Application of image recognition in workpiece classification

Abstract

With the rapid development of information technology and widespread use of the Internet of Things, machine intelligence will undoubtedly emerge as a leading research topic in the future. The main purpose of the present research is to incorporate an image recognition system into a robotic arm motion to achieve automatic classification. First, we upload captured images to a PC for classification process and use chess patterns to conduct a sampling test. Next, when the system identifies these patterns as proper chess patterns, the robotic arm grabs the objects and moves them to designated locations. The project is divided into two main sections: image recognition and robotic arm motion. In the image recognition section, we use Keras and the Tensorflow open source learning machine to build a convolutional neural network model. Then, we use a learning model network that is a considerably more compact variant of the VGGNet network in the image recognition system. With this model, we achieve a recognition accuracy of 95%. In the robotic arm section, we use a five-axis robotic arm and an Arduino Uno board as the controller. We design the Denavit–Hartenberg parameters of the arm and calculate the direct (inverse) kinematics parameters to plan its trajectory. Thereafter, we use MATLAB software to simulate prototype processes, such as grabbing, moving, and placing. Finally, we import the program into the controller so that the robotic arm can execute classification based on the chess pattern.

Multi-Model Fusion Fine-Grained Image Classification Method Based on Migration Learning

“…Aiming at the GC deficiency of the current SM method and the solidification of the weights of the traditional MMF method, the study proposes a dynamic weighted MMF method for FGI classification by utilizing ML. Convolutional Neural Networks (CNN) and Deep Neural Networks are the basic technologies for the approach, so the study first examines both of them.CNN is a feedforward neural network that was developed using DL, and its operation was influenced by the visual cortex of the human eye, which is naturally better at recognising images [15][16]. CNN uses a "end-to-end" approach to image recognition, but it can be intuitively divided into two parts based on the functions played by each component of its structure: feature extraction and classification.…”

“…Finally, the output module refers to the decision matrix from the weight adjustment and fusion module after the fusion of the maximum probability value by rows, this maximum probability value corresponding to the category of the column that is the fusion model of the sample's predicted classification, and after comparing with the real label, the final classification probability is output. In addition, the algorithm is evaluated from the classification effect and algorithm efficiency respectively in the experiment, in which the recall, accuracy, precision and F1 value are selected as the evaluation indexes for the classification effect, and the corresponding computational expressions are shown in equation ( 14) and equation (15).…”