• 한국지능시스템학회논문지
• /
• 제25권3호
• /
• pp.254-259
• /
• 2015

본 논문은 BCI(Brain Computer Interface)기반의 정상상태시각유발전위(SSVEP : Steady-State Visual Evoked Potential)를 사용하여 무선 로봇 제어를 위한 시스템을 제안하였다. CPSD(Cross Power Spectral Density)를 사용하여 전극의 신호를 분석하였다. 또한 분류를 위해서 LDA(Linear Discriminant Analysis)와 SVM(Support Vector Machine)을 사용하였다. 그 결과 피험자들의 평균 분류율은 약 70%로 나타났다. 로봇제어의 경우 뇌파의 값을 분류하여 나타난 결과 값으로 로봇이 움직일 수 있도록 구현하였고, 블루투스 통신을 이용하여 로봇제어를 수행하였다.

• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.960-968
• /
• 2018

The mobile visual search service uses a query image to acquire linkage information through pre-constructed DB search. From the standpoint of this purpose, it would be more useful if you could perform a search on a web-based keyword search system instead of a pre-built DB search. In this paper, we propose a representative query extraction algorithm to be used as a keyword on a web-based search system. To do this, we use image classification labels generated by the CNN (Convolutional Neural Network) algorithm based on Deep Learning, which has a remarkable performance in image recognition. In the query extraction algorithm, dictionary meaningful words are extracted using Wikipedia, and hierarchical categories are constructed using WordNet. The performance of the proposed algorithm is evaluated by measuring the system response time.

• 한국정밀공학회지
• /
• 제15권7호
• /
• pp.26-35
• /
• 1998

This paper presents a visual inspection algorithm looking for solder joint defects of IC chips on PCBs (Printed Circuit Boards). In this algorithm, seven features are proposed in order to categorize the solder joints into four classes such as normal, insufficient, excess, and no solder, and optimal back-propagation network is determined by error evaluation which depend on the number of neurons in hidden and out-put layers and selection of the features. In the end, a good accuracy of classification performance, an optimal determination of network structure and the effectiveness of chosen seven features are examined by experiment using proposed inspection algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3383-3397
• /
• 2023

Scene graphs serve as semantic abstractions of images and play a crucial role in enhancing visual comprehension and reasoning. However, the performance of Scene Graph Generation is often compromised when working with biased data in real-world situations. While many existing systems focus on a single stage of learning for both feature extraction and classification, some employ Class-Balancing strategies, such as Re-weighting, Data Resampling, and Transfer Learning from head to tail. In this paper, we propose a novel approach that decouples the feature extraction and classification phases of the scene graph generation process. For feature extraction, we leverage a transformer-based architecture and design an adaptive calibration function specifically for predicate classification. This function enables us to dynamically adjust the classification scores for each predicate category. Additionally, we introduce a Distribution Alignment technique that effectively balances the class distribution after the feature extraction phase reaches a stable state, thereby facilitating the retraining of the classification head. Importantly, our Distribution Alignment strategy is model-independent and does not require additional supervision, making it applicable to a wide range of SGG models. Using the scene graph diagnostic toolkit on Visual Genome and several popular models, we achieved significant improvements over the previous state-of-the-art methods with our model. Compared to the TDE model, our model improved mR@100 by 70.5% for PredCls, by 84.0% for SGCls, and by 97.6% for SGDet tasks.

• 한국멀티미디어학회논문지
• /
• 제23권10호
• /
• pp.1250-1257
• /
• 2020

The early detection of diseases is important in agriculture because diseases are major threats of reducing crop yield for farmers. The shape and color of plant leaf are changed differently according to the disease. So we can detect and estimate the disease by inspecting the visual feature in leaf. This study presents a vision-based leaf classification method for detecting the diseases of tomato crop. ResNet-50 model was used to extract the visual feature in leaf and classify the disease of tomato crop, since the model showed the higher accuracy than the other ResNet models with different depths. We propose a new ensemble approach using several DCNN classifiers that have the same structure but have been trained at different ranges in the DCNN layers. Experimental result achieved accuracy of 97.19% for PlantVillage dataset. It validates that the proposed method effectively classify the disease of tomato crop.

• 한국지능시스템학회논문지
• /
• 제22권4호
• /
• pp.515-520
• /
• 2012

In brain computer interface (BCI) system, the most important part is classification of human thoughts in order to translate into commands. The more accuracy result in classification the system gets, the more effective BCI system is. To increase the quality of BCI system, we proposed to reduce noise and artifact from the recording data to analyzing data. We used auditory stimuli instead of visual ones to eliminate the eye movement, unwanted visual activation, gaze control. We applied independent component analysis (ICA) algorithm to purify the sources which constructed the raw signals. One of the most famous spatial filter in BCI context is common spatial patterns (CSP), which maximize one class while minimize the other by using covariance matrix. ICA and CSP also do the filter job, as a raw filter and refinement, which increase the classification result of linear discriminant analysis (LDA).

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.945-950
• /
• 1990

An automatic visual classification system is introduced which provides for measuring the length and diameter of coilform cores and dividing them into 5 different classed in terms of how far their length be from the desired length. This task is fully automated by controlling two STEP motors and by using image processing techniques. The classification procedure is broken into three logical parts, First, cores in the form of randomly stacked bundle are lined up one by one so as to be well captured by a camera. The second part involves capturing core image. Then, it enters the measuring process. Finally, this machine would retain all the information relating to the length. According to the final result, cores are sent to the corresponding bin. This considerably simplifies the selecting task and facilitates a greatly improved reliablity in precision. The average classifying capability is about 2 pieces per second.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.302-307
• /
• 1990

An automatic visual classification system is introduced which provides for measuring the length and diameter of coilform cores and dividing them into 5 different classes in terms of how far their length be from the desired length. This task is fully automated by controlling two STEP motors and by using image processing techniques. The classification procedure is broken into three logical parts. Fist, cores in the form of randomly stacked bundle are lined up one by one so as to be well captured by a cameras. The second part involves capturing core image. Then, it enters the measuring process. Finally, this machine would retain all tire information relating to the length. According to the final result, cores are sent to the corresponding bin. This considerably simplifies the selecting task and facilitates a greatly improved reliability in precision. The average classifying capability about 2 pieces per second.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2004년도 추계학술발표회 논문집
• /
• pp.251-256
• /
• 2004

The image classification is one of the most important studies in the remote sensing. In general, the MLC(Maximum Likelihood Classification) classification that in consideration of distribution of training information is the most effective way but it produces a bad result when we apply it to actual hyperspectral image with the same classification technique. The purpose of this research is to reveal that which one is the most effective and suitable way of the classification algorithms iii the hyperspectral image classification. To confirm this matter, we apply the MLC classification algorithm which has distribution information and SAM(Spectral Angle Mapper), SFF(Spectral Feature Fitting) algorithm which use average information of the training class to both multispectral image and hyperspectral image. I conclude this result through quantitative and visual analysis using confusion matrix could confirm that SAM and SFF algorithm using of spectral pattern in vector domain is more effective way in the hyperspectral image classification than MLC which considered distribution.

• 한국가스학회지
• /
• 제19권2호
• /
• pp.45-53
• /
• 2015

외관검사공정의 성능을 개선하기 위하여 기존의 자동외관검사장비 및 인간검사원에 추가하여 새로이 나이브 베이즈 분류기를 이용한 공정 구성을 개발하였다. 나이브 베이즈 분류기를 공정에 적용함으로써 불량의 유출 및 인간검사원의 작업량을 동시에 개선할 수 있다. 이때 분류기의 판정기준으로 기존의 MAP 방법 대신 AMPB 방법을 제안하여 적용하였다. 카메라모듈 용 필터 제품을 이용한 실험 결과 유출율 1.14%, 인간검사원 작업량 비율 75.5% 수준에서 공정을 구성하는 것이 가능함을 확인할 수 있었다. 본 연구의 결과는 검사 장비 및 인간이 협업을 하여 수행하는 타 공정 - 가스 누출 탐지 - 등에도 적용될 수 있다는 것에 넓은 범위에서의 의의가 있다.