• Journal of the Korea Society of Computer and Information
• /
• v.9 no.3
• /
• pp.121-125
• /
• 2004

In the most of recognizing systems of hand-written numbers. extraction of feature shape by using character elements shapes and a method of morphological analysis by using then extraction of feature shapes were usually used. In this paper, however, peculiar chain-code is used, and differential code which gets minimal value by differentiating the chain-code which is generated by the peculiar chain-code is made. We found this differential code is very successful in discriminating hand-written numbers according to the result of applying to most of the hand-written numbers. Testing recognition of hand-written numbers by HMM network. From the results, we can recognize of 96.1 percentage hand-written numbers but can not recognize extremely distorted hand-written numbers.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.5
• /
• pp.1058-1063
• /
• 1997

Though the Preparata code of length 8 over $Z_{4}$ satisfies the chain condition, the Preparata code of length 16 or 32 over $Z_{4}$ does not satisfy the chain condition. In this paper we show that the Preparata code of length $2^{m}$ over $Z_{4}$ does not satisfy the chain condition for m=4, 5, 6 and 8 by investigating relations between weight hierarchy and chain condition.

• Journal of Intelligence and Information Systems
• /
• v.13 no.4
• /
• pp.35-44
• /
• 2007

This paper proposes a new method of weighted template matching for machine-printed numeral recognition. The proposed weighted template matching, which emphasizes the feature of a pattern using adaptive Hamming distance on local feature areas, improves the recognition rate while template matching processes an input image as one global feature. Template matching is vulnerable to random noises that generate ragged outlines of a pattern when it is binarized. This paper offers a method of chain code trimming in order to remove ragged outlines. The method corrects specific chain codes within the chain codes of the inner and the outer contour of a pattern. The experiment compares confusion matrices of both the template matching and the proposed weighted template matching with chain code trimming. The result shows that the proposed method improves fairly the recognition rate of the machine-printed numerals.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.1067-1070
• /
• 2009

It is important to control environment information such as temperature in distribution & logistics systems. To manage temperature and environment information in realtime, SCCM(Smart Cold Chain Management) system must manage and integrate tags and various types sensor information. But, it needs standard code system to manage and integrate various types tags and sonsors. In this paper, we propose standard code system to apply the SCCM system.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.4
• /
• pp.63-68
• /
• 2003

Almost the system are usually taken by means of shapes and positions of ridge's end-points and bifurcation in the fingerprint recognition. but we studied about recognition of polluted fingerprint by chain code ridges. the results and sequence of processing are summarized as follows. (1)Capture several kinds of polluted fingerprint image. (2)Preprocessing(median filtering for removing noises, local and global histogram equalization, dilation and erosion, thinning and remove pseudo image), (3)Rebuild ridge line after Least Square Processing, (4)Compute distribution of chain code vector, (5)The results are almost same values of each vector of preprocessed fingerprint images. From the results, we can surmised more successful fingerprints recognition system in combination with other system by singular points

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.149-152
• /
• 2011

A Multi-Vision needs an image adjust of each product to make the same picture quality for all products when it's installed. Owing to this reason need individual control. This document request indivisual control method for each product with the Remote controller. To realize this method need make Set ID and Picture ID on the UI and need daisy chain of cable to connect Remocon code(IR Signal) In to Out, After allocation the Set ID for each product. Picture ID of the product which want to change picture quality make equal to Set ID. And the product which is same Set ID and Picture ID is only controlled through decoding of Remocon code to Scaler.

• The Journal of Fisheries Business Administration
• /
• v.38 no.1 s.73
• /
• pp.115-132
• /
• 2007

Implementing the automatic identification in supply chain management is essential for effective and efficient process control. Though the GTIN based bar code system is generally used as an automatic identification method in most industries, it can not identify individual item, and is not appropriated for products' reliability and safety management. So the RFID system with EPC is considered as a better solution for resolving those problems. This study reviewed automatic identification code systems and the attributes and characteristics of RFID Gen 2 which became a global standard recently for supply chain management. Particularly, this study analyzed RFID Gen 2 systems' read rates on various conditions including distances between tags and readers and between antennas, condensation, and several packing materials in practical supply chain environment. The results of this study showed that the RFID Gen 2 had high read ratio in practical application and would be adopted as a new automatic identification means for traceability systems.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.16 no.5
• /
• pp.582-594
• /
• 2016

Various test data compression techniques have been developed to reduce the test costs of system-on-a-chips. In this paper, a scan chain reordering algorithm for code-based test data compression techniques is proposed. Scan cells within an acceptable relocation distance are ranked to reduce the number of conflicts in all test patterns and rearranged by a positioning algorithm to minimize the routing overhead. The proposed method is demonstrated on ISCAS '89 benchmark circuits with their physical layout by using a 180 nm CMOS process library. Significant improvements are observed in compression ratio and test power consumption with minor routing overhead.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.8
• /
• pp.756-760
• /
• 2010

In this paper, a new method to recognize various motions of fighting with an aid of HMM is proposed. There are four kinds of fighting motion such as hook, jab, uppercut, and straight as the fighting motion. The motion graph is generalized to define each motion in motion data and the new 3D-chain code is used to convert motion data to motion graphs. The recognition experiment has been performed with HMM algorithm on motion graphs. The motion data is captured by a motion capture system developed in this study and by five actors. Experimental results are given with relatively high recognition rate of at least 85%.

• Journal of Industrial Technology
• /
• v.29 no.A
• /
• pp.47-54
• /
• 2009

In this paper, we proposed hand detection and hand gesture recognition from USB camera video. Firstly, we extract hand region extraction using skin color information from a difference images. Background image is initially stored and extracted from the input images in order to reduce problems from complex backgrounds. After that, 16-directional chain code sequence is computed from the tracking of hand motion. These chain code sequences are compared with pre-trained models using DP matching. Our hand gesture recognition system can be used to control PowerPoint slides or applied to multimedia education systems. We got 92% hand region extraction accuracy and 82.5% gesture recognition accuracy, respectively.