• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.365-372
• /
• 2022

The accurate object recognition is important for the precise and accurate manipulation. To enhance the recognition performance, we can use various types of sensors. In general, acquired data from sensors have a high sampling rate. So, in the past, the RNN-based model is commonly used to handle and analyze the time-series sensor data. However, the RNN-based model has limitations of excessive parameters. CNN-based model also can be used to analyze time-series input data. However, CNN-based model also has limitations of the small receptive field in early layers. For this reason, when we use a CNN-based model, model architecture should be deeper and heavier to extract useful global features. Thus, traditional methods like RN N -based and CN N -based model needs huge amount of learning parameters. Recently studied result shows that Fast Fourier Convolution (FFC) can overcome the limitations of traditional methods. This operator can extract global features from the first hidden layer, so it can be effectively used for feature extracting of sensor data that have a high sampling rate. In this paper, we propose the algorithm to recognize objects using tactile sensor data and the FFC model. The data was acquired from 11 types of objects to verify our posed model. We collected pressure, current, position data when the gripper grasps the objects by random force. As a result, the accuracy is enhanced from 84.66% to 91.43% when we use the proposed FFC-based model instead of the traditional model.

• Journal of the Korean Institute of Navigation
• /
• v.18 no.3
• /
• pp.31-49
• /
• 1994

In the meantime Korean Insurance Industry has been developed a steady growth under government's political protection. But insurance market seems to be opened unavoidably owing to the liberalization of international trade by the Agreements of UR and the bloc of economy by EC Integration and the Organization of NAFTA. By the above reason, especially, in case of hull insurance, the rate of hull insurance is being instituted as a problem. Accordingly the recognition for the problem like this, in thsi study, explained the major objectives of rate making and described the basic rate making methods that are used in property and liability insurance, and searched the rate making schemes of hull insurance rate of the major nations by comparing method. And as a conclusion, the writer presented several schemes including new rate making scheme of hull insurance rate and the security of statistical data about loss ratio, and the establishment of Korean Hull Insurance Association.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.2
• /
• pp.67-73
• /
• 2005

Recently, the social requirement of personal identification techniques has been increasing. Fingerprint recognition is one of the biometries methods that has been widely used for this requirement. This paper proposes the fingerprint matching algorithm that uses the information of the ridge shapes of minutiae. In which, the data of the ridge shape are expressed in one-dimensional discrete-time signals. In our algorithm, we obtain one-dimensional discrete-time signals for ridge at every minutiae from input and registered fingerprints, and find pairs of minutia which have the similar ridge shape by comparing input fingerprint with registered fingerprint, thereafter we find candidates of rotation angle and moving displacement from the pairs of similar minutia, and obtain the final rotation angle and moving displacement value from those candidates set by using clustering method. After that, we align an input fingerprint by using obtained data, and calculate the matching rate by counting the number of corresponded pairs of minutia within the overlapped area of an input and registered fingerprints. As a result of experiment, false rejection rate(FRR) of $18.0\%$ at false acceptance rate(FAR) of $0.79\%$ is achieved.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.9
• /
• pp.1657-1665
• /
• 2016

Various fields are being researched through Deep Learning using CNN(Convolutional Neural Network) and these researches show excellent performance in the image recognition. In this paper, we provide streamlined GoogLeNet of CNN architecture that is capable of learning a large-scale Korean character database. The experimental data used in this paper is PHD08 that is the large-scale of Korean character database. PHD08 has 2,187 samples for each character and there are 2,350 Korean characters that make total 5,139,450 sample data. As a training result, streamlined GoogLeNet showed over 99% of test accuracy at PHD08. Also, we made additional Korean character data that have fonts that are not in the PHD08 in order to ensure objectivity and we compared the performance of classification between streamlined GoogLeNet and other OCR programs. While other OCR programs showed a classification success rate of 66.95% to 83.16%, streamlined GoogLeNet showed 89.14% of the classification success rate that is higher than other OCR program's rate.

• KIISE Transactions on Computing Practices
• /
• v.21 no.6
• /
• pp.424-429
• /
• 2015

This research proposes a new system for calculating the total amount of coins in an image. The proposed system identified and classified the coins in the image in realtime. The image was obtained using a USB camera. Most previous coin calculation systems only used size information. If the size of an object was incorrectly detected, it caused a misclassification. Especially, in case of the former 10 won, it had high error rate because it was similar in size to the 50 won and 100 won coin. The proposed system combines hue histogram information with size information to reduce errors in the classification process. When we only used size information in the classification experiment of 2,290 coins, the recognition rate was on average about 88.2%. When we combined hue information with size information the recognition rate increased to about 99.3%.

• Journal of Korea Multimedia Society
• /
• v.13 no.2
• /
• pp.216-224
• /
• 2010

A RAM-based Neural Network(RNN) has the advantages of processing speed and hardware implementation. In spite of these advantages, it has a saturation problem, weakness of repeated learning and extract of a generalized pattern. To resolve these problems of RNN, the 3DNS model using cumulative multi discriminator was proposed. But that model does not solve the saturation problem yet. In this paper, we proposed a adaptive weight cumulative neural net(AWCNN) using the adaptive weight neuron (AWN) for solving the saturation problem. The proposed nets improved a recognition rate and the saturation problem of 3DNS. We experimented with the MNIST database of NIST without preprocessing. As a result of experimentations, the AWCNN was 1.5% higher than 3DNS in a recognition rate when all input patterns were used. The recognition rate using generalized patterns was similar to that using all input patterns.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.6
• /
• pp.35-46
• /
• 2011

In this paper, we proposed the method of emotion recognition using staged classification model and Fisher's linear discriminant. By organizing the staged classification model, the proposed method improves the classification rate on the Fisher's feature space with high complexity. The staged classification model is achieved by the successive combining of binary classification model which has simple structure and high performance. On each stage, it forms Fisher's linear discriminant according to the two groups which contain each emotion class, and generates the binary classification model by using Adaboost method on the Fisher's space. Whole learning process is repeatedly performed until all the separations of emotion classes are finished. In experimental results, the proposed method provides about 72% classification rate on 8 classes of emotion and about 93% classification rate on specific 3 classes of emotion.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.3
• /
• pp.16-24
• /
• 2011

The vehicle electronic control system is being developed as the legal and social demand for ensuring driver's safety is rising. The various Driver Assistance Systems with various sensors such as radars, camera, and lasers are in practical use because of the falling price of hardware and the high performance of sensor and processer. In the preceding study of this research, the program was developed to recognize the experiment vehicle's driving lane and the cars nearby or approaching the experiment vehicle throughout the images taken by CCD camera. In addition, the 'dangerous driving analysis program' which is Vision System basis was developed to analyze the cause and consequence of dangerous driving. However, the Vision system developed in the previous studyhad poor recognition rate of lane and vehicles at the time of passing a tunnel, sunrise, or sunset. Therefore, through mounting the brightness response algorithm to the Vision System, the present study is aimed to analyze the causes of driver's dangerous driving clearly by improving the recognition rate of lane and vehicle, regardless of when and where it is.

• Journal of the HCI Society of Korea
• /
• v.1 no.1
• /
• pp.29-36
• /
• 2006

Tactile displays can provide useful information without disturbing others and are particularly useful for people with visual or auditory impairments. They can also complement other displays. In this paper, we present a new vibrotactile display device for wearable, mobile, and ubiquitous computing environments. The proposed vibrotactile device has a $5{\times}5$ array configuration for displaying complex information such as letters, numbers, and haptic patterns as well as simple directional ques and situation awareness alarms. Commercially available coin-type vibration motors are embedded vertically in flexible mounting pads in order to best localize vibrations on the skin. An embedded microprocessor controls the motors sequentially with an advanced tracing mode to increase recognition rate. User studies with the vibrotactile device on the top of the foot show 86.7% recognition rate for alphabet characters after some training. In addition, applying vibrotactile device to driving situation shows 83.9% recognition rate. We also propose some potentially useful application scenarios including Caller Identification for mobile phones and Navigation Aids for GPS systems while driving.

• Journal of Distribution Science
• /
• v.6 no.2
• /
• pp.81-93
• /
• 2008

This paper has analyzed the factors and purchasing places affecting the purchasing caned coffee which is classified into low involvement goods. As the result of research, it was discovered that affected factor has arisen out of distribution or recognition other than satisfaction of goods. Consumers who have low satisfaction level switch but this occasion happen at a much lesser rate than expected and on the contrary, even customers who were lesser satisfied expressed that they would buy the same brand again. Although this paper demonstrates the importance of the distribution and recognition factors (publicity), among other marketing mixes, that play a greater role than the product when purchasing the product, it has not taken the effects of promotion into consideration. In the future, the consequences of promotions should be explored and simultaneously look into how each of the factors influence direct sales and weigh how much impact each factor has.