Minimizing Model Size of CNN-Based Vehicle Make Recognition for Frontal Vehicle Images
Vehicle Make Model Recognition (VMMR) is commonly used in Intelligent Transportation Systems (ITS), free-flow image-based toll systems, and enforcement systems. These systems must analyze and process vehicle front images for use as evidence. Convolutional Neural Networks (CNN) are widely used for im...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11015954/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850215461887672320 |
|---|---|
| author | Wiput Puisamlee Rathachai Chawuthai |
| author_facet | Wiput Puisamlee Rathachai Chawuthai |
| author_sort | Wiput Puisamlee |
| collection | DOAJ |
| description | Vehicle Make Model Recognition (VMMR) is commonly used in Intelligent Transportation Systems (ITS), free-flow image-based toll systems, and enforcement systems. These systems must analyze and process vehicle front images for use as evidence. Convolutional Neural Networks (CNN) are widely used for image classification and VMMR problems. Complex model structures and more internal parameters are needed to improve classification accuracy with many classes. Issues included larger models and longer processing times. The goal of this work is to study and create a smaller CNN model that can be used on devices with limited resources, like embedded computers and embedded computer cameras, to figure out what kind of car it is from a front view picture. Real free-flow toll systems were used to train a CNN model that recognized vehicle makes with 99% accuracy. The model is smaller than VGG16, InceptionV3, Yolo11m-cls, and ResNet50 and has over 90% accuracy. It reduced parameters by 69.95% and developed the CTv1 model to achieve an F1 score 2.06% higher than InceptionV3, the best. The model was tested on a Raspberry Pi 3 Model B, processing images in 1 second and using 25 mWh. The compact version of the proposed model also adjusts the Padding and Stride of the Convolutional Layer and reduces the CNN model size using Depth-wise Separable Convolutional and <inline-formula> <tex-math notation="LaTeX">$1\times 1$ </tex-math></inline-formula> Convolutional Dimension Reduction (Bottleneck) methods to test vehicle make recognition accuracy, training time, processing time, and model size. |
| format | Article |
| id | doaj-art-c26b097a763b4df68d3e44c46cb32b8a |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-c26b097a763b4df68d3e44c46cb32b8a2025-08-20T02:08:36ZengIEEEIEEE Access2169-35362025-01-0113974099742010.1109/ACCESS.2025.357418711015954Minimizing Model Size of CNN-Based Vehicle Make Recognition for Frontal Vehicle ImagesWiput Puisamlee0https://orcid.org/0009-0000-7041-950XRathachai Chawuthai1https://orcid.org/0000-0002-9303-48101Department of Electrical Engineering, School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok, Thailand2Department of Computer Engineering, School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok, ThailandVehicle Make Model Recognition (VMMR) is commonly used in Intelligent Transportation Systems (ITS), free-flow image-based toll systems, and enforcement systems. These systems must analyze and process vehicle front images for use as evidence. Convolutional Neural Networks (CNN) are widely used for image classification and VMMR problems. Complex model structures and more internal parameters are needed to improve classification accuracy with many classes. Issues included larger models and longer processing times. The goal of this work is to study and create a smaller CNN model that can be used on devices with limited resources, like embedded computers and embedded computer cameras, to figure out what kind of car it is from a front view picture. Real free-flow toll systems were used to train a CNN model that recognized vehicle makes with 99% accuracy. The model is smaller than VGG16, InceptionV3, Yolo11m-cls, and ResNet50 and has over 90% accuracy. It reduced parameters by 69.95% and developed the CTv1 model to achieve an F1 score 2.06% higher than InceptionV3, the best. The model was tested on a Raspberry Pi 3 Model B, processing images in 1 second and using 25 mWh. The compact version of the proposed model also adjusts the Padding and Stride of the Convolutional Layer and reduces the CNN model size using Depth-wise Separable Convolutional and <inline-formula> <tex-math notation="LaTeX">$1\times 1$ </tex-math></inline-formula> Convolutional Dimension Reduction (Bottleneck) methods to test vehicle make recognition accuracy, training time, processing time, and model size.https://ieeexplore.ieee.org/document/11015954/Deep learningconvolutional neural networkintelligent transportation systemvehicle makemodel recognition |
| spellingShingle | Wiput Puisamlee Rathachai Chawuthai Minimizing Model Size of CNN-Based Vehicle Make Recognition for Frontal Vehicle Images IEEE Access Deep learning convolutional neural network intelligent transportation system vehicle make model recognition |
| title | Minimizing Model Size of CNN-Based Vehicle Make Recognition for Frontal Vehicle Images |
| title_full | Minimizing Model Size of CNN-Based Vehicle Make Recognition for Frontal Vehicle Images |
| title_fullStr | Minimizing Model Size of CNN-Based Vehicle Make Recognition for Frontal Vehicle Images |
| title_full_unstemmed | Minimizing Model Size of CNN-Based Vehicle Make Recognition for Frontal Vehicle Images |
| title_short | Minimizing Model Size of CNN-Based Vehicle Make Recognition for Frontal Vehicle Images |
| title_sort | minimizing model size of cnn based vehicle make recognition for frontal vehicle images |
| topic | Deep learning convolutional neural network intelligent transportation system vehicle make model recognition |
| url | https://ieeexplore.ieee.org/document/11015954/ |
| work_keys_str_mv | AT wiputpuisamlee minimizingmodelsizeofcnnbasedvehiclemakerecognitionforfrontalvehicleimages AT rathachaichawuthai minimizingmodelsizeofcnnbasedvehiclemakerecognitionforfrontalvehicleimages |