QuickBrowser: A Unified Model to Detect and Read Simple Object in Real-time
This addresses the need for lightweight, efficient detect-and-read systems in applications like barcode scanning and license plate recognition, though it is incremental as it builds on existing object detection methods.
The paper tackles the problem of detecting and reading simple structured objects like barcodes and license plates in real-time by proposing a unified one-stage model that integrates multi-digit recognition, eliminating duplicate feature extraction. Experimental results show it outperforms industrial tools and state-of-the-art methods in detection/decoding rates and inference speed, achieving real-time fps at VGA resolution.
There are many real-life use cases such as barcode scanning or billboard reading where people need to detect objects and read the object contents. Commonly existing methods are first trying to localize object regions, then determine layout and lastly classify content units. However, for simple fixed structured objects like license plates, this approach becomes overkill and lengthy to run. This work aims to solve this detect-and-read problem in a lightweight way by integrating multi-digit recognition into a one-stage object detection model. Our unified method not only eliminates the duplication in feature extraction (one for localizing, one again for classifying) but also provides useful contextual information around object regions for classification. Additionally, our choice of backbones and modifications in architecture, loss function, data augmentation and training make the method robust, efficient and speedy. Secondly, we made a public benchmark dataset of diverse real-life 1D barcodes for a reliable evaluation, which we collected, annotated and checked carefully. Eventually, experimental results prove the method's efficiency on the barcode problem by outperforming industrial tools in both detecting and decoding rates with a real-time fps at a VGA-similar resolution. It also did a great job expectedly on the license-plate recognition task (on the AOLP dataset) by outperforming the current state-of-the-art method significantly in terms of recognition rate and inference time.