Explore the vast range of titles available.

With the rapid advancement of computer vision technology, traditional manual methods of reading meters are increasingly being replaced by automated water meter reading technologies based on image recognition. This technology can precisely locate and recognize the readings on captured images of water meter dials, laying a solid technical foundation for the implementation of remote automatic meter reading systems. However, in practical applications, the recognition of water meter readings still faces challenges due to interference from factors such as shooting angles and changes in environmental lighting. To address these challenges, this paper proposes an innovative method based on deep learning. Firstly, the ResNet-based Feature Pyramid Network (FPN) is used to detect the reading area of the water meter to ensure the accuracy of the detection. For the problem of digit character detection, the character detection attention mechanism is introduced to improve the performance of digit detection and reduce the interference of background noise while ensuring high accuracy. For numerical character recognition, the improved LeNet-5 network can better identify water meter readings in natural scenes. Additionally, the integration of a global average pooling layer within the network effectively alleviates the issue of overfitting. To verify the effectiveness of our method, we conducted experiments on the CCF real-world water meter reading automatic identification dataset. The experimental results show that by scaling the water meter reading area and introducing the character attention mechanism to assist in numerical character detection, the recognition accuracy of individual digits improved by 8.8% and 5.5%, respectively, and the overall recognition accuracy of the final water meter reading also increased by 7.0% and 2.2%. These significant improvements demonstrate the superiority and effectiveness of our method in practical applications.

Detecting irregular or arbitrary shape text in natural scene images is a challenging task that has recently attracted considerable attention from research communities. However, limited by the CNN receptive field, these methods cannot directly capture relations between distant component regions by local convolutional operators. In this paper, we propose a novel method that can effectively and robustly detect irregular text in natural scene images. First, we employ a fully convolutional network architecture based on VGG16_BN to generate text components via the estimated character center points, which can ensure a high text component detection recall rate and fewer noncharacter text components. Second, text line grouping is treated as a problem of inferring the adjacency relations of text components with a graph convolution network (GCN). Finally, to evaluate our algorithm, we compare it with other existing algorithms by performing experiments on three public datasets: ICDAR2013, CTW-1500 and MSRA-TD500. The results show that the proposed method handles irregular scene text well and that it achieves promising results on these three public datasets.

This paper analyses the development status of the cultural tourism industry in Shenyang by extracting Shenyang's cultural tourism industry data, establishing a statistical index system for the development of Shenyang tourism industry based on big data tools, and uses big data tools to collect massive amounts of data and break the traditional data sample size. Based on the big data mathematical model, the tourism market in Shenyang was predicted and analysed, and the bottlenecks of small, time delay and low accuracy were obtained. Finally, it proposes to improve the management strategy of Shenyang's cultural tourism industry, enhance the marketing strategy of cultural travel, strengthen the strategy of cultural travel services, and promote the high-quality development of the cultural tourism industry in Shenyang.

Harmony search (HS) is a new evolutionary algorithm inspired by the process of music improvisation. During the past decade, HS has shown excellent performance in many fields. However, its search strategy often demonstrates insufficient exploitation ability when facing some complex practical problems. Moreover, the HS performance is significantly influenced by its control parameters. To enhance the search efficiency, an adaptive harmony search with best-based search strategy (ABHS) is proposed. In the search process, ABHS exploits the beneficial information from the global-best solution to improve the search ability, while it adaptively tunes its control parameters according to the feedback from the search process. Experiments are conducted on a set of classical test functions. The experimental results show that ABHS significantly enhances the search efficiency of HS.

Soft tissue adhesion on the electrosurgical electrode has been a major concern in clinical surgery. In order to improve the adhesion property of the electrode, micro-textures with different morphologies including micro-dimples, longitudinal micro-channels, and lateral micro-channels were created on the electrode surface by laser surface texturing (LST). Electric cutting experiments were then performed to investigate the adhesion behavior of different electrodes. Experimental results showed that the textured electrode surfaces could reduce the soft tissue adhesion significantly due to the effect of air in micro-textures and the reduction of contact area between the electrode and the soft tissue. Moreover, the temperature distribution of the electric cutting process was simulated through COMSOL to verify the effect of different micro-textures on adhesion behavior. It was demonstrated that the better anti-adhesion property could be obtained at a large area density combined with lateral micro-channels.