• Journal of Broadcast Engineering
• /
• v.7 no.2
• /
• pp.145-152
• /
• 2002

As the number of digital images available to users is exponentially growing due to the rapid development of digital technology, content-based image retrieval (CBIR) has been one of the most active research areas. A variety of image retrieval methods have been proposed, where, given an input query image, the images that are similar to the input are retrieved from an image database based on low-level features such as colors and textures. However, most of the existing retrieval methods did not consider the case when an input query image is a part of a whole image in the database due to the high complexity involved in partial matching. In this paper, we present an efficient method for partial image matching by using the histogram distribution relationships between query image and whole image. The proposed approach consists of two steps: the first step prunes the search space and the second step performs block-based retrieval using partial image matching to rank images in candidate set. The experimental results demonstrate the feasibility of the proposed algorithm after assuming that the response tune of the system is very high while retrieving only by using partial image matching without Pruning the search space.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.2
• /
• pp.99-105
• /
• 2017

Generally, stereo matching methods are used to estimate depth information based on color and spatial similarity. However, most depth estimation methods suffer from the occlusion region because occlusion regions cause inaccurate depth information. Moreover, they do not consider the temporal dimension when estimating the disparity. In this paper, we propose a temporal stereo matching method, considering occlusion and disregarding inaccurate temporal depth information. First, we apply a global stereo matching algorithm to estimate the depth information, we segment the image to occlusion and non-occlusion regions. After occlusion detection, we fill the occluded region with a reasonable disparity value that are obtained from neighboring pixels of the current pixel. Then, we apply a temporal disparity estimation method using the reliable information. Experimental results show that our method detects more accurate occlusion regions, compared to a conventional method. The proposed method increases the temporal consistency of estimated disparity maps and outperforms per-frame methods in noisy images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.4
• /
• pp.617-623
• /
• 2018

In this paper, we propose a novel seamless video composition method based on shape matching and Poisson equation. Video composition method consists of video segmentation process and video blending process. In the video segmentation process, the user first sets a trimap for the first frame, and then performs a grab-cut algorithm. Next, considering that the performance of video segmentation may be reduced if the color, brightness and texture of the object and the background are similar, the object region segmented in the current frame is corrected through shape matching between the objects of the current frame and the previous frame. In the video blending process, the object of source video and the background of target video are blended seamlessly using Poisson equation, and the object is located according to the movement path set by the user. Simulation results show that the proposed method has better performance not only in the naturalness of the composite video but also in computational time.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.4
• /
• pp.164-174
• /
• 2015

In a real scenario, radiometric change has frequently occurred in the stereo image acquisition process using multiple cameras with geometric characteristics or moving a single camera because it has different camera parameters and illumination change. Conventional stereo matching algorithms have a difficulty in finding correct corresponding points because it is assumed that corresponding pixels have similar color values. In this paper, we present a new method based on the local descriptor reflecting intensity, gradient and texture information. Furthermore, an adaptive weight for local descriptor based on the entropy is applied to estimate correct corresponding points under radiometric variation. The proposed method is tested on Middlebury datasets with radiometric changes, and compared with state-of-the-art algorithms. Experimental result shows that the proposed scheme outperforms other comparison algorithms around 5% less matching error on average.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.450-453
• /
• 2002

In radiotherapy treatment planning, it is critical to deliver the radiation dose to tumor and protect surrounding normal tissue. Recent developments in functional imaging and radiotherapy treatment technology have been raising chances to control tumor saving normal tissues. A brain phantom which could be used for image registration technique of CT-MR and CT-SPECT images using surface matching was developed. The brain phantom was specially designed to obtain imaging dataset of CT, MR, and SPECT. The phantom had an external frame with 4 N-shaped pipes filled with acryl rods, Pb rods for CT, MR, and SPECT imaging, respectively. 8 acrylic pipes were inserted into the empty space of the brain phantom to be imaged for geometric evaluation of the matching. For an optimization algorithm of image registration, we used Downhill simplex algorithm suggested as a fast surface matching algorithm. Accuracy of image fusion was assessed by the comparison between the center points of the section of N-shaped bars in the external frame and the inserted pipes of the phantom and minimized cost functions of the optimization algorithm. Technique with partially transparent, mixed images using color on gray was used for visual assessment of the image registration process. The errors of image registration of CT-MR and CT-SPECT were within 2mm and 4mm, respectively. Since these errors were considered within a reasonable margin from the phantom study, the phantom is expected to be used for conventional image registration between multimodal image datasets..

• Journal of IKEEE
• /
• v.28 no.1
• /
• pp.65-71
• /
• 2024

This paper proposes a neural network that can reduce the number of parameters while reducing matching errors in occluded regions to increase the accuracy of depth maps in stereo matching. Stereo matching-based object recognition is utilized in many fields to more accurately recognize situations using images. When there are many objects in a complex image, an occluded area is generated due to overlap between objects and occlusion by background, thereby lowering the accuracy of the depth map. To solve this problem, existing research methods that create context information and combine it with the cost volume or RoIselect in the occluded area increase the complexity of neural networks, making it difficult to learn and expensive to implement. In this paper, we create a depthwise seperable neural network that enhances regional feature extraction before cost volume generation, reducing the number of parameters and proposing a neural network that is robust to occlusion errors. Compared to PSMNet, the proposed neural network reduced the number of parameters by 30%, improving 5.3% in color error and 3.6% in test loss.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.15 no.2
• /
• pp.15-24
• /
• 1997

In DTP systems, satisfactory matching the appearance of displayed image on CRT and that of a reproduced binary image is very important. Most halftoning techniques assume that the printed color dots are square. However, most printers produce roughly circular dots. Thus, there is overlap between adjacent dots, and dots accupy adjcent space that should be empty space. These results are because the significant image distortion on the reproduced images. In this paper, we proposed a new tone correction digital halftoning method based on equi-visual perception characteristic.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.151-154
• /
• 2000

차량 번호판 영상을 안정적으로 추출하여 인식하는 방법에는 여러 가지 땅법들이 제시되어 왔다. 기존의 연구들은 번호판 영역 추출에는 높은 성공률을 보이고 있으나 상대적으로 문자 인식의 성공률이 그에 미치지 못해서 전체적인 인식 성공률에 저하를 가져오는 경우가 대부분 이었다. 따라서 본 연구에서는 칼라 정보를 이용하여 입력 영상의 밝기 보정과 번호판 영역을 추출하고 N4M (Normalized 4 - Mash)을 적용하여 문자인식 처리 시간을 단축시키고 인식글을 향상시킬 수 있었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.8C
• /
• pp.772-781
• /
• 2009

This paper proposes a novel algorithm for the efficient classification and retrieval of medical images. After color and edge features are extracted from medical images, these two feature vectors are then applied to a multi-class Support Vector Machine, to give membership vectors. Thereafter, the two membership vectors are combined into an ensemble feature vector. Also, to reduce the search time, Correlated Categories Vector is proposed for similarity matching. The experimental results show that the proposed system improves the retrieval performance when compared to other methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.417-417
• /
• 2000

This paper proposes a face detection and recognition method that combines the template matching method and the eigenface method with the neural network. In the face extraction step, the skin color information is used. Therefore, the search region is reduced. The global property of the face is achieved by the eigenface method. Face recognition is performed by a neural network that can learn the face property.