• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.6
• /
• pp.49-59
• /
• 2008

SIFT(Scale Invariant Feature Transform) is an algorithm to extract vectors at pixels around keypoints, in which the pixel colors are very different from neighbors, such as vortices and edges of an object. The SIFT algorithm is being actively researched for various image processing applications including 3-D image constructions, and its most computation-intensive stage is a keypoint localization. In this paper, we develope a fixed-point model of the keypoint localization and propose its efficient hardware architecture for embedded applications. The bit-length of key variables are determined based on two performance measures: localization accuracy and error rate. Comparing with the original algorithm (implemented in Matlab), the accuracy and error rate of the proposed fixed point model are 93.57% and 2.72% respectively. In addition, we found that most of missing keypoints appeared at the edges of an object which are not very important in the case of keypoints matching. We estimate that the hardware implementation will give processing speed of $10{\sim}15\;frame/sec$, while its fixed point implementation on Pentium Core2Duo (2.13 GHz) and ARM9 (400 MHz) takes 10 seconds and one hour each to process a frame.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.4
• /
• pp.325-332
• /
• 2022

Determination of VLBI IVP (Very Long Baseline Interferometry Invariant Point) position with high accuracy is required to compute local tie vectors between the space geodetic techniques. In general, reflective targets are attached on VLBI antenna and slant distances, horizontal and vertical angles are measured from the pillars. Then, adjustment computation is performed by using the mathematical model which connects measurements and unknown parameters. This indicates that the accuracy of the estimated solutions is affected by the accuracy of the measurements. One of issues in local tie surveying, however, is that the reflective targets are not in favorable condition, that is, the reflective sheet target cannot be perfectly aligned to the instrument perpendicularly. Deviation from the line of sight of an instrument may cause different type of measurement errors. This inherent limitation may lead to incorrect stochastic modeling for the measurements in adjustment computation procedures. In this study, error characteristics by measurement types and pillars are analyzed, respectively. The analysis on the studentized residuals is performed after adjustment computation. The normality of the residuals is tested and then equal variance test between the measurement types are performed. The results show that there are differences in variance according to the measurement types. Differences in variance between distances and angle measurements are observed when F-test is performed for the measurements from each pillar. Therefore, more detailed stochastic modeling is required for optimal solutions, especially in local tie survey.

• The KIPS Transactions:PartD
• /
• v.9D no.2
• /
• pp.173-184
• /
• 2002

This paper discuss an index-based subsequence matching that supports time warping in large sequence databases. Time warping enables finding sequences with similar patterns even when they are of different lengths. In earlier work, Kim et al. suggested an efficient method for whole matching under time warping. This method constructs a multidimensional index on a set of feature vectors, which are invariant to time warping, from data sequences. For filtering at feature space, it also applies a lower-bound function, which consistently underestimates the time warping distance as well as satisfies the triangular inequality. In this paper, we incorporate the prefix-querying approach based on sliding windows into the earlier approach. For indexing, we extract a feature vector from every subsequence inside a sliding window and construct a multidimensional index using a feature vector as indexing attributes. For query processing, we perform a series of index searches using the feature vectors of qualifying query prefixes. Our approach provides effective and scalable subsequence matching even with a large volume of a database. We also prove that our approach does not incur false dismissal. To verify the superiority of our approach, we perform extensive experiments. The results reveal that our approach achieves significant speedup with real-world S&P 500 stock data and with very large synthetic data.

• Journal of KIISE:Software and Applications
• /
• v.27 no.1
• /
• pp.62-73
• /
• 2000

In this paper, we propose a criteria which can be applied to classify conventional color feature based Content Based Image Retrieval (CBIR) methods with its application areas, and a new image retrieval method which can represent sufficient spatial information in the image and is powerful in invariant searching to translation, rotation and enlargement transform. As the conventional color feature based CBIR methods can not sufficiently include the spatial information in the image, in general, they have drawbacks, which are weak to the translation or rotation, enlargement transform. To solve it, they have represented the spatial information by partitioning the image. Retrieval efficiency, however, is decreased rapidly as increasing the number of the feature vectors. We classify conventional methods to ones using 1st order relations and ones using 2nd order relations as their color object relation, and propose a new method using 3rd order relation of color objects which is good for the translation, rotation and enlargement transform. It makes quantized 24 buckets and selects 3 high scored histogram buckets and calculates 3 mean positions of pixels in 3 buckets and 3 angles. Then, it uses them as feature vectors of a given image. Experiments show that the proposed method is especially good at enlarged images and effective for its small calculation.

• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.463-472
• /
• 2000

In this paper, we consider the problem of realizing associative memories via cellular neural network(CNN). After introducing qualitative properties of the CNN model, we formulate the synthesis of CNN that can store given binary vectors with optimal performance as a constrained optimization problem. Next, we observe that this problem's constraints can be transformed into simple inequalities involving linear matrix inequalities(LMIs). Finally, we reformulate the synthesis problem as a generalized eigenvalue problem(GEVP), which can be efficiently solved by recently developed interior point methods. Proposed method can be applied to both space varying template CNNs and space-invariant template CNNs. The validity of the proposed approach is illustrated by design examples.

• Journal of Intelligence and Information Systems
• /
• v.12 no.1
• /
• pp.95-105
• /
• 2006

This paper proposes a novel approach to represent the image by using shape descriptor having an information of area. The proposed descriptor is a set of vectors, consists of radius, area and direction parameters in the concentrated center point. Due to the area parameter, we know our descriptor can obtain the information of area. Also, we give an extended shape descriptor to get more detailed representation. To do this, we move the center point of our vision to that point for region of interest. By doing so about all of region of interest, we can get our descriptor for detailed information of the image. From more detailed descriptor, it's natural that it's more efficient fur representation, retrievals and so on. We make it the normalized pattern and expand to improve its quality. The proposed method is invariant to scale, position and rotation. The results show that it can be used efficiently for image representation as we can see in retrievals of silhouette images.

• Journal of KIISE:Databases
• /
• v.35 no.4
• /
• pp.345-355
• /
• 2008

SIFT is popularly used in computer vision application such as object recognition, motion tracking, and 3D reconstruction among various shape descriptors. However, it is not easy to apply SIFT into the image similarity search as it is since it uses many high dimensional keypoint vectors. In this paper, we present a SIFT based image similarity search method using an edge image pyramid and an interesting region detection. The proposed method extracts keypoints, which is invariant to contrast, scale, and rotation of image, by using the edge image pyramid and removes many unnecessary keypoints from the image by using the hough transform. The proposed hough transform can detect objects of ellipse type so that it can be used to find interesting regions. Experimental results demonstrate that the retrieval performance of the proposed method is about 20% better than that of traditional SIFT in average recall.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1176-1194
• /
• 2018

The object classification using the images' contents is a big challenge in computer vision. The superpixels' information can be used to detect and classify objects in an image based on locations. In this paper, we proposed a methodology to detect and classify the image's pixels' locations using enhanced bag of words (BOW). It calculates the initial positions of each segment of an image using superpixels and then ranks it according to the region score. Further, this information is used to extract local and global features using a hybrid approach of Scale Invariant Feature Transform (SIFT) and GIST, respectively. To enhance the classification accuracy, the feature fusion technique is applied to combine local and global features vectors through weight parameter. The support vector machine classifier is a supervised algorithm is used for classification in order to analyze the proposed methodology. The Pascal Visual Object Classes Challenge 2007 (VOC2007) dataset is used in the experiment to test the results. The proposed approach gave the results in high-quality class for independent objects' locations with a mean average best overlap (MABO) of 0.833 at 1,500 locations resulting in a better detection rate. The results are compared with previous approaches and it is proved that it gave the better classification results for the non-rigid classes.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.11A
• /
• pp.1946-1956
• /
• 2001

In this paper, we propose a novel 2-D partial matching algorithm based on model-based stochastic analysis of feature correspondences in a relation vector space, which is quite robust to shape variations as well as invariant to geometric transformations. We represent an object using the ARG (Attributed Relational Graph) model with features of a set of relation vectors. In addition, we statistically model the partial occlusion or noise as the distortion of the relation vector distribution in the relation vector space. Our partial matching algorithm consists of two-phases. First, a finite number of candidate sets areselected by using logical constraint embedding local and structural consistency Second, the feature loss detection is done iteratively by error detection and voting scheme thorough the error analysis of relation vector space. Experimental results on real images demonstrate that the proposed algorithm is quite robust to noise and localize target objects correctly even inseverely noisy and occluded scenes.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.1
• /
• pp.15-22
• /
• 2005

In this paper, we propose a face recognition system by using the CCD color image. We first get the face candidate image by using YCbCr color model and adaptive skin color information. And we use it initial curve of active contour model to extract face region. We use the Eye map and mouth map using color information for extracting facial feature from the face image. To obtain center point of Log-polar image, we use extracted facial feature from the face image. In order to obtain feature vectors, we use extracted coefficients from DCT and wavelet transform. To show the validity of the proposed method, we performed a face recognition using neural network with BP learning algorithm. Experimental results show that the proposed method is robuster with higher recogntion rate than the conventional method for the rotation and scale variant.