• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.2
• /
• pp.83-90
• /
• 2011

In cell biology area, microscopy enables detecting objects inside cells that are stained or fluorescently tagged. It is disadvantageous for observing these objects because of the noisy characteristics of their environmental surrounding. In this paper, a framework is proposed to increase the throughput and reliability for analysis of these images. First, we apply adaptive beamlet transform to extract edges meaningfully followed by orientation, location, and length in different scales. Then, a post-process is implemented to extend and map them onto original image. Our proposed scheme is compared with Canny edge detector and conventional beamlet transform from four evaluation aspects. It produces better results when experiments are conducted on real images. Much better results for observing internal parts make this framework competitive for analysis of cell images.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.163-165
• /
• 2019

The task of image denoising is gaining popularity in the computer vision research field. Its main objective of restoring the sharp image from given noisy input is demanded in all image processing procedure. In this work, we treat the process of residual hair removal on faces images similar to the task of image denoising. In particular, our method removes the residual hair that presents on the frontal or profile face images and in-paints it with the relevant skin color. To achieve this objective, we employ a deep neural network that able to perform both tasks in one time. Furthermore, simple technic of residual hair color augmentation is introduced to increase the number of training data. This approach is beneficial for improving the robustness of the network. Finally, we show that the experimental results demonstrate the superiority of our network in both quantitative and qualitative performances.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.62-65
• /
• 2010

Image annotations allow users to access a large image database with textual queries. But since the surrounding text of Web images is generally noisy. an efficient image annotation and retrieval system is highly desired. which requires effective image search techniques. Data mining techniques can be adopted to de-noise and figure out salient terms or phrases from the search results. Clustering algorithms make it possible to represent visual features of images with finite symbols. Annotationbased image search engines can obtains thousands of images for a given query; but their results also consist of visually noise. In this paper. we present a new algorithm Double-Circles that allows a user to remove noise results and characterize more precise representative annotations. We demonstrate our approach on images collected from Flickr image search. Experiments conducted on real Web images show the effectiveness and efficiency of the proposed model.

• Applied Microscopy
• /
• v.50
• /
• pp.23.1-23.9
• /
• 2020

We propose an effective deep learning model to denoise scanning transmission electron microscopy (STEM) image series, named Noise2Atom, to map images from a source domain 𝓢 to a target domain 𝓒, where 𝓢 is for our noisy experimental dataset, and 𝓒 is for the desired clear atomic images. Noise2Atom uses two external networks to apply additional constraints from the domain knowledge. This model requires no signal prior, no noise model estimation, and no paired training images. The only assumption is that the inputs are acquired with identical experimental configurations. To evaluate the restoration performance of our model, as it is impossible to obtain ground truth for our experimental dataset, we propose consecutive structural similarity (CSS) for image quality assessment, based on the fact that the structures remain much the same as the previous frame(s) within small scan intervals. We demonstrate the superiority of our model by providing evaluation in terms of CSS and visual quality on different experimental datasets.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.4
• /
• pp.49-57
• /
• 2012

This paper presents a fast multiple-image-based deblurring method that decreases the computation loads in the image deblurring, enhancing the sharpness of the textures or edges of the restored images. First, two blurred images with some blurring artifacts and one noisy image including severe noises are consecutively captured under a relatively long and short exposures, respectively. To improve the processing speeds, the captured multiple images are downsampled at the ratio of two, and then a way of estimating the point spread function(PSF) based on the image or edge patches extracted from the whole images, is introduced. The method enables to effectively reduce the computation time taken in the PSF prediction. Next, the texture-enhanced image deblurring method of supplementing the ability of the texture representation degraded by the downsampling of the input images, is developed and then applied. Finally, to get the same image size as the original input images, an upsampling method of utilizing the sharp edges of the captured noisy image is applied. By using the proposed method, the processing times taken in the image deblurring, which is the main obstacle of its application to the digital cameras, can be shortened, while recovering the fine details of the textures or edge components.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1987.04a
• /
• pp.42-45
• /
• 1987

In this paper a target tracking algorithm of the centroid extraction from moving edges is proposed, It aims to avoid the difficulty of imahe segmentation in case of the centroid extraction from one frame. The performance of the proposed algorithmfor noisy and occluded images is discussed Finally it is also applied to a real time target tracker.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.622-624
• /
• 2002

본 논문에서는 선택적 주의에 기반한 잡영 영상에서의 목표물 탐지 방법에 대해 기술한다. 특히 제안하는 방법은 목표물에 대한 아무런 지식을 사용하지 않고, 단지 입력되는 영상의 상향식 단서만을 사용하여 목표물을 탐지해냄으로써 여러 다양한 분야에 일반적으로 사용될 수 있다. 제안하는 시스템에서는 몇 가지 기본 특징들이 입력된 영상에서 바로 추출되며, 이러한 특징들이 서로 통합되어 가는 과정에서 목표물 탐지에 유용하지 않은 정보는 자연스럽게 걸러지며, 유용한 정보는 추가되고 부각되어진다. 간단한 영상부터 복잡한 자연영상에 이르는 다양한 잡영 영상을 대상으로 실험하여 제안하는 시스템의 성능을 평가하였다.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.485-488
• /
• 2003

A conventional correlation target tracker is analysed with a simple mathematical approach. And, we will propose a correlation measure with selective attentional property in order to overcome the false-peak problem of the conventional methods. Various experimental results show that the proposed correlation measure is able to reduce considerably the probability of false-peaks degraded by the correlation between background images of a reference block and a distorted and noisy sensor input image.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.4
• /
• pp.817-823
• /
• 2004

This paper describes a three dimensional motion recognition algorithm and a system which adopts the algorithm for non-contact human-computer interaction. From sequence of stereos images, five feature regions are extracted with simple color segmentation algorithm and then those are used for three dimensional locus calculation precess. However, the result is not so stable, noisy, that we introduce principal component analysis method to get more robust motion recognition results. This method can overcome the weakness of conventional algorithms since it directly uses three dimensional information motion recognition.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1313-1316
• /
• 1993

This paper presents a fuzzy system that estimates the optimal bit allocation matrices for the spatially active subimage classes of adaptive transform image coding in noisy channels. Transform image coding is good for image data compression but it requires a transmission error protection scheme to maintain the performance since the channel noise degrades its performance. The fuzzy system provides a simple way of estimating the bit allocation matrices from the optimal bit map computed by the method of minimizing the mean square error between the transform coefficients of the original and the reconstructed images.