• Journal of KIISE
• /
• v.42 no.2
• /
• pp.203-212
• /
• 2015

This paper proposes a traffic sign recognition method in real road environments. The video stream in driving environments has two different characteristics compared to a general object video stream. First, the number of traffic sign types is limited and their shapes are mostly simple. Second, the camera cannot take clear pictures in the road scenes since there are many illumination changes and weather conditions are continuously changing. In this paper, we improve a modified census transform(MCT) to extract features effectively from the road scenes that have many illumination changes. The extracted features are collected by histograms and are transformed by the dense descriptors into very high dimensional vectors. Then, the high dimensional descriptors are encoded into a low dimensional feature vector by Fisher-vector coding and Gaussian Mixture Model. The proposed method shows illumination invariant detection and recognition, and the performance is sufficient to detect and recognize traffic signs in real-time with high accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.4
• /
• pp.811-819
• /
• 2017

A behavior pattern analysis algorithm based on descriptors consists of information of a moving object and temporal histogram is proposed. Background learning is performed first for detecting, tracking and analyzing moving objects. Each object is identified using an association of the center of gravity of objects and tracked individually. A temporal histogram represents a motion pattern using positions of the center of gravity and time stamp of objects. The characteristic and behavior of objects are figured out by comparing each coordinates of a position history in the histogram. Behavior information which is comprised with numbers of a start and end frame, and coordinates of positions of objects is stored and managed in the linked list. Descriptors are made with the stored information and the video retrieval algorithm is designed. We confirmed the higher retrieval accuracy compare with conventional methods.

• Journal of Broadcast Engineering
• /
• v.20 no.5
• /
• pp.778-781
• /
• 2015

The paper presents a new way of visual descriptor for deformable object retrieval on the basis of partition based description. The proposed descriptor technology partitions a given object into boundary area and interior area and extracts a descriptor from each area. The final descriptor combines these descriptors. From a given image, deformable object is segmented. The center position of the deformable object is calculated. The object is partitioned into N × N blocks on the basis of the given center position. Blocks are classified as boundary area and interior area depending on the pixels in the block. The proposed descriptor consists of extracted MPEG-7 dominant descriptors from both the boundary and interior area. The performance of proposed method is tested on a database of 1,973 handbag images constructed with view point changes. ARR (Average Retrieval Rate) is used for the retrieval accuracy of the proposed algorithm, compared with MPEG-7 dominant color descriptor.

• Journal of Korea Multimedia Society
• /
• v.16 no.4
• /
• pp.483-492
• /
• 2013

SURF is an algorithm which extracts feature points and generates their descriptors from input images, and it is being used for many applications such as object recognition, tracking, and constructing panorama pictures. Although SURF is known to be robust to changes of scale, rotation, and view points, it is hard to implement it in real time due to its complex and repetitive computations. Using 3.3 GHz Pentium, in our experiment, it takes 240ms to extract feature points and create descriptors in a VGA image containing about 1,000 feature points, which means that software implementation cannot meet the real time requirement, especially in embedded systems. In this paper, we present a hardware architecture that can compute the SURF algorithm very fast while consuming minimum hardware resources. Two key concepts of our architecture are parallelism (for repetitive computations) and efficient line memory usage (obtained by analyzing memory access patterns). As a result of FPGA synthesis using Xilinx Virtex5LX330, it occupies 101,348 LUTs and 1,367 KB on-chip memory, giving performance of 30 frames per second at 100 MHz clock.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.263-272
• /
• 2007

This paper proposes a skeleton-based hierarchical shape description scheme, called a skeleton tree, for accurate shape-based image retrieval. A skeleton tree represents an object shape as a hierarchical tree where high-level nodes describe parts of coarse trunk regions and low-level nodes describe fine details of boundary regions. Each node refines the shape of its parent node. Most of the noise disturbances are limited to bottom level nodes and the boundary noise is reduced by decreasing weights on the bottom levels. The similarity of two skeleton trees is computed by considering the best match of a skeleton tree to a sub-tree of another skeleton tree. The proposed method uses a hybrid similarity measure by employing both Fourier descriptors and moment invariants in computing the similarity of two skeleton trees. Several experimental results are presented demonstrating the validity of the skeleton tree scheme for the shape description and indexing.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.692-702
• /
• 2017

Face detection using the LBP based feature descriptor has issues in that it can not represent spatial information between facial shape and facial components such as eyes, nose and mouth. To address these issues, in previous research, a facial image was divided into a number of square sub-regions. However, since the sub-regions are divided into different numbers and sizes, the division criteria of the sub-region suitable for the database used in the experiment is ambiguous, the dimension of the LBP histogram increases in proportion to the number of sub-regions and as the number of sub-regions increases, the sensitivity to facial orientation rotation increases significantly. In this paper, we present a novel facial region segmentation method that can solve in-plane rotation issues associated with LBP based feature descriptors and the number of dimensions of feature descriptors. As a result, the proposed method showed detection accuracy of 99.0278% from a single facial image rotated in orientation.

• Journal of the Korean Chemical Society
• /
• v.45 no.5
• /
• pp.422-428
• /
• 2001

Retention relative times(RRTs) of PAH molecules and their derivatives in gas chromatography are trained and predicted in testing sets using a multiple linear regression(MLR) and an artificial neural network(ANN). The main descriptors of PAHs and their derivatives in QSRR are the square root of molecular weight(sqmw), molecular connectivity($^1{\chi}_v$), molecular dipole moment(D) and length-to-breadth ratios(L/B). The results of MLR shows that a heavy molecule has a propensity for long retention time. L/B closely related with slot model is a good descriptor in MLR. On the other hand, ANN which is not effected by the linear dependencies among the descriptors were exclusively based on molecular weight and molecular dipole moment. The variances which shows the accuracy of prediction for retention times in testing sets are 1.860, 0.206 for MLR and ANN, respectively. It was shown that ANN can exceed the MLR in prediction accuracy.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.60 no.1
• /
• pp.75-84
• /
• 2015

Sesame (Sesamum indicum L.) is one of the most important oilseed crops with high oil contents and rich nutrient value. The development of a core collection could facilitate easier access to sesame genetic resources for their use in crop improvement programs and simplify the genebank management. The present study was initiated to the development and evaluation of a core collection of sesame based on 5 qualitative and 10 quantitative trait descriptors on 2,751 sesame accessions. The accessions were different countries of origin. About 10.1 percent of accessions were selected by using the power core program to constitute a core collection consisting of 278 accessions. Mean comparisons using t-test, Nei's diversity index of 10 morphological descriptors and correlation coefficients among traits indicated that the existing genetic variation for these traits in the entire collection has been preserved in the core collection. The results from this study will provide effective information for future germplasm conservation and improvement programs in sesame.

• Journal of the Korean Chemical Society
• /
• v.36 no.4
• /
• pp.485-495
• /
• 1992

The viscosities of organic compounds (alcohols, acetates, alkanes, acids, substituted $NH_2$) in liquid states, gas states and the binary mixtures of n-alkane / 1-chloroalkane were calculated by molecular modeling techniques. The molecular descriptors of molecular modeling technique are Molecular connectivity indices, Wiener indices and ad hoc descriptors, which can encode the information of compound properties about the effect of size, branching, cyclization, unsaturation, heteroatom content, polarizability, and so on. The successful results among method have been Molecular connectivity indices, binary mixtures of n-alkane / 1-chloroalkane, Wiener indices for gas state and ad hoc descriptor for liquid states. Also we obtained the regression equations for viscosities using molecular modeling indices for gas, liquid states and binary mixtures of n-alkane / 1-chloroalkane. The calculated viscosity values for organic compounds are in good agreement with experimental results.

• Journal of the Korean Home Economics Association
• /
• v.24 no.4
• /
• pp.147-162
• /
• 1986

This research has dual purposes. First, it was designed to determine the level of children's spatial environment in the residences, thereby, to make a vision for children's furniture as an industrial design product. Second, it was intened to find out the children's perceptual pattern toward the furniture, thereby to give some implications for future design development. For the second purpose, descriptors were screened with construct validity and their factor structure was identified. The subjects were 1,197 children from 1st grade of elemantary school through 3rd grade of middle school, and their 1,197 parents for the first purpose, and 560 children from 6th grades of elemantary school and 3rd grade of middle school for the second purpose. The first parts of findings were 1) present interests of parents of household above middle income level in Seoul in making their children's spatial environment desirable is quite high. 2) Space segregation stage in terms of physical and conceptual aspects showed very fast development, that is, there will have been very good changes for children's room to be a very well furnished and independent space for them. 3) Children's opinions were quite well reflected when purchasing the present furniture, and this tendency seemed to be more likely happend in future. These findings mentioned above gave and confirmed the visions for future children's furnished environment. The second parts of findings were such that the perceptual pattern for furniture by children showed aesthetic design appearance, functionality and durability, and the characteristic of line. This result impliated especially that designers should be every careful to manipulate or use the line of the furniture products. The 22 representative descriptors selected can be used as an evaluation instrument for furniture products.