Pengenalan Logo Kendaraan Menggunakan Metode Local Binary Pattern dan Random Forest

The vehicle logo is one of the features that can be used to identify a vehicle. Even so, a lot of Intelligent Transport System which are developed nowadays has yet to use a vehicle logo recognition system as one of its vehicle identification tools. Hence there are still cases of traffic crimes that haven't been able to be examined by the system, such as cases of counterfeiting vehicle license plates. Vehicle logo recognition itself could be done by using various feature extraction and classification methods. This research project uses the Local Binary Pattern feature extraction method which is often used for many kinds of image recognition systems. Then, the classification method used is Random Forest which is known to be effective and accurate for various classification problems. The data used for this study were as many as 2000 vehicle logo images consisting of 5 brand classes, namely Honda, Kia, Mazda, Mitsubishi, and Toyota. The results of the tests carried out obtained the best accuracy value of 88.89% for the front view logo image dataset, 77.03% for the side view logo image dataset, and 83% for the dataset with both types of images.

Vehicle Logo Recognition Based on Enhanced Matching for Small Objects, Constrained Region and SSFPD Network

Vehicle Logo Recognition (VLR) is an important part of vehicle behavior analysis and can provide supplementary information for vehicle identification, which is an essential research topic in robotic systems. However, the inaccurate extraction of vehicle logo candidate regions will affect the accuracy of logo recognition. Additionally, the existing methods have low recognition rate for most small vehicle logos and poor performance under complicated environments. A VLR method based on enhanced matching, constrained region extraction and SSFPD network is proposed in this paper to solve the aforementioned problems. A constrained region extraction method based on segmentation of the car head and car tail is proposed to accurately extract the candidate region of logo. An enhanced matching method is proposed to improve the detection performance of small objects, which augment each of training images by copy-pasting small objects many times in the unconstrained region. A single deep neural network based on a reduced ResNeXt model and Feature Pyramid Networks is proposed in this paper, which is named as Single Shot Feature Pyramid Detector (SSFPD). The SSFPD uses the reduced ResNeXt to improve classification performance of the network and retain more detailed information for small-sized vehicle logo detection. Additionally, it uses the Feature Pyramid Networks module to bring in more semantic context information to build several high-level semantic feature maps, which effectively improves recognition performance. Extensive evaluations have been made on self-collected and public vehicle logo datasets. The proposed method achieved 93.79% accuracy on the Common Vehicle Logos Dataset and 99.52% accuracy on another public dataset, respectively, outperforming the existing methods.