Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
ÇѱÛÁ¦¸ñ(Korean Title) |
Ÿºê ¼ýÀÚ ÀνÄÀ» À§ÇÑ ±â°è ÇнÀ ¾Ë°í¸®ÁòÀÇ ¼º´É ºñ±³ |
¿µ¹®Á¦¸ñ(English Title) |
Performance Comparison of Machine Learning Algorithms for TAB Digit Recognition |
ÀúÀÚ(Author) |
ÇãÀçÇõ
ÀÌÇöÁ¾
ȲµÎ¼º
Jaehyeok Heo
Hyunjung Lee
Doosung Hwang
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 08 NO. 01 PP. 0019 ~ 0026 (2019. 01) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®¿¡¼´Â ±âŸ Ÿºê ¾Çº¸¿¡¼ ÃßÃâÇÑ ÇÁ·¿ ¹øÈ£¸¦ ´ë»óÀ¸·Î ÇнÀ ¾Ë°í¸®ÁòÀÇ ºÐ·ù ¼º´ÉÀ» ºñ±³ÇÑ´Ù. Ÿºê ¾Çº¸·ÎºÎÅÍ ¼¼±×¸ÕÆ®¸¦ ÅëÇØ ÃßÃâµÈ Ÿºê ¼ýÀÚ µ¥ÀÌÅʹ Ÿºê ¼±°ú ¾Çº¸ ±âÈ£°¡ Æ÷ÇÔÇϱ⠶§¹®¿¡ ·¹ÀÌºí¸µ ±â¹ý°ú ºñ¼±Çü ÇÊÅ͸¦ ÀÌ¿ëÇÏ¿© ÇÁ·¿ ¼ýÀÚ¸¦ ÃßÃâÇÑ´Ù. Ãß°¡ÀûÀÎ µ¥ÀÌÅÍ È®º¸¸¦ À§ÇØ Àü󸮰¡ ¼öÇàµÈ µ¥ÀÌÅÍ¿¡ ´ëÇØ 4 ¹æÇâÀ¸·Î À̵¿ ¿¬»êÀ» ¼öÇàÇÑ´Ù. ¼±ÅÃµÈ ÇнÀ ¸ðµ¨Àº º£ÀÌÁö¾È ºÐ·ù±â, ÁöÁöº¤Åͱâ±â, ÇÁ·ÎÅäŸÀÔ ±â¹Ý ÇнÀ, ´ÙÃþ ½Å°æ¸Á ±×¸®°í ÇÕ¼º°ö ½Å°æ¸Á ¸ðµ¨ µîÀÌ´Ù. ½ÇÇè °á°ú º£ÀÌÁö¾È ºÐ·ù±â´Â 85.0% Æò±Õ Á¤È®µµ¸¦ º¸¿´°í ³ª¸ÓÁö ºÐ·ù±â´Â 99.0% ÀÌ»óÀÇ Æò±Õ Á¤È®µµ¸¦ º¸¿´´Ù. ÀϹÝÈ ¼º´É°ú Àüó¸® ´Ü°è¸¦ °í·Á ½Ã ÇÕ¼º°ö ½Å°æ¸ÁÀÌ ´Ù¸¥ ÇнÀ ¸ðµ¨µéº¸´Ù ¿ì¼öÇÏ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
In this paper, the classification performance of learning algorithms is compared for TAB digit recognition. The TAB digits that are segmented from TAB musical notes contain TAB lines and musical symbols. The labeling method and non-linear filter are designed and applied to extract fret digits only. The shift operation of the 4 directions is applied to generate more data. The selected models are Bayesian classifier, support vector machine, prototype based learning, multi-layer perceptron, and convolutional neural network. The result shows that the mean accuracy of the Bayesian classifier is about 85.0% while that of the others reaches more than 99.0%. In addition, the convolutional neural network outperforms the others in terms of generalization and the step of the data preprocessing. |
Å°¿öµå(Keyword) |
¼ýÀÚ ÀνÄ
±â°èÇнÀ
ÇÁ·ÎÅäŸÀÔ ¼±ÅÃ
¿µ»óó¸®
±³Â÷Æò°¡
Digit Recognition
Machine Learning
Prototype Selection
Image Processing
Cross-Validation
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|