• International Journal of Internet, Broadcasting and Communication
• /
• 제9권4호
• /
• pp.1-7
• /
• 2017

Clipart is artificial visual contents that are created using various tools such as Illustrator to highlight some information. Here, the style of the clipart plays a critical role in determining how it looks. However, previous studies on clipart are focused only on the object recognition [16], segmentation, and retrieval of clipart images using hand-craft image features. Recently, some clipart classification researches based on the style similarity using CNN have been proposed, however, they have used different CNN-models and experimented with different benchmark dataset so that it is very hard to compare their performances. This paper presents an experimental analysis of the clipart classification based on the style similarity with two well-known CNN-models (Inception Resnet V2 [13] and VGG-16 [14] and transfers learning with the same benchmark dataset (Microsoft Style Dataset 3.6K). From this experiment, we find out that the accuracy of Inception Resnet V2 is better than VGG for clipart style classification because of its deep nature and convolution map with various sizes in parallel. We also find out that the end-to-end training can improve the accuracy more than 20% in both CNN models.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.442-444
• /
• 2019

직물결함 분류는 원단 품질관리에 있어 중요한 문제이다. 하지만, 다양한 결함의 종류를 영상으로 식별하기 어렵기 때문에 자동화가 어렵다. 따라서 직물결함 분류는 대부분 사람에게 의존하고 있다. 본 논문에서는, 이를 해결하기 위해 직물결함 분류 문제에 CNN을 적용한다. 또한 CNN의 학습을 보다 쉽게 하기 위하여, 사람이 영상에 결함 영역을 표시하는 방법을 제안한다. 본 논문에서는 제안방법과 원본영상에 대한 비교실험을 수행하여, 제안방법이 학습에 효과가 있다는 것을 확인하였다.

• The Plant Pathology Journal
• /
• 제39권4호
• /
• pp.319-334
• /
• 2023

Plant disease is an important factor affecting crop yield. With various types and complex conditions, plant diseases cause serious economic losses, as well as modern agriculture constraints. Hence, rapid, accurate, and early identification of crop diseases is of great significance. Recent developments in deep learning, especially convolutional neural network (CNN), have shown impressive performance in plant disease classification. However, most of the existing datasets for plant disease classification are a single background environment rather than a real field environment. In addition, the classification can only obtain the category of a single disease and fail to obtain the location of multiple different diseases, which limits the practical application. Therefore, the object detection method based on CNN can overcome these shortcomings and has broad application prospects. In this study, an annotated apple leaf disease dataset in a real field environment was first constructed to compensate for the lack of existing datasets. Moreover, the Faster R-CNN and YOLOv3 architectures were trained to detect apple leaf diseases in our dataset. Finally, comparative experiments were conducted and a variety of evaluation indicators were analyzed. The experimental results demonstrate that deep learning algorithms represented by YOLOv3 and Faster R-CNN are feasible for plant disease detection and have their own strong points and weaknesses.

• Korean Journal of Radiology
• /
• 제20권8호
• /
• pp.1275-1284
• /
• 2019

Objective: To develop algorithms using convolutional neural networks (CNNs) for automatic segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) and compare them with conventional algorithms, including a thresholding-based segmentation. Materials and Methods: Between September 2005 and August 2015, 429 patients presenting with acute cerebral ischemia (training:validation:test set = 246:89:94) were retrospectively enrolled in this study, which was performed under Institutional Review Board approval. Ground truth segmentations for acute ischemic lesions on DWI were manually drawn under the consensus of two expert radiologists. CNN algorithms were developed using two-dimensional U-Net with squeeze-and-excitation blocks (U-Net) and a DenseNet with squeeze-and-excitation blocks (DenseNet) with squeeze-and-excitation operations for automatic segmentation of acute ischemic lesions on DWI. The CNN algorithms were compared with conventional algorithms based on DWI and the apparent diffusion coefficient (ADC) signal intensity. The performances of the algorithms were assessed using the Dice index with 5-fold cross-validation. The Dice indices were analyzed according to infarct volumes (< 10 mL, ≥ 10 mL), number of infarcts (≤ 5, 6-10, ≥ 11), and b-value of 1000 (b1000) signal intensities (< 50, 50-100, > 100), time intervals to DWI, and DWI protocols. Results: The CNN algorithms were significantly superior to conventional algorithms (p < 0.001). Dice indices for the CNN algorithms were 0.85 for U-Net and DenseNet and 0.86 for an ensemble of U-Net and DenseNet, while the indices were 0.58 for ADC-b1000 and b1000-ADC and 0.52 for the commercial ADC algorithm. The Dice indices for small and large lesions, respectively, were 0.81 and 0.88 with U-Net, 0.80 and 0.88 with DenseNet, and 0.82 and 0.89 with the ensemble of U-Net and DenseNet. The CNN algorithms showed significant differences in Dice indices according to infarct volumes (p < 0.001). Conclusion: The CNN algorithm for automatic segmentation of acute ischemic lesions on DWI achieved Dice indices greater than or equal to 0.85 and showed superior performance to conventional algorithms.

• 한국측량학회지
• /
• 제34권5호
• /
• pp.525-534
• /
• 2016

쌀은 오랜 기간 동안 남한 지역의 주식임과 동시에 농부들의 주 수입원이며, 농업 분야 관련 정책 수립을 위한 수학적인 쌀 생산량 추정 모델의 구축이 필요하다. 본 연구의 목적은 (1) 쌀 생산량 추정을 위한 회선신경망 모델의 구축과, (2) 최고의 성능을 보이는 회선신경망의 파라미터를 결정하는 것과, (3) 인공신경망 모델과의 비교를 통해 회선신경망의 성능을 평가하는 것이다. 각 모델의 입력데이터로는 2000~2013년도의 4~9월까지에 해당하는 기상자료와 MODIS 위성자료를 사용하였으며, 정확도 평가를 위해 교차 검증을 실시하였다. 회선신경망과 인공신경망은 쌀 생산 표본점을 대상으로 각각 36.10kg/10a, 48.61kg/10a와 시군구 지역을 대상으로 각각 31.30kg/10a, 39.31kg/10a의 RMSE를 보였다. 회선신경망 모델은 인공신경망 모델보다 우수한 성능을 보였으며, 본 연구를 통해 쌀 생산량 추정 분야에 대한 회선신경망 모델의 적용 가능성을 확인할 수 있었다.

• 한국항해항만학회지
• /
• 제46권3호
• /
• pp.243-250
• /
• 2022

본 연구에서는 인공지능을 활용한 영상분석 기술을 통해 영상 내의 월파를 실시간으로 감지하고 처오름 높이를 산정하는 기술을 제안하였다. 본 연구에서 제안한 월파 감지 시스템은 실시간으로 악기상 및 야간에도 월파를 감지할 수 있음을 확인하였다. 특히, 합성곱 신경망을 적용하여 실시간으로 CCTV 영상에서 파랑의 처오름을 감지하고 월파 여부를 판단하는 여과 알고리즘을 적용하여 월파의 발생 감지에 대한 정확성을 향상시켰다. AP50을 통해 월파 감지 결과의 정확도는 59.6%로 산정되었으며, 월파 감지 모델의 속도는 GPU 기준 70fps로 실시간 감지에 적합한 정확도와 속도를 보임을 확인하였다.

• 한국전자통신학회논문지
• /
• 제14권6호
• /
• pp.1207-1214
• /
• 2019

4차 산업혁명의 기술이 우리도 모르는 사이 우리의 삶 속으로 스며들고 있다. CNN이 이미지 인식 분야에서 탁월한 능력을 보여준 이후 많은 IoT 기반 홈보안 시스템은 침입자로부터 가족과 가정을 보호하며 얼굴을 인식하기 위한 좋은 생체인식 방법으로 CNN을 사용하고 있다. 본 논문에서는 2D와 2.5D 이미지에 대하여 여러 종류의 입력 이미지 크기와 필터를 가지고 있는 CNN의 구조를 연구한다. 실험 결과는 50*50 크기를 가진 2.5D 입력 이미지, 2 컨벌류션과 맥스풀링 레이어, 3*3 필터를 가진 CNN 구조가 0.966의 인식률을 보여 주었고, 1개의 입력 이미지에 대하여 가장 긴 CPU 소비시간은 0.057S로 나타났다. 홈보안 시스템은 좋은 얼굴 인식률과 짧은 연산 시간을 요구하므로 본 논문에서 제안한 구조의 CNN은 홈보안 시스템에서 얼굴인식을 기반으로 하는 액추에이터 제어 등에 적합한 방법이 될 것이다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2018년도 추계학술대회
• /
• pp.11-14
• /
• 2018

The aim of this study is to rectify the misclassified image features and enhance the performance of image classification tasks by incorporating a channel- coding technique, widely used in telecommunication. Specifically, the proposed algorithm employs the error - correcting mechanism of convolutional coding combined with the convolutional neural networks (CNNs) that are the state - of- the- arts image classifier s. We develop an encoder and a decoder to employ the error - correcting capability of the convolutional coding. In the encoder, the label values of the image data are converted to convolutional codes that are used as target outputs of the CNN, and the network is trained to minimize the Euclidean distance between the target output codes and the actual output codes. In order to correct misclassified features, the outputs of the network are decoded through the trellis structure with Viterbi algorithm before determining the final prediction. This paper demonstrates that the proposed architecture advances the performance of the neural networks compared to the traditional one- hot encoding method.

• Advances in nano research
• /
• 제15권5호
• /
• pp.451-466
• /
• 2023

Gastrointestinal cancer (GC) is a prevalent malignant tumor of the digestive system that poses a severe health risk to humans. Due to the specific organ structure of the gastrointestinal system, both endoscopic and MRI diagnoses of GIC have limited sensitivity. The primary factors influencing curative efficacy in GIC patients are drug inefficacy and high recurrence rates in surgical and pharmacological therapy. Due to its unique optical features, good biocompatibility, surface effects, and small size effects, nanotechnology is a developing and advanced area of study for the detection and treatment of cancer. Because of its deep location and complex surgery, diagnosing and treating gastrointestinal cancer is very difficult. The early diagnosis and urgent treatment of gastrointestinal illness are enabled by nanotechnology. As diagnostic and therapeutic tools, nanoparticles directly target tumor cells, allowing their detection and removal. XGBoost was used as a classification method known for achieving numerous winning solutions in data analysis competitions, to capture nonlinear relations among many input variables and outcomes using the boosting approach to machine learning. The research sample included 300 GC patients, comprising 190 males (72.2% of the sample) and 110 women (27.8%). Using convolutional neural networks (CNN) and artificial neural networks (ANN)-EXtreme Gradient Boosting (XGBoost), the patients mean± SD age was 50.42 ± 13.06. High-risk behaviors (P = 0.070), age at diagnosis (P = 0.037), distant metastasis (P = 0.004), and tumor stage (P = 0.015) were shown to have a statistically significant link with GC patient survival. AUC was 0.92, sensitivity was 81.5%, specificity was 90.5%, and accuracy was 84.7 when analyzing stomach picture.

• 방송공학회논문지
• /
• 제25권6호
• /
• pp.944-953
• /
• 2020

객체 검출 알고리즘은 자율주행 시스템 구현을 위한 핵심 요소이다. 최근 심층 합성곱 신경망 (Deep Convolutional Neural Network) 기반의 영상 인식 기술이 발전함에 따라 심층 학습을 이용한 객체 검출 관련 연구들이 활발히 진행되고 있다. 본 논문에서는 객체 검출에 가장 널리 사용되고 있는 Mask R-CNN의 경량화 모델을 제안하여 도로 내 다양한 객체들의 위치와 형태를 효율적으로 예측하는 방법을 제안한다. 또한, 주의 모듈(Attention Module)을 Mask R-CNN 내 각각 다른 역할을 수행하는 신경망 계층에 적용함으로써 특징 지도를 적응적으로 재교정(Re-calibration)하여 검출 성능을 향상시킨다. 실제 주행 영상에 대한 다양한 실험 결과를 통해 제안하는 방법이 기존 방법 대비 크게 감소된 신경망 매개변수만을 이용하여 고성능 검출 성능을 유지함을 보인다.