• Title/Summary/Keyword: 데이터 증강

Search Result 46, Processing Time 0.098 seconds

Data augmentation in voice spoofing problem (데이터 증강기법을 이용한 음성 위조 공격 탐지모형의 성능 향상에 대한 연구)

  • Choi, Hyo-Jung;Kwak, Il-Youp
    • The Korean Journal of Applied Statistics
    • /
    • v.34 no.3
    • /
    • pp.449-460
    • /
    • 2021
  • ASVspoof 2017 deals with detection of replay attacks and aims to classify real human voices and fake voices. The spoofed voice refers to the voice that reproduces the original voice by different types of microphones and speakers. data augmentation research on image data has been actively conducted, and several studies have been conducted to attempt data augmentation on voice. However, there are not many attempts to augment data for voice replay attacks, so this paper explores how audio modification through data augmentation techniques affects the detection of replay attacks. A total of 7 data augmentation techniques were applied, and among them, dynamic value change (DVC) and pitch techniques helped improve performance. DVC and pitch showed an improvement of about 8% of the base model EER, and DVC in particular showed noticeable improvement in accuracy in some environments among 57 replay configurations. The greatest increase was achieved in RC53, and DVC led to an approximately 45% improvement in base model accuracy. The high-end recording and playback devices that were previously difficult to detect were well identified. Based on this study, we found that the DVC and pitch data augmentation techniques are helpful in improving performance in the voice spoofing detection problem.

Study on data augmentation methods for deep neural network-based audio tagging (Deep neural network 기반 오디오 표식을 위한 데이터 증강 방법 연구)

  • Kim, Bum-Jun;Moon, Hyeongi;Park, Sung-Wook;Park, Young cheol
    • The Journal of the Acoustical Society of Korea
    • /
    • v.37 no.6
    • /
    • pp.475-482
    • /
    • 2018
  • In this paper, we present a study on data augmentation methods for DNN (Deep Neural Network)-based audio tagging. In this system, an audio signal is converted into a mel-spectrogram and used as an input to the DNN for audio tagging. To cope with the problem associated with a small number of training data, we augment the training samples using time stretching, pitch shifting, dynamic range compression, and block mixing. In this paper, we derive optimal parameters and combinations for the augmentation methods through audio tagging simulations.

A Study on Synthesizing Training Data for One-stage Object Detector (단일 단계 검출 방법을 위한 이미지 합성기반 학습 데이터 증강에 관한 연구)

  • Lee, Seon-Gyeong;Jeong, Chi Yoon;Moon, KyeongDeok;Kim, Chae-Kyu
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • /
    • pp.446-450
    • /
    • 2020
  • 딥러닝 기반의 영상 분석 방법들은 많은 양의 학습 데이터가 필요하며, 학습 데이터 구축에는 많은 시간과 노력이 소요된다. 특히 객체 검출 분야의 경우 영상 내 객체의 위치, 크기, 범주 등의 정보가 모두 필요하여 학습 데이터 구축에 더 많은 어려움이 있으며, 이를 해결하기 위해 최근 이미지 합성기반 데이터 증강에 관한 연구가 활발히 진행되고 있다. 이미지 합성기반 데이터 증강 방법은 배경 영상에 객체를 합성할 때 객체와 배경 영상이 접한 영역에서 아티팩트(Artifact)가 발생하며, 이는 객체 검출 모델이 아티팩트를 객체의 특징으로 모델링하여 검출 성능이 저하되는 원인이 된다. 이러한 문제를 해결하기 위하여 본 논문에서는 양방향 필터 기반의 이미지 합성 방법을 제안하고, 단일 단계 검출의 대표적인 방법인 RetinaNet을 이용하여 이미지 합성기반 데이터 증강 방법의 성능을 분석하였다. 공개 데이터셋에 대한 실험 결과 본 논문에서 사용한 단일 검출 방법 및 데이터 증강 기법을 사용하면 더 적은 양의 증강 데이터로 기존 방법과 동일한 성능을 보여주는 것을 확인하였다.

Enhancement of Tongue Segmentation by Using Data Augmentation (데이터 증강을 이용한 혀 영역 분할 성능 개선)

  • Chen, Hong;Jung, Sung-Tae
    • The Journal of Korea Institute of Information, Electronics, and Communication Technology
    • /
    • v.13 no.5
    • /
    • pp.313-322
    • /
    • 2020
  • A large volume of data will improve the robustness of deep learning models and avoid overfitting problems. In automatic tongue segmentation, the availability of annotated tongue images is often limited because of the difficulty of collecting and labeling the tongue image datasets in reality. Data augmentation can expand the training dataset and increase the diversity of training data by using label-preserving transformations without collecting new data. In this paper, augmented tongue image datasets were developed using seven augmentation techniques such as image cropping, rotation, flipping, color transformations. Performance of the data augmentation techniques were studied using state-of-the-art transfer learning models, for instance, InceptionV3, EfficientNet, ResNet, DenseNet and etc. Our results show that geometric transformations can lead to more performance gains than color transformations and the segmentation accuracy can be increased by 5% to 20% compared with no augmentation. Furthermore, a random linear combination of geometric and color transformations augmentation dataset gives the superior segmentation performance than all other datasets and results in a better accuracy of 94.98% with InceptionV3 models.

Efficient Collecting Scheme the Crack Data via Vector based Data Augmentation and Style Transfer with Artificial Neural Networks (벡터 기반 데이터 증강과 인공신경망 기반 특징 전달을 이용한 효율적인 균열 데이터 수집 기법)

  • Yun, Ju-Young;Kim, Donghui;Kim, Jong-Hyun
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • /
    • pp.667-669
    • /
    • 2021
  • 본 논문에서는 벡터 기반 데이터 증강 기법(Data augmentation)을 제안하여 학습 데이터를 구축한 뒤, 이를 합성곱 신경망(Convolutional Neural Networks, CNN)으로 실제 균열과 가까운 패턴을 표현할 수 있는 프레임워크를 제안한다. 건축물의 균열은 인명 피해를 가져오는 건물 붕괴와 낙하 사고를 비롯한 큰 사고의 원인이다. 이를 인공지능으로 해결하기 위해서는 대량의 데이터 확보가 필수적이다. 하지만, 실제 균열 이미지는 복잡한 패턴을 가지고 있을 뿐만 아니라, 위험한 상황에 노출되기 때문에 대량의 데이터를 확보하기 어렵다. 이러한 데이터베이스 구축의 문제점은 인위적으로 특정 부분에 변형을 주어 데이터양을 늘리는 탄성왜곡(Elastic distortion) 기법으로 해결할 수 있지만, 본 논문에서는 이보다 향상된 균열 패턴 결과를 CNN을 활용하여 보여준다. 탄성왜곡 기법보다 CNN을 이용했을 때, 실제 균열 패턴과 유사하게 추출된 결과를 얻을 수 있었고, 일반적으로 사용되는 픽셀 기반 데이터가 아닌 벡터 기반으로 데이터 증강을 설계함으로써 균열의 변화량 측면에서 우수함을 보였다. 본 논문에서는 적은 개수의 균열 데이터를 입력으로 사용했음에도 불구하고 균열의 방향 및 패턴을 다양하게 생성하여 쉽게 균열 데이터베이스를 구축할 수 있었다. 이는 장기적으로 구조물의 안정성 평가에 이바지하여 안전사고에 대한 불안감에서 벗어나 더욱 안전하고 쾌적한 주거 환경을 조성할 것으로 기대된다.

  • PDF

Data Augmentation Method for Deep Learning based Medical Image Segmentation Model (딥러닝 기반의 대퇴골 영역 분할을 위한 훈련 데이터 증강 연구)

  • Choi, Gyujin;Shin, Jooyeon;Kyung, Joohyun;Kyung, Minho;Lee, Yunjin
    • Journal of the Korea Computer Graphics Society
    • /
    • v.25 no.3
    • /
    • pp.123-131
    • /
    • 2019
  • In this study, we modified CT images of femoral head in consideration of anatomically meaningful structure, proposing the method to augment the training data of convolution Neural network for segmentation of femur mesh model. First, the femur mesh model is obtained from the CT image. Then divide the mesh model into meaningful parts by using cluster analysis on geometric characteristic of mesh surface. Finally, transform the segments by using an appropriate mesh deformation algorithm, then create new CT images by warping CT images accordingly. Deep learning models using the data enhancement methods of this study show better image division performance compared to data augmentation methods which have been commonly used, such as geometric conversion or color conversion.

A layered-wise data augmenting algorithm for small sampling data (적은 양의 데이터에 적용 가능한 계층별 데이터 증강 알고리즘)

  • Cho, Hee-chan;Moon, Jong-sub
    • Journal of Internet Computing and Services
    • /
    • v.20 no.6
    • /
    • pp.65-72
    • /
    • 2019
  • Data augmentation is a method that increases the amount of data through various algorithms based on a small amount of sample data. When machine learning and deep learning techniques are used to solve real-world problems, there is often a lack of data sets. The lack of data is at greater risk of underfitting and overfitting, in addition to the poor reflection of the characteristics of the set of data when learning a model. Thus, in this paper, through the layer-wise data augmenting method at each layer of deep neural network, the proposed method produces augmented data that is substantially meaningful and shows that the method presented by the paper through experimentation is effective in the learning of the model by measuring whether the method presented by the paper improves classification accuracy.

Text Augmentation Using Hierarchy-based Word Replacement

  • Kim, Museong;Kim, Namgyu
    • Journal of the Korea Society of Computer and Information
    • /
    • v.26 no.1
    • /
    • pp.57-67
    • /
    • 2021
  • Recently, multi-modal deep learning techniques that combine heterogeneous data for deep learning analysis have been utilized a lot. In particular, studies on the synthesis of Text to Image that automatically generate images from text are being actively conducted. Deep learning for image synthesis requires a vast amount of data consisting of pairs of images and text describing the image. Therefore, various data augmentation techniques have been devised to generate a large amount of data from small data. A number of text augmentation techniques based on synonym replacement have been proposed so far. However, these techniques have a common limitation in that there is a possibility of generating a incorrect text from the content of an image when replacing the synonym for a noun word. In this study, we propose a text augmentation method to replace words using word hierarchy information for noun words. Additionally, we performed experiments using MSCOCO data in order to evaluate the performance of the proposed methodology.

Development of an Image Data Augmentation Apparatus to Evaluate CNN Model (CNN 모델 평가를 위한 이미지 데이터 증강 도구 개발)

  • Choi, Youngwon;Lee, Youngwoo;Chae, Heung-Seok
    • Journal of Software Engineering Society
    • /
    • v.29 no.1
    • /
    • pp.13-21
    • /
    • 2020
  • As CNN model is applied to various domains such as image classification and object detection, the performance of CNN model which is used to safety critical system like autonomous vehicles should be reliable. To evaluate that CNN model can sustain the performance in various environments, we developed an image data augmentation apparatus which generates images that is changed background. If an image which contains object is entered into the apparatus, it extracts an object image from the entered image and generate s composed images by synthesizing the object image with collected background images. A s a method to evaluate a CNN model, the apparatus generate s new test images from original test images, and we evaluate the CNN model by the new test image. As a case study, we generated new test images from Pascal VOC2007 and evaluated a YOLOv3 model with the new images. As a result, it was detected that mAP of new test images is almost 0.11 lower than mAP of the original test images.

  • PDF