CB-26 Improve the Identification Accuracy of Parking Stickers with A Deep Neural Network and Persistent Homology Features

YOLO is a cutting-edge object detection model that has demonstrated exceptional effectiveness in object recognition. However, YOLO is sensitivity to similar-shaped objects, leading to false positive detections. Our experimental results show that YOLO mistakenly identified non-sticker objects with high confidence due to their shape resemblance to parking stickers. Increasing the confidence threshold lowered these false positives but also caused real stickers to be missed. This issue indicated that YOLO struggles with distinguishing fine-grained features in objects of similar shape, especially when the dataset is small and manually labeled, leading to potential annotation errors. Persistent homology provides a topological approach to image analysis by representing image domains as simplicial complexes. In this study, we applied persistent homology features to enhance parking sticker identification in vehicle images, addressing the limitations of traditional deep-learning-based detection methods. We employed YOLO-V10 for initial sticker detection. However, misclassifications occurred due to the similarity of certain objects to stickers, prompting us to integrate persistent homology features, such as critical pairs, persistence values, and bounding box areas, into machine learning classifiers. Among several tested models, the Hist-Gradient Boosting classifier exhibited the best performance, which significantly improving classification accuracy. Experimental results demonstrated that persistent homology features provide a robust solution for distinguishing parking stickers from visually similar objects, effectively complementing YOLO-V10's detection capabilities.