No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Quality inspection method of micro-nano parts based on deep learning
Abstract
There are some disadvantages such as low efficiency, high work intensity by using the manual methods to detect the quality of micro-nano parts because of the characteristics such as small size and fragile structure. Considering about the disadvantages, computer microscopic vision is introduced into the detection system in this paper, which can collects the image information of the parts into the computer system efficiently. The parts to be detected are transmitted by the spin material platform driven by the stepping motor. It is CNN based on deep learning that used to detect the surface quality and classify the defects of the parts according to the image information in this paper, which can improve the accuracy of the detection and reduce the work intensity of human compared with not only the traditional manual detection methods but also some edge detection methods that former researchers used.
ResearchGate has not been able to resolve any citations for this publication.
Image segmentation is used to separate objects from the background, and thus it has proved to be a powerful tool in bio-medical imaging. In this paper, an Improved Edge Detection algorithm for brain-tumor segmentation is presented. It is based on Sobel edge detection. It combines the Sobel method with image dependent thresholding method, and finds different regions using closed contour algorithm. Finally tumors are extracted from the image using intensity information within the closed contours. The algorithm is implemented in C and its performance is measured objectively as well as subjectively. Simulation results show that the proposed algorithm gives superior performance over conventional segmentation methods. For comparative analysis, various parameters are used to demonstrate the superiority of proposed method over the conventional ones.
Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.
An automatic system is developed to realize high precision assembly of two components in the size of mm level with an interference fit in 3-dimensional (3-D) space with 6-degree-of- freedoms (DOF), which consists of a manipulator, an adjusting platform, a sensing system and a computer. The manipulator is employed to align component B to the component A in position. The adjusting platform aligns the component A to component B in orientations and inserts A into B. The sensing system includes three microscopes and a force sensor. The three microscopes are mounted approximately orthogonal to observe components from different directions in the aligning stage. The force sensor is introduced to detect the contact force in assembly process. In the aligning stage, a pose control method based on image Jacobian matrix is proposed. In the insertion stage, a position control method based on the contact force is proposed. The calibration of image Jacobian matrix is also presented. Experimental results demonstrate the effectiveness of the proposed system and methods.
Theoretical results strongly suggest that in order to learn the kind of complicated functions that can repre- sent high-level abstractions (e.g. in vision, language, an d other AI-level tasks), one needs deep architec- tures. Deep architectures are composed of multiple levels of non-linear operations, such as in neural nets with many hidden layers or in complicated propositional formulae re-using many sub-formulae. Searching the parameter space of deep architectures is a difficult opti mization task, but learning algorithms such as those for Deep Belief Networks have recently been proposed to tackle this problem with notable success, beating the state-of-the-art in certain areas. This paper d iscusses the motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer models such as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks.
Multilayer neural networks trained with the back-propagation
algorithm constitute the best example of a successful gradient based
learning technique. Given an appropriate network architecture,
gradient-based learning algorithms can be used to synthesize a complex
decision surface that can classify high-dimensional patterns, such as
handwritten characters, with minimal preprocessing. This paper reviews
various methods applied to handwritten character recognition and
compares them on a standard handwritten digit recognition task.
Convolutional neural networks, which are specifically designed to deal
with the variability of 2D shapes, are shown to outperform all other
techniques. Real-life document recognition systems are composed of
multiple modules including field extraction, segmentation recognition,
and language modeling. A new learning paradigm, called graph transformer
networks (GTN), allows such multimodule systems to be trained globally
using gradient-based methods so as to minimize an overall performance
measure. Two systems for online handwriting recognition are described.
Experiments demonstrate the advantage of global training, and the
flexibility of graph transformer networks. A graph transformer network
for reading a bank cheque is also described. It uses convolutional
neural network character recognizers combined with global training
techniques to provide record accuracy on business and personal cheques.
It is deployed commercially and reads several million cheques per day
TensorFlow is Google’s recently released open-source software for deep learning. What are its applications for computational biology?