• Journal of the Semiconductor & Display Technology
• /
• v.13 no.2
• /
• pp.45-52
• /
• 2014

This paper proposes an efficient photo retrieval system that automatically indexes for searching of relevant images, using a combination of geo-coded information, direction/location of image capture device and content-based visual features. A photo image is labeled with its GPS (Global Positioning System) coordinates and direction of the camera view at the moment of capture, and the label leads to generate a geo-spatial index with three core elements of latitude, longitude and viewing direction. Then, content-based visual features are extracted and combined with the geo-spatial information, for indexing and retrieving the photo images. For user's querying process, the proposed method adopts two steps as a progressive approach, filtering the relevant subset prior to use a content-based ranking function. To evaluate the performance of the proposed scheme, we assess the simulation performance in terms of average precision and F-score, using a natural photo collection. Comparing the proposed approach to retrieve using only visual features, an improvement of 20.8% was observed. The experimental results show that the proposed method exhibited a significant enhancement of around 7.2% in retrieval effectiveness, compared to previous work. These results reveal that a combination of context and content analysis is markedly more efficient and meaningful that using only visual feature for image search.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2004.05a
• /
• pp.479-485
• /
• 2004

The purpose of this study is to develop a practical image inspection system that could recognize it correctly, endowing flexibility to the productive field, although the same object for work will be changed in the size and rotated. In this experiment, it selected a fighter, rotating the direction from $30^{\circ}\;to\;45^{\circ}$ simultaneously while changing the size from 1/4 to 1/16, as an object inspection without using another hardware for exclusive image processing. The invariant moments, Hu has suggested, was used as feature vector moment descriptor. As a result of the experiment the image inspection system developed from this research was operated in real-time regardless of the chance of size and rotation for the object inspection, and it maintained the correspondent rates steadily above from 94% to 96%. Accordingly, it is considered as the flexibility can be considerably endowed to the factory automation when the image inspection system developed from this research is applied to the productive field.

• The Journal of the Korea Contents Association
• /
• v.17 no.3
• /
• pp.42-52
• /
• 2017

Panorama image is a single image obtained by combining images taken at several viewpoints through matching of corresponding points. Existing panoramic image generation methods that find the corresponding points are extracting local invariant feature points in each image to create descriptors and using descriptor matching algorithm. In the case of video sequence, frames may be a lot, so therefore it may costs significant amount of time to generate a panoramic image by the existing method and it may has done unnecessary calculations. In this paper, we propose a method to quickly create a single panoramic image from a video sequence. By assuming that there is no significant changes between frames of the video such as in locally, we use the FAST algorithm that has good repeatability and high-speed calculation to extract feature points and the Lucas-Kanade algorithm as each feature point to track for find the corresponding points in surrounding neighborhood instead of existing descriptor matching algorithms. When homographies are calculated for all images, homography is changed around the center image of video sequence to warp images and obtain a planar panoramic image. Finally, the spherical panoramic image is obtained by performing inverse transformation of the spherical coordinate system. The proposed method was confirmed through the experiments generating panorama image efficiently and more faster than the existing methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.1 s.307
• /
• pp.39-44
• /
• 2006

In this paper, search result list synthesis method is proposed using borda count method for still image retrieval based on MPEG-7 descriptors. MPEG-7 standardizes descriptors that extract feature information from media data. In many cases, using a single descriptor lacks of correctness, it is suggested to use multiple descriptors to enhance retrieval efficiency. In this paper, retrieval efficiency enhancement is achieved by combining multiple search results which are from each descriptor. In combining search result, newly calculated borda count method is proposed. Comparing current frequency compensated calculation, rank considered frequency compensation is used to score animage in database. This combining method is considered in Content based image retrieval system with relevance feedback algorithm which uses high level information from system user. In each relevance iteration step, adoptive borda count method is used to calculate score of images.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.52-60
• /
• 2022

Few-shot learning is a sub-area of machine learning problems, which aims to classify target images that only contain a few labeled samples for training. As a representative few-shot learning method, the Prototypical network has been received much attention due to its simplicity and promising results. However, the Prototypical network uses the sample mean of samples from the same class as the prototypes of that class, which easily results in learning uncharacteristic features in the low-data scenery. In this study, we propose to use local descriptors (i.e., patches along the channel within feature maps) from the same class to explicitly obtain more representative prototypes for Prototypical Network so that significant intra-class feature information can be maintained and thus improving the classification performance on few-shot learning tasks. Experimental results on various benchmark datasets including mini-ImageNet, CUB-200-2011, and tiered-ImageNet show that the proposed method can learn more discriminative intra-class features by the local descriptors and obtain more generic prototype representations under the few-shot setting.

• The KIPS Transactions:PartB
• /
• v.15B no.5
• /
• pp.391-396
• /
• 2008

Motion of object in a video clip often plays an important role in characterizing the content of the clip. A number of methods have been developed to analyze and retrieve video contents using motion information. However, most of these methods focused more on the analysis of direction or trajectory of motion but less on the analysis of the movement of an object itself. In this paper, we propose the shape sequence descriptor to describe and compare the movement based on the shape deformation caused by object motion along the time. A movement information is first represented a sequence of 2D shape of object extracted from input image sequence, and then 2D shape information is converted 1D shape feature using the shape descriptor. The shape sequence descriptor is obtained from the shape descriptor sequence by frequency transform along the time. Our experiment results show that the proposed method can be very simple and effective to describe the object movement and can be applicable to semantic applications such as content-based video retrieval and human movement recognition.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.77-80
• /
• 2013

SURF algorithm is an algorithm to extract feature points and to generate descriptors from input images. It is robust to change of environment such as scale, rotation, illumination and view points. Because of these features, it is used for many image processing applications such as object recognition, constructing panorama pictures and 3D image restoration. But there is disadvantage for real time operation because many recognition algorithms such as SURF algorithm requires a lot of calculations. In this paper, we propose a design of feature extractor and descriptor generator based on SURF for high memory efficiency. The proposed design reduced a memory access and memory usage to operate in real time.

• Journal of Korea Multimedia Society
• /
• v.14 no.3
• /
• pp.368-377
• /
• 2011

This paper explains the hardware structure of SURF(Speeded Up Robust Feature) based feature point extractor and its FPGA verification result. SURF algorithm produces novel scale- and rotation-invariant feature point and descriptor which can be used for object recognition, creation of panorama image, 3D Image restoration. But the feature point extraction processing takes approximately 7,200msec for VGA-resolution in embedded environment using ARM11(667Mhz) processor and 128Mbytes DDR memory, hence its real-time operation is not guaranteed. We analyzed integral image memory access pattern which is a key component of SURF algorithm to reduce memory access and memory usage to operate in c real-time. We assure feature extraction that using a Vertex-5 FPGA gives 60frame/sec of VGA image at 100Mhz.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.49-60
• /
• 2020

To solve the edge ringing or block effect caused by the partial differential diffusion in image enhancement domain, a new image enhancement algorithm based on bidirectional diffusion, which smooths the flat region or isolated noise region and sharpens the edge region in different types of defect images on aviation composites, is presented. Taking the image pixel's neighborhood intensity and spatial characteristics as the attribute descriptor, the presented bidirectional diffusion model adaptively chooses different diffusion criteria in different defect image regions, which are elaborated are as follows. The forward diffusion is adopted to denoise along the pixel's gradient direction and edge direction in the pixel's smoothing area while the backward diffusion is used to sharpen along the pixel's gradient direction and the forward diffusion is used to smooth along the pixel's edge direction in the pixel's edge region. The comparison experiments were implemented in the delamination, inclusion, channel, shrinkage, blowhole and crack defect images, and the comparison results indicate that our algorithm not only preserves the image feature better but also improves the image contrast more obviously.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.12-20
• /
• 2011

In this paper, we propose an efficient object detection and classification algorithm for video surveillance applications. Previous researches mainly concentrated either on object detection or classification using particular type of feature e.g., Scale Invariant Feature Transform (SIFT) or Speeded Up Robust Feature (SURF) etc. In this paper we propose an algorithm that mutually performs object detection and classification. We combinedly use heterogeneous types of features such as texture and color distribution from local patches to increase object detection and classification rates. We perform object detection using spatial clustering on interest points, and use Bag of Words model and Naive Bayes classifier respectively for image representation and classification. Experimental results show that our combined feature is better than the individual local descriptor in object classification rate.