• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.425-430
• /
• 2022

As robots are considered one of the mainstream digital transformations, robots with machine vision becomes a main area of study providing the ability to check what robots watch and make decisions based on it. However, it is difficult to find a small object in the image mainly due to the flaw of the most of visual recognition networks. Because visual recognition networks are mostly convolution neural network which usually consider local features. So, we make a model considering not only local feature, but also global feature. In this paper, we propose a detection method of a small marker on the object using deep learning and an algorithm that considers global features by combining Transformer's self-attention technique with a convolutional neural network. We suggest a self-attention model with new definition of Query, Key and Value for model to learn global feature and simplified equation by getting rid of position vector and classification token which cause the model to be heavy and slow. Finally, we show that our model achieves higher mAP than state of the art model YOLOr.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.5 s.305
• /
• pp.103-114
• /
• 2005

This paper presents a content-based image retrieval (CBIR) method using the combination of color and texture features. As a color feature, a color autocorrelogram is chosen which is extracted from the hue and saturation components of a color image. As a texture feature, BDIP(block difference of inverse probabilities) and BVLC(block variation of local correlation coefficients) are chosen which are extracted from the value component. When the features are extracted, the color autocorrelogram and the BVLC are simplified in consideration of their calculation complexity. After the feature extraction, vector components of these features are efficiently quantized in consideration of their storage space. Experiments for Corel and VisTex DBs show that the proposed retrieval method yields 9.5% maximum precision gain over the method using only the color autucorrelogram and 4.0% over the BDIP-BVLC. Also, the proposed method yields 12.6%, 14.6%, and 27.9% maximum precision gains over the methods using wavelet moments, CSD, and color histogram, respectively.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.3
• /
• pp.167-173
• /
• 2002

In this paper, we propose an interactive genetic algorithm (IGA) to implement an automated 2D avatar synthesis. The IGA technique is capable of expressing user's personality in the avatar synthesis by using the user's response as a candidate for the fitness value. Our suggested IGA method is applied to creating avatars automatically. Unlike the previous works, we introduce the concepts of 'hidden population', as well as 'primitive avatar' and 'simplified genotype', which are used to overcome the shortcomings of IGA such as human fatigue or reliability, and reasonable rates of convergence with a less number of iterations. The procedure of designing avatar models consists of two steps. The first step is to detect the facial feature points and the second step is to create the subjectively optimal avatars with diversity by embedding user's preference, intuition, emotion, psychological aspects, or a more general term, KANSEI. Finally, the combined processes result in human-friendly avatars in terms of both genetic optimality and interactive GUI with reliability.

• Journal of Korea Multimedia Society
• /
• v.6 no.4
• /
• pp.698-706
• /
• 2003

The primary goal of surface approximation is to reduce the degree of deviation of the simplified surface from the original surface. However it is difficult to define the metric that can measure the amount of deviation quantitatively. Many of the existing studies analogize it by using the change of the scalar quantity before and after simplification. This approach makes a lot of sense in the point that the local surfaces with small scalar are relatively less important since they make a low impact on the adjacent areas and thus can be removed from the current surface. However using scalar value alone there can exist many cases that cannot compute the degree of geometric importance of local surface. Especially the perceptual geometric features providing important clues to understand an object, in our observation, are generally constructed with small scalar value. This means that the distinguishing features can be removed in the earlier stage of the simplification process. In this paper, to resolve this problem, we present various factors and their combination as the metric for calculating the deviation error by introducing the orientation of local surfaces. Experimental results indicate that the surface orientation has an important influence on measuring deviation error and the proposed combined error metric works well retaining the relatively high curvature regions on the object's surface constructed with various and complex curvatures.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.10 no.2
• /
• pp.63-71
• /
• 1992

The digital map database is often produced for multiple purposes, including mapping at multiple scales; it is increasingly rare that a base map is digitized for mapping at a single scale. The most important problems in process of line simplification in map generalization and multiple representation is that tolerance value selected for simplifying base map information must be modified as feature geometry varies within the digital file to ensure both accuracy and recognizability of graphic details on a generalized map. In this study, we explored various algorithms regarding to line simplication at many scales from a single digital file, and presents a rule by which to determine those scale at which line feature geometry might be expected to change in map representation. By applying two measured of displacement between a digitized line and its simplification, five algorithms have been evaluated. The results indicate that, of the five, the Douglas-Peucker routine produced less displacement between a line and its simplification. The research has proved to automating map simplification, incorporating numeric guidelines into digital environment about what magnitude and variation in geometric detail should be preserved as the digital data is simplified for representation at reduced map scales.

• Journal of KIISE
• /
• v.42 no.4
• /
• pp.475-482
• /
• 2015

Developing a high-performance Semantic Role Labeling (SRL) system for a domain requires manually annotated training data of large size in the same domain. However, such SRL training data of sufficient size is available only for a few domains. Performances of Korean SRL are degraded by almost 15% or more, when it is directly applied to another domain with relatively small training data. This paper proposes two techniques to minimize performance degradation in the domain transfer. First, a domain adaptation algorithm for Korean SRL is proposed which is based on the prior model that is one of domain adaptation paradigms. Secondly, we proposed to use simplified features related to morphological and syntactic tags, when using small-sized target domain data to suppress the problem of data sparseness. Other domain adaptation techniques were experimentally compared to our techniques in this paper, where news and Wikipedia were used as the sources and target domains, respectively. It was observed that the highest performance is achieved when our two techniques were applied together. In our system's performance, F1 score of 64.3% was considered to be 2.4~3.1% higher than the methods from other research.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.722-727
• /
• 2010

This paper is presented to study simplification of face image using cubic spline interpolation for a business card with 2D barcode. People often forget business card's owner because business cards don't be included a face picture generally. To solve such problem, many applications have be developed through mobile devices, Internet and so on. But they couldn't caught up with value of existing business card mad by paper. Hence, some methods which can put information on business card using 1D or 2D barcode had suggested. but they couldn't include information like face image or company logo image which have too much data. Therefore, we study the simplification method of face image to encode from a face image to 2D barcode. The simplification method using spline curves defined by feature points which we dotted on face, ears, hair, eyebrows, nose, lips, neck, etc.. on a face area. for experiment, we see real face image and simplified face image made by proposed method after we automatically extract face watch through camera. In experimental results, data of simplified face image was reduced as small as it can be expressed by 2D barcode, and confirmed that it can effectively express features.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.83-93
• /
• 2013

Recently, the SURF algorithm, which is conjugated for object tracking system as part of many computer vision applications, is a well-known scale- and rotation-invariant feature detection algorithm. The SURF, due to its high computational complexity, there is essential to develop a hardware accelerator in order to be used on an IP in embedded environment. However, the SURF requires a huge local memory, causing many problems that increase the chip size and decrease the value of IP in ASIC and SoC system design. In this paper, we proposed a way to design a SURF algorithm in hardware with greatly reduced local memory by partitioning the algorithms into several Sub-IPs using external memory and a DMA. To justify validity of the proposed method, we developed an example of simplified object tracking algorithm. The execution speed of the hardware IP was about 31 frame/sec, the logic size was about 74Kgate in the 30nm technology with 81Kbytes local memory in the embedded system platform consisting of ARM Cortex-M0 processor, AMBA bus(AHB-lite and APB), DMA and a SDRAM controller. Hence, it can be used to the hardware IP of SoC Chip. If the image processing algorithm akin to SURF is applied to the method proposed in this paper, it is expected that it can implement an efficient hardware design for target application.