Optical character recognition (OCR) technology is promoting the process of automation in daily information recording and inspection of industrial meters. However, bad installation scenes and long-time running cause industrial meters to age to varying degrees, which increases the difficulty of OCR. Besides, in practice, operators typically use handheld cameras to extract tag information from industrial meters. During the shooting process, extreme lighting, free shooting angles, and shooting distance also cause many difficulties for OCR. Considering such difficulties, an end-to-end recognition architecture is developed to obtain a better OCR performance. The proposed architecture can quickly extract structured information from normal or skewed text images. A novel yolov5_adaloss with a specific penalty factor is designed to alleviate the influence of illumination, installation scene, age, skew, and distance on the classification accuracy of Tags. For images with large skew angles, a mathematical method is proposed to calculate the text inclination angle for better OCR performance. The contribution of this work is twofold. First, the architecture proposed is lightweight, which only needs a low computing cost and a short inference time. Second, as a practical application-oriented architecture, this work does not require much training, labeling, and fine-tuning, which is easy to generalize to other structured text recognition tasks. Experiments show that the method proposed in this article can achieve excellent performance in meter tag recognition tasks on actual industrial images of meters.

As client applications evolve with new businesses and features, new performance overheads may be introduced. For example, in the application startup scenario, the initialization of newly connected SDKs and the addition of disk access operations on the main thread can increase the startup time, leading to a decline in user experience. Traditional performance testing detects application indicators through automated testing, video frame splitting, or log tracking, but due to fluctuations in the offline environment, test results often fluctuate, and confidence is not high. To optimize performance in a more refined way, it is necessary to not only evaluate performance through indicators but also to pinpoint the cause of the problem accurately. Domino is a client-side performance testing platform based on Trace analysis. In this demonstration, we will provide two versions of AndroidDemo applications, simulate several performance issues, and use the Domino platform to more precisely locate performance problems and provide development repair suggestions.