Search results

The current popular image processing technologies based on convolutional neural network have the characteristics of large computation, high storage cost and low accuracy for tiny defect detection, which is contrary to the high real-time and accuracy, limited computing resources and storage required by industrial applications. Therefore, an improved YOLOv4 named as YOLOv4-Defect is proposed aim to solve the above problems.

On the one hand, this study performs multi-dimensional compression processing on the feature extraction network of YOLOv4 to simplify the model and improve the feature extraction ability of the model through knowledge distillation. On the other hand, a prediction scale with more detailed receptive field is added to optimize the model structure, which can improve the detection performance for tiny defects.

The effectiveness of the method is verified by public data sets NEU-CLS and DAGM 2007, and the steel ingot data set collected in the actual industrial field. The experimental results demonstrated that the proposed YOLOv4-Defect method can greatly improve the recognition efficiency and accuracy and reduce the size and computation consumption of the model.

This paper proposed an improved YOLOv4 named as YOLOv4-Defect for the detection of surface defect, which is conducive to application in various industrial scenarios with limited storage and computing resources, and meets the requirements of high real-time and precision.

Information overload has led to a situation where users are swamped with too much information, resulting in difficulty sifting through material in search of relevant content. Aims to address this issue from the perspective of collaborative querying, an approach that helps users formulate queries by harnessing the collective knowledge of other searchers.

The design and implementation of the Query Graph Visualizer (QGV), a collaborative querying system which harvests and clusters previously issued queries to form query networks that represent related information needs are described. A preliminary evaluation of the QGV is also described in which a group of participants evaluated the usability and usefulness of the system by completing a set of tasks and a questionnaire based on Nielsen's heuristic evaluation technique.

In the QGV, a submitted query is matched to its closest cluster and a recursive algorithm is applied to find other related clusters, forming a query network. The queries in the network are explored in the QGV, helping users locate other queries that might meet their current information needs. The results of the evaluation suggest the usefulness and usability of the system. Participants could complete their assigned tasks using the QGV and positively rated the system in terms of usability.

The techniques described can be used to design information retrieval systems that learn from the trials and tribulations of other searchers and help users in their quest for relevant and quality information