Improvement of High-Speed Detection Algorithm for Nonwoven Material Defects Based on Machine Vision

Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial fields.This paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus model.Using the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection framework.Within this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection accuracy.The half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection speed.Performance comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production.

Three-Dimensional Model Reconstruction of Nonwovens from Multi-Focus Images

The three-dimensional(3D)model is of great significance to analyze the performance of nonwovens.However,the existing modelling methods could not reconstruct the 3D structure of nonwovens at low cost.A new method based on deep learning was proposed to reconstruct 3D models of nonwovens from multi-focus images.A convolutional neural network was trained to extract clear fibers from sequence images.Image processing algorithms were used to obtain the radius,the central axis,and depth information of fibers from the extraction results.Based on this information,3D models were built in 3D space.Furthermore,self-developed algorithms optimized the central axis and depth of fibers,which made fibers more realistic and continuous.The method with lower cost could reconstruct 3D models of nonwovens conveniently.

Intelligent Metal Detection and Disposal Automation Equipment Based on Geometric Optimization Driving Algorithm

In order to solve the problem of metal impurities mixed in the production line of wood pulp nonwoven raw materials,intelligent metal detection and disposal automation equipment is designed.Based on the principle of electromagnetic induction,the precise positioning of metal coordinates is realized by initial inspection and multi-directional re-inspection.Based on a geometry optimization driving algorithm,the cutting area is determined by locating the center of the circle that covers the maximum area.This approach aims to minimize the cutting area and maximize the use of materials.Additionally,the method strives to preserve as many fabrics at the edges as possible by employing the farthest edge covering circle algorithm.Based on a speed compensation algorithm,the flexible switching of upper and lower rolls is realized to ensure the maximum production efficiency.Compared with the metal detection device in the existing production line,the designed automation equipment has the advantages of higher detection sensitivity,more accurate metal coordinate positioning,smaller cutting material areas and higher production efficiency,which can make the production process more continuous,automated and intelligent.

Real applications of quantum communications in China

The first metropolitan quantum cryptography network for government administration, which is named 'Q-Government', has recently been field tested in Wuhu, Anhui Province by researchers of Key Laboratory

基于皮革毛孔分布特征的牛/羊皮革鉴别

不同种类的皮革成本与性能均不同,因此开发皮革鉴别方法是很有必要的。目前皮革种类鉴别方法往往需要复杂的设备,或者依赖测试人员的经验。对皮革的显微镜图像进行处理,确定毛孔的位置,根据牛皮革与羊皮革毛孔分布的差异,提取两个特征来区分这两种材料,之后借助线性分类器对皮革的特征数据进行训练。训练后的模型能够鉴别牛皮革与羊皮革,准确率约为89.2%。该方法仅需要光学显微镜,全程依赖图形图像算法和数据分析技术进行鉴别,不受主观因素的影响。