Intelligent image recognizing system and device

Abstract

The invention belongs to the technical field of image recognition, and particularly discloses an intelligent image recognizing system and device. The intelligent image recognizing device comprises a supporting ring. A supporting film is arranged on the inner side of the supporting ring. An outer cylinder is arranged on the outer side of the supporting ring. The outer cylinder is connected with thesupporting ring through an elastic film. A U-shaped groove is fixedly connected with the top of the outer cylinder. A driven gear is clamped on the inner side of the U-shaped groove. A camera is installed on an installing rod of the driven gear, an object where imaging recognition is going to be conducted is put on the supporting ring or the supporting film first, after the object stays still, amotor is controlled by a controller to work, the motor drives a driving gear to rotate, the driving gear drives the driven gear to rotate, then the driven gear drives the camera on the top thereof torotate, in the rotating process of the camera, the controller controls the camera to conduct continuous imaging on the object, when multi-directional imaging is performed over rotating by one cycle, the object cannot shake or deform, and collecting precision and collecting efficiency are ensured.

Description

technical field [0001] The invention belongs to the technical field of image recognition, in particular to an intelligent image recognition system and a recognition device thereof. Background technique [0002] Image recognition refers to the technology of using computers to process, analyze and understand images to identify targets and objects in various patterns. It is a practical application of deep learning algorithms. At this stage, image recognition technology is generally divided into face recognition and commodity recognition. Face recognition is mainly used in security inspection, identity verification and mobile payment; commodity recognition is mainly used in the process of commodity circulation, especially unmanned shelves, smart retail cabinets, etc. In the field of unmanned retail, the traditional recognition process of images is divided into four steps: image acquisition→image preprocessing→feature extraction→image recognition. Plants are mostly recognized by ...

AI Technical Summary

Problems solved by technology

[0003] There are also some technical solutions on image recognition in the prior art. For example, the Chinese patent application No. 2018207983820 discloses an intelligent plant image recognition device, which uses the main camera and auxiliary camera on the device to perform multiple plant information. The collection of angles enables the multi-directional collection of plant information, and then transmits the collected image information to a central control module, which compares the image information with the information stored in the data memory through the central control module, and then identifies the plants. Rotate the carrier plate to rotate the plants to be identified on the carrier plate, increase the number of plant information collected by the main camera and the auxiliary camera, and increase the accuracy of recognition. Rotation, rotation will cause the object to shake. If the shape of the object that needs to collect images is easy to change during movement, such as when collecting plants, it will cause inaccurate image collection. It is necessary to wait until the object is completely still before collecting, reducing improve the efficiency of image acquisition, in view of this, the present invention provides an intelligent image recognition system and its identification device, which can improve the accuracy of acquisition and the speed of acquisition under the situation of realizing panoramic acquisition

Images