The Experts below are selected from a list of 24375 Experts worldwide ranked by ideXlab platform
Fumihiko Saitoh - One of the best experts on this subject based on the ideXlab platform.
-
Reliable Template Matching Using First Derivation Edge-Direction
IEEJ Transactions on Electronics Information and Systems, 2012Co-Authors: Atsuhiro Hirosawa, Fumihiko SaitohAbstract:This paper proposes a new and more reliable method for Template matching that is using the first derivation edge-direction. A Template Image is separated into local block areas and sum of inferior angle between edge-directions of target Image and edge-directions of Template Image are calculated in all block areas. For each block, a coordinate that is the highest similarity of edge-directions gets a vote and a target coordinate is decided by its result. The experimental results show that the proposed method was robust to the debased target Image with the conventional methods.
-
High‐speed Image matching using partial Template consisting of multiple rectangular areas extracted by genetic algorithm
Electronics and Communications in Japan, 2011Co-Authors: Keita Okada, Fumihiko SaitohAbstract:In normalized correlation matching, a Template Image is set by manual operation before the matching process. Namely, the contents and the size of a Template Image are determined by the human sense. This paper proposes a method of performing high-speed normalized correlation matching by extracting multiple partial areas automatically, which is effective in Image matching. These extracted multiple partial areas become the new Template Image. The proposed method extracts multiple partial areas suitable for matching by genetic algorithm. The experimental results show that multiple partial areas including an Image pattern that was useful for matching were extracted by the proposed method and that the processing time for Image matching was reduced to 50%. The proposed method has higher reliability than conventional methods. © 2011 Wiley Periodicals, Inc. Electron Comm Jpn, 94(10): 1–9, 2011; Published online in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/ecj.10373
-
High-speed Image Matching Using Partial Template Consisting of Plural Rectangular Areas Extracted by Genetic Algorithm
IEEJ Transactions on Electronics Information and Systems, 2010Co-Authors: Keita Okada, Fumihiko SaitohAbstract:In normalized correlation matching, a Template Image is set by manual operation before the matching process. Namely, the contents and the size of a Template Image are determined by the human sense. This paper proposes a method to perform a high-speed normalized correlation matching by extracting plural partial areas automatically that is effective in the Image matching. These extracted plural partial areas become the new Template Image. The proposed method extracts plural partial areas suitable for matching by genetic algorithm. The experimental results show that the plural partial areas including an Image pattern that was useful for the matching was extracted by the proposed method and processing time for Image matching was reduced to 50%. The proposed method has a higher reliability in comparison with the conventional methods.
-
Moving object detection based on correlation rate subtraction using local region Template matching
Eighth International Conference on Quality Control by Artificial Vision, 2007Co-Authors: Kunihiro Goto, Fumihiko Saitoh, Kazuhiko Yamamoto, Kunihito KatoAbstract:This paper proposes a method to detect moving objects by the background subtraction using the normalized correlation matching. The normalized correlation matching is known as one of general-purposed Template matching methods. And the method is robust against change of brightness. Therefore, it is expected that the stable detection of moving objects will be performed by using the normalized correlation matching against changing brightness of background. The proposed method regards the background Image as the Template Image and evaluates correlation rates between the background Image and the scene Image in order to extract moving objects. We also adopt the integration technique of the correlation rate to realize more stable detection.
-
Image Matching Based on Relation between Pixels Located on the Maximum and Minimum Gray-levels in Local Area
IEEJ Transactions on Electrical and Electronic Engineering, 2007Co-Authors: Fumihiko SaitohAbstract:This paper proposes a Template matching method maximum and minimum gray levels pixels sign matching (MMM) which is based on a comparison of the gray levels of a pair of pixels whose locations are on the pixels with the maximum and the minimum gray levels in a local area in a Template Image. In this method, the locations of the pixels with the maximum and the minimum gray levels are registered in a local area whose center is every pixel in a Template Image. The target Image area is searched from the matching ratio which is obtained by the relation between the gray levels of the two pixels whose locations have been registered in the Template Image. The experimental results show that the proposed method had equal or better robustness to the inferior factors of objective Images in comparison with the three typical conventional Template matching methods. Copyright © 2007 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
Hsin-chang Yang - One of the best experts on this subject based on the ideXlab platform.
-
Document Recognition and Retrieval - Image retrieval by spatial topology distances with high-order shape features
Document Recognition and Retrieval IX, 2001Co-Authors: Hsin-chang YangAbstract:We achieved content-based Image retrieval by using the shape information contained in a Image. A kind of high-order Image features which emulate the feature detection process of human eyes were used to represent both input Image and the Template Images stored in a database. Template matching was then applied between the input Image and each Template Image to obtain the retrieval result. The matching process performs a kind of pseudo elastic matching between the feature sets of the input Image and each Template Image. Such elastic matching process, together with the high-order features, provides an excellent approach to measure the dissimilarity, namely the spatial topology distance, between Images. The method had been tested on the Columbia Object Image Library database. Preliminary experiments suggested promising result by our approach.
-
ACM Multimedia Workshops - Shaped-based Image retrieval by spatial topology distances
Proceedings of the 2001 ACM workshops on Multimedia multimedia information retrieval - MULTIMEDIA '01, 2001Co-Authors: Hsin-chang YangAbstract:Shaped-based Image retrieval is achieved by measuring the spatial topology distance between the input Image and each Template Image in the database. The contour of an object in the input Image is regularly sampled as feature points which are matched to those of a Template Image by a pseudo elastic matching process. The elastic matching is achieved by performing the self-organizing map algorithm on the network which is constructed by distributing neurons to feature locations of the Template Image. The spatial topology distance is measured by the degree of distortion of the Template pattern before and after elastic matching. We tested the method on the Columbia Object Image Library database. Preliminary experiments suggested promising result by our approach.
Zhang Jia-ming - One of the best experts on this subject based on the ideXlab platform.
-
Algorithm of target tracking based on Mean-Shift with adaptive bandwidth of kernel function
Journal of Computer Applications, 2009Co-Authors: Zhang Jia-mingAbstract:To achieve adaptive bandwidth of kernel function in Mean-Shift tracking algorithm,a new method based on comparing Bhattacharyya coefficients was proposed,in which,the Bhattacharyya coefficient was firstly computed out by using of center weighted and edge weighted histograms of Template Image,and then,a new Bhattacharyya coefficient during tracking was computed out according to the edge weighted histogram of candidate Image and center weighted histogram of Template Image,finally 10% of the bandwidth of kernel function was expanded or shrunk by comparing two coefficients.The experiment results show that the method can avoid the problem of nonstop shrinking bandwidth effectively,and adapt tracking window to the change of the target size successfully.
Joel S. Perlmutter - One of the best experts on this subject based on the ideXlab platform.
-
Atlas Template Images for nonhuman primate neuroimaging: baboon and macaque.
Methods in enzymology, 2004Co-Authors: Kevin J. Black, Jonathan M. Koller, Abraham Z. Snyder, Joel S. PerlmutterAbstract:Publisher Summary This chapter elaborates the use of atlas Template Images for nonhuman primate neuroimaging. Neuroimaging in humans offers many advantages, but nonhuman species may be more appropriate for some studies, such as lesion models of human disease, drug development, pharmacologic investigations, and methods development. Baboons have been employed frequently in positron emission tomography (PET) studies due to their relatively large brain volume. The first step in creating the MRI Template Image is to transform each of the nine individual baboon MPRAGE Images to atlas space. This bootstrap step is accomplished using a previously validated but labor-intensive method that requires expert identification of certain radiological landmarks. The Images are intensity scaled using a histogram method and averaged together voxelwise to create the initial Template Image. It is found that the transformation from the 12-scan average Image to PET Template is computed by matrix multiplication of the 12-scan to MPRAGE and MPRAGE to the MRI Template. The final use of the Templates is to provide anatomic identification for the results of the statistical analysis.
-
Template Images for nonhuman primate neuroimaging 1 baboon
NeuroImage, 2001Co-Authors: Kevin J. Black, Jonathan M. Koller, Abraham Z. Snyder, Mokhtar H Gado, Joel S. PerlmutterAbstract:Abstract Coregistration of functional brain Images across many subjects offers several experimental advantages and is widely used for studies in humans. Voxel-based coregistration methods require a high-quality 3-D Template Image, preferably one that corresponds to a published atlas. Template Images are available for human, but we could not find an appropriate Template for neuroimaging studies in baboon. Here we describe the formation of a T1-weighted structural MR Template Image and a PET blood flow Template, derived from 9 and 7 baboons, respectively. Custom software aligns individual MR Images to the MRI Template; human supervision is needed only to initially estimate any gross rotational misalignment. In these aligned individual Images, internal subcortical fiducial points correspond closely to a photomicrographic baboon atlas with an average error of 1.53 mm. Cortical test points showed a mean error of 1.99 mm compared to the mean location for each point. Alignment of individual PET blood flow Images directly to the PET Template was compared to a two-step alignment process via each subject's MR Image. The two transformations were identical within 0.41 mm, 0.54°, and 1.0% (translation, rotation, and linear stretch; mean). These quantities provide a check on the validity of the alignment software as well as of the Template Images. The baboon structural MR and blood flow PET Templates are available on the Internet (purl.org/net/kbmd/b2k) and can be used as targets for any Image registration software.
Wan-chi Siu - One of the best experts on this subject based on the ideXlab platform.
-
Document Image Template matching based on component block list
Pattern Recognition Letters, 2001Co-Authors: Hanchuan Peng, Fuhui Long, Zheru Chi, Wan-chi SiuAbstract:Abstract Document Image matching is the key technique for document Image registration and retrieval. In this paper, a new matching method based on document component block list (CBL) is proposed. A document Image is firstly parsed into a number of component blocks that are defined as non-adherent rectangular areas of substantial document contents. Then these blocks are organized as a list, on which several matching operations are defined. The Template Image that is most similar to the querying document Image is selected as the matching result. Our method can effectively make use of the local information of each page component block and the global information of document page layout. We investigate the method with large-scale document Template Image database. Our method manifests good matching accuracy and good robustness to Image distortion, filled-in text, and noises.
