• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.547-550
• /
• 2009

The object recognition mechanism of human being is not well understood yet. On research of animal experiment using an ape, however, neurons that respond to simple shape (e.g. circle, triangle, square and so on) were found. And Hypothesis has been set up as human being may recognize object as combination of such simple shapes. That mechanism is called Figure Alphabet Hypothesis, and those simple shapes are called Figure Alphabet. As one way to research object recognition algorithm, we focused attention to this Figure Alphabet Hypothesis. Getting idea from it, we proposed the feature extraction algorithm for object recognition. In this paper, we described recognition of binarized images of multifont alphabet characters by the recognition model which combined three-layered neural network in the feature extraction algorithm. First of all, we calculated the difference between the learning image data set and the template by the feature extraction algorithm. The computed finite difference is a feature quantity of the feature extraction algorithm. We had it input the feature quantity to the neural network model and learn by backpropagation (BP method). We had the recognition model recognize the unknown image data set and found the correct answer rate. To estimate the performance of the contriving recognition model, we had the unknown image data set recognized by a conventional neural network. As a result, the contriving recognition model showed a higher correct answer rate than a conventional neural network model. Therefore the validity of the contriving recognition model could be proved. We'll plan the research a recognition of natural image by the contriving recognition model in the future.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.132-134
• /
• 2006

To improve equipment throughput and device yield, a malfunction in plasma equipment should be accurately diagnosed. A recognition model for plasma diagnosis was constructed by applying neural network to scanning electron microscope (SEM) image of plasma-etched patterns. The experimental data were collected from a plasma etching of tungsten thin films. Faults in plasma were generated by simulating a variation in process parameters. Feature vectors were obtained by applying direct and wavelet techniques to SEM Images. The wavelet techniques generated three feature vectors composed of detailed components. The diagnosis models constructed were evaluated in terms of the recognition accuracy. The direct technique yielded much smaller recognition accuracy with respect to the wavelet technique. The improvement was about 82%. This demonstrates that the direct method is more effective in constructing a neural network model of SEM profile information.

• 한국컴퓨터정보학회논문지
• /
• 제10권4호
• /
• pp.17-27
• /
• 2005

본 논문에서는 문자인식과 복원을 위한 신경회로망 시스템을 제안한다. 제안하는 시스템은 인식부와 연상부로 구성되었다. 인식부에서는 ART 신경회로망의 인식성능을 개선하기 위해 불필요한 하향틀의 생성과 변화를 제한하여 효과적인 패턴인식이 가능한 모델을 제안하였다. 또한, 한글의 구조적인 특징을 능동적으로 적용할 수 있게 구성된 위치특징 추출 알고리즘을 적용하였다. 연상부에서는 Hopfield 신경회로망으로, 입력된 이미지 패턴의 복원이 가능한 모델을 구성하였다. 제안하는 시스템은 그 성능을 확인하기 위해 각 부분별 실험을 하였다. 그 결과 인식율이 개선되고 복원이 가능함을 보였다.

• Journal of information and communication convergence engineering
• /
• 제16권3호
• /
• pp.160-165
• /
• 2018

This paper designed and developed the image processing system of integrating feature extraction and matching by using convolutional neural network (CNN), rather than relying on the simple method of processing feature extraction and matching separately in the image processing of conventional image recognition system. To implement it, the proposed system enables CNN to operate and analyze the performance of conventional image processing system. This system extracts the features of an image using CNN and then learns them by the neural network. The proposed system showed 84% accuracy of recognition. The proposed system is a model of recognizing learned images by deep learning. Therefore, it can run in batch and work easily under any platform (including embedded platform) that can read all kinds of files anytime. Also, it does not require the implementing of feature extraction algorithm and matching algorithm therefore it can save time and it is efficient. As a result, it can be widely used as an image recognition program.

• 한국지능시스템학회논문지
• /
• 제2권3호
• /
• pp.50-57
• /
• 1992

Neural networks have become more popular recently and are now being applied to numerous fiedls. One of the major applications of neural networks is image recognition. Various image recognition system have been proposed so far, but there is no definite solution yet. In this paper, we propose a design of Fuzzy Neural Network Image Recognizer(FNNIR). Our model uses a fuzzy neural network model, named SONN[KIM90]. This model returns the information of the number of clusters and cluster and cluster center values for a given image data ste. Unlike the well-kinwn backpropagation technique, we do not need retraining for new data. Our newly designed image recongitionsystem FNNIR that uses fuzzy merger is proposed and experimented for a sample color image.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.977-985
• /
• 2020

Aiming at the problem of complex feature extraction and low accuracy in human action recognition, this paper proposed a network structure combining batch normalization algorithm with GoogLeNet network model. Applying Batch Normalization idea in the field of image classification to action recognition field, it improved the algorithm by normalizing the network input training sample by mini-batch. For convolutional network, RGB image was the spatial input, and stacked optical flows was the temporal input. Then, it fused the spatio-temporal networks to get the final action recognition result. It trained and evaluated the architecture on the standard video actions benchmarks of UCF101 and HMDB51, which achieved the accuracy of 93.42% and 67.82%. The results show that the improved convolutional neural network has a significant improvement in improving the recognition rate and has obvious advantages in action recognition.

• International Journal of Internet, Broadcasting and Communication
• /
• 제13권1호
• /
• pp.210-218
• /
• 2021

CNN (Convolutional Neural Network), a type of deep learning algorithm, is a type of artificial neural network used to analyze visual images. In deep learning, it is classified as a deep neural network and is most commonly used for visual image analysis. Accordingly, an AI autonomous driving model was constructed through real-time image processing, and a crosswalk image of a road was used as an obstacle. In this paper, we proposed a low-cost model that can actually implement autonomous driving based on the CNN model. The most well-known deep neural network technique for autonomous driving is investigated and an end-to-end model is applied. In particular, it was shown that training and self-driving on a simulated road is possible through a practical approach to realizing lane detection and keeping.

• International journal of advanced smart convergence
• /
• 제5권3호
• /
• pp.1-7
• /
• 2016

In existing Convolutional Neural Network (CNNs) for object recognition task, there are only few efforts known to reduce the noises from the images. Both convolution and pooling layers perform the features extraction without considering the noises of the input image, treating all pixels equally important. In computer vision field, there has been a study to weight a pixel importance. Seam carving resizes an image by sacrificing the least important pixels, leaving only the most important ones. We propose a new way to combine seam carving approach with current existing CNN model for object recognition task. We attempt to remove the noises or the "unimportant" pixels in the image before doing convolution and pooling, in order to get better feature representatives. Our model shows promising result with CIFAR-10 dataset.

• International Journal of Advanced Culture Technology
• /
• 제7권4호
• /
• pp.327-333
• /
• 2019

Wind speed data constitute important weather information for aircrafts flying at low altitudes, such as drones. Currently, the accuracy of low altitude wind predictions is much lower than that of high-altitude wind predictions. Deep neural networks are proposed in this study as a method to improve wind speed forecast information. Deep neural networks mimic the learning process of the interactions among neurons in the brain, and it is used in various fields, such as recognition of image, sound, and texts, image and natural language processing, and pattern recognition in time-series. In this study, the deep neural network model is constructed using the wind prediction values generated by the numerical model as an input to improve the wind speed forecasts. Using the ground wind speed forecast data collected at the Boseong Meteorological Observation Tower, wind speed forecast values obtained by the numerical model are compared with those obtained by the model proposed in this study for the verification of the validity and compatibility of the proposed model.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.128-132
• /
• 2023

Recently, with the development of deep learning technology, research on pedestrian attribute recognition technology using deep neural networks has been actively conducted. Existing pedestrian attribute recognition techniques can be obtained in such a way as global-based, regional-area-based, visual attention-based, sequential prediction-based, and newly designed loss function-based, depending on how pedestrian attributes are detected. It is known that the performance of these pedestrian attribute recognition technologies varies greatly depending on the type of backbone network that constitutes the deep neural networks model. Therefore, in this paper, several backbone networks are applied to the baseline pedestrian attribute recognition model and the performance changes of the model are analyzed. In this paper, the analysis is conducted using Resnet34, Resnet50, Resnet101, Swin-tiny, and Swinv2-tiny, which are representative backbone networks used in the fields of image classification, object detection, etc. Furthermore, this paper analyzes the change in time complexity when inferencing each backbone network using a CPU and a GPU.