손글씨 인식을 위한 딥러닝에서 훈련 옵션의 영향 분석

서지정보

ㆍ발행기관 : 한국복합신소재구조학회 ㆍ수록지정보 : 복합신소재구조학회 논문집 / 8권 / 2호
ㆍ저자명 : 손병직

목차

1. 서 론
2. CNN 개요
3. 손글씨 인식을 위한 CNN
3.1 Step 1 : Load the Image Data
3.2 Step 2 : Specify Training and Test Sets
3.3 Step 3 : Define the Network Layers
3.4 Step 4 : Specify the Training Options
3.5 Step 5 : Train the Network using TrainingData
3.6 Step 6 : Classify the Images in the TestData and Compute Accuracy
4. 해석 예 및 결과 분석
5. 요약 및 결론
ACKNOWLEDGMENT
REFERENCES

영어 초록

Deep learning techniques are being studied and developed throughout the medical, agricultural, aviation, and automotive industries. It can be applied to construction fields such as concrete cracks and welding defects. One of the best performing techniques of deep running is CNN technique. In this study, we analyzed the classification of handwritten images using CNN technique before applying them to construction field. Deep running is generally more accurate with deeper layers, but analysis cost is high. In addition, many variations can occur depending on training options. Therefore, this study performed a parametric study to be a reference when CNN technique was applied through accuracy analysis according to training options.

참고 자료

없음