2021
DOI: 10.7717/peerj-cs.576
|View full text |Cite
|
Sign up to set email alerts
|

Full depth CNN classifier for handwritten and license plate characters recognition

Abstract: Character recognition is an important research field of interest for many applications. In recent years, deep learning has made breakthroughs in image classification, especially for character recognition. However, convolutional neural networks (CNN) still deliver state-of-the-art results in this area. Motivated by the success of CNNs, this paper proposes a simple novel full depth stacked CNN architecture for Latin and Arabic handwritten alphanumeric characters that is also utilized for license plate (LP) chara… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 11 publications
(5 citation statements)
references
References 41 publications
0
5
0
Order By: Relevance
“…The results in Table I of the trials carried out, for testing the image training data as much as 576 with image testing data as much as 384, then the calculation of the percentage of success is carried out to determine the level of accuracy the application made. Based on the results of trials that have been conducted on 24 Korean letters (Hangul), the percentage details begin with the lowest, which is 56.25 percent on the letter G, and work their way up to the highest (1). A total of 68.75 percent of the next order contains the letters B, H, and the word YES in the percentage value (3).…”
Section: Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…The results in Table I of the trials carried out, for testing the image training data as much as 576 with image testing data as much as 384, then the calculation of the percentage of success is carried out to determine the level of accuracy the application made. Based on the results of trials that have been conducted on 24 Korean letters (Hangul), the percentage details begin with the lowest, which is 56.25 percent on the letter G, and work their way up to the highest (1). A total of 68.75 percent of the next order contains the letters B, H, and the word YES in the percentage value (3).…”
Section: Resultsmentioning
confidence: 99%
“…The letters EU and I have a 93.75 percent success rate, respectively (2). The letter N is the owner of the greatest percentage, which is 100 percent (1).…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…A CNN is a type of deep-learning system that specializes in image recognition. After repeating the combination of the "convolution layer" and "pooling layer" multiple times, it finally outputs the result through a connected layer [44,45]. "Convolution" is an imageprocessing technique that extracts image features through a filter or kernel.…”
Section: Convolutional Neural Networkmentioning
confidence: 99%
“…Many scholars have proposed various algorithms for digital recognition [17][18][19]. Due to the rapid development of convolutional neural networks (CNNs), image recognition and classification based on CNNs have become increasingly mature.…”
Section: Master Ruler Digit Recognitionmentioning
confidence: 99%