• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3976-3990
• /
• 2022

Currently, cross-attention is widely used in Siamese trackers to replace traditional correlation operations for feature fusion between template and search region. The former can establish a similar relationship between the target and the search region better than the latter for robust visual object tracking. But existing trackers using cross-attention only focus on rich semantic information of high-level features, while ignoring the appearance information contained in low-level features, which makes trackers vulnerable to interference from similar objects. In this paper, we propose a Multi-level Cross-attention Siamese network(MCSiam) to aggregate the semantic information and appearance information at the same time. Specifically, a multi-level cross-attention module is designed to fuse the multi-layer features extracted from the backbone, which integrate different levels of the template and search region features, so that the rich appearance information and semantic information can be used to carry out the tracking task simultaneously. In addition, before cross-attention, a target-aware module is introduced to enhance the target feature and alleviate interference, which makes the multi-level cross-attention module more efficient to fuse the information of the target and the search region. We test the MCSiam on four tracking benchmarks and the result show that the proposed tracker achieves comparable performance to the state-of-the-art trackers.

• Journal of information and communication convergence engineering
• /
• v.8 no.5
• /
• pp.575-580
• /
• 2010

Eye gaze as a form of input was primarily developed for users who are unable to use usual interaction devices such as keyboard and the mouse; however, with the increasing accuracy in eye gaze detection with decreasing cost of development, it tends to be a practical interaction method for able-bodied users in soon future as well. This paper explores a low-cost, robust, rotation and illumination independent eye gaze system for gaze enhanced user interfaces. We introduce two brand-new algorithms for fast and sub-pixel precise pupil center detection and 2D Eye Gaze estimation by means of deformable template matching methodology. In this paper, we propose a new algorithm based on the deformable angular integral search algorithm based on minimum intensity value to localize eyeball (iris outer boundary) in gray scale eye region images. Basically, it finds the center of the pupil in order to use it in our second proposed algorithm which is about 2D eye gaze tracking. First, we detect the eye regions by means of Intel OpenCV AdaBoost Haar cascade classifiers and assign the approximate size of eyeball depending on the eye region size. Secondly, using DAISMI (Deformable Angular Integral Search by Minimum Intensity) algorithm, pupil center is detected. Then, by using the percentage of black pixels over eyeball circle area, we convert the image into binary (Black and white color) for being used in the next part: DTBGE (Deformable Template based 2D Gaze Estimation) algorithm. Finally, using DTBGE algorithm, initial pupil center coordinates are assigned and DTBGE creates new pupil center coordinates and estimates the final gaze directions and eyeball size. We have performed extensive experiments and achieved very encouraging results. Finally, we discuss the effectiveness of the proposed method through several experimental results.

• The KIPS Transactions:PartD
• /
• v.14D no.5
• /
• pp.509-516
• /
• 2007

The demand for Web applications that un on databases has been rapidly increased in every area including business. Comparing to this growing demand, it still takes much time to write and maintain Web applications. In this paper, we introduce the Web script generator, WebGen that generates the Web forms as application interface and the Web scripts that process the queries by the forms operating with a database. WebGen generates five Web scripts(Search, Select, Edit, Information, and Action) from built-in templates that are the frames for those scripts by applying the declarative contents of a user-written configuration file. Each script except the Action script generates a corresponding form as user interface. Therefore, WebGen enhances Web application productivity by reducing the development time and effort for Web applications. Unlike the commercial Web script generators, WebGen supports easy version management because it is based on independent templates. Moreover, a WebGen-generated form includes not only the interested entity but also the entities that are related directly and indirectly with the interested entity.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.623-632
• /
• 2009

In this paper, we propose a pulmonary nodule registration for the tracking of lung nodules in sequential CT scans. Our method consists of following five steps. First, a translational mismatch is corrected by aligning the center of optimal bounding volumes including each segmented lung. Second, coronal maximum intensity projection(MIP) images including a rib structure which has the highest intensity region in baseline and follow-up CT series are generated. Third, rigid transformations are optimized by normalized average density differences between coronal MIP images. Forth, corresponding nodule candidates are defined by Euclidean distance measure after rigid registration. Finally, template matching is performed between the nodule template in baseline CT image and the search volume in follow-up CT image for the nodule matching. To evaluate the result of our method, we performed the visual inspection, accuracy and processing time. The experimental results show that nodules in serial CT scans can be rapidly and correctly registered by coronal MIP-based rigid registration and local template matching.

• Journal of Broadcast Engineering
• /
• v.13 no.6
• /
• pp.875-882
• /
• 2008

Ear detection in an image processing is the one of the important area in biometrics. In this paper we propose a human ear detection algorithm with side face images. First, we search a face candidate area in an input image by using skin-color model and try to find an ear area based on Haar-like feature. Then, to verity whether it is the ear area or not, we use the template which is excellent object classification compare to recognize the characters in the plate. In this experiment, the proposed method showed that the processing speed is improved by 60% than previous works and the detection success rate is 92%.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.48 no.2
• /
• pp.165-173
• /
• 2012

Nationally, flatfish vaccination has been performed manually, and is a laborious and time-consuming procedure with low accuracy. The handling requirement also makes it prone to contamination. With a view to eliminating these drawbacks, we designed an automatic vaccine system in which the injection is delivered by a Cartesian coordinate robot guided by a vision system. The automatic vaccine injection system is driven by an injection site location algorithm that uses a template-matching technique. The proposed algorithm was designed to derive the time and possible angles of injection by comparing a search area with a template. The algorithm is able to vaccinate various sizes of flatfish, even when they are loaded at different angles. We validated the performance of the proposed algorithm by analyzing the injection error under randomly generated loading angles. The proposed algorithm allowed an injection rate of 2000 per hour on average. Vaccination of flatfish with a body length of up to 500mm was possible, even when the orientation of the fish was random. The injection errors in various sizes of flatfish were very small, ranging from 0 to 0.6mm.

• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.213-223
• /
• 2004

In this paper, we propose a new face detection method for real-time applications. It is based on the template-matching and appearance-based method. At first, we apply Min-max normalization with histogram equalization to the input image according to the variation of intensity. By applying the PCA transform to both the input image and template, PC components are obtained and they are applied to the LDA transform. Then, we estimate the distances between the input image and template, and we select one region which has the smallest distance. SVM is used for final decision whether the candidate face region is a real face or not. Since we detect a face region not the full region but within the $\pm$12 search window, our method shows a good speed and detection rate. Through the experiments with 6 category input videos, our algorithm shows the better performance than the existing methods that use only the PCA transform. and the PCA and LDA transform.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.417-417
• /
• 2000

This paper proposes a face detection and recognition method that combines the template matching method and the eigenface method with the neural network. In the face extraction step, the skin color information is used. Therefore, the search region is reduced. The global property of the face is achieved by the eigenface method. Face recognition is performed by a neural network that can learn the face property.

• Proceedings of the PSK Conference
• /
• 2003.10b
• /
• pp.186.1-186.1
• /
• 2003

Bradykinin is an autocoid related to acute and chronic pain and inflammation. The non-peptide bradykinin antagonists are of interest as novel anti-inflammatory therapeutics. Some active compounds such as FR 173657, LF 160687, and bradyzide were reported very recently. In our search for the new bradykinin antagonists, we designed and synthesized the iminodiacetic acid derivatives having two or three amide bonds and lipophilic ring system in each molecule. Liquid phase combinatorial synthesis using the iminodiacetic acid template gave diverse individual compounds rapidly and efficiently on a 10-50 mg scale. (omitted)

• Journal of the Semiconductor & Display Technology
• /
• v.12 no.1
• /
• pp.1-7
• /
• 2013

Grey-level statistical models have been widely used in many applications for object location and identification. However, conventional models yield some problems in model refinement when training images are not properly aligned, and have difficulties for real-time recognition of arbitrarily rotated models. This paper presents improved grey-level statistical models that align training images using image or feature matching to overcome problems in model refinement of conventional models, and that enable real-time recognition of arbitrarily rotated objects using efficient hierarchical search methods. Edges or features extracted from a mean training image are used for accurate alignment of models in the search image. On the aligned position and orientation, fitness measure based on grey-level statistical models is computed for object recognition. It is demonstrated in various experiments in PCB inspection that proposed methods are superior to conventional methods in recognition accuracy and speed.