2020
DOI: 10.29244/jika.7.2.105-113
|View full text |Cite
|
Sign up to set email alerts
|

Penerjemahan Bahasa Indonesia ke Bahasa Minang dari Optical Character Recognition dengan Menggunakan Algoritme Edit Distance

Abstract: Tri Gatra Bangun Bahasa yaitu utamakan Bahasa Indonesia, lestarikan bahasa daerah, dan kuasai bahasa asing. Melalui ini, maka bahasa daerah sebagai salah satu kekayaan bangsa Indonesia perlu dilestarikan. Selain itu, bahasa daerah juga berfungsi sebagai pendukung bahasa nasional yakni Bahasa Indonesia. Pemanfaatan teknologi dapat digunakan sebagai upaya dalam pelestarian bahasa daerah. Penelitian ini memanfaatkan teknologi kecerdasan buatan yakni mesin penerjemah yang menerjemahkan Bahasa Indonesia ke bahasa d… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2020
2020
2020
2020

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 5 publications
0
2
0
Order By: Relevance
“…The presence of noise in the picture will lead to the reduction of the SNR of the image, which will have an impact on the accuracy of subsequent invoice recognition and the speed of network recognition. Therefore, image denoising must be completed before character cutting [16]. At present, the commonly used denoising method refers to the direct operation on the pixels of the image, mainly including median filtering neighborhood average method is also known as mean filtering.…”
Section: Image Preprocessingmentioning
confidence: 99%
“…The presence of noise in the picture will lead to the reduction of the SNR of the image, which will have an impact on the accuracy of subsequent invoice recognition and the speed of network recognition. Therefore, image denoising must be completed before character cutting [16]. At present, the commonly used denoising method refers to the direct operation on the pixels of the image, mainly including median filtering neighborhood average method is also known as mean filtering.…”
Section: Image Preprocessingmentioning
confidence: 99%
“…However for images, every pixel in an image is the input parameter of a primitive, if the build neural network connects all the nodes and the input parameters to find characteristics, not only can cause too complicate network model to complex calculation, also will have serious over fitting phenomenon, make the network to learn too much irrelevant features and noise information, The generalization performance and stability of the model are reduced [16]. In order to solve this problem, people refer to the idea of Convolution kernel in traditional feature extraction, and extract image features by setting Convolution Layer to perform multiple Convolution operations on the image.…”
Section: Figure 2 Schematic Diagram Of Artificial Neural Networkmentioning
confidence: 99%