• Journal of the Korea Convergence Society
• /
• v.9 no.4
• /
• pp.47-55
• /
• 2018

In this paper, we propose a novel face recognition(FR) method that takes advantage of combining weighted deep local features extracted from multiple Deep Convolutional Neural Networks(DCNNs) learned with a set of facial local regions. In the proposed method, the so-called weighed deep local features are generated from multiple DCNNs each trained with a particular face local region and the corresponding weight represents the importance of local region in terms of improving FR performance. Our weighted deep local features are applied to Joint Bayesian metric learning in conjunction with Nearest Neighbor(NN) Classifier for the purpose of FR. Systematic and comparative experiments show that our proposed method is robust to variations in pose, illumination, and expression. Also, experimental results demonstrate that our method is feasible for improving face recognition performance.

• Journal of Advanced Navigation Technology
• /
• v.28 no.2
• /
• pp.238-245
• /
• 2024

In this paper, we propose a framework for improving the performance of semantic segmentation of agricultural multispectral image using feature fusion techniques. Most of the semantic segmentation models being studied in the field of smart farms are trained on RGB images and focus on increasing the depth and complexity of the model to improve performance. In this study, we go beyond the conventional approach and optimize and design a model with multispectral and attention mechanisms. The proposed method fuses features from multiple channels collected from a UAV along with a single RGB image to increase feature extraction performance and recognize complementary features to increase the learning effect. We study the model structure to focus on feature fusion and compare its performance with other models by experimenting with favorable channels and combinations for crop images. The experimental results show that the model combining RGB and NDVI performs better than combinations with other channels.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.1-10
• /
• 2005

In this Paper, we propose a new block matching a1gorithm that extracts motion vectors from consecutive range data. The proposed method defines a matching metric that integrates intensity, hue, and range. Our algorithm begins matching with a small matching template. If the matching degree is not good enough, we slightly expand the size of a matching template and then repeat the matching process until our matching criterion is satisfied or the predetermined maximum size has been reached. As the iteration proceeds, we adaptively adjust weights of the matching metric by considering the importance of each feature. In the experiments, we show that our block matching approach can work as a promising solution by comparing the proposed method with previously known method in terms of performance.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.1
• /
• pp.23-30
• /
• 2014

Feature matching using image descriptors is robust method used recently. However, mismatches occur in 3D transformed images, illumination-changed images and repetitive-pattern images. In this paper, we observe that there are a lot of mismatches in the images which have repetitive patterns. We analyze it and propose a method to eliminate these mismatches. MDMF(Multiple Descriptors-based Mismatch Filtering) eliminates mismatches by using descriptors of nearest several features of one specific feature point. In experiments, for geometrical transformation like scale, rotation, affine, we compare the match ratio among SIFT, ASIFT and MDMF, and we show that MDMF can eliminate mismatches successfully.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2005.11a
• /
• pp.191-194
• /
• 2005

본 논문에서는 방송 영상에서 조명효과와 크기변화 등에 강인한 얼굴패턴 검출기법을 제시한다. 제안된 얼굴검출 모델은 영상 전처리 과정과 얼굴패턴 검출 과정으로 이루어진다. 전처리 과정은 조명변화에 대한 보정기능과 다중필터에 의한 후보영역 선별기능으로 구분된다. 얼굴패턴 검출과정은 다단계의 특징지도 생성과정과 패턴분류 과정으로 이루어진다. 특징지도를 생성하기 위하여 가보(Gabor) 필터계층을 포함하는 CNN(Convolutional Neural Networks)모델을 도입하였다. 다양한 배경을 고려한 효과적인 학습을 위하여 본 논문에서는 억제성의 뉴런(Inhibitory neuron)을 포함하는 구조의 CNN모델을 적용한다. CNN으로부터 추출되는 특징집합은 최종 단계에서 WFMM(Weighted Fuzzy Min Max) 모델을 사용하여 분류된다. 이때 사용되는 특징집합의 크기는 분류기의 규모 및 계산량의 결정적인 역할을 준다. 이에 본 연구에서는 최종 분류 과정에 사용되는 특징의 수를 효과적으로 줄이기 위해 FMM모델을 사용하는 적응적인 특징 선별 기법을 제안한다. 또한 실제 영상을 통한 실험결과로부터 제안된 이론의 타당성을 고찰한다.

• Journal of the Korea Society of Computer and Information
• /
• v.5 no.2
• /
• pp.22-29
• /
• 2000

The purpose of this paper is to propose a method to maximize a content-based image retrieval efficiency in multiple images. To perform an image retrieval job efficiently, it is necessary to minimize the number of candidate-images. Furthermore, a miximum efficiency of image retrieval could not be expected if an image retrieval job in the multiple images is done on the basis of patterns of single image distinctive features. In this method, a multiple SOFM neural network system is adopted to select automatically distinctive feature patterns which have a maximum efficiency of image retrieval in the multiple images. In this method. an image retrieval efficiency is improved 3% than individual features and the number of candidate-images is reduced by the multiple SOFM neural network system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.2
• /
• pp.39-49
• /
• 2000

In this paper, we propose an optimizing feature extraction method for multiclass problems assuming normal distributions. Initially, We start with an arbitrary feature vector Assuming that the feature vector is used for classification, we compute the classification error Then we move the feature vector slightly in the direction so that classification error decreases most rapidly This can be done by taking gradient We propose two search methods, sequential search and global search In the sequential search, an additional feature vector is selected so that it provides the best accuracy along with the already chosen feature vectors In the global search, we are not constrained to use the chosen feature vectors Experimental results show that the proposed algorithm provides a favorable performance.

• Journal of KIISE:Software and Applications
• /
• v.29 no.11
• /
• pp.818-825
• /
• 2002

Depth information is one of the most important factor for the recognition of a digital face image. Range images are very useful, when comparing one face with other faces, because of implicating depth information. As the processing for the whole fare produces a lot of calculations and data, face images ran be represented in terms of a vector of feature descriptors for a local area. In this paper, depth areas of a 3 dimensional(3D) face image were extracted by the contour line from some depth value. These were resampled and stored in consecutive location in feature vector using multiple feature method. A comparison between two faces was made based on their distance in the feature space, using Euclidian distance. This paper reduced the number of index data in the database and used fewer feature vectors than other methods. Proposed algorithm can be highly recognized for using local depth information and less feature vectors or the face.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.6
• /
• pp.473-480
• /
• 2004

In this paper we propose an effective feature compensation scheme based on the speech model in order to achieve robust speech recognition. The proposed feature compensation method is based on parallel combined mixture model (PCMM). The previous PCMM works require a highly sophisticated procedure for estimation of the combined mixture model in order to reflect the time-varying noisy conditions at every utterance. The proposed schemes can cope with the time-varying background noise by employing the interpolation method of the multiple mixture models. We apply the‘data-driven’method to PCMM tot move reliable model combination and introduce a frame-synched version for estimation of environments posteriori. In order to reduce the computational complexity due to multiple models, we propose a technique for mixture sharing. The statistically similar Gaussian components are selected and the smoothed versions are generated for sharing. The performance is examined over Aurora 2.0 and speech corpus recorded while car-driving. The experimental results indicate that the proposed schemes are effective in realizing robust speech recognition and reducing the computational complexities under both simulated environments and real-life conditions.

• Annual Conference on Human and Language Technology
• /
• 2001.10d
• /
• pp.41-47
• /
• 2001

본 논문에서는 한국어 형태소 해석기에 다중 스레드 기법을 도입하여 다중 처리가 가능하도륵 하였다. 기존의 여러 형태소 해석기들은 언어 분석에만 관심이 있었기 때문에 다량의 문서를 동시에 처리하는 기능을 고려하지 않았다. 그러나 형태소 해석기가 정보 검색 시스템 분야에서 사용되기 시작하면서, 다수의 사용자가 대량의 문서를 처리해야 하는 필요성이 생겼다. 스레드 간에는 메모리 영역과 같은 자원을 공유한다. 이러한 특징 때문에 자칫하면 예상치 못한 결과가 야기될 수 있다. 따라서, 다중 스레드 기법을 사용하기 위해서는 스레드의 특징을 고려한 조치가 필요하다 기존의 한국어 형태소 해석기의 소스 코드를 분석하여 자주 사용되는 전역 변수는 하나의 구조체로 구성하였다. 그리고 이러한 전역 변수와 크기가 큰 지역 변수를 사용할 때 메모리를 동적으로 할당하였다. 또한, 파일에서 입력값을 읽어오거나 파일에 결과값을 쓰는 등 여러 스레드가 접근할 때 값이 변경될 위험이 있는 부분은 조건 변수를 이용하여 동기화 시켰다. 구현된 시스템의 검증을 위하여, 단일 스레드 방식으로 순차적인 처리를 하는 원래의 형태소 해석기와 비교 실험을 실시하였다. 35Kbyte 문서 30개를 처리하는 경우, 다중 처리가 가능한 형태소 해석기가 단일 스레드 방식의 형태소 해석기보다 처리속도가 약 12% 향상되었다.