• ETRI Journal
• /
• v.38 no.3
• /
• pp.502-509
• /
• 2016

Feature detection and description are key ingredients of common image processing and computer vision applications. Most existing algorithms focus on robust feature matching under challenging conditions, such as inplane rotations and scale changes. Consequently, they usually fail when the scene is blurred by camera shake or an object's motion. To solve this problem, we propose a new feature description algorithm that is robust to image blur and significantly improves the feature matching performance. The proposed algorithm builds a feature descriptor by considering the integral projection along four angular directions ($0^{\circ}$, $45^{\circ}$, $90^{\circ}$, and $135^{\circ}$) and by combining four projection vectors into a single highdimensional vector. Intensive experiment shows that the proposed descriptor outperforms existing descriptors for different types of blur caused by linear motion, nonlinear motion, and defocus. Furthermore, the proposed descriptor is robust to intensity changes and image rotation.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.38-41
• /
• 2002

Mammography is considered the single most important diagnostic tool in the early detection of breast cancer. Today's dedicated mammographic equipment, specially designed x-ray screen/film combinations, coupled with controlled film processing, produces excellent image quality and can detect very low contrast small lesions. In mammography, it is most important to produce consistent high-contrast, high-resolution images at the lowest radiation dose consistent with high image quality. Some of the major technical development milestones that have let to today's high quality in mammographic imaging are reviewed. Both the American College of Radiology Mammography Accreditation Program and the Mammography Quality Standards Act have significant impact on the improvement of the technical quality of mammographic images in the United States and worldwide. A most recent development in digital mammography has opened up avenues for improving diagnosis.

• Journal of Korea Multimedia Society
• /
• v.20 no.11
• /
• pp.1720-1728
• /
• 2017

Active shape model is widely used in the field of image processing especially on arbitrary meaningful shape extraction from single gray level image. Cootes et. al. showed efficient detection of variable shape from image by using covariance and mean shape from learning. There are two stages of learning and testing. Hahn applied enhanced shape alignment method rather than using Cootes's rotation and scale scheme. Hahn did not modified the profile itself. In this paper, the method using directional one dimensional profile is proposed to enhance Cootes's one dimensional profile and the shape alignment algorithm of Hahn is combined. The performance of the proposed method was superior to Cootes's and Hahn's. Average landmark estimation error for each image was 27.72 pixels and 39.46 for Cootes's and 33.73 for Hahn's each.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.5
• /
• pp.465-472
• /
• 2009

This paper proposes a multimodal information transformation system that converts the image information to the voice information to provide the sight impaired people with walking area and obstacles, which are extracted by an acquired image from a single CCD camera. Using a chain-code line detection algorithm, the walking area is found from the vanishing point and boundary of a sidewalk on the edge image. And obstacles are detected by Gabor filter of extracting vertical lines on the walking area. The proposed system expresses the voice information of pre-defined sentences, consisting of template words which mean walking area and obstacles. The multi-modal information transformation system serves the useful voice information to the sight impaired that intend to reach their destination. The experiments of the proposed algorithm has been implemented on the indoor and outdoor environments, and verified its superiority to exactly provide walking parameters sentences.

• Journal of information and communication convergence engineering
• /
• v.2 no.1
• /
• pp.52-57
• /
• 2004

In this paper, we propose a panorama-based object tracking scheme for wide-view surveillance systems that can detect and track moving objects with a pan-tilt camera. A dynamic mosaic of the background is progressively integrated in a single image using the camera motion information. For the camera motion estimation, we calculate affine motion parameters for each frame sequentially with respect to its previous frame. The camera motion is robustly estimated on the background by discriminating between background and foreground regions. The modified block-based motion estimation is used to separate the background region. Each moving object is segmented by image subtraction from the mosaic background. The proposed tracking system has demonstrated good performance for several test video sequences.

• The Journal of the Korea Contents Association
• /
• v.17 no.1
• /
• pp.137-144
• /
• 2017

Face detection is still a challenging task under severe face pose variations in complex background. This paper proposes an effective algorithm which can detect single or multiple faces based on skin color detection and depth information. We introduce Gaussian mixture model(GMM) for skin color detection in a color image. The depth information is from three dimensional depth sensor of Kinect V2 device, and is useful in segmenting a human body from the background. Then, a labeling process successfully removes non-face region using several features. Experimental results show that the proposed face detection algorithm can provide robust detection performance even under variable conditions and complex background.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.70-80
• /
• 2010

This study proposes the algorithm to automate image alignment and detect marginal bone destructions, based on subtraction radiography for dental radiographic images necessary for dental PACS, which hasn't been covered by related literatures. The proposed algorithm enables a quick and precise detection of marginal bone destructions around teeth including implant through the knowlege-based multi-template matching in reference to ROI(Region Of Interest) obtained from applicable teeth using information about their geometric forms to solve problems single-template matching is exposed to. Actually, the test showed that it was possible not only to quickly and precisely detect marginal bone destructions around teeth, but also to get more objective and quantitative results through the algorithm.

• 한국지형공간정보학회:학술대회논문집
• /
• 1993.10a
• /
• pp.141-145
• /
• 1993

A new digital change detection algorithm, Euclidean Distance Analysis, was developed in an attempt to utilize the multi-band information in a selected band-comination, as an alternative to the conventional single-band analysis methods. To evaluate the relative performance of this new method, image differencing was applied. The better performance in change detection between the two algorithms investigated was provided by the Euclidean distance analysis. The new technique of Euclidean distance analysis holds promise for change detection, since it summarizes the multiple-band information on the cover-type changes and reduces the data dimensionality. It is suggested to further evaluate this new method, quantitatively, in the different environments. The use of different accuracy indices was also examined in the determining the optimal threshold level for each change image. As the standard measure for classification accuracy, the Kappa coefficient of agreement was used for evaluation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.75-77
• /
• 2012

In this paper, We proposed that real-time pupil detection using local binarization at each region of eyes in image. In image obtained a single low-resolution web-camera, we detect a region of face using haar-like feature and then detect each region of eyes depending upon the rate of width and height of region of face respectively. In each region of eyes, we detect the pupil after local preprocessing and binarizing. This pupil detection can be variously used for HCI(Human-Computer Interface) systems.

• Journal of Broadcast Engineering
• /
• v.28 no.1
• /
• pp.124-131
• /
• 2023

Object detection techniques are increasingly used to obtain information on physical characteristics or situations of a specific area from remote images. The accuracy of object detection is decreased in remote sensing images with low resolution because the low resolution reduces the amount of detail that can be captured in an image. A single neural network is proposed to joint the super-resolution method and object detection method. The proposed method constructs a deep residual-based network to restore object features in low-resolution images. Moreover, the proposed method is used to improve the performance of object detection by jointing a single network with YOLOv5. The proposed method is experimentally tested using VEDAI data for low-resolution images. The results show that vehicle detection performance improved by 81.38% on mAP@0.5 for VISIBLE data.