• 전기전자학회논문지
• /
• 제26권4호
• /
• pp.742-745
• /
• 2022

본 논문에서 우리는 열화상에서 전력선 유무를 검출하는 영상처리 기법과 딥러닝 기반의 하이브리드 방법을 제안한다. 딥러닝은 다수의 데이터로부터 목적에 부합하는 특징 벡터를 학습할 수 있는 장점 덕분에 영상 인식, 객체 검출 등 다양한 분야에서 기존의 직접 설계한 특징 벡터를 사용하는 방법들보다 높은 성능을 달성할 수 있는 장점이 있고, 영상처리 기법은 사람의 직관을 그대로 적용할 수 있다는 장점이 있다. 두 장점을 모두 이용하여 열화상에서 전력선 유무를 검출하는 방법을 제안한다. 전력선 유무 검출에 가장 적합한 영상처리 기법을 찾기 위해 총 5가지 방법을 적용 및 비교하였고, 그 결과로 제안하는 방법은 기존의 영상처리 기반 방법과 딥러닝 기반의 방법 두 가지 모두에 비해 더 높은 99.48%의 정확도로 전력선 유무를 검출할 수 있다.

• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1326-1335
• /
• 2021

As part of the cell division method, we proposed a method for segmenting images generated by topography microscopes through deep learning-based feature generation and graph segmentation. Hybrid vector shapes preserve the overall shape and boundary information of cells, so most cell shapes can be captured without any post-processing burden. NIH-3T3 and Hela-S3 cells have satisfactory results in cell description preservation. Compared to other deep learning methods, the proposed cell image segmentation method does not require postprocessing. It is also effective in preserving the overall morphology of cells and has shown better results in terms of cell boundary preservation.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.965-976
• /
• 2020

We present in this work a segmentation method of E. coli bacterial images generated via phase contrast microscopy using a deep learning based hybrid feature generation. Unlike conventional machine learning methods that use the hand-crafted features, we adopt the denoising autoencoder in order to generate a precise and accurate representation of the pixels. We first construct a hybrid vector that combines original image, difference of Gaussians and image gradients. The created hybrid features are then given to a deep autoencoder that learns the pixels' internal dependencies and the cells' shape and boundary information. The latent representations learned by the autoencoder are used as the inputs of a softmax classification layer and the direct outputs from the classifier represent the coarse segmentation mask. Finally, the classifier's outputs are used as prior information for a graph partitioning based fine segmentation. We demonstrate that the proposed hybrid vector representation manages to preserve the global shape and boundary information of the cells, allowing to retrieve the majority of the cellular patterns without the need of any post-processing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권9호
• /
• pp.2882-2903
• /
• 2022

Image super-resolution (SR) processing is of great value in the fields of digital image processing, intelligent security, film and television production and so on. This paper proposed a densely connected deep learning network based on cascade architecture, which can be used to solve the problem of super-resolution in the field of image quality enhancement. We proposed a more efficient residual scaling dense block (RSDB) and the multi-channel cascade architecture to realize more efficient feature reuse. Also we proposed a hybrid loss function based on L₁ error and L_∞ error to achieve better L_∞ error performance. The experimental results show that the overall performance of the network is effectively improved on cascade architecture and residual scaling. Compared with the residual dense net (RDN), the PSNR / SSIM of the new method is improved by 2.24% / 1.44% respectively, and the L_∞ performance is improved by 3.64%. It shows that the cascade connection and residual scaling method can effectively realize feature reuse, improving the residual convergence speed and learning efficiency of our network. The L_∞ performance is improved by 11.09% with only a minimal loses of 1.14% / 0.60% on PSNR / SSIM performance after adopting the new loss function. That is to say, the L_∞ performance can be improved greatly on the new loss function with a minor loss of PSNR / SSIM performance, which is of great value in L_∞ error sensitive tasks.