• 전기학회논문지
• /
• 제67권9호
• /
• pp.1224-1231
• /
• 2018

Automatic age estimation has been used in many social network applications, practical commercial applications, and human-computer interaction visual-surveillance biometrics. However, it has rarely been explored. In this paper, we propose an automatic age estimation system, which includes face detection and convolutional deep learning based on an inception module. The latter is a 22-layer-deep network that serves as the particular category of the inception design. To evaluate the proposed approach, we use 4,000 images of eight different age groups from the Adience age dataset. k-fold cross-validation (k = 5) is applied. A comparison of the performance of the proposed work and recent related methods is presented. The results show that the proposed method significantly outperforms existing methods in terms of the exact accuracy and off-by-one accuracy. The off-by-one accuracy is when the result is off by one adjacent age label to the above or below. For the exact accuracy, the age label of "60+" is classified with the highest accuracy of 76%.

• 전기학회논문지
• /
• 제67권7호
• /
• pp.928-933
• /
• 2018

Nowadays, gastropathy is a common disease. As endoscopic equipment are developed and used widely, it is possible to provide a large number of endoscopy images. Computer-aided Diagnosis (CADx) systems aim at helping physicians to identify possibly malignant abnormalities more accurately. In this paper, we present a CADx system to detect and classify the abnormalities of gastric lesions which include bleeding, ulcer, neuroendocrine tumor and cancer. We used an Inception module based deep learning model. And we used data augmentation for learning. Our preliminary results demonstrated promising potential for automatically labeled region of interest for endoscopy doctors to focus on abnormal lesions for subsequent targeted biopsy, with Az values of Receiver Operating Characteristic(ROC) curve was 0.83. The proposed CADx system showed reliable performance.

• Journal of Information Processing Systems
• /
• 제16권4호
• /
• pp.795-808
• /
• 2020

Due to the poor evaluation indexes such as detection accuracy and recall rate when Yolov3 network detects aircraft in remote sensing images, in this paper, we propose a remote sensing image aircraft detection method based on machine vision. In order to improve the target detection effect, the Inception module was introduced into the Yolov3 network structure, and then the data set was cluster analyzed using the k-means algorithm. In order to obtain the best aircraft detection model, on the basis of our proposed method, we adjusted the network parameters in the pre-training model and improved the resolution of the input image. Finally, our method adopted multi-scale training model. In this paper, we used remote sensing aircraft dataset of RSOD-Dataset to do experiments, and finally proved that our method improved some evaluation indicators. The experiment of this paper proves that our method also has good detection and recognition ability in other ground objects.

• 정보과학회 논문지
• /
• 제45권1호
• /
• pp.94-98
• /
• 2018

본 논문은 자율주행을 위한 실시간 의미론적 분할 방법으로 최적화된 심층 신경망 구조인 Wide Inception ResNet (WIR Net)을 제안한다. 신경망 구조는 Residual connection과 Inception module을 적용하여 특징을 추출하는 인코더와 Transposed convolution과 낮은 층의 특징 맵을 사용하여 해상도를 높이는 디코더로 구성하였고 ELU 활성화 함수를 적용함으로써 성능을 올렸다. 또한 신경망의 전체 층수를 줄이고 필터 수를 늘리는 방법을 통해 성능을 최적화하였다. 성능평가는 NVIDIA Geforce gtx 1080과 TX1 보드를 사용하여 주행환경의 Cityscapes 데이터에 대해 클래스와 카테고리별 IoU를 평가하였다. 실험 결과를 통해 클래스 IoU 53.4, 카테고리 IoU 81.8의 정확도와 TX1 보드에서 $640{\times}360$, $720{\times}480$ 해상도 영상처리에 17.8fps, 13.0fps의 실행속도를 보여주는 것을 확인하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 춘계학술발표대회
• /
• pp.372-374
• /
• 2020

최근 화장품이나 뷰티산업의 성장이 가속화되고 있다. 이에 따라 시장에 다양한 뷰티제품들이 출시되고 있지만 그로 인해 오히려 본인에게 적합한 제품이 무엇인지 알지 못하는 경우가 많다. 온라인을 통해 구매하는 경우 구매후기 및 광고에 의지해야 하며 전문가의 조언을 구하기 위해서는 오프라인 상점을 방문할 수밖에 없다. 그러나 오프라인 상점을 방문한 경우에도 자신에게 적합한 화장품을 추천받는 것 또한 다분하지 않다. 본 논문에서는 이러한 문제점을 해결하고자 온라인 환경에서 소비자에게 맞는 상품의 광고 및 정보를 받을 수 있는 화장품 추천 서비스를 제안한다. 또한 제안서비스는 AI기능을 적용하여 기존의 방식보다 소비자 친화적인 서바스를 제공하는 것을 목표로 한다.

• Journal of Plant Biotechnology
• /
• 제49권4호
• /
• pp.300-306
• /
• 2022

The mitogen-activated protein kinase (MAPK) signaling cascade is essential for a wide range of cellular responses in plants, including defense responses, responses to abiotic stress, hormone signaling, and developmental processes. Recent investigations have shown that the stress, ethylene, and MAPK signaling pathways negatively affect the formation of nitrogen-fixing nodules by directly modulating the symbiotic signaling components. However, the molecular mechanisms underlying the defense responses mediated by MAPK signaling in the organogenesis of nitrogen-fixing nodules remain unclear. In the present study, I demonstrate that the Medicago truncatula mitogen-activated protein kinase kinase 5 (MtMKK5)-Medicago truncatula mitogen-activated protein kinase 3/6 (MtMPK3/6) signaling module, expressed specifically in the symbiotic nodules, promotes defense signaling, but not ethylene signaling pathways, thereby inhibiting nodule development in M. truncatula. U0126 treatment resulted in increased cell division in the nodule meristem zone due to the inhibition of MAPK signaling. The phosphorylated TEY motif in the activation domain of MtMPK3/6 was the target domain associated with specific interactions with MtMKK5. I have confirmed the physical interactions between M. truncatula nodule inception (MtNIN) and MtMPK3/6. In the presence of high expression levels of the defense-related genes FRK1 and WRKY29, MtMKK5a overexpression significantly enhanced the defense responses of Arabidopsis against Pseudomonas syringae pv. tomato DC3000 (Pst DC3000). Overall, my data show that the negative regulation of symbiotic nitrogen-fixing nodule organogenesis by defense signaling pathways is mediated by the MtMKK5-MtMPK3/6 module.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.203-211
• /
• 2020

This study proposes a method for estimating gender and age that is robust to various external environment changes by applying deep learning-based learning. To improve the accuracy of the proposed algorithm, an improved CNN network structure and learning method are described, and the performance of the algorithm is also evaluated. In this study, in order to improve the learning method based on CNN composed of 6 layers of hidden layers, a network using GoogLeNet's inception module was constructed. As a result of the experiment, the age estimation accuracy of 5,328 images for the performance test of the age estimation method is about 85%, and the gender estimation accuracy is about 98%. It is expected that real-time age recognition will be possible beyond feature extraction of face images if studies on the construction of a larger data set, pre-processing methods, and various network structures and activation functions have been made to classify the age classes that are further subdivided according to age.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.525-528
• /
• 2019

Atmospheric particle removal is a challenging task and attacks wide interests in computer vision filed. In this paper, we proposed a single image snow removal framework based on deep residual networks. According to the fact that there are various snow sizes in a snow image, the inception module which consists of different filter kernels was adopted to extract multiple resolution features of the input snow image. Except the traditional mean square error loss, the perceptual loss and total variation loss were employed to generate more clean images. Experimental results on synthetic and realistic snow images indicated that the proposed method achieves superior performance in respect of visual perception and objective evaluation.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권10호
• /
• pp.403-410
• /
• 2019

눈이 내리는 영상에서 눈송이들에 의하여 영상의 질이 저하되고 영상 내에 존재하는 객체들을 명확히 탐지하기 위해서는 눈송이를 제거해야할 필요성이 있다. 이 연구에서는 지각 Generative Adversarial Network에 기반하여 단일 영상으로부터 눈송이를 제거하는 방법을 제시한다. 잔류 U-Net을 눈송이가 제거된 영상을 생성하는 생성기로 설계하였다. 다양한 크기의 눈송이를 처리하기 위하여 다양한 필터 커널의 인셉션 모듈을 설계하고 입력한 눈이 내리는 영상의 다양한 해상도 특징을 추출하기 위하여 적용되었다. 눈송이 제거 영상의 품질을 높이기 위해서 대립손실을 제외하고는, 지각적 손실과 총 변동 손실 함수를 적용하여 제설 이미지와의 유사도를 찾아갈 수 있도록 하였다. 합성 강설 이미지와 실제 강설 이미지를 대상으로 제안 네크워크의 제설 기능을 실험하였다. 실험 결과 제안 알고리즘은 합성 이미지와 강설 이미지 모든 분야에서 육안으로 관찰해본 결과 화질이 우수함을 보여주었고, 객관적 평가를 위하여 신호강도를 나타내는 PSNR과 구조변화를 측정하는 SSIM 인덱스를 비교하였으며, 제안 알고리즘이 지수 상으로도 가장 우수한 성능을 보여주었다.