Sub-pixel Edge Detection Method Research Articles

Machine Vision Based Defect Detection Method for Electronic Component Solder Pads

<p>This paper proposes a machine vision based solder pad detection method to improve the detection accuracy and efficiency of PCB solder pad defects in electronic components due to missed detection and low detection efficiency. Firstly, preprocess the electronic component pad images collected by the visual system, then use threshold segmentation method to perform preliminary segmentation of the pad images. Then, the coarse segmented images are finely segmented using mean clustering method, and the fine segmented images are pixel edge extracted. Finally, the matrix subpixel edge detection method is used to improve the edge detection accuracy. Simulation experiments have shown that the proposed method can significantly improve the accuracy and speed of defect recognition.</p> <p> </p>

Research on the Measurement of Thermal Deformation of Tools on High-speed Machining Centers Based on Image Processing Technology

This paper focuses on the issues of tool thermal deformation during machine preheating，designing an image-processing-based solution for measuring these tool thermal deformation, to obtain the axial thermal error of the tool as a function of preheating time.This paper uses a high-speed camera to collect images of tool thermal deformation. Using MATLAB software, rough localization of images by Canny algorithm for edge extraction. Accurately locating tool edge outlines using a sub-pixel fitted edge detection method, that is, using the least squares method to fit a tool tip arc curve. From this, the thermal deformation during tool preheating is calculated. This study will serve as a basis for the compensation of thermal errors in machine tools.

Sub-pixel dimensional and vision measurement method of eccentricity for annular parts.

Eccentricity measurement of annular parts with millimeter scale and micrometer precision requirements is widely used in mechanical engineering applications. To realize accurate eccentricity measurement for large-scaled annular parts, a vision-based and sub-pixel dimensional measurement method is proposed. First, to facilitate the eccentricity measurement, an improved auto focus algorithm is introduced to provide better focused images of the measured parts. Then the traditional Canny operator is modified in gradient direction calculation and a double threshold process to locate the pixel edge more accurately. Next, a model-based sub-pixel edge detection method is studied to extract the sub-pixel edge coordinates. Finally, the eccentricity is calculated according to these sub-pixel edge coordinates. To guarantee measurement accuracy, the pixel equivalent and manual installation error of three degree of freedom (DOF) stages are calibrated, and the verification experiments indicate that the measurement error of the proposed method is better than 1.0 µm.

An adaptive sub-pixel edge detection method based on improved Zernike moment

An adaptive sub-pixel edge detection method based on improved Zernike moment

An adaptive sub-pixel edge detection method based on improved Zernike moment

An adaptive sub-pixel edge detection method based on improved Zernike moment

A Novel Subpixel Edge Detection Method of Pantograph Slide in Complicated Surroundings

Pantograph slide is a vulnerable component because of the contact and friction between the pantograph and catenary while the train runs with a high speed. Condition monitoring of the slide is a necessary and meaningful work to improve the operation efficiency and reduce the occurrence of accident. It is a hard work to measure the slide abrasion due to the dynamic and complicated environment. In this article, an accurate edge extraction method based on image analysis is proposed, which aims at providing an image metric property based on vision measurement to detect the wear of slide. First, a subpixel edge detection method is proposed. The gradient in horizontal direction is first taken into account, which filters out the nonhorizontal edges. Then, the upper and lower edges of the slide are located using the geometric restriction. The subpixel edge feature are also extracted in the image process, which can be used to the vision measurement system for monitoring the wear condition of the slide. The experiment results shows that the proposed algorithm can precisely detect the subpixel edges of the slide. The measurement error of the slide is less than 2 mm, which demonstrates that the proposed algorithm has a high accuracy in the large field of view.

Research on Subpixel Algorithm of Fixed-Point Tool Path Measurement.

Tool safety is an important part of machining and machine tool safety, and machine tool path image detection can effectively obtain the in-machine condition of a tool. To obtain an accurate image edge and improve image processing accuracy, a novel subpixel edge detection method is proposed in this study. The precontour is segmented by binarization, the second derivative in the neighborhood of the demand point is calculated, and the obtained value is sampled according to the specified rules for curve fitting. The point whose curve ordinate is 0 is the subpixel position. The experiment proves that an improved subpixel edge can be obtained. Results show that the proposed method can extract a satisfactory subpixel contour, which is more accurate and reliable than the edge results obtained by several current pixel-level operators, such as the Canny operator, and can be used in edge detection with high-accuracy requirements, such as the contour detection of online tools.

Effect of Vibration on Surface Roughness in Finish Turning: Simulation Study

This paper presents the results of simulation analyses carried out to investigate the effect of adding controlled vibration of varying amplitudes and frequencies onto simulated workpiece profiles on surface roughness. The surface profiles were generated using the nose edge image of a real cutting tool insert at various stages of wear. The invariant moment sub-pixel edge detection method was used to extract the precise tool nose profile. The extracted nose profile was duplicated 20 times to generate the simulated workpiece profile. Vibration signals in the form of sine waves of amplitudes 0 to 50 % of the peak-to-valley height of the original workpiece profile and various frequencies were added to the simulated profile. Noise signals emanating from real machining were also added to the original profile to investigate their effect on roughness. The simulation study has shown that average roughness may increase continuously or fluctuate randomly depending on the magnitude of vibration added to the vibration-free workpiece profile. In the absence of vibration, the surface roughness of the workpiece decreases due to flattening effect of the tool nose during early stages of tool wear.

Monocular Vision-Based Calibration Method for Determining Frequency Characteristics of Low-Frequency Vibration Sensors

Calibration is required to determine the frequency characteristics of vibration sensors to ensure their measurement accuracy in engineering applications. Thus, a monocular vision-based calibration method for low-frequency vibration sensors is investigated in this study. A sub-pixel edge detection method which based on Gaussian curve fitting is applied to extract the edges of motion sequence images in order to accurately measure the excitation acceleration of the sensors. Because the motion sequence images and the output signal of the sensors cannot be collected synchronously, it is very difficult to align the excitation acceleration signal obtained from the images and the output signal in the time domain. Although the misalignment only has a negligible effect on the magnitude frequency characteristic calibration, it dramatically decreases the calibration accuracy of the phase frequency characteristic, especially with the increasing of the frequency. A time-spatial synchronization technique is proposed to accurately calibrate the phase frequency characteristic by determining the phase of the excitation acceleration signal at a specific spatial position and that of the output signal at the corresponding time. Finally, both the magnitude and phase frequency characteristics are simultaneously calibrated by the investigated method with a flexible and low-cost vision system. The experimental results compared with laser interferometry show that the investigated method accomplishes the high-accuracy magnitude and phase frequency characteristics calibration in a broad low-frequency range. Its calibration accuracy is superior to that of laser interferometry when the frequency is less than 0.3 Hz, and is equivalent at other frequencies.

Adaptive Image Edge Extraction Based on Discrete Algorithm and Classical Canny Operator

In order to improve the accuracy of image edge detection, this paper studies the adaptive image edge detection technology based on discrete algorithm and classical Canny operator. First, the traditional sub-pixel edge detection method is illustrated based on the related literature research. Then, Canny operator is used for detection, the edge model of the quadric curve is established using discrete data, and the adaptive image edge parameters are obtained using one-dimensional gray moment. Experimental results show that the accuracy of feature detection is 99%, which can be applied to the practice of image edge detection to a certain extent.

High Precision Dimensional Measurement with Convolutional Neural Network and Bi-Directional Long Short-Term Memory (LSTM).

In modern industries, high precision dimensional measurement plays a pivotal role in product inspection and sub-pixel edge detection is the core algorithm. Traditional interpolation and moment methods have achieved some success. However, those methods still have shortcomings. For example, the accuracy is still insufficient with the resolution limitation of the image sensor. Moreover, prediction results can be affected by image noise. With the recent success of deep learning technology, we propose a sub-pixel edge detection method based on convolution neural network (CNN) and bi-directional long short-term memory (LSTM). First, one-dimensional visual geometry group-16 (VGG-16) is employed to extract edge features. Then, a transformation operation is developed to generate sequence information. Lastly, bi-directional LSTM with fully-connected layers is introduced to output edge positions. Experimental results on our steel plate dataset demonstrate that our method achieves superior accuracy and anti-noise ability than traditional methods.

Real-time Human Corneal Images Processing Analysis of Placido Disk Corneal Topography Using Extenics

A sub-pixel image edge detection method based on polar coordinates is proposed in order to accurately detect images obtained from corneal topographic instrument based on Placido disk. The corneal image obtained by the corneal topographic instrument has the following characteristics: 1. Real time. The image acquisition video is set to 30 frames/sec, so the image processing algorithm should have the millisecond level of computing performance; 2. Quality is not stable. Because of the influence of photographing environment, machine and human entry factors, the images of cornea will have various kinds of noises. So we should propose a stable and effective preprocessing algorithm. 3. Image offset. Due to the operation characteristics of such corneal topographic system, the consecutive images’ centers are unavoidable drifted during the process of image acquisition. So it is necessary to match the same serial target pictures. According to the above characteristics, based on the theory of extension and matter-element data structure, this paper efficiently structured captured images and uses two-dimensional Gaussian smoothing function to preprocess the data of all kinds of noises, including real human eyelashes removing and uses mixed Canbel (combining the canny and Sobel algorithms) and regional three-polynomial fitting method to effectively detect the sub-pixel edges of corneal images which we derive. Based on the experiments of standard simulation eye and real human eye, it is proved that the algorithm presented in this paper has good robustness and detection accuracy (the refractive error distributions of standard simulation eyes with different curvatures are less than 0.25D), which meets the operation requirements of actual systems used in industry. So our algorithm can be used in such corneal topographer in order to help detection of various eye diseases.

Accurate characterisation of hole size and location by projected fringe profilometry

The ability to accurately estimate the location and geometry of holes is often required in the field of quality control and automated assembly. Projected fringe profilometry is a potentially attractive technique on account of being non-contacting, of lower cost, and orders of magnitude faster than the traditional coordinate measuring machine. However, we demonstrate in this paper that fringe projection is susceptible to significant (hundreds of µm) measurement artefacts in the neighbourhood of hole edges, which give rise to errors of a similar magnitude in the estimated hole geometry. A mechanism for the phenomenon is identified based on the finite size of the imaging system’s point spread function and the resulting bias produced near to sample discontinuities in geometry and reflectivity. A mathematical model is proposed, from which a post-processing compensation algorithm is developed to suppress such errors around the holes. The algorithm includes a robust and accurate sub-pixel edge detection method based on a Fourier descriptor of the hole contour. The proposed algorithm was found to reduce significantly the measurement artefacts near the hole edges. As a result, the errors in estimated hole radius were reduced by up to one order of magnitude, to a few tens of µm for hole radii in the range 2–15 mm, compared to those from the uncompensated measurements.

The Line Scan Camera Calibration Based on Space Rings Group

In addition to the accuracy requirements, the calibration of the line scan camera (LSC) should also have strong operability and portability. This paper presents a low-cost high-reliability LSC calibration method. First, a 3D right-angle stereo target based on concentric rings is designed, which is named space rings group, and it is suitable for static calibration of LSC. The calibration target has a simple structure and is easy to carry. The calibration process does not require other auxiliary instruments, greatly improving the operability of the calibration for the line camera. Second, in order to improve the positioning accuracy of subpixel edges in the image and reduce the computational complexity, a subpixel edge detection method is adopted, which is a region-by-region localization algorithm, a combination of global adaptive Canny detection and local partial area effect (Local-Canny-PAE, LCPAE). Then, the relationship between the actual spatial point and the image point is established by using the invariant nature of the image and the imaging model of the camera, and the two-step particle swarm optimization (TS_PSO) algorithm is used to solve the internal parameters of the camera. Finally, the validity of this method is verified by computer simulation and real experiment.

Accurate calibration method for camera and projector in fringe patterns measurement system.

The 3D measurement system based on fringe patterns is widely applied in diverse fields. The measurement accuracy is mainly determined by camera and projector calibration accuracy. In the existing methods, the system is calibrated by a dot calibration board with traditional image process algorithms. In this paper, an improved calibration method is proposed to increase camera and projector calibration accuracy simultaneously. To this end, first, a subpixel edge detection method is proposed to improve the detection accuracy of reference features for coarse calibration; second, an iterative compensation algorithm is developed to improve the detection accuracy of the reference feature centers for fine calibration. The experimental results demonstrate that the proposed calibration method can improve the calibration accuracy and measurement accuracy.

A subpixel edge detection method based on an arctangent edge model

The sub-pixel edge detection method is widely applied in image processing to improve accuracy of measurement and recognition. Detection methods often encounter difficulties with low computational efficiency or poor robustness. To address such difficulties, a new least-squared-error-based method is proposed in this paper. First, a one-dimensional solution is derived by means of an arctangent edge model. In the two-dimensional situation, the Sobel operator and the cubic surface fitting method are used to determine the normal direction of edge. Then, two-dimensional edge detection can be transformed into a one-dimensional problem that can be solved with a one-dimensional solution. Because there is no complicated surface fitting in this least-squared-error-based method, it will provide an opportunity to ascertain quickly the accurate location of an edge. The experiment is described at the end of the paper, comparing three edge detection methods. The results indicate that the new detection approach has robustness equal to the traditional least-squared-error-based methods, while run time is much faster and very close to the moment-based methods. The above advantages indicate this approach is very suitable for on-line accurate detection.

Subpixel Edge Detection for Segmentation of the Pulp Fiber Image

In this paper the problem of accurate edge detection for pulp fibers images is discussed. The images are acquired by the smart CCD camera. Subpixel edge detection is considered that applied in the system to improve the measurement accuracy of pulp fibers. The location of a precise edge is the basis of kink index, kink Angle, curl index and other measurement parameters for the pulp fibers. A new method for subpixel edge detection of the pulp fibers is introduced. Canny operator is used to get the pixel level edge. Each edge point determines five pixels in the gradient direction. Then the least squares fitting is used to locate its sub-pixel edge. The measurement results show that the proposed subpixel edge detection method is valid to improve measurement accuracy for real time measuring the pulp fiber parameters.

A New Sub-pixel Edge Detection Method of Color Images

Modern image measurement needs to take full advantage of sub-pixel edge information of images. This paper presents a sub-pixel edge detection method of color images based on image dimensionality reduction and the least square method. First of all we get the pixel level edge by Ostu algorithm and then combine gray processing algorithm based on color spatial distance and the least square method for sub-pixel edge location. Experimental results show that the algorithm positioning accuracy can reach 0.13 pixel which provides a basis for the selection of color image sub-pixel edge positioning. DOI : http://dx.doi.org/10.11591/telkomnika.v12i5.4921

A Sub-Pixel Edge Detection Method Combining the Interpolation with the Moment Theory

A new sub-pixel edge detection method is proposed to improve the detection accuracy. Firstly, using the theory of interpolation to acquire the continuous gray level distribution in one-dimensional .Therefore, the location of edge is determined. Secondly, in view of the two-dimensional edge detection, the moment spatial is taken into account. At last, the two-dimensional edge detection simplified as one-dimensional. From the test ,its known that the accuracy of the this algorithm is higher, especially for images with noise. So, the proposed algorithm has good applicability in image processing.

Method for CCD Edge Signal Processing

In order to improve the measuring precision of the one-dimension line-matrix CCD, a new sub-pixel edge detection method is proposed. Firstly the date collected by the line-matrix CCD is converted to digital data by virtual oscillograph. Base on threshold comparison, the fitting part of the edge signal is picked up for further processing; secondly, the pixels are expanded following the edge direction of the edge point, and the edge signal is fitted through the two order multinomial; finally, comparing the two order curve with the threshold voltage through the least square fit method, the precise position of the edge point can achieve the sub-pixel edge location precision.