Research on track fastener positioning method based on local unidirectional template matching

Commonly used fastener positioning methods include pixel statistics (PS) method and template matching (TM) method. For the PS method, it is difficult to judge the image segmentation threshold due to the complex background of the track. For the TM method, the search in both directions of the global is easily affected by complex background, as a result, the locating accuracy of fasteners is low. To solve the above problems, this paper combines the PS method with the TM method and proposes a new fastener positioning method called local unidirectional template matching (LUTM). First, the rail positioning is achieved by the PS method based on the gray-scale vertical projection. Then, based on the prior knowledge, the image of the rail and the surrounding area of the rail is obtained which is referred to as the 1-shaped rail image; then, the 1-shaped rail image and the produced offline symmetrical fastener template is pre-processed. Finally, the symmetrical fastener template image is searched from top to bottom along the rail and the correlation is calculated to realize the fastener positioning. Experiments have proved that the method in this paper can effectively realize the accurate locating of the fastener for ballastless track and ballasted track at the same time.

An Advanced Image Processing Prototype for Corrosion Finding Using Image Processing

The main objective of the research work is to recognize the rust of the substance with the help of Image Processing. The recognition of the rust portion of an image is carried out by quantizing of image in matrix form. The quantization process helps to perform the fundamental operation on image and also helps to identify the desired oxidation portion of an image. The corrosion portion was identified through the threshold operation, edge detection and segmentation. Threshold value assists to describe the types of the rust. Further the abrupt modification of colour in the images was captured by the edge detection method. Consequently partitioning of an image find the colour changes in the oxidized image. The corrosion portion was recognized by combining the edge recognition and partitioning process. Finally recommended methods provide the 98% accuracy to detect the rust.

Furnace flame recognition based on improved particle swarm optimization algorithm

Industrial furnace kiln internal combustion flame directly reflects the combustion of fuel quality and stability and determines the security of the whole production process. The flame image contains many important information that cannot be observed by people’s eyes, as a result, how to effectively separate the flame image from the surrounding background by means of science and technology has the great research significance and application value. In this article, the idea of neighborhood particles is introduced into the standard particle swarm optimization algorithm, and a furnace flame recognition method is proposed based on improved particle swarm optimization algorithm. The method first uses red, green and blue color space to design the extraction model of flame image, then uses the proposed improved particle swarm optimization algorithm and Otsu algorithm to solve the optimal segmentation threshold involved in the model. Experimental results show that the proposed improved particle swarm optimization algorithm can always find the optimal segmentation threshold of the flame image within no more than 100 iterations and reduce the computation time nearly 0.01 s. Compared with the previous research results, the recognition rate of the extraction model designed in this article has been greatly improved to over 93%, which is of great value for the safe and stable operation of industrial furnaces.

Identification of Cabbage Seedling Defects in a Fast Automatic Transplanter Based on the maxIOU Algorithm

The automatic identification of seedling defects is an important technology of an intelligent automatic transplanting machine, which effectively improves the quality of the transplanting machine’s operation. The accurate segmentation of seedling substrate and seedling region is the key to the success of the seedling defect recognition algorithm. This paper proposes the maxIOU algorithm to calculate the image segmentation threshold: The image G channel and excess green color space were selected as the color space for the segmentation of the substrate region and seedling region by analyzing the color histogram. Several images were randomly selected from the dataset to generate a training set and were labeled manually as the ground truth. The training set images were segmented using a threshold of zero to 255, and the intersection over union (IOU) were calculated using the algorithm segmented result and the ground truth. The threshold corresponding to the average IOU maximum was used as the segmentation threshold. After image segmentation, three features (area of the substrate, area of the seedling, and filling ratio of the lower part of the substrate) were obtained by the algorithm, and the image was identified for whether there was an empty conveyor belt, seedling deficiency, multiple seedlings, skew, and damaged substrate. The algorithm was tested on the automatic transplanter test platform. The experiment results were as follows: Firstly, the image segmentation threshold was calculated by the maxIOU method. The color component interval corresponding to the segmented substrate region was [0, 24] in the G channel, and the color component interval corresponding to the segmented seedling region was [21, 255] in the excess green channel. The average IOU of the substrate area was 0.854, and the average IOU of the seedling area was 0.820 in the verification experiment. Secondly, a dataset including 431 normal seedling images and 69 defective seedling images (empty conveyor belt, seedling deficiency, multiple seedlings, skew, and damaged substrate) was identified for defects. The accuracy, precision, and recall were 97.6%, 97.4%, and 99.8%. The processing time was 71.4 ms. The conclusion of the experiment was as follows: the maxIOU algorithm had high accuracy in the segmentation of the substrate and seedling region. The defect identification algorithm had high accuracy for defect identification of cabbage seedlings, and the algorithm had good real-time performance, which can be applied to high speed field transplanters.

Multilevel Image Thresholding for Image Segmentation using Hybrid Algorithm

Image thresholding is an extraction method of objects from a background scene, which is used most of the time to evaluate and interpret images because of their advanced simplicity, robustness, time reduced, and precision. The main objective is to distinguish the subject from the background of the image segmentation. As the ordinary image segmentation threshold approach is computerized costly while the necessity for optimization techniques are highly recommended for multi-tier image thresholds. Level object segmentation threshold by using Shannon entropy and Fuzzy entropy maximized with hGSA-PS. An entropy maximization of hGSA-PS dependent multilevel image thresholds is developed, where the results are best demonstrated in PSNR, misclassification, structural similarity index and segmented image quality compared to the Firefly algorithm, adaptive cuckoo search algorithm and the search algorithm gravitational.

Accuracy of in vitro mandibular volumetric measurements from CBCT of different voxel sizes with different segmentation threshold settings

Background: To determine the accuracy of volumetric measurements of the mandible in vitro by cone-beam computed tomography (CBCT) and to analyze the influence of voxel sizes and segmentation threshold settings on it. Methods：The samples were obtained from pig mandibles and scanned with 4 voxel sizes: .125 mm, .20 mm, .30 mm, and .40 mm. The minimum segmentation thresholds in Hounsfield units (HU) were set as 0, 100, 200, 300, and 400, respectively, for each voxel size for 3D reconstruction. Laser scanning as the reference, the volumes of each CBCT scanning, the mean iterative distances of superimposition and total positive and negative deviations were recorded and compared. Results：The volumes of CBCT-scan deviated from those of laser-scan by +7.67% to -3.05% with different HU and voxel sizes. The deviation increased with the voxel size. There was a more suitable minimum HU threshold of segmentation (HU100 for .125 mm, 200 for .20 mm, 300 for .30 mm, and 400 for .40 mm) for each voxel size. Conclusions：Voxel sizes and Hounsfield unit thresholds influence the accuracy of volumetric measurements in CBCT scanning. The volume increase with the voxel size, and different voxel sizes correspond to different optimal Hounsfield unit thresholds.

Accuracy of in vitro mandibular volumetric measurements from CBCT of different voxel sizes with different segmentation threshold settings

Background: To determine the accuracy of volumetric measurements of the mandible in vitro by cone-beam computed tomography (CBCT) and to analyze the influence of voxel sizes and segmentation threshold settings on it. Methods：The samples were obtained from pig mandibles and scanned with 4 voxel sizes: .125 mm, .20 mm, .30 mm, and .40 mm. The minimum segmentation thresholds in Hounsfield units (HU) were set as 0, 100, 200, 300, and 400, respectively, for each voxel size for 3D reconstruction. Laser scanning as the reference, the volumes of each CBCT scanning, the mean iterative distances of superimposition and total positive and negative deviations were recorded and compared. Results：The volumes of CBCT-scan deviated from those of laser-scan by +7.67% to -3.05% with different HU and voxel sizes. The deviation increased with the voxel size. There was a more suitable minimum HU threshold of segmentation (HU100 for .125 mm, 200 for .20 mm, 300 for .30 mm, and 400 for .40 mm) for each voxel size. Conclusions：Voxel sizes and Hounsfield unit thresholds influence the accuracy of volumetric measurements in CBCT scanning. The volume increase with the voxel size, and different voxel sizes correspond to different optimal Hounsfield unit thresholds.

Accuracy of in vitro mandibular volumetric measurements from CBCT of different voxel sizes with different segmentation threshold settings

Background: To determine the accuracy of volumetric measurements of the mandible in vitro by cone-beam computed tomography (CBCT) and to analyze the influence of voxel sizes and segmentation threshold settings on it. Methods：The samples were obtained from pig mandibles and scanned with 4 voxel sizes: .125 mm, .20 mm, .30 mm, and .40 mm. The minimum segmentation thresholds in Hounsfield units (HU) were set as 0, 100, 200, 300, and 400, respectively, for each voxel size for 3D reconstruction. Laser scanning as the reference, the volumes of each CBCT scanning, the mean iterative distances of superimposition and total positive and negative deviations were recorded and compared. Results：The volumes of CBCT-scan deviated from those of laser-scan by +7.67% to -3.05% with different HU and voxel sizes. The deviation increased with the voxel size. There was a more suitable minimum HU threshold of segmentation (HU100 for .125 mm, 200 for .20 mm, 300 for .30 mm, and 400 for .40 mm) for each voxel size. Conclusions：Voxel sizes and Hounsfield unit thresholds influence the accuracy of volumetric measurements in CBCT scanning. The volume increase with the voxel size, and different voxel sizes correspond to different optimal Hounsfield unit thresholds.

A Wear Debris Segmentation Method for Direct Reflection Online Visual Ferrography

Wear debris in lube oil was observed using a direct reflection online visual ferrograph (OLVF) to monitor the machine running condition and judge wear failure online. The existing research has mainly concentrated on extraction of wear debris concentration and size according to ferrograms under transmitted light. Reports on the segmentation algorithm of the wear debris ferrograms under reflected light are lacking. In this paper, a wear debris segmentation algorithm based on edge detection and contour classification is proposed. The optimal segmentation threshold is obtained by an adaptive canny algorithm, and the contour classification filling method is applied to overcome the problems of excessive brightness or darkness of some wear debris that is often neglected by traditional segmentation algorithms such as the Otsu and Kittler algorithms.