Location Recognition Algorithm for Vision-Based Industrial Sorting Robot via Deep Learning
Authors:
- 7 June 2019
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 33 (07)
Abstract
In this paper, the deep convolutional neural network (DCNN) is applied to locating and recognizing complex workpieces automatically for the vision-based sorting robot in industrial production process. Firstly, in order to obtain the location of workpieces, the pixel projection algorithm (PPA), which consists of pre-procession and pixel projection operation, is presented to eliminate uneven illumination, and locate and segment workpieces images. Then, we get the objective information and identify the object by training DCNN, which is used to recognize the rational degree and type of workpieces at a high rate of speed. Finally, experimental results prove the validity of the location-recognition algorithms for the vision-based sorting robot. The location error and recognition accuracy can be significantly improved in the experimental environment.Keywords
Funding Information
- National Natural Science Foundation of China (61603107, 61863007)
This publication has 22 references indexed in Scilit:
- Deep patch learning for weakly supervised object classification and discoveryPattern Recognition, 2017
- Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studiesExpert Systems with Applications, 2017
- A deep learning ensemble approach for crude oil price forecastingEnergy Economics, 2017
- Emotion-modulated attention improves expression recognition: A deep learning modelNeurocomputing, 2017
- Voronoi-Based Compact Image Descriptors: Efficient Region-of-Interest Retrieval With VLAD and Deep-Learning-Based DescriptorsIEEE Transactions on Multimedia, 2017
- A Method for Optimizing the Base Position of Mobile Painting ManipulatorsIEEE Transactions on Automation Science and Engineering, 2016
- A Deep Learning Scheme for Motor Imagery Classification based on Restricted Boltzmann MachinesIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2016
- Deep learningNature, 2015
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989
- Workpiece recognition and inspection by a model-based scene analysis systemPattern Recognition, 1984