• ETRI Journal
• /
• 제41권1호
• /
• pp.73-83
• /
• 2019

This paper describes in detail the processing path leading to successful phase images stitching in digital holographic microscope for the extension of the field of view. It applies FIJI Grid/Collection Stitching Plugin, which is a general tool for images stitching, non-specific for phase images. The FIJI plugin is extensively supported by aberration and phase offset correction. Comparative analysis of different aberration correction methods and data processing strategies is presented, together with the critical analysis of their applicability. The proposed processing path provides good background for statistical phase analysis of cell cultures and digital phase pathology.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.571-585
• /
• 2021

Applications for object detection are expanding as it is automated through artificial intelligence-based processing, such as deep learning, on a large volume of images and videos. High dependence on training data and a non-transparent way to find answers are the common characteristics of deep learning. Attacks on training data and training models have emerged, which are closely related to the nature of deep learning. Privacy, integrity, and robustness for the extracted information are important security issues because deep learning enables object recognition in images and videos. This paper summarizes the security issues that need to be addressed for future applications and analyzes the state-of-the-art security studies related to robustness, privacy, and integrity of object detection for images and videos.

• Journal of information and communication convergence engineering
• /
• 제19권1호
• /
• pp.36-41
• /
• 2021

Text-based image retrieval is not only cumbersome as it requires the manual input of keywords by the user, but is also limited in the semantic approach of keywords. However, content-based image retrieval enables visual processing by a computer to solve the problems of text retrieval more fundamentally. Vision applications such as extraction and mapping of image characteristics, require the processing of a large amount of data in a mobile environment, rendering efficient power consumption difficult. Hence, an effective image retrieval method on mobile platforms is proposed herein. To provide the visual meaning of keywords to be inserted into images, the efficiency of image retrieval is improved by extracting keywords of exchangeable image file format metadata from images retrieved through a content-based similar image retrieval method and then adding automatic keywords to images captured on mobile devices. Additionally, users can manually add or modify keywords to the image metadata.

• 한국정밀공학회지
• /
• 제10권3호
• /
• pp.220-230
• /
• 1993

Photoelastic isochromatic fringes related to the difference of principal stresses have some bandwidth whose light intensities are not constant and asymmetrical in experimental images. Hence, it is difficult to measure fringe order accurately at a data point by visual observation. In this study, a method of fringe sharpening, which can extract shapened lines from both full-and half-order fringes by digital image processing, is developed. To test the method, various simple photelastic fringe patterns are simulated and their images are processed to yield sharpened lines. The method is then applied to general problems such as images of a circular disk compressed by diametrically concentrated loads and a circular cylinder sybject to internal pressure. The procedure is proved to be capable of extracting sharpened lines accurately from photoelastic isochromatic fringes.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.764-767
• /
• 2021

While Generative Adversarial Networks (GANs) have seen huge success in image synthesis tasks, synthesizing high-quality images from text descriptions is a challenging problem in computer vision. This paper proposes a method named Text-to-Face Generation Using Multi-Scale Gradients for Conditional Generative Adversarial Networks (T2F-MSGGANs) that combines GANs and a natural language processing model to create human faces has features found in the input text. The proposed method addresses two problems of GANs: model collapse and training instability by investigating how gradients at multiple scales can be used to generate high-resolution images. We show that T2F-MSGGANs converge stably and generate good-quality images.

• 한국분무공학회지
• /
• 제29권2호
• /
• pp.91-97
• /
• 2024

When investigating the droplet, spray, and impact of liquid on a solid plate, backlight imaging has been widely used to understand these phenomena. However, some previous studies have suffered from poor image quality. In this study, various combinations of image processing algorithms, such as white image correction, histogram equalization, CLAHE, Otsu's binarization, and multi-Otsu's binarization, have been applied to flash boiling spray images to enhance image quality for qualitative observation and semi-quantitative spray angle evaluation. To acquire images with high contrast for qualitative observation, applying CLAHE was effective, making small droplets and detailed shapes of the jet noticeable. However, when images were averaged to determine spray angle or penetration length based on intensity, this method induced artifact unphysical patterns, thus requiring careful consideration. Based on the algorithm proposed in this study, the spray angle variation according to injection pressure and temperature has been calculated, showing a reasonable trend.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.835-838
• /
• 2000

Popular methods for extracting a text region in video images are in general based on analysis of a whole image such as merge and split method, and comparison of two frames. Thus, they take long computing time due to the use of a whole image. Therefore, this paper suggests the faster method of extracting a text region without processing a whole image. The proposed method uses line sampling methods, FFT and neural networks in order to extract texts in real time. In general, text areas are found in the higher frequency domain, thus, can be characterized using FFT The candidate text areas can be thus found by applying the higher frequency characteristics to neural network. Therefore, the final text area is extracted by verifying the candidate areas. Experimental results show a perfect candidate extraction rate and about 92% text extraction rate. The strength of the proposed algorithm is its simplicity, real-time processing by not processing the entire image, and fast skipping of the images that do not contain a text.

• 한국인터넷방송통신학회논문지
• /
• 제19권2호
• /
• pp.19-24
• /
• 2019

디지털 영상 분야의 디지털 테크놀로지 발전은 다양한 형태의 미디어 환경을 만들어 내며 급격하게 변모하고 있다. 이러한 영상분야는 멀티미디어 테크놀로지의 급격한 발전을 통해 방송 영상 처리 기술 분야에서는 보다 실감나는 영상을 제공하기 위해 지속적인 발전을 하고 있으며 평면 화질 향상의 요구는 거의 충족되어 기술적 포화상태에 이르게 되었다. 현재 평면 화질에서는 3D 입체 영상 화질에서 충족시킬 수 없는 시각피로 분야에 대한 자유성 및 대중성을 갖고 있다는 장점을 보유하고 있으며 보완 작업 기술 분야로는 평면 화질에서의 입체감 향상 기술이라고 할 수 있다. 본 연구에서는 평면 디스플레이에서 제공되는 그래픽 영상을 대상으로 색채 속성과의 연관성을 알아보고자 입체감 관련 실험을 진행하고 이를 분석하였다. 실험에 사용된 색채 속성으로는 색상, 밝기, 채도를 차등적으로 그래픽 영상에 적용하여 입체감이 가장 큰 요인에 대해 분석하고 아노바 분산분석을 통해 교호작용을 검증하였다. 본 연구에서 진행된 실험결과를 분석하여 입체감과 관련 있는 색채 요인의 유의미 여부를 정의하고 그래픽 영상 처리 시 입체감 향상을 위한 색채 조절 방안을 제시한다.

• 정보처리학회논문지A
• /
• 제19A권3호
• /
• pp.121-128
• /
• 2012

본 논문은 다양한 해상도에서의 초음파 영상 처리를 위한 최적의 프로세싱 엘리먼트 구조를 제안한다. 이를 위해 본 논문에서는 각 프로세싱 엘리먼트(processing element, PE)당 처리되는 영상 데이터(data-per-processing element, DPE) 수를 변화시키는 실험을 통해 시스템의 성능(system performance), 에너지 효율(energy efficiency), 면적 효율(area efficiency)을 각각 측정하고, 측정된 결과를 바탕으로 최적의 매니코어 프로세서 구조를 선택하였다. 모의실험 결과, 에너지 효율은 $256{\times}256$, $768{\times}1,024$, $1,024{\times}1,280$ 해상도를 갖는 영상에서 PE 개수가 각각 1,024개, 4,096개, 16,384개일 때 가장 높았다. 또한 면적 효율은 $256{\times}256$ 해상도의 영상에서는 PE 개수가 256개, $768{\times}1,024$와 $1,024{\times}1,280$ 해상도의 영상에서는 4,096개에서 가장 높은 효율을 보였다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권1호
• /
• pp.49-54
• /
• 2016

Regarding global and local factors of a set of features, a given single image or multiple images is a common approach in image processing. This paper introduces an application of an adaptive version of non-local filter whose original version searches non-local similarity for removing noise. Since most images involve texture partner in both foreground and background, extraction of signified regions with texture is a challenging task. Aiming to the detection of visual attention regions for images with texture, we present the contrast analysis of image patches located in a whole image but not nearby with assistance of the adaptive filter for estimation of non-local divergence. The method allows extraction of signified regions with texture of images of wild life. Experimental results for a benchmark demonstrate the ability of the proposed method to deal with the mentioned challenge.