• Journal of Biomedical Engineering Research
• /
• v.42 no.3
• /
• pp.80-85
• /
• 2021

We developed a model to classify the absence of cervical cancer using deep learning from the cervical image to which the histogram equalization algorithm was applied, and to compare the performance of each model. A total of 4259 images were used for this study, of which 1852 images were normal and 2407 were abnormal. And this paper applied Image Sharpening(IS), Histogram Equalization(HE), and Contrast Limited Adaptive Histogram Equalization(CLAHE) to the original image. Peak Signal-to-Noise Ratio(PSNR) and Structural Similarity index for Measuring image quality(SSIM) were used to assess the quality of images objectively. As a result of assessment, IS showed 81.75dB of PSNR and 0.96 of SSIM, showing the best image quality. CLAHE and HE showed the PSNR of 62.67dB and 62.60dB respectively, while SSIM of CLAHE was shown as 0.86, which is closer to 1 than HE of 0.75. Using ResNet-50 model with transfer learning, digital image-processed images are classified into normal and abnormal each. In conclusion, the classification accuracy of each model is as follows. 90.77% for IS, which shows the highest, 90.26% for CLAHE and 87.60% for HE. As this study shows, applying proper digital image processing which is for cervical images to Computer Aided Diagnosis(CAD) can help both screening and diagnosing.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.430-436
• /
• 2021

The non-contact body temperature measurement system is one of the key factors, which is manage febrile diseases in mass facilities using optical and thermal imaging cameras. Conventional systems can only be used for simple body temperature measurement in the face area, because it is used only a deep learning-based face detection algorithm. So, there is a limit to detecting abnormal symptoms of the infants and young children, who have difficulty expressing their opinions. This paper proposes an improved facial expression recognition algorithm for detecting abnormal symptoms in infants and young children. The proposed method uses an object detection model to detect infants and young children in an image, then It acquires the coordinates of the eyes, nose, and mouth, which are key elements of facial expression recognition. Finally, facial expression recognition is performed by applying a selective sharpening filter based on the obtained coordinates. According to the experimental results, the proposed algorithm improved by 2.52%, 1.12%, and 2.29%, respectively, for the three expressions of neutral, happy, and sad in the UTK dataset.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.1 s.307
• /
• pp.9-16
• /
• 2006

This Paper proposes an adaptive error diffusioThis paper proposes an adaptive error diffusion algorithm for text enhancement followed by an efficient text segmentation that uses the maximum gradient difference (MGD). The gradients are calculated along with scan lines, and the MGD values are filled within a local window to merge the potential text segments. Isolated segments are then eliminated in the non-text region filtering process. After the left segmentation, a conventional error diffusion method is applied to the background, while the edge enhancement error diffusion is used for the text. Since it is inevitable that visually objectionable artifacts are generated when using two different halftoning algorithms, the gradual dilation is proposed to minimize the boundary artifacts in the segmented text blocks before halftoning. Sharpening based on the gradually dilated text region (GDTR) prevents the printing of successive dots around the text region boundaries. The error diffusion algorithm with edge enhancement is extended to halftone color images to sharpen the tort regions. The proposed adaptive error diffusion algorithm involves color halftoning that controls the amount of edge enhancement using a general error filter. The multiplicative edge enhancement parameters are selected based on the amount of edge sharpening and color difference. Plus, the additional error factor is introduced to reduce the dot elimination artifact generated by the edge enhancement error diffusion. By using the proposed algorithm, the text of a scanned image is sharper than that with a conventional error diffusion without changing background.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1889-1900
• /
• 2022

Roads are an essential factor in the physical functioning of modern society. The spatial information of the road has much longer update cycle than the traffic situation information, and it is necessary to generate the information faster and more accurately than now. In this study, as a way to achieve that goal, the Pan-sharpening technique was applied to satellite images of Kompsat 3 and 3A to improve spatial resolution. Then, the data were used for road extraction using the semantic segmentation technique, which has been actively researched recently. The acquired Kompsat 3/3A pan-sharpened images were trained by putting it into a U-Net based segmentation model along with Massachusetts road data, and the applicability of the images were evaluated. As a result of training and verification, it was found that the model prediction performance was maintained as long as certain conditions were maintained for the input image. Therefore, it is expected that the possibility of utilizing satellite images such as Kompsat satellite will be even higher if rich training data are constructed by applying a method that minimizes the impact of surrounding environmental conditions affecting models such as shadows and surface conditions.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.3
• /
• pp.27-34
• /
• 2011

In this paper, the novel approach for image contrast enhancement is introduced. The method is based on the unsharp mask and directional information of images. Since the unsharp mask techniques give better visual quality than the conventional sharpening mask, there are much works on image enhancement using unsharp masks. The proposed algorithm decomposes the image to several blocks and extracts directional information using DCT. From the geometric properties of the block, each block is labeled as appropriate type and processed by adaptive unsharp mask. The masking process is skipped at the flat area to reduce the noise artifact, but at the texture and edge area, the adaptive unsharp mask is applied to enhance the image contrast based on the edge direction. Experiments show that the proposed algorithm produces the contrast enhanced images with superior visual quality, suppressing the noise effects and enhancing edge at the same time.

• Journal of information and communication convergence engineering
• /
• v.9 no.6
• /
• pp.689-694
• /
• 2011

Cellular automata are discrete dynamical systems, which provide the basis for the synthesis of complex emergent behavior. This paper proposes a new algorithm of digital watermarking based on cellular automata transform (CAT). The idea of two-dimensional CAT is introduced into the algorithm. After the original image is disassembled with 2D CAT, the watermark information is embedded into the Middle-frequency of the carrier picture. Cellular automata have a huge number of combinations, such as gateway values, rule numbers, initial configuration, boundary condition, etc. Using CAT, the robustness of the watermark will be tremendous strengthened as well as its imperceptibility. Experimental results show that this algorithm can resist some usual attacks such as compression, sharpening and so on. The proposed method is robust to different attacks and is more security.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.200-203
• /
• 2019

영상처리 분야에서 이미지 샤프닝 기법은 주관적 화질 향상에 큰 역할을 하고 있다. 본 논문에서는 모폴로지 기법을 이용한 향상된 이미지 샤프닝 알고리듬을 제안한다. 기존의 Sobel이나 Laplacian 연산자는 에지 검출에 있어서 잡음에 취약하다는 단점이 있다. 이를 해결하기 위해 잡음에 상대적으로 민감하지 않은 모폴로지 기법을 이용했다. 우선, 침식 연산을 수행한 이미지와 원본 이미지와의 차를 통해 에지를 얻는다. 이 에지는 원본 이미지의 히스토그램의 표준 편자 값을 기반으로 원본 이미지와 가중합을 통해 에지를 중점적으로 선명하게 만든다. 실험을 통해 제안하는 알고리듬은 기존의 Sobel이나 Laplacian 연산자 보다 우수한 성능을 보임을 알 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.28-30
• /
• 2011

본 논문에서는 특이값 분해(Singular Value Decomposition)을 이용하여 이미지의 주파수 영역 내에 정보를 은닉하는 방법을 제시한다. 이미지를 주파수 영역으로 변환하기 위하여 블록 단위로 이산 코사인 변환(Discrete Cosine Transform)을 수행한다. 이후 인접한 네 블록의 DC 값들로 구성된 행렬의 특이값을 은닉하고자 하는 정보에 따라 변환한다. 원래의 DC 값은 정보에 따라 변환된 DC 값으로 대체되고 역 이산 코사인 변환(Inverse Discrete Cosine Transform)을 수행하여 정보가 은닉된 이미지를 얻는다. 제안하는 알고리즘의 성능을 분석하기 위해 JPEG(Joint Photographic Coding Experts Group), 선명화(Sharpening), 히스토그램 등화(Histogram Equalization)와 같이 다양한 이미지 변화를 거친 후, 은닉된 정보의 신뢰도를 비교한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1998.11a
• /
• pp.186-189
• /
• 1998

셀룰러 오토마타는 복잡한 자연 세계를 단순한 규칙으로 해석할 수 있고, 병렬 계산이 가능하다. 본 논문에서는 국부적인 천이 규칙(transient rule)에 의해 움직이는 셀룰러 오토마타를 이용해 화상에 대한 아무런 사전 지식이 없는 상태에서의 화상 첨예화 알고리즘을 제안한다. 제안된 셀룰러 오토마타는 화상의 첨예화를 위한 3개의 천이 규칙을 가지며, 화상의 각 픽셀에서 4연결 이웃과 자유 경계조건을 가진다. 각 규칙은 각기 고유한 특징을 가지면서 화상을 첨예화한다. 또한 이러한 셀룰러 오토마타는 순차적이고 병렬적인 움직임을 가지며, 이 움직임은 Lyapunov functional을 만족하는 감소함수로 표현된다. 따라서 셀룰러 오토마타를 이용한 화상의 첨예화는 매우 빠른 속도로 수렴하고, 잡음에도 안정적인 결과를 나타낸다. 실험을 통해 본 방법의 유효성을 확인한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.11a
• /
• pp.104-106
• /
• 2017

본 논문에서는 급부상하고 있는 가상현실 기술에서의 저작권 보호를 위해 VR영상을 타겟으로 하는 워터마킹 방법을 제안한다. 제안하는 방법은 VR영상의 합성에 널리 사용되는 SIFT 알고리즘을 통해 조건에 만족하는 점을 찾고, 그 점을 중심으로 한 주변 영역에 이산 웨이블릿 변환을 수행하여 워터마크를 삽입하는 방법이다. 또한 추출할 때에는 기존에 삽입한 워터마크와의 NCC값을 비교하여 일정 임계값 이상의 데이터들을 추출하고, 통계적 방법으로 최종 워터마크를 확정하게 된다. 이에 대해 가우시안 필터. 가우시안 노이즈, Sharpening, 회전변환, JPEG 압축 등의 공격을 가하고, 공격 후 추출되는 워터마크의 NCC, BER 값을 비교하여 워터마크의 강인성(robustness)을 확인한다.