TY - GEN
T1 - Image classification for vehicle type dataset using state-of-the-art convolutional neural network architecture
AU - Seo, Yian
AU - Shin, Kyung Shik
N1 - Publisher Copyright:
© 2018 Association for Computing Machinery.
PY - 2018/12/21
Y1 - 2018/12/21
N2 - Fast development in Deep Learning and its hybrid methodologies has led diverse applications in different domains. For image classification tasks in vehicle related fields, Convolutional Neural Network (CNN) is mostly chosen for recent usages. To train the CNN classifier, various vehicle image datasets are used, however, most of previous studies have learned features from datasets with a single form of images taken in the controlled condition such as surveillance camera vehicle image dataset from the same road, which results the classifier cannot guarantee the generalization of the model onto different forms of vehicle images. In addition, most of researches using CNN have used LeNet, GoogLeNet, or VGGNet for their main architecture. In this study, we perform vehicle type (convertible, coupe, crossover, sedan, SUV, truck, and van) classification and we use our own collected dataset with vehicle images taken in different angles and backgrounds to ensure the generalization and adaptability of proposed classifier. Moreover, we use the state-of-the-art CNN architecture, NASNet, which is a hybrid CNN architecture having Recurrent Neural Network structure trained by Reinforcement Learning to find optimal architecture. After 10 folded experiments, the average final test accuracy points 83%, and on the additional evaluation with random query images, the proposed model achieves accurate classification.
AB - Fast development in Deep Learning and its hybrid methodologies has led diverse applications in different domains. For image classification tasks in vehicle related fields, Convolutional Neural Network (CNN) is mostly chosen for recent usages. To train the CNN classifier, various vehicle image datasets are used, however, most of previous studies have learned features from datasets with a single form of images taken in the controlled condition such as surveillance camera vehicle image dataset from the same road, which results the classifier cannot guarantee the generalization of the model onto different forms of vehicle images. In addition, most of researches using CNN have used LeNet, GoogLeNet, or VGGNet for their main architecture. In this study, we perform vehicle type (convertible, coupe, crossover, sedan, SUV, truck, and van) classification and we use our own collected dataset with vehicle images taken in different angles and backgrounds to ensure the generalization and adaptability of proposed classifier. Moreover, we use the state-of-the-art CNN architecture, NASNet, which is a hybrid CNN architecture having Recurrent Neural Network structure trained by Reinforcement Learning to find optimal architecture. After 10 folded experiments, the average final test accuracy points 83%, and on the additional evaluation with random query images, the proposed model achieves accurate classification.
KW - Convolutional Neural Network
KW - NASNet
KW - Recurrent Neural Network
KW - Reinforcement Learning
KW - Vehicle Image Classification
UR - http://www.scopus.com/inward/record.url?scp=85062951828&partnerID=8YFLogxK
U2 - 10.1145/3299819.3299822
DO - 10.1145/3299819.3299822
M3 - Conference contribution
AN - SCOPUS:85062951828
T3 - ACM International Conference Proceeding Series
SP - 139
EP - 144
BT - AICCC 2018 - Proceedings of 2018 Artificial Intelligence and Cloud Computing Conference
PB - Association for Computing Machinery
Y2 - 21 December 2018 through 23 December 2018
ER -