ABSTRACT
Visual saliency refers to the human's ability to quickly focus on important parts of their visual field, which is a crucial aspect of image processing, particularly in fields like medical imaging and robotics. Understanding and simulating this mechanism is crucial for solving complex visual problems. In this paper, we propose a salient object detection method based on boundary enhancement, which is applicable to both 2D and 3D sensors data. To address the problem of large-scale variation of salient objects, our method introduces a multi-level feature aggregation module that enhances the expressive ability of fixed-resolution features by utilizing adjacent features to complement each other. Additionally, we propose a multi-scale information extraction module to capture local contextual information at different scales for back-propagated level-by-level features, which allows for better measurement of the composition of the feature map after back-fusion. To tackle the low confidence issue of boundary pixels, we also introduce a boundary extraction module to extract the boundary information of salient regions. This information is then fused with salient target information to further refine the saliency prediction results. During the training process, our method uses a mixed loss function to constrain the model training from two levels: pixels and images. The experimental results demonstrate that our salient target detection method based on boundary enhancement shows good detection effects on targets of different scales, multi-targets, linear targets, and targets in complex scenes. We compare our method with the best method in four conventional datasets and achieve an average improvement of 6.2% on the mean absolute error (MAE) indicators. Overall, our approach shows promise for improving the accuracy and efficiency of salient object detection in a variety of settings, including those involving 2D/3D semantic analysis and reconstruction/inpainting of image/video/point cloud data.
ABSTRACT
Understanding and analyzing 2D/3D sensor data is crucial for a wide range of machine learning-based applications, including object detection, scene segmentation, and salient object detection. In this context, interactive object segmentation is a vital task in image editing and medical diagnosis, involving the accurate separation of the target object from its background based on user annotation information. However, existing interactive object segmentation methods struggle to effectively leverage such information to guide object-segmentation models. To address these challenges, this paper proposes an interactive image-segmentation technique for static images based on multi-level semantic fusion. Our method utilizes user-guidance information both inside and outside the target object to segment it from the static image, making it applicable to both 2D and 3D sensor data. The proposed method introduces a cross-stage feature aggregation module, enabling the effective propagation of multi-scale features from previous stages to the current stage. This mechanism prevents the loss of semantic information caused by multiple upsampling and downsampling of the network, allowing the current stage to make better use of semantic information from the previous stage. Additionally, we incorporate a feature channel attention mechanism to address the issue of rough network segmentation edges. This mechanism captures richer feature details from the feature channel level, leading to finer segmentation edges. In the experimental evaluation conducted on the PASCAL Visual Object Classes (VOC) 2012 dataset, our proposed interactive image segmentation method based on multi-level semantic fusion demonstrates an intersection over union (IOU) accuracy approximately 2.1% higher than the currently popular interactive image segmentation method in static images. The comparative analysis highlights the improved performance and effectiveness of our method. Furthermore, our method exhibits potential applications in various fields, including medical imaging and robotics. Its compatibility with other machine learning methods for visual semantic analysis allows for integration into existing workflows. These aspects emphasize the significance of our contributions in advancing interactive image-segmentation techniques and their practical utility in real-world applications.
ABSTRACT
BACKGROUND: Nasopharyngeal carcinoma (NPC) is a rare malignancy in most parts of the world but is common in southern China. A recent report from the Hong Kong Cancer Registry, a high-risk area for NPC in southern China, showed that incidence rate decreased by 29% for males and by 30% for females from 1980-1999, while mortality rate decreased by 43% for males and 50% for females. Changing environmental risk factors and improvements in diagnosis and treatment were speculated to be the major factors contributing to the downward trend of the incidence and mortality rates of NPC. To investigate the secular trends in different Cantonese populations with different socio-economic backgrounds and lifestyles, we report the incidences and mortality rates from two population-based cancer registries in Sihui and Cangwu counties from 1978-2002. METHODS: Incidence and mortality rates were aggregated by 5-year age groups and 5 calendar years. To adjust for the effect of difference in age composition for different periods, the total and age-specific rates of NPC incidence and mortality rate were adjusted by direct standardization according to the World Standard Population (1960). The Estimated Annual Percentage Change (EAPC) was used as an estimate of the trend. RESULTS: The incidence rate of NPC has remained stable during the recent two decades in Sihui and in females in Cangwu, with a slight increase observed in males in Cangwu from 17.81 to 19.76 per 100,000. The incidence rate in Sihui is 1.4-2.0 times higher during the corresponding years than in Cangwu, even though the residents of both areas are of Cantonese ethnicity. A progressive decline in mortality rate was observed in females only in Sihui, with an average reduction of 6.3% (p = 0.016) per five-year period. CONCLUSION: To summarize, there is great potential to work in the area of NPC prevention and treatment in southern China to decrease NPC risk and improve survival risk rates in order to reduce M:I ratios. Future efforts on effective prevention, early detection and treatment strategies were also discussed in this paper. Furthermore, the data quality and completeness also need to be improved.
