To solve the problems of traditional garbage classification relying on manual work,low recognition accuracy,and unhygienic contact-based disposal,an inductive intelligent garbage recycling system based on a micro-cont...To solve the problems of traditional garbage classification relying on manual work,low recognition accuracy,and unhygienic contact-based disposal,an inductive intelligent garbage recycling system based on a micro-controller is designed.The system takes STM32F103ZET6 as the core,integrates speech recognition,visual recognition,and infrared induction modules,and adopts a dual recognition fusion strategy of“speech priority+visual verification”to realize con-tactless induction lid opening,accurate garbage classification,and remote status monitoring functions.Speech recognition completes keyword matching through the LD3320 module,visual recognition realizes image feature extraction and classification based on the BP neural network,and the ESP8266 module is responsible for uploading device status to the Cloud platform.It is applicable to multiple scenarios such as households and communities,effectively improving the efficiency and convenience of garbage classification,and has good practical value.展开更多
Fusion of multiple instances within a modality for biometric verification performance improvement has received considerable attention. In this letter, we present an iris recognition method based on multiinstance fusio...Fusion of multiple instances within a modality for biometric verification performance improvement has received considerable attention. In this letter, we present an iris recognition method based on multiinstance fusion, which combines the left and right irises of an individual at the matching score level. When fusing, a novel fusion strategy using minimax probability machine （MPM） is applied to generate a fused score for the final decision. The experimental results on CASIA and UBIRIS databases show that the proposed method can bring obvious performance improvement compared with the single-instance method. The comparison among different fusion strategies demonstrates the superiority of the fusion strategy based on MPM.展开更多
基金2024 Ministry of Education Supply-Demand Docking Employment and Education Projects(Project No.:2024101679202,Project No.:2024121116066)2023 Ministry of Education Supply-Demand Docking Employment and Education Projects(Project No.:2023122927732,Project No.:2023122925618)+1 种基金2024“Innovation Strong Institute Project”Construction Project(Project No.:2024CQ-29)Talent Project of the Open University of Guangdong:Research on key technologies for improving the performance of blockchain application platforms(Project No.:2021F001).
文摘To solve the problems of traditional garbage classification relying on manual work,low recognition accuracy,and unhygienic contact-based disposal,an inductive intelligent garbage recycling system based on a micro-controller is designed.The system takes STM32F103ZET6 as the core,integrates speech recognition,visual recognition,and infrared induction modules,and adopts a dual recognition fusion strategy of“speech priority+visual verification”to realize con-tactless induction lid opening,accurate garbage classification,and remote status monitoring functions.Speech recognition completes keyword matching through the LD3320 module,visual recognition realizes image feature extraction and classification based on the BP neural network,and the ESP8266 module is responsible for uploading device status to the Cloud platform.It is applicable to multiple scenarios such as households and communities,effectively improving the efficiency and convenience of garbage classification,and has good practical value.
基金supported by the PhD Programs Foundation of Ministry of Education of China (No.20050698025)the National Natural Science Foundation of China (No.60602025).
文摘Fusion of multiple instances within a modality for biometric verification performance improvement has received considerable attention. In this letter, we present an iris recognition method based on multiinstance fusion, which combines the left and right irises of an individual at the matching score level. When fusing, a novel fusion strategy using minimax probability machine （MPM） is applied to generate a fused score for the final decision. The experimental results on CASIA and UBIRIS databases show that the proposed method can bring obvious performance improvement compared with the single-instance method. The comparison among different fusion strategies demonstrates the superiority of the fusion strategy based on MPM.
