EKSTRAKSI CIRI TEKS PADA GAMBAR ALAMI ENGGUNAKAN ALGORITMA RANDOM FERNS DAN CONVOLUTIONAL CO-OCCURRENCE HOG
Total View This Week0

Institusion

Universitas Sriwijaya

Author

MUHAMMAD DANIEL (STUDENT ID : 09111002018)
Samsuryadi Samsuryadi (LECTURER ID : 0004027101)
Anggina Primanita (LECTURER ID : 0206088901)

Subject

R858-859.7 Computer applications to medicine. Medical informatics 

Datestamp

2019-09-12 07:31:59 

Abstract :
A natural image is images that represents what the human eye sees daily. The recognition of text in natural images has many obstacles, such as lighting, shooting angle, and variations of fonts used. The process of recognizing a word in a natural image consists of three stages, detecting the location of characters in the image, recognizing detected characters, and combining recognized characters into words. This study is focused in feature extraction process of character detection using Random Ferns method, and recognition of detected characters using the Convolutional Co-Occurrence Histogram of Oriented Gradient method, which was trained and tested on the ICDAR dataset 2003. The results of this study provide a high accuracy on detected words. 

File :
RAMA_55201_09111002018_ 0004027101_ 0206088901_01_front_ref.pdf
RAMA_55201_09111002018_ 0004027101_ 0206088901_02.pdf
RAMA_55201_09111002018_ 0004027101_ 0206088901_03.pdf
RAMA_55201_09111002018_ 0004027101_ 0206088901_04.pdf
RAMA_55201_09111002018_ 0004027101_ 0206088901_05_ref.pdf
RAMA_55201_09111002018_ 0004027101_ 0206088901_06_lamp.pdf