Automated learning of model classifications

Ip, Cheuk Yiu; Regli, William C.; Sieger, Leonard; Shokoufandeh, Ali

doi:10.1145/781650.781659

Cited by 8 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu and Jen [25] proposed a three-dimensional pyramidal parts classification neural network, for which images were collected from three perspectives of three-dimensional parts, and edge information from the parts were extracted for the input of a polygon classifier. Ip et al [26] and Ip and Regli [27] proposed a classification method for mechanical CAD parts based on machine learning. Ip and Regl [28] use a support vector machine (SVM) to classify prismatic machined parts and post-casting machined parts by using four types of surface curvatures as input vectors for a support vector machine.…”

Section: B Deep Learning Based Three-dimensional Object Recognition Methodsmentioning

confidence: 99%

PolishNet-2d and PolishNet-3d: Deep Learning-Based Workpiece Recognition

Liu

Wang

2019

IEEE Access

View full text Add to dashboard Cite

In recent years, there have been many deep learning research projects based on two-dimensional object detection and three-dimensional point cloud recognition. However, relatively few of these combine the two, and the number of projects based on a three-dimensional workpiece recognition method for the industrial field is even fewer. In this paper, to perform the recognition task for polishing workpieces in manufacturing, we use RGB-D images as input, and propose our designed PolishNet-2d for two-dimensional workpiece detection and our designed PolishNet-3d for three-dimensional workpiece recognition. The two deep neural networks are employed together in series to first detect and then recognize polishing workpieces in an industrial environment. For this paper, a large number of experiments have been carried out on deep learning datasets of polishing workpieces. These datasets were created by us to contain diverse combinations of real and simulated workpieces in real and simulated industrial environments. The contributions of this paper are as follows: (1) A rotation parameter learning network is proposed and a two-dimensional workpiece detection neural network, named PolishNet-2d, which was constructed by integrating our designed algorithms with the backbone networks ResNet101 and region proposal network (RPN), is introduced; (2) A hierarchical feature extraction network is proposed and a three-dimensional workpiece recognition neural network, named PolishNet-3d, which was constructed by integrating our designed algorithms with the backbone network PointNet, is introduced; (3) PolishNet-2d and PolishNet-3d are employed in series, with the detection output of PolishNet-2d being used as the input for PolishNet-3d for its recognition tasks: the workpiece regions are detected in the RGB image; the workpiece point cloud is segmented in the corresponding regions in the depth image, and lastly the segmented point cloud is placed into PolishNet-3d to identify the workpiece; (4) For the experiments in this paper, datasets containing rich and diverse data types of polishing workpieces for industrial fields have been constructed; (5) Numerous experimental results on polishing workpiece datasets show that the conjunction of PolishNet-2d and PolishNet-3d can achieve exemplary recognition results on polishing workpiece datasets.INDEX TERMS Deep learning, 2d workpiece detection, 3d workpiece recognition.

show abstract

Section: B Deep Learning Based Three-dimensional Object Recognition Methodsmentioning

confidence: 99%

PolishNet-2d and PolishNet-3d: Deep Learning-Based Workpiece Recognition

Liu

Wang

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In Ip et al . (2003) the authors define a new feature space based on metrics features ( inner, outer , and mixed distances ) over which they approach the classification of solid models using learning techniques (decision tree and reinforcement learning), that allow the automated categorization of wheels , sockets , and housing models. In Yiu Ip and Regli (2005), the authors present another approach to automate the classification of CAD models with machine learning techniques.…”

Section: Problem Specification and Related Workmentioning

confidence: 99%

A methodology for part classification with supervised machine learning

Rucco

Giannini

Lupinetti

et al. 2018

AIEDAM

View full text Add to dashboard Cite

In this paper, we report on a data analysis process for the automated classification of mechanical components. In particular, here, we describe, how to implement a machine learning system for the automated classification of parts belonging to several sub-categories. We collect models that are typically used in the mechanical industry, and then we represent each object by a collection of features. We illustrate how to set-up a supervised multi-layer artificial neural network with an ad-hoc classification schema. We test our solution on a dataset formed by 2354 elements described by 875 features and spanned among 15 sub-categories. We state the accuracy of classification in terms of average area under ROC curves and the ability to classify 606 unknown 3D objects by similarity coefficients. Our parts’ classification system outperforms a classifier based on the Light Field Descriptor, which, as far as we know, actually represents the gold standard for the identification of most types of 3D mechanical objects.

show abstract

“…They refined Osada's D2 shape distribution function. Recently, Ip et al [14] extended this approach with a technique to automatically categorize a large model database, given a categorization on a number of training examples from the database. Ohbuchi et al [15] investigated another extension of the D2 shape distribution function, called the Absolute Angle-Distance histogram.…”

Section: Extracting Shape Descriptorsmentioning

confidence: 99%

An overview of content-based three-dimensional model retrieval methods

Jia

Zhang

Chen

et al. 2008

2008 IEEE International Conference on System of Systems Engineering

View full text Add to dashboard Cite

Recent advancement in computer hardware and software have led to an increasing amount of 3D models. Furthermore, the rapid development of WWW enables the access to 3D models constructed by people all over the world. This paper surveyed the background, state-of-theart review and progress of content-based 3D shape retrieval, and analyzed and described several topics, including the preprocessing, coordinates standardization, feature extraction, similarity matching, query interface and existing typical 3D model search engines. Also, we classified the existing 3D shape similarity measures and focus on several 3D model similarity measures. Finally, advantages and disadvantages of these methods are discussed and future works are proposed.

show abstract

Automated learning of model classifications

Cited by 8 publications

References 12 publications

PolishNet-2d and PolishNet-3d: Deep Learning-Based Workpiece Recognition

PolishNet-2d and PolishNet-3d: Deep Learning-Based Workpiece Recognition

A methodology for part classification with supervised machine learning

An overview of content-based three-dimensional model retrieval methods

Contact Info

Product

Resources

About