Cigarette positioning device and method based on deep learning

Abstract

The invention discloses a cigarette positioning device and method based on deep learning, and belongs to the technical field of industrial detection and computer vision. The cigarette positioning device comprises a lighting device, an industrial camera, a data acquisition and processing system and a rejection device which are connected in sequence; the industrial camera and the lighting device are installed on the fixing support and located on the inclined upper side of the cigarette. The data acquisition and processing system is used for triggering the industrial camera and acquiring and processing cigarette image data; and the removing device is used for removing unqualified cigarettes. According to the cigarette positioning method, the cigarette positioning device based on deep learning is adopted to carry out positioning detection on cigarettes; the positioning detection method comprises a data preparation stage, a model training stage and a model application stage. Cigarette detection is carried out through the model based on deep learning, cigarettes in a cigarette packet are accurately positioned, the problem of cigarette positioning errors existing in a traditional cigarette detector is solved, target self-adaption in the equipment debugging process is achieved, and consumption of manpower and material resources is reduced.

Description

technical field [0001] The invention belongs to the technical field of industrial detection and computer vision, and in particular relates to a device and method for locating cigarettes based on deep learning. Background technique [0002] In the process of tobacco processing and production, the quality of cigarettes directly affects the quality of the final product, and the cigarettes transported from the crimping machine to the packaging line will have various defective products due to various reasons. In order to ensure the quality of cigarettes in the final pack, a cigarette detector needs to be installed on the packaging line to detect the filling status of individual cigarettes in the pack (empty and loose ends detection) and the integrity of the entire cigarette pack (missing sticks, mouth gap detection), and send a rejection signal to the control system of the packaging unit for defective cigarette packs. [0003] The use of computer vision to inspect product qualit...

AI Technical Summary

Problems solved by technology

[0005] Cigarette detectors designed using traditional computer vision technology are often helpless in the face of equipment jitter and uncertainty in system triggering time to cause cigarette positioning errors; at the same time, the equipment debugging process cannot adapt to the target, and equipment debugging often takes a lot of money. a lot of manpower

Images