• 대한전자공학회논문지SP
• /
• 제48권4호
• /
• pp.116-128
• /
• 2011

본 논문에서는 기존의 방법에 비해서 사용되는 메모리의 증가가 없이, 혹은 메모리의 증가를 최소화하는 영상 메모리의 회전 변환 기법을 개발하여 얼굴 회전 변화에 강인한 고성능 실시간 얼굴 검출 엔진 구조를 제안하였으며 FPGA 구현을 통하여 제안 구조의 타당성을 검증하였다. 고성능 얼굴 검출을 위해 기존에 사용하던 조명 변화에 강인한 MCT(Modified Census Transform) 변환 기법과 최적화된 학습데이터 생성을 위한 Adaboost 학습 기법 이외에 얼굴 회전 변환에 강인함을 위한 영상 회전 기법을 이용하였다. 제안한 하드웨어 구조는 색좌표 변환부, 잡음 제거부, 메모리 인터페이스부, 영상 회전부, 크기 조정부, MCT 생성부, 얼굴 후보 검출부/ 신뢰도 비교부, 좌표 재조정부, 데이터 검증부, 검출 결과 표시부/컬러 기반 검출 결과 표시부로 구성되어있다. 구현 및 검증을 위해 Virtex5 LX330 FPGA 보드와 QVGA급 CMOS 카메라, LCD Display를 이용하였으며, 다양한 실생활 환경 및 얼굴 검출 표준 데이터베이스에 대해서 뛰어난 성능을 나타냄을 검증하였다. 결과적으로 실생활 환경에서 초당 60프레임 이상의 속도로 실시간 처리가 가능하며, 조명 변화 및 얼굴 회전 변화에 강인하고, 동시에 32개의 다양한 크기의 얼굴 검출이 가능한 고성능 실시간 얼굴 검출 엔진을 개발하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2809-2821
• /
• 2023

Effective recommendation of similar business groups is a critical factor in obtaining market information for companies. In this study, we propose a novel method for enhancing similar business group recommendation by incorporating derivative criteria and web crawling. We use employment announcements, employment incentives, and corporate vocational training information to derive additional criteria for similar business group selection. Web crawling is employed to collect data related to the derived criteria from 'credit jobs' and 'worknet' sites. We compare the efficiency of different datasets and machine learning methods, including XGBoost, LGBM, Adaboost, Linear Regression, K-NN, and SVM. The proposed model extracts derivatives that reflect the financial and scale characteristics of the company, which are then incorporated into a new set of recommendation criteria. Similar business groups are selected using a Euclidean distance-based model. Our experimental results show that the proposed method improves the accuracy of similar business group recommendation. Overall, this study demonstrates the potential of incorporating derivative criteria and web crawling to enhance similar business group recommendation and obtain market information more efficiently.

• Computers and Concrete
• /
• 제32권3호
• /
• pp.233-246
• /
• 2023

Accurate prediction of concrete compressive strength can minimize the need for extensive, time-consuming, and costly mixture optimization testing and analysis. This study attempts to enhance the prediction accuracy of compressive strength using stacking ensemble machine learning (ML) with feature engineering techniques. Seven alternative ML models of increasing complexity were implemented and compared, including linear regression, SVM, decision tree, multiple layer perceptron, random forest, Xgboost and Adaboost. To further improve the prediction accuracy, a ML pipeline was proposed in which the feature engineering technique was implemented, and a two-layer stacked model was developed. The k-fold cross-validation approach was employed to optimize model parameters and train the stacked model. The stacked model showed superior performance in predicting concrete compressive strength with a correlation of determination (R²) of 0.985. Feature (i.e., variable) importance was determined to demonstrate how useful the synthetic features are in prediction and provide better interpretability of the data and the model. The methodology in this study promotes a more thorough assessment of alternative ML algorithms and rather than focusing on any single ML model type for concrete compressive strength prediction.

• 제어로봇시스템학회논문지
• /
• 제21권12호
• /
• pp.1109-1114
• /
• 2015

This paper presents an improved learning-based visual inspection method for auto parts inspection in severe lighting changes. Automobile sunroof frames are produced automatically by robots in most production lines. In the sunroof frame manufacturing process, there is a quality problem with some parts such as volts are missed. Instead of manual sampling inspection using some mechanical jig instruments, a learning-based machine vision system was proposed in the previous research[1]. But, in applying the actual sunroof frame production process, the inspection accuracy of the proposed vision system is much lowered because of severe illumination changes. In order to overcome this capricious environment, some selective feature vectors and cascade classifiers are used for each auto parts. And we are able to improve the inspection accuracy through the re-learning concept for the misclassified data. The effectiveness of the proposed visual inspection method is verified through sufficient experiments in a real sunroof production line.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 춘계학술발표대회
• /
• pp.633-635
• /
• 2016

Convolutional Networks (ConvNets) are powerful models that learn hierarchies of visual features, which could also be used to obtain image representations for transfer learning. The basic pipeline for transfer learning is to first train a ConvNet on a large dataset (source task) and then use feed-forward units activation of the trained ConvNet as image representation for smaller datasets (target task). Our key contribution is to demonstrate superior performance of multiple ConvNet layer features over single ConvNet layer features. Combining multiple ConvNet layer features will result in more complex feature space with some features being repetitive. This requires some form of feature selection. We use AdaBoost with single stumps to implicitly select only distinct features that are useful towards classification from concatenated ConvNet features. Experimental results show that using multiple ConvNet layer activation features instead of single ConvNet layer features consistently will produce superior performance. Improvements becomes significant as we increase the distance between source task and the target task.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2014년도 하계학술대회
• /
• pp.254-257
• /
• 2014

최근 얼굴 인식 기술과 하드웨어의 빠른 발전으로 인해 실시간 얼굴 검출이 가능한 다양한 어플리케이션이 제시되고 있다. 특히 네트워크의 발달과 영상 장비의 저 비용화로 IP 기반의 네트워크 감시 카메라와 얼굴 검출 기술을 이용한 스마트 감시 카메라의 요구와 저장된 감시카메라의 영상에서 얼굴 검출을 할 수 있는 스마트 감시 시스템의 요구가 증대되고 있다. 그러나 대부분의 감시 시스템은 네트워크 대역폭과 저장 용량을 감소시키기 위하여 영상을 압축하고 있다. 압축된 영상을 전부 디코딩 하고 모든 프레임에서 얼굴 검출을 하는 것은 시스템 성능 요구사항을 증대시키므로 압축된 영상을 이용한 빠른 얼굴 검출기법이 요구되고 있다. 본 논문은 기존의 Haar like features와 adaboost 학습기 등의 고속화된 얼굴 검출 알고리즘과 모션정보를 이용한 프레임 저감기법을 이용하여 압축된 프레임에서 고속으로 얼굴검출을 하는 방법을 제시하고 방송 응용분야에 대해 논의 하고자 한다.

• 제어로봇시스템학회논문지
• /
• 제19권12호
• /
• pp.1081-1088
• /
• 2013

Hyperspectral cameras acquire reflectance values at many different wavelength bands. Dimensions tend to increase because spectral information is stored in each pixel. Several attempts have been made to reduce dimensional problems such as the feature selection using Adaboost and dimension reduction using the Simulated Annealing technique. We propose a novel material detection method that consists of four steps: feature band selection, feature extraction, SVM (Support Vector Machine) learning, and target and specific region detection. It is a combination of the band ratio method and Simulated Annealing algorithm based on detection rate. The experimental results validate the effectiveness of the proposed feature selection and band ratio method.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2013년도 추계학술발표대회
• /
• pp.9-11
• /
• 2013

본 논문에서는 귀의 형태와 색을 통해서 질병을 자가진단 후 귀의 특정 부위를 자극하는 이침요법을 위한 시술 보조 시스템을 제안한다. 제안 시스템은 피시술자의 귀의 이미지 정보와 질병에 대한 정보를 처리하여 이침을 위한 혈자리를 귀 이미지에 표시해 주는 시스템을 구현하였다. 특히 귀를 인식하는 부분에 있어서, Haar-like feature와 Adaboost알고리즘을 사용하는 OpenCV내의 함수를 사용하였고 인식된 귀영역을 그리드 영역으로 나누고 질병에 대한 사전 정보에 따라서 그리드 영역내의 이침혈자리 시스템을 표시하는 시스템으로 구성하였다.

• 제어로봇시스템학회논문지
• /
• 제15권5호
• /
• pp.457-464
• /
• 2009

The weak classifier of AdaBoost algorithm is a central classification element that uses a single criterion separating positive and negative learning candidates. Finding the best criterion to separate two feature distributions influences learning capacity of the algorithm. A common way to classify the distributions is to use the mean value of the features. However, positive and negative distributions of Haar-like feature as an image descriptor are hard to classify by a single threshold. The poor classification ability of the single threshold also increases the number of boosting operations, and finally results in a poor classifier. This paper proposes a weak classifier that uses multiple criterions by adding a probabilistic criterion of the positive candidate distribution with the conventional mean classifier: the positive distribution has low variation and the values are closer to the mean while the negative distribution has large variation and values are widely spread. The difference in the variance for the positive and negative distributions is used as an additional criterion. In the learning procedure, we use a new classifier that provides a better classifier between them by selective switching between the mean and standard deviation. We call this new type of combined classifier the "Mixed Weak Classifier". The proposed weak classifier is more robust than the mean classifier alone and decreases the number of boosting operations to be converged.

• 반도체디스플레이기술학회지
• /
• 제14권2호
• /
• pp.29-34
• /
• 2015

Traffic lights are common in cities and are important cues for the path planning of intelligent vehicles. In this paper, we propose a robust and efficient algorithm for recognizing traffic lights from video sequences captured by a low cost off-the-shelf camera. Instead of using color information for recognizing traffic lights, a shape based approach is adopted. In learning and detection phase, Histogram of Oriented Gradients (HOG) feature is used and a cascade classifier based on Adaboost algorithm is adopted as the main classifier for locating traffic lights. To decide the color of the traffic light, a technique based on histogram analysis in HSV color space is utilized. Experimental results on several video sequences from typical urban environment prove the effectiveness of the proposed algorithm.