• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.1 s.307
• /
• pp.1-8
• /
• 2006

This paper presents a fast full search algorithm for motion estimation applicable to multiple reference images. The proposed method is an extended version of the rate constrained successive elimination algorithm (RSEA) for multiple reference frame applications. We will show that motion estimation for the reference images temporally preceding the first reference image can be less intensive in computation compared with that for the first reference image. for computational reduction, we will drive a new condition to lead the smaller number of candidate blocks for the best matched block. Simulation results explain that our method reduces computation complexity although it has the same quality as RSEA.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5C
• /
• pp.536-541
• /
• 2007

In video coding standard H.264/AVC, motion estimation using multiple reference pictures improves compression efficiency but the efficiency depends upon image content not the number of reference pictures. So, the motion estimation includes a large amount of computation of no worth according to image. This paper proposes fast motion estimation algorithm that removes worthless computation in the motion estimation using multiple reference pictures. The proposed algorithm classifies a block into valid and invalid blocks for the multiple reference pictures and removes the workless computation by applying a single reference picture to the invalid block. To estimate the proposed algorithm's performance, image quality, bit rate, and motion estimation time are compared with ones of the conventional algorithm in the reference software JM 9.5. The simulation results show that the proposed algorithm can considerably save about 38.67% the averaged motion estimation time while keeping the image quality and the bit rate, whose are average values are -0.02dB and -0.77% respectively, as good as the conventional algorithm.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.1
• /
• pp.101-109
• /
• 2011

This paper describes the attempts to improve the performance of an image matching method for multiple image. Typically, matching between two images is performed by using correlation between a reference and corresponding images. The proposed multiple image matching algorithm performs matching in an object space, chooses the image closest to the true vertical image as a reference image, calculates the correlation based on the chosen reference image. The algorithm also detects occluded regions automatically and keep them from matching. We could find that it is possible to create high quality DEM by this method, regardless of the location of image. From the performance improvement experiments through the occlusion detection, we could confirm the possibility of a more accurate representation of 3D information.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.75-86
• /
• 2022

The existing image quality assessment (IQA) datasets have a small number of samples. Some methods based on transfer learning or data augmentation cannot make good use of image quality-related features. A No Reference (NR)-IQA method based on multi-task training and quality awareness is proposed. First, single or multiple distortion types and levels are imposed on the original image, and different strategies are used to augment different types of distortion datasets. With the idea of weak supervision, we use the Full Reference (FR)-IQA methods to obtain the pseudo-score label of the generated image. Then, we combine the classification information of the distortion type, level, and the information of the image quality score. The ResNet50 network is trained in the pre-train stage on the augmented dataset to obtain more quality-aware pre-training weights. Finally, the fine-tuning stage training is performed on the target IQA dataset using the quality-aware weights to predicate the final prediction score. Various experiments designed on the synthetic distortions and authentic distortions datasets (LIVE, CSIQ, TID2013, LIVEC, KonIQ-10K) prove that the proposed method can utilize the image quality-related features better than the method using only single-task training. The extracted quality-aware features improve the accuracy of the model.

• ETRI Journal
• /
• v.39 no.1
• /
• pp.97-107
• /
• 2017

A fast and accurate building-level visual place recognition method built on an image-retrieval scheme using street-view images is proposed. Reference images generated from street-view images usually depict multiple buildings and confusing regions, such as roads, sky, and vehicles, which degrades retrieval accuracy and causes matching ambiguity. The proposed practical database refinement method uses informative reference image and keypoint selection. For database refinement, the method uses a spatial layout of the buildings in the reference image, specifically a building-identification mask image, which is obtained from a prebuilt three-dimensional model of the site. A global-positioning-system-aware retrieval structure is incorporated in it. To evaluate the method, we constructed a dataset over an area of $0.26km^2$. It was comprised of 38,700 reference images and corresponding building-identification mask images. The proposed method removed 25% of the database images using informative reference image selection. It achieved 85.6% recall of the top five candidates in 1.25 s of full processing. The method thus achieved high accuracy at a low computational complexity.

• International Journal of Advanced Culture Technology
• /
• v.7 no.4
• /
• pp.321-326
• /
• 2019

As AI technology is recently introduced into various fields, it is being applied to the fashion field. This paper proposes a system for recommending cody clothes suitable for a user's selected clothes. The proposed system consists of user app, cody recommendation module, and server interworking of each module and managing database data. Cody recommendation system classifies clothing images into 80 categories composed of feature combinations, selects multiple representative reference images for each category, and selects 3 full body cordy images for each representative reference image. Cody images of the representative reference image were determined by analyzing the user's preference using Google survey app. The proposed algorithm classifies categories the clothing image selected by the user into a category, recognizes the most similar image among the classification category reference images, and transmits the linked cody images to the user's app. The proposed system uses the ResNet-50 model to categorize the input image and measures similarity using ORB and HOG features to select a reference image in the category. We test the proposed algorithm in the Android app, and the result shows that the recommended system runs well.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.5
• /
• pp.548-554
• /
• 2009

We propose an automatic inspection system for hologram with multiple patterns. The system hardware consists of illuminations, camera, and vision processor. Multiple illuminations using LEDs are arranged in different directions to acquire each image of patterns. The system software consists of pre-processing, pattern generation, and pattern matching. The acquired images of input hologram are compared with their reference patterns by developed matching algorithm. To compensate for the positioning error of input hologram, reference patterns of hologram for different position should be generated in on-line. We apply a frequency transformation based CGH(computer-generated hologram) method to generate reference images. For the fast pattern matching, we also apply the matching method in the frequency domain. Experimental results for hologram of Korean currency are then presented to verify the usefulness of proposed system.

• Radiation Oncology Journal
• /
• v.35 no.2
• /
• pp.101-111
• /
• 2017

The number of imaging data sets has significantly increased during radiation treatment after introducing a diverse range of advanced techniques into the field of radiation oncology. As a consequence, there have been many studies proposing meaningful applications of imaging data set use. These applications commonly require a method to align the data sets at a reference. Deformable image registration (DIR) is a process which satisfies this requirement by locally registering image data sets into a reference image set. DIR identifies the spatial correspondence in order to minimize the differences between two or among multiple sets of images. This article describes clinical applications, validation, and algorithms of DIR techniques. Applications of DIR in radiation treatment include dose accumulation, mathematical modeling, automatic segmentation, and functional imaging. Validation methods discussed are based on anatomical landmarks, physical phantoms, digital phantoms, and per application purpose. DIR algorithms are also briefly reviewed with respect to two algorithmic components: similarity index and deformation models.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.521-524
• /
• 2005

This paper proposes a fusion algorithm which merges multiple vein pattern images into a single image, larger than those images. As a preprocessing step of template matching, during the verification of biometric data such as fingerprint image, vein pattern image of hand, etc., the fusion technique is used to make reference image larger than the candidate images in order to enhance the matching performance. In this paper, a new algorithm, called BSA (Boundary Stitching Algorithm) is proposed, in which the boundary rectilinear parts extracted from the candidate images are stitched to the reference image in order to enlarge its matching space. By applying BSA to practical vein pattern verification system, its verification rate was increased by about 10%.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.410-413
• /
• 1988

In this paper, the real-time optical associative memory using multiple hologram which is generated with two angular multiplexed reference beams and Fourier transformed object beam in the $BaTiO_{3}$ crystal based on DFWM mechanism. When one image is recorded in the $BaTiO_{3}$ crystal, complete image can be recalled by 9 % partial input of the stored original image without any additional thresholding and optical feedback process. As an experimental result of multiple Fourier hologram which is recorded with two binary images, OHCHAS and PARKHK, we can obtain complete image recalled by 1/6 partial input of the stored image.