• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.648-651
• /
• 2003

In this paper, we propose the recognition system of a license plate using SOM algorithm. The recognition of license plate was investigated by means of the SOM algorithm. The morphological information of horizontal and vertical edges was used to extract a plate region from a car image. In addition, the 4-direction contour tracking algorithm was applied to extract the specific area, which includes characters from an extracted plate area. Therefore, we proposed how to extract license plate region using morphological information and how to recognize the character string using SOM algorithm. In this paper, 50 car images were tested. The extraction rate obtained by the proposed extraction method showed better results than that from the color information of RGB and HSI, respectively. And the license plate recognition using SOM algorithm was very efficient.

• Korean Journal of Pharmacognosy
• /
• v.26 no.4
• /
• pp.411-418
• /
• 1995

In order to clarify the originality of several Alisma Rhizomes, we investigated the differences of their morphological, anatomical and physiochemical characteristics. Morphological observation shows the variability of Alisma shape and quality. The diversities in morphological shapes and qualities of tuber were observed among different origins. Chinese product looked like corm shape, but korean's irregular shape. The microscopic observation of korean Alisma revealed the presence of irregular vascular bundle which was scattered transversely and longitudinaly, which was different from that of the rhizome. This facts suggest that the portion of crude drug in Alisma should be the corm rather than the rhizome. In the physicochemical differences, chinese Alisma contains larger amount of mineral elements such as K, Na and Ca than korean Alisma. On the contrary, protein contents in lyophilized powder of aqueous extracts in korean Alisma rhizome was significantly higher than chinese Alisma rhizome. The leaves and stems contained larger amount of Ca and Na than tuber, and may be used as the osmotic diuretics for chinese traditional medicine.

• Journal of Plant Biology
• /
• v.35 no.1
• /
• pp.61-67
• /
• 1992

Principal component analysis of the morphological characters was applied to ordinate and examine morphological variation of Enteromorpha linza due to differences in environmental factors. As results, the samples from exposed populations to wave action were characterized by having longer stipe and maximum length, and narrower maximum width than samples from sheltered populations. The results of multiple comparision in each character among populations provided further support for the hypothesized existence of exposed, moderate, and sheltered morphotypes.otypes.

• Korean Journal of Plant Resources
• /
• v.22 no.5
• /
• pp.473-476
• /
• 2009

Rubus hongnoensis Nakai, Korean endemic species were reexamined on the basis of morphological characters. Both sides of leaves are pubscent and particularly glandular hairs are present on main vein. All parts except petals and stems are hairy. Petioles and stem have prickles. Leaflets are 3-7. Fruits is red.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.9 no.2
• /
• pp.229-234
• /
• 2004

Six entomopathogenic fungus isolates, Beauveria bassiana J57A, Nomuraea rileyi J125A, Paecilomyces farinosus J3A, Paecilomyces fumosoroseus J50A, Metarhizium anisopliae J88, Aspergilius sp. J64A, causing muscardine disease and aspergillosis in the silkworm, Bombyx mori were investigated for their cultural and morphological characteristics (on PDA culture media within 14 days at $24^{\circ}C$). The results showed that they differ each other from the features of cultural characteristics (colony elevation, colony color, colony growth rate) or morphological characteristics (conidiogenous cell structure, phialides, conidia size and shape). Among cultural characteristics, colony color is the easiest recognizable character between isolates. The morphological characteristics of each fungal isolate correspond to the descriptions of current system of classification.

• Animal Systematics, Evolution and Diversity
• /
• v.11 no.3
• /
• pp.329-334
• /
• 1995

The epicranial bony system of the six species of the family Cynoglossidae were examined based on the specimens collected from the coast of Korea from 1992 to 1994. They were divided into four groups by the morphological features of epicranial bony system as follow: 1. Paraplagusia japonica, 2. Cynoglossus joyneri and C. robustus, 3. C. semilaeuis and C. abbreuiatus, and 4. C. interruptus. Among them, P japonica showed the most derived character in the erisma and frontal elements of the epicranial bony system. And it was remarked that the number of proximal radials supporting erisma show much differences among the species. It is discussed that the morphological differences in the epicranial bony system are significant character for interspecific relationships in family Cynoglossidae.

• Herbal Formula Science
• /
• v.11 no.2
• /
• pp.213-232
• /
• 2003

Objectives : This study was designed to establish a characteristic discrimination of internal and external morphological standard of original plants and herbal states in Arisaema amurense var. serratum $N_{AKAI}$ and A. amurense $M_{AXIM}.$. Methods : In this studies, the external-internal morphological standards were determined by using stereoscope and butanol series. Results : 1. In the external shape of original plant, Arisaema amurense var. serratum $N_{AKAI}$ has high stem, an oval-elliptic leaflet and a serrate leaf margin. But A. amurense $M_{AXIM}$ has a relatively low stem, an upside oval leaflet and no serrate leaf margin. 2. On the herbs character of original plant, Arisaema amurense var. serratum $N_{AKAI}$ is small in height and diameter, but A. amurense $M_{AXIM}$ is relatively large in height and diameter. 3. On the gathered herbs character of original plant, the section of Arisaema amurense var. serratum $N_{AKAI}$ is brightly white, easily spilt and strong scent. But the section of A. amurense $M_{AXIM}$ is thin yellowish brown, not easily spilt and weak scent. Also the grade of gathered herbs, both can be classified by diameter and external scent. 4. In the current herbs character, Korean and Sichuan Province products are irregullar shape and have no scent, Jilin Province products are regular shape. Also, Guangxi Province products are small size and concave in one side, Hebei Province products are irregular size and shape. 5. In internal shape of original plant, epidermal cell of Arisaema amurense var. serratum is very tight. With the except of micro difference in parenchyma cell of cortex, on the whole there are nearly no differences with A. amurense $M_{AXIM}.$ Also, samely in the internal shape, according to collecting sites, epidermis exhibits a lot layer in curving state and secreting duct is developed and vascular bundle and exists between parenchyma cell of cortex. Conclusion : In the future, additional study is needed to distinguish herb and effect between same genus-degree of relatedness.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.7
• /
• pp.46-55
• /
• 1999

We proposed the new method of postprocessing which not only reduces the frequency of dictionary access using morphological analysis but improve the recognition rate of character recognizer. In this paper, after estimating morphological construction of mis-recognized word using the part of speech that is analyzed, correct presumed mis-recognized morphology. The postprocessing using a morphology unit reduce candidate because of short than word and frequency of dictionary access because there is no need to morphological analysis for candidate. To select right candidate is only necessary to dictionary access. The proposed results show that reduced the frequency of dictionary access to 60% than postprocessing method using a word unit and recognition rate improved from 94% to 97%.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.3
• /
• pp.47-56
• /
• 1999

Various phonological alteration occurs when we pronounce continuously in korean. This phonological alteration is one of the major reasons which make the speech recognition of korean difficult. This paper presents a rule-based system which converts a speech recognition character string to a text-based character string. The recovery results are morphologically analyzed and only a correct text string is generated. Recovery is executed according to four kinds of rules, i.e., a syllable boundary final-consonant initial-consonant recovery rule, a vowel-process recovery rule, a last syllable final-consonant recovery rule and a monosyllable process rule. We use a x-clustering information for an efficient recovery and use a postfix-syllable frequency information for restricting recovery candidates to enter morphological analyzer. Because this system is a rule-based system, it doesn't necessitate a large pronouncing dictionary or a phoneme dictionary and the advantage of this system is that we can use the being text based morphological analyzer.

• Journal of KIISE:Software and Applications
• /
• v.27 no.3
• /
• pp.290-301
• /
• 2000

Most morphological analysis methods require repetitive procedures of input character code conversion, segmentation and lemmatization of constituent morphemes, filtering of candidate results through looking up lexicons, which causes run-time inefficiency. To alleviate such problem of run-time inefficiency, many systems have introduced the notion of 'pre-analysis' of words. However, this method based on pre-analysis dictionary of surface also has a critical drawback in its practical application because the size of the dictionaries increases indefinite to cover all words. This paper hybridizes both extreme approaches methodologically to overcome the problems of the two, and presents a method of morphological analysis based on pre-analysis of partial words. Under such hybridized scheme, most computational overheads, such as segmentation and lemmatization of morphemes, are shifted to building-up processes of the pre-analysis dictionaries and the run-time dictionary look-ups are greatly reduced, so as to enhance the run-time performance of the system. Moreover, additional computing overheads such as input character code conversion can also be avoided because this method relies upon no graphemic processing.