any dynamic information can not be acquired in off-line handwritten character recognition since there are extreme overlapping between consonants and vowels, and heavily noisy images between strokes, which change the recognition performance with the result of the preprocessing. This paper proposes a method that effectively extracts the stroke including dynamic information of characters for off-line Korean handwritten character recognition. First of all, this method makes improvement and binarization of input handwritten character image as preprocessing procedure using watershed algorithm. The next procedure is extraction of skeleton by using the transformed Lu and Wang's thinning: algorithm, and segment pixel array is extracted by abstracting the feature point of the characters. Then, the vectorization is executed with a maximum permission error method. In the case that a few strokes are bound in a segment, a segment pixel array is divided with two or more segment vectors. In order to reconstruct the extracted segment vector with a complete stroke, the directional component of the vector is mortified by using right-hand writing coordinate system. With combination of segment vectors which are adjacent and can be combined, the reconstruction of complete stroke is made out which is suitable for character recognition. As experimentation, it is verified that the proposed method is suitable for handwritten Korean character recognition.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.5
• /
• pp.407-414
• /
• 2015

Interest points are generally located at the pixels where height changes occur. So, interest points can be the significant pixels for DSM generation, and these have the important role to generate accurate and reliable matching results. Manual operation is widely used to extract the interest points and to match stereo satellite images using these for generating height information, but it causes economic and time consuming problems. Thus, a tie point extraction method using Harris-affine technique and SIFT(Scale Invariant Feature Transform) descriptors was suggested to analyze height information of buildings in this study. Interest points on buildings were extracted by Harris-affine technique, and tie points were collected efficiently by SIFT descriptors, which is invariant for scale. Searching window for each interest points was used, and direction of tie points pairs were considered for more efficient tie point extraction method. Tie point pairs estimated by proposed method was used to analyze height information of buildings. The result had RMSE values less than 2m comparing to the height information estimated by manual method.

• Journal of KIISE:Software and Applications
• /
• v.31 no.1
• /
• pp.54-60
• /
• 2004

Face recognition is one of the problems to be solved by appearance based matching technique. However, the appearance of face image is very sensitive to variation in illumination. One of the easiest ways for better performance is to collect more training samples acquired under variable lightings but it is not practical in real world. ]:n object recognition, it is desirable to focus on feature extraction or normalization technique rather than focus on classifier. This paper presents a simple approach to normalization of faces subject to directional illumination. This is one of the significant issues that cause error in the face recognition process. The proposed method, ICR(illumination Compensation based on Multiple Linear Regression), is to find the plane that best fits the intensity distribution of the face image using the multiple linear regression, then use this plane to normalize the face image. The advantages of our method are simple and practical. The planar approximation of a face image is mathematically defined by the simple linear model. We provide experimental results to demonstrate the performance of the proposed ICR method on public face databases and our database. The experimental results show a significant improvement of the recognition accuracy.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.6
• /
• pp.81-89
• /
• 2004

In this paper, we compare face recognition rate by PCA algorithm using distance change and embedded data being input left side and right side image in stereo images. The proposed method detects face region from RGB color space to YCbCr color space. Also, The extracted face image's scale up/down according to distance change and extracts more robust face region. The proposed method through an experiment could establish standard distance (100cm) in distance about 30∼200cm, and get 99.05% (100cm) as an average recognition result by scale change. The definition of super state is specification region in normalized size (92${\times}$112), and the embedded data extracts the inner factor of defined super state, achieved face recognition through PCA algorithm. The orignal images can receive specification data in limited image's size (92${\times}$112) because embedded data to do learning not that do all learning, in image of 92${\times}$112 size averagely 99.05%, shows face recognition rate of test 1 99.05%, test 2 98.93%, test 3 98.54%, test 4 97.85%. Therefore, the proposed method through an experiment showed that if apply distance change rate could get high recognition rate, and the processing speed improved as well as reduce face information.

• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.455-461
• /
• 2021

Cardiomegaly is one of the most common diseases seen on chest X-rays, but if it is not detected early, it can cause serious complications. In view of this, in recent years, many researches on image analysis in which deep learning algorithms using artificial intelligence are applied to medical care have been conducted with the development of various science and technology fields. In this paper, we would like to evaluate whether the Inception V3 deep learning model is a useful model for the classification of Cardiomegaly using chest X-ray images. For the images used, a total of 1026 chest X-ray images of patients diagnosed with normal heart and those diagnosed with Cardiomegaly in Kyungpook National University Hospital were used. As a result of the experiment, the classification accuracy and loss of the Inception V3 deep learning model according to the presence or absence of Cardiomegaly were 96.0% and 0.22%, respectively. From the research results, it was found that the Inception V3 deep learning model is an excellent deep learning model for feature extraction and classification of chest image data. The Inception V3 deep learning model is considered to be a useful deep learning model for classification of chest diseases, and if such excellent research results are obtained by conducting research using a little more variety of medical image data, I think it will be great help for doctor's diagnosis in future.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.1-12
• /
• 2005

Image registration is a process to establish the spatial correspondence between images of the same scene, which are acquired at different view points, at different times, or by different sensors. This paper presents a new algorithm for robust registration of the images acquired by multiple sensors having different modalities; the EO (electro-optic) and IR(infrared) ones in the paper. The two feature-based and intensity-based approaches are usually possible for image registration. In the former selection of accurate common features is crucial for high performance, but features in the EO image are often not the same as those in the R image. Hence, this approach is inadequate to register the E0/IR images. In the latter normalized mutual Information (nHr) has been widely used as a similarity measure due to its high accuracy and robustness, and NMI-based image registration methods assume that statistical correlation between two images should be global. Unfortunately, since we find out that EO and IR images don't often satisfy this assumption, registration accuracy is not high enough to apply to some applications. In this paper, we propose a two-stage NMI-based registration method based on the analysis of statistical correlation between E0/1R images. In the first stage, for robust registration, we propose two preprocessing schemes: extraction of statistically correlated regions (ESCR) and enhancement of statistical correlation by filtering (ESCF). For each image, ESCR automatically extracts the regions that are highly correlated to the corresponding regions in the other image. And ESCF adaptively filters out each image to enhance statistical correlation between them. In the second stage, two output images are registered by using NMI-based algorithm. The proposed method provides prospective results for various E0/1R sensor image pairs in terms of accuracy, robustness, and speed.

• 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.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.2
• /
• pp.64-70
• /
• 2011

Portable artificial electronic nose (E-nose) system suffers from noisy fluctuation in surroundings such as temperature, vapor concentration, and gas flow, because its measuring condition is not controled precisely as in the laboratory. It is important to develop a simple and robust vapor recognition technique applicable to this uncontrolled measurement, especially for the portable measuring and diagnostic system which are expanding its area with the improvements in micro bio sensor technology. This study used a PDA-based portable E-nose to collect the uncontrolled vapor measurement signals, and applied the image matching algorithm developed in the previous study on the measured signal to verify its robustness and improved accuracy in portable vapor recognition. The results showed not only its consistent performance under noisy fluctuation in the portable measurement signal, but also an advanced recognition accuracy for 2 similar vapor species which have been hard to discriminate with the conventional maximum sensitivity feature extraction method. The proposed method can be easily applied to the data processing of the ubiquitous sensor network (USN) which are usually exposed to various operating conditions. Furthermore, it will greatly help to realize portable medical diagnostic and environment monitoring system with its robust performance and high accuracy.