5results about How to "Improve detection and recognition efficiency" patented technology

The present invention discloses an intelligent feeder for material collection and release inspection, comprising: a frame, a feeding wheel arranged at one end of the frame, a film collection wheel arranged above the feeding wheel, a material guide platform arranged at the rear end of the feeding wheel, a plurality of first material guide rollers arranged between the feeding wheel and the material guide platform, a visual inspection mechanism arranged on the material guide platform, a material pulling mechanism arranged beside the material guide platform, a counterweight wheel arranged at the rear end of the material guide platform, a plurality of second material guide rollers arranged beside the counterweight wheel, and a material collection wheel arranged at the rear end of the counterweight wheel, wherein the counterweight wheel reciprocates up and down on the frame, and a sensing module is arranged beside the counterweight wheel. The present invention detects and identifies the materials on the material belt through the visual inspection mechanism, and determines whether the materials are qualified, thereby replacing the traditional manual identification method, improving the efficiency of detection and identification and the overall work efficiency, and can ensure the accuracy of detection and identification, meeting the needs of mass production activities.

The invention provides plastic film quality detection equipment, and relates to the technical field of optical test identification, the plastic film quality detection equipment comprises a bottom plate, a light supplementing table, a lifting mechanism and a detection clearing assembly, the surface of the bottom plate is screwed with the light supplementing table, the side edge of the bottom plate is welded with a side plate, the top of the side plate is welded with a top plate, one end of the top plate is integrally provided with an extension plate, and the extension plate is provided with a light supplementing mechanism. A visual camera is inserted into the bottom of the extension plate, and the visual camera is aligned with the center point of the bottom light supplementing table. After the situation that stains exist on the surface of a plastic film is detected through visual identification, the rough position of the stains on the plastic film can be judged, and the stains can be accurately detected; according to the plastic film cleaning device, the stains are removed in a targeted mode by accurately controlling the follow-up detecting and removing assembly, and a supporting effect is always provided for the plastic film around the stains in the removing process, so that the vibration amplitude of the plastic film in an erasing area is effectively reduced, the influence on a plastic film body is reduced, and the probability of deformation is reduced.

The invention discloses a double-station online visual inspection method and system. The double-station online visual inspection method and system are based on a multi-thread technology and a machine visual inspection technology integrated with a deep learning algorithm. Two sets of detection processes of the software control system are reasonably distributed into two thread pools, the problem that two production lines interfere with each other in the detection process is avoided by using a multi-thread technology, and all modules of the system are high in independence, convenient to use independently and integrally and convenient to maintain and upgrade. According to the machine vision detection technology integrated with the deep learning algorithm, the detection and recognition accuracy is effectively improved, the detection and recognition efficiency is improved in cooperation with a multi-thread technology, and the production cost is reduced.

This application provides a deep learning-based QR code detection method and apparatus. The method obtains a first feature map through multi-scale feature extraction and feature fusion. Based on the first feature map, a segmentation map of a second preset scale for a first preset channel is obtained. The segmentation map is used to obtain the core region of the QR code to be tested according to its set confidence range. Based on the segmentation map, a first detection box of the QR code is obtained. The first detection box is the minimum area bounding rectangle of the contour in the segmentation map, and it is used to detect and identify the QR code to be tested. This application only needs to obtain the core region of the QR code to be tested through the segmentation map, that is, the process of the segmentation map classifying the core region and non-core region of the QR code, reducing the process required to obtain the QR code detection box, thereby reducing the time spent obtaining the QR code detection box and improving the efficiency of QR code detection and recognition.