• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1464-1479
• /
• 2018

In face recognition, sometimes the number of available training samples for single category is insufficient. Therefore, the performances of models trained by convolutional neural network are not ideal. The small sample face recognition algorithm based on novel Siamese network is proposed in this paper, which doesn't need rich samples for training. The algorithm designs and realizes a new Siamese network model, SiameseFacel, which uses pairs of face images as inputs and maps them to target space so that the $L_2$ norm distance in target space can represent the semantic distance in input space. The mapping is represented by the neural network in supervised learning. Moreover, a more lightweight Siamese network model, SiameseFace2, is designed to reduce the network parameters without losing accuracy. We also present a new method to generate training data and expand the number of training samples for single category in AR and labeled faces in the wild (LFW) datasets, which improves the recognition accuracy of the models. Four loss functions are adopted to carry out experiments on AR and LFW datasets. The results show that the contrastive loss function combined with new Siamese network model in this paper can effectively improve the accuracy of face recognition.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.927-939
• /
• 2020

Gait recognition can identify people's identity from a long distance, which is very important for improving the intelligence of the monitoring system. Among many human features, gait features have the advantages of being remotely available, robust, and secure. Traditional gait feature extraction, affected by the development of behavior recognition, can only rely on manual feature extraction, which cannot meet the needs of fine gait recognition. The emergence of deep convolutional neural networks has made researchers get rid of complex feature design engineering, and can automatically learn available features through data, which has been widely used. In this paper,conduct feature metric learning in the three-dimensional space by combining the three-dimensional convolution features of the gait sequence and the Siamese structure. This method can capture the information of spatial dimension and time dimension from the continuous periodic gait sequence, and further improve the accuracy and practicability of gait recognition.

• 한국정보통신학회논문지
• /
• 제25권3호
• /
• pp.389-395
• /
• 2021

본 논문에서는 샴 네트워크 기반의 객체 추적 알고리즘의 성능 향상을 위한 표적 이미지 교환 모델을 제안한다. 샴 네트워크 기반의 객체 추적 알고리즘은 시퀀스의 첫 프레임에서 지정된 표적 이미지만을 사용하여 탐색 이미지 내에서 가장 유사한 부분을 찾아 객체를 추적한다. 첫 프레임의 객체와 유사도를 비교하기 때문에 추적에 한 번 실패하게 되면 오류가 축적되어 추적 객체가 아닌 부분에서 표류하게 되는 현상이 발생한다. 따라서 CNN(Convolutional Neural Network)기반의 모델을 설계하여 추적이 잘 진행되고 있는지 확인하고 샴 네트워크 기반의 객체 추적 알고리즘에서 출력되는 점수를 이용하여 표적 이미지 교환 시기를 정의하였다. 제안 모델은 VOT-2018 데이터 셋을 이용하여 성능을 평가하였고 최종적으로 정확도 0.611 견고도 22.816을 달성하였다.

• 한국멀티미디어학회논문지
• /
• 제24권6호
• /
• pp.796-804
• /
• 2021

In computer vision, visual tracking method addresses the problem of localizing an specific object in video sequence according to the bounding box. In this paper, we propose a tracking method by introducing the feature correlation comparison into the siamese network to increase its matching identification. We propose a way to compute location of object to improve matching performance by a correlation operation, which locates parts for solving the searching problem. The higher layer in the network can extract a lot of object information. The lower layer has many location information. To reduce error rate of the object center point, we built a siamese network that extracts the distribution and location information of target objects. As a result of the experiment, the average center error rate was less than 25%.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권7호
• /
• pp.271-278
• /
• 2021

현재 사이버 공격이 더욱 지능화됨에 따라 기존의 침입 탐지 시스템(Intrusion Detection System)은 저장된 패턴에서 벗어난 지능형 공격을 탐지하기 어렵다. 이를 해결하려는 방법으로, 데이터 학습을 통해 지능형 공격의 패턴을 분석하는 딥러닝(Deep Learning) 기반의 침입 탐지 시스템 모델이 등장했다. 침입 탐지 시스템은 설치 위치에 따라 호스트 기반과 네트워크 기반으로 구분된다. 호스트 기반 침입 탐지 시스템은 네트워크 기반 침입 탐지 시스템과 달리 시스템 내부와 외부를 전체적으로 관찰해야 하는 단점이 있다. 하지만 네트워크 기반 침입 탐지 시스템에서 탐지할 수 없는 침입을 탐지할 수 있는 장점이 있다. 따라서, 본 연구에서는 호스트 기반의 침입 탐지 시스템에 관한 연구를 수행했다. 호스트 기반의 침입 탐지 시스템 모델의 성능을 평가하고 개선하기 위해서 2018년에 공개된 호스트 기반 LID-DS(Leipzig Intrusion Detection-Data Set)를 사용했다. 해당 데이터 세트를 통한 모델의 성능 평가에 있어서 각 데이터에 대한 유사성을 확인하여 정상 데이터인지 비정상 데이터인지 식별하기 위해 1차원 벡터 데이터를 3차원 이미지 데이터로 변환하여 재구성했다. 또한, 딥러닝 모델은 새로운 사이버 공격 방법이 발견될 때마다 학습을 다시 해야 한다는 단점이 있다. 즉, 데이터의 양이 많을수록 학습하는 시간이 오래 걸리기 때문에 효율적이지 못하다. 이를 해결하기 위해 본 논문에서는 적은 양의 데이터를 학습하여 우수한 성능을 보이는 Few-Shot Learning 기법을 사용하기 위해 Siamese-CNN(Siamese Convolutional Neural Network)을 제안한다. Siamese-CNN은 이미지로 변환한 각 사이버 공격의 샘플에 대한 유사성 점수에 의해 같은 유형의 공격인지 아닌지 판단한다. 정확성은 Few-Shot Learning 기법을 사용하여 정확성을 계산했으며, Siamese-CNN의 성능을 확인하기 위해 Vanilla-CNN(Vanilla Convolutional Neural Network)과 Siamese-CNN의 성능을 비교했다. Accuracy, Precision, Recall 및 F1-Score 지표를 측정한 결과, Vanilla-CNN 모델보다 본 연구에서 제안한 Siamese-CNN 모델의 Recall이 약 6% 증가한 것을 확인했다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3608-3626
• /
• 2021

The detection of bolts is an important task in high-speed train inspection systems, and it is frequently performed to ensure the safety of trains. The difficulty of the vision-based bolt inspection system lies in small sample defect detection, which makes the end-to-end network ineffective. In this paper, the problem is resolved in two stages, which includes the detection network and cascaded classification networks. For small bolt detection, all bolts including defective bolts and normal bolts are put together for conducting annotation training, a new loss function and a new boundingbox selection based on the smallest axis-aligned convex set are proposed. These allow YOLOv3 network to obtain the accurate position and bounding box of the various bolts. The average precision has been greatly improved on PASCAL VOC, MS COCO and actual data set. After that, the Siamese network is employed for estimating the status of the bolts. Using the convolutional Siamese network, we are able to get strong results on few-shot classification. Extensive experiments and comparisons on actual data set show that the system outperforms state-of-the-art algorithms in bolt inspection.

• 한국멀티미디어학회논문지
• /
• 제22권1호
• /
• pp.1-9
• /
• 2019

Single image rain removal is a typical inverse problem which decomposes the image into a background scene and a rain streak. Recent works have witnessed a substantial progress on the task due to the development of convolutional neural network (CNN). However, existing CNN-based approaches train the network with synthetically generated training examples. These data tend to make the network bias to the synthetic scenes. In this paper, we present an unsupervised framework for removing rain streaks from real-world rainy images. We focus on the natural phenomena that static rainy scenes capture a common background but different rain streak. From this observation, we train siamese network with the real rain image pairs, which outputs identical backgrounds from the pairs. To train our network, a real rainy dataset is constructed via web-crawling. We show that our unsupervised framework outperforms the recent CNN-based approaches, which are trained by supervised manner. Experimental results demonstrate that the effectiveness of our framework on both synthetic and real-world datasets, showing improved performance over previous approaches.

• 한국멀티미디어학회논문지
• /
• 제25권1호
• /
• pp.72-81
• /
• 2022

Visual Object Tracking is known as the most fundamental problem in the field of computer vision. Object tracking localize the region of target object with bounding box in the video. In this paper, a custom CNN is created to extract object feature that has strong and various information. This network was constructed as a Siamese network for use as a feature extractor. The input images are passed convolution block composed of a bottleneck layers, and features are emphasized. The feature map of the target object and the search area, extracted from the Siamese network, was input as a local proposal network. Estimate the object area using the feature map. The performance of the tracking algorithm was evaluated using the OTB2013 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.611 in Success Plot and 0.831 in Precision Plot were achieved.

• 스마트미디어저널
• /
• 제9권3호
• /
• pp.9-17
• /
• 2020

Hippocampus is a complex brain structure embedded deep into the temporal lobe. Studies have shown that this structure gets affected by neurological and psychiatric disorders and it is a significant landmark for diagnosing neurodegenerative diseases. Hippocampus features play very significant roles in region-of-interest based analysis for disease diagnosis and prognosis. In this study, we have attempted to learn the embeddings of this important biomarker. As conventional metric learning methods for feature embedding is known to lacking in capturing semantic similarity among the data under study, we have trained deep Siamese convolutional neural network for learning metric of the hippocampus. We have exploited Gwangju Alzheimer's and Related Dementia cohort data set in our study. The input to the network was pairs of three-view patches (TVPs) of size 32 × 32 × 3. The positive samples were taken from the vicinity of a specified landmark for the hippocampus and negative samples were taken from random locations of the brain excluding hippocampi regions. We have achieved 98.72% accuracy in verifying hippocampus TVPs.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.247-256
• /
• 2022

Visual tracking of selected target objects is fundamental challenging problems in computer vision. Object tracking localize the region of target object with bounding box in the video. We propose a Siam-FPN based custom fully CNN to solve visual tracking problems by regressing the target area in an end-to-end manner. A method of preserving the feature information flow using a feature map connection structure was applied. In this way, information is preserved and emphasized across the network. To regress object region and to classify object, the region proposal network was connected with the Siamese network. The performance of the tracking algorithm was evaluated using the OTB-100 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.621 in Success Plot and 0.838 in Precision Plot were achieved.