• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.10
• /
• pp.1977-1985
• /
• 2007

The character recognition technique is one of the artificial intelligence and has been widely applied in the automated system robot HCI(Human Computer Interaction), etc. This paper introduces the character set and the representative character that can be used in the recognition of the mage ROI. The character codes in this ROI include the digit, symbol, English and Hereat etc. We proposed the efficient multi-classifier structure by combining the small-size classifiers hierarchically. Moreover, we generated each small-size classifiers by delta-bar-delta learning algorithm. We tested the performance with various kinds of images and achieved the accuracy of 99%. The proposed multi-classifier showed the efficiency and the reliability for the mixed character code set.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.9
• /
• pp.1120-1131
• /
• 2016

In this paper, we propose a smoker recognition algorithm, detecting smokers in a video sequence in order to prevent fire accidents. We use description-based method in hierarchical approaches to recognize smoker's activity, the algorithm consists of background subtraction, object detection, event search, event judgement. Background subtraction generates slow-motion and fast-motion foreground image from input image using Gaussian mixture model with two different learning-rate. Then, it extracts object locations in the slow-motion image using chain-rule based contour detection. For each object, face is detected by using Haar-like feature and smoke is detected by reflecting frequency and direction of smoke in fast-motion foreground. Hand movements are detected by motion estimation. The algorithm examines the features in a certain interval and infers that whether the object is a smoker. It robustly can detect a smoker among different objects while achieving real-time performance.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.4
• /
• pp.509-523
• /
• 2005

We are developing a novel framework, PRIDE (PRediction In Dynamic Environments), to perform moving object prediction (MOP) for autonomous ground vehicles. The underlying concept is based upon a multi-resolutional, hierarchical approach which incorporates multiple prediction algorithms into a single, unifying framework. The lower levels of the framework utilize estimation-theoretic short-term predictions while the upper levels utilize a probabilistic prediction approach based on situation recognition with an underlying cost model. The estimation-theoretic short-term prediction is via an extended Kalman filter-based algorithm using sensor data to predict the future location of moving objects with an associated confidence measure. The proposed estimation-theoretic approach does not incorporate a priori knowledge such as road networks and traffic signage and assumes uninfluenced constant trajectory and is thus suited for short-term prediction in both on-road and off-road driving. In this article, we analyze the complementary role played by vehicle kinematic models in such short-term prediction of moving objects. In particular, the importance of vehicle process models and their effect on predicting the positions and orientations of moving objects for autonomous ground vehicle navigation are examined. We present results using field data obtained from different autonomous ground vehicles operating in outdoor environments.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.67-78
• /
• 1996

The purpose of this paper is object recognition even in the presence of occlusion by using generalized Hough transform(GHT). The GHT can be considered as a kind of model based object recognition algorithm and is executed in the following two stages. The first stage is to store the information of the model in the form of R-table (Reference table). The next stage is to identify the existence of the objects in the image by using the R-table. The improved GHT method is proposed for the practical vision system. First, in constructing the R-table, we extracted the partial arc from the portion of the whole object boundary, and this partial arc can be used for constructing the R-table. Also, clustering algorithm is employed for compensating an error arised by digitizing an object image. Second, an efficient method is introduced to avoid Ballard's use of 4-D array which is necessary for estimating position, orientation and scale change of an object. Only 2-D array is enough for recognizing an object. Especially, scale token method is introduced for calculating the scale change which is easily affected by camera zoom. The results of our test show that the improved hierarchical GHT method operates stably in the realistic vision situation, even in the case of object occlusion.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.25-34
• /
• 2020

In this paper, we empirically compare the effectiveness of training models to recognize beauty-related skin disease using supervised deep learning algorithms. Recently, deep learning algorithms are being actively applied for various fields such as industry, education, and medical. For instance, in the medical field, the ability to diagnose cutaneous cancer using deep learning based artificial intelligence has improved to the experts level. However, there are still insufficient cases applied to disease related to skin beauty. This study experimentally compares the effectiveness of identifying beauty-related skin disease by applying deep learning algorithms, considering CNN, ResNet, and SE-ResNet. The experimental results using these training models show that the accuracy of CNN is 71.5% on average, ResNet is 90.6% on average, and SE-ResNet is 95.3% on average. In particular, the SE-ResNet-50 model, which is a SE-ResNet algorithm with 50 hierarchical structures, showed the most effective result for identifying beauty-related skin diseases with an average accuracy of 96.2%. The purpose of this paper is to study effective training and methods of deep learning algorithms in consideration of the identification for beauty-related skin disease. Thus, it will be able to contribute to the development of services used to treat and easy the skin disease.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.251-258
• /
• 2003

A support vector machine (SVM) is supposed to provide a good generalization performance, but the actual performance of a actually implemented SVM is often far from the theoretically expected level. This is largely because the implementation is based on an approximated algorithm, due to the high complexity of time and space. To improve this limitation, we propose ensemble of SVMs by using Bagging (bootstrap aggregating) and Boosting. By a Bagging stage each individual SVM is trained independently using randomly chosen training samples via a bootstrap technique. By a Boosting stage an individual SVM is trained by choosing training samples according to their probability distribution. The probability distribution is updated by the error of independent classifiers, and the process is iterated. After the training stage, they are aggregated to make a collective decision in several ways, such ai majority voting, the LSE(least squares estimation) -based weighting, and double layer hierarchical combining. The simulation results for IRIS data classification, the hand-written digit recognition and Face detection show that the proposed SVM ensembles greatly outperforms a single SVM in terms of classification accuracy.

• Journal of radiological science and technology
• /
• v.26 no.1
• /
• pp.71-82
• /
• 2003

In this paper, I proposed a classifier of liver cirrhotic step using T1-weighted MRI(magnetic resonance imaging) and hierarchical neural network. The data sets for classification of each stage, which were normal, 1type, 2type and 3type, were obtained in Pusan National University Hospital from June 2001 to december 2001. And the number of data was 46. We extracted liver region and nodule region from T1-weighted MR liver image. Then objective interpretation classifier of liver cirrhotic steps in T1-weighted MR liver images. Liver cirrhosis classifier implemented using hierarchical neural network which gray-level analysis and texture feature descriptors to distinguish normal liver and 3 types of liver cirrhosis. Then proposed Neural network classifier teamed through error back-propagation algorithm. A classifying result shows that recognition rate of normal is 100%, 1type is 82.3%, 2type is 86.7%, 3type is 83.7%. The recognition ratio very high, when compared between the result of obtained quantified data to that of doctors decision data and neural network classifier value. If enough data is offered and other parameter is considered, this paper according to we expected that neural network as well as human experts and could be useful as clinical decision support tool for liver cirrhosis patients.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.941-944
• /
• 2009

In this paper, we present a improved algorithm for thinning vein pattern. The vein image scanned using near infra-red is sliced in the horizontality or verticality direction, and then average value is gained from each slice image. Using curvature value changed from average value, search candidate part and extract vein pattern through re-searched candidate part in overlapping area. For the extracted vein pattern connecting, we proposed a DAL method that verify distance, angle and luminosity on pattern before tracking pattern extracted. The proposed improved thinning method is helpful for accurate connecting of vein pattern more than method used distance material in candidate part.

• The Korean Journal of Applied Statistics
• /
• v.35 no.3
• /
• pp.407-419
• /
• 2022

The semiconductor fabrication process is complex and time-consuming. There are sometimes errors in the process, which results in defective die on the wafer bin map (WBM). We can detect the faulty WBM by finding some patterns caused by dies. When one manually seeks the failure on WBM, it takes a long time due to the enormous number of WBMs. We suggest a two-step approach to discover the probable pattern on the WBMs in this paper. The first step is to separate the normal WBMs from the defective WBMs. We adapt a hierarchical clustering for de-noising, which nicely performs this work by wisely tuning the number of minimum points and the cutting height. Once declared as a faulty WBM, then it moves to the next step. In the second step, we classify the patterns among the defective WBMs. For this purpose, we extract features from the WBM. Then machine learning algorithm classifies the pattern. We use a real WBM data set (WM-811K) released by Taiwan semiconductor manufacturing company.