ÇѱÛÁ¦¸ñ(Korean Title) |
¾Ö¿Ïµ¿¹° ºÐ·ù¸¦ À§ÇÑ µö·¯´× |
¿µ¹®Á¦¸ñ(English Title) |
Deep Learning for Pet Image Classification |
ÀúÀÚ(Author) |
½Å±¤¼º
½Å¼ºÀ±
Kwang-Seong Shin
Seong-Yoon Shin
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 23 NO. 01 PP. 0151 ~ 0152 (2019. 05) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®¿¡¼´Â µ¿¹° À̹ÌÁö ºÐ·ù¸¦À§ÇÑ ÀÛÀº µ¥ÀÌÅÍ ¼¼Æ®¸¦ ±â¹ÝÀ¸·Î °³¼± µÈ ½ÉÃþ ÇнÀ ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ù°, CNNÀº ¼Ò±Ô¸ð µ¥ÀÌÅÍ ¼¼Æ®¿¡ ´ëÇÑ ±³À° ¸ðµ¨À» ÀÛ¼ºÇÏ°í µ¥ÀÌÅÍ ¼¼Æ®¸¦ »ç¿ëÇÏ¿© ±³À° ¼¼Æ®ÀÇ µ¥ÀÌÅÍ ¼¼Æ®¸¦ È®ÀåÇÏ´Â µ¥ »ç¿ëµÈ´Ù. µÑ°, VGG16°ú °°Àº ´ë±Ô¸ð µ¥ÀÌÅÍ ¼¼Æ®¿¡ »çÀü ÈÆ·ÃµÈ ³×Æ®¿öÅ©¸¦ »ç¿ëÇÏ¿© ÀÛÀº µ¥ÀÌÅÍ ¼¼Æ®ÀÇ º´¸ñÀ» ÃßÃâÇÏ¿© »õ·Î¿î ±³À° µ¥ÀÌÅÍ ¼¼Æ® ¹× Å×½ºÆ® µ¥ÀÌÅÍ ¼¼Æ®·Î µÎ °³ÀÇ NumPy ÆÄÀÏ¿¡ ÀúÀåÇÏ°í, ¸¶Áö¸·À¸·Î ¿ÏÀüÈ÷ ¿¬°áµÈ ³×Æ®¿öÅ©¸¦ »õ·Î¿î µ¥ÀÌÅÍ ¼¼Æ®·Î ÇнÀÇÑ´Ù. |
¿µ¹®³»¿ë (English Abstract) |
In this paper, we propose an improved learning method based on a small data set for animal image classification. First, CNN creates a training model for a small data set and uses the data set to expand the data set of the training set Second, a bottleneck of a small data set is extracted using a pre-trained network for a large data set such as VGG16 and stored in two NumPy files as a new training data set and a test data set, finally, learn the fully connected network as a new data set. |
Å°¿öµå(Keyword) |
Animal Image Classification
Training Model
VGG16
NumPy file
Connected Network
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|