An Efficient Image-Based Method for Detection of Fastener on Railway

2011 ◽  
Vol 346 ◽  
pp. 731-737 ◽  
Author(s):  
Jin Feng Yang ◽  
Man Hua Liu ◽  
Hui Zhao ◽  
Wei Tao
Keyword(s):  
Image Processing ◽  
Efficient Method ◽  
Template Matching ◽  
Detection Method ◽  
Experimental Results ◽  
Feature Descriptor ◽  
Complex Environment ◽  
Computation Efficiency ◽  
The Status ◽  
Direction Field

This paper presents an efficient method to detect the fastener based on the technologies of image processing and optical detection. As feature descriptor, the Direction Field of fastener image is computed for template matching. This fastener detection method can be used to determine the status of fastener on the corresponding track, i.e., whether the fastener is on the track or missing. Experimental results are presented to show that the proposed method is computation efficiency and is robust for fastener detection in complex environment.

scholarly journals Random Forest with Adaptive Local Template for Pedestrian Detection

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Tao Xiang ◽  
Tao Li ◽  
Mao Ye ◽  
Zijian Liu
Keyword(s):  
Computer Vision ◽  
Random Forest ◽  
Classification Accuracy ◽  
Template Matching ◽  
Detection Method ◽  
State Of The Art ◽  
Pedestrian Detection ◽  
Sliding Window ◽  
Experimental Results ◽  
Training Samples

Pedestrian detection with large intraclass variations is still a challenging task in computer vision. In this paper, we propose a novel pedestrian detection method based on Random Forest. Firstly, we generate a few local templates with different sizes and different locations in positive exemplars. Then, the Random Forest is built whose splitting functions are optimized by maximizing class purity of matching the local templates to the training samples, respectively. To improve the classification accuracy, we adopt a boosting-like algorithm to update the weights of the training samples in a layer-wise fashion. During detection, the trained Random Forest will vote the category when a sliding window is input. Our contributions are the splitting functions based on local template matching with adaptive size and location and iteratively weight updating method. We evaluate the proposed method on 2 well-known challenging datasets: TUD pedestrians and INRIA pedestrians. The experimental results demonstrate that our method achieves state-of-the-art or competitive performance.

Detection of Microbubbles Using the Hough Transform

2013 ◽  
Vol 378 ◽  
pp. 478-482
Author(s):  
Yoshihiro Mitani ◽  
Toshitaka Oki
Keyword(s):  
Image Processing ◽  
Error Rate ◽  
Hough Transform ◽  
Detection Method ◽  
Experimental Results ◽  
Average Error ◽  
Image Processing Techniques ◽  
Average Error Rate ◽  
Processing Techniques

The microbubble has been widely used and shown to be effective in various fields. Therefore, there is an importance of measuring accurately its size by image processing techniques. In this paper, we propose a detection method of microbubbles by the approach based on the Hough transform. Experimental results show only 4.49% of the average error rate of the undetected microbubbles and incorrectly detected ones. This low percentage of the error rate shows the effectiveness of the proposed method.

Application of Object-Based Image Processing Technique in Printing Defect Online Detection

2015 ◽  
Vol 731 ◽  
pp. 210-213
Author(s):  
Shu Feng Liu ◽  
Shao Hong Shen
Keyword(s):  
Image Processing ◽  
Detection Method ◽  
Main Idea ◽  
Color Difference ◽  
Processing Technique ◽  
Experimental Results ◽  
Image Processing Technique ◽  
Online Detection ◽  
Multi Scale ◽  
Color Printing

In this paper ,a color printing defect automatic online detection method based on digital image processing technique is proposed. The main idea of this method is comparison of defect product and template and it makes up of following key models. Firstly, multi-scale segmentation is applied to composed image which is overlaid by detecting product and template image. Secondly, an automatic region similarity analysis calculation is taken to segmentation obtained in multi-scale segmentation. The color difference between detecting product and template can be calculated accurately. Thirdly, defect detection results can be obtained according to threshold segmentation. Finally, the characteristics and advantages are approved by experimental analysis and discussion. Algorithm parameters are adjusted and modified to improve the stability and effectiveness. Experimental results approve that color printing defect automatic detection method in this paper has the characteristics of effectiveness and applicability. And experimental results indicate that this method has the advantage of judging the defect types automatically.

The Contour Size Detection of Driver Airbag Based on Image Processing Technology

2013 ◽  
Vol 658 ◽  
pp. 546-550
Author(s):  
Xiao Dong Wang ◽  
Xiao Wei Chen ◽  
Wei Zhang ◽  
Bo Liu ◽  
Liang Dong An
Keyword(s):  
Image Processing ◽  
Template Matching ◽  
Detection Method ◽  
Detection Efficiency ◽  
Ccd Camera ◽  
Processing Technology ◽  
Edge Extraction ◽  
Image Preprocessing ◽  
The Poor ◽  
Image Processing Technology

In this paper we have developed a new methodology for detecting the contour size of driver airbag based on image processing technology and Machine vision. Through the CCD camera we can obtain the image, and then do the following operations by a computer, such as binarization, edge extraction and so on the other image preprocessing. This methodology uses intelligent template matching technology to detect the airbags and by comparing with the predefined parameter to determine whether the contour size is qualified .The experimental results show that: this new detection method solves the disadvantage of traditional detection method, such as the low detection efficiency, the detection precision is not high, the poor detection repeatability, the higher rate of detection miscarriage of justice.

scholarly journals FAST AND ROBUST REGISTRATION OF MULTIMODAL REMOTE SENSING IMAGES VIA DENSE ORIENTATED GRADIENT FEATURE

2017 ◽  
Vol XLII-2/W7 ◽  
pp. 1009-1015 ◽  
Author(s):  
Y. Ye
Keyword(s):  
Remote Sensing ◽  
Computational Efficiency ◽  
Template Matching ◽  
Remote Sensing Data ◽  
Experimental Results ◽  
Feature Descriptor ◽  
Remote Sensing Images ◽  
Registration Accuracy ◽  
Registration System ◽  
Similarity Metric

This paper presents a fast and robust method for the registration of multimodal remote sensing data (e.g., optical, LiDAR, SAR and map). The proposed method is based on the hypothesis that structural similarity between images is preserved across different modalities. In the definition of the proposed method, we first develop a pixel-wise feature descriptor named Dense Orientated Gradient Histogram (DOGH), which can be computed effectively at every pixel and is robust to non-linear intensity differences between images. Then a fast similarity metric based on DOGH is built in frequency domain using the Fast Fourier Transform (FFT) technique. Finally, a template matching scheme is applied to detect tie points between images. Experimental results on different types of multimodal remote sensing images show that the proposed similarity metric has the superior matching performance and computational efficiency than the state-of-the-art methods. Moreover, based on the proposed similarity metric, we also design a fast and robust automatic registration system for multimodal images. This system has been evaluated using a pair of very large SAR and optical images (more than 20000 × 20000 pixels). Experimental results show that our system outperforms the two popular commercial software systems (i.e. ENVI and ERDAS) in both registration accuracy and computational efficiency.

Research on the Inspection and Mark on the Defects of Printed Matter Based on Template Matching Algorithm

2015 ◽  
Vol 713-715 ◽  
pp. 377-380
Author(s):  
Shi Yuan Xing ◽  
Yan Qiu Liu ◽  
Yuan Song Zheng
Keyword(s):  
Image Processing ◽  
Template Matching ◽  
High Speed ◽  
Detection Method ◽  
Automatic Detection ◽  
Printing Industry ◽  
Matching Algorithm ◽  
Displacement Error ◽  
Noise Function ◽  
Neighborhood Method

Defects inspection of printed matter that combines the image processing technology with printing principle is a kind of automatic detection method for high speed printing. In view of the displacement error, stains wrinkle, fuzzy words in the current printing industry, this paper has adopted template matching algorithm to compare the standard image and the detected image, followed by the neighborhood method to analyze, then extracted the defects and marked the defect location. This study has good anti-noise function and makes detection precision be controlled within 0.5mm×0.5mm.

Developing an Inkjet Printer I: RGB Image to CMY Ink Amounts - Image Processing and Color Management

2020 ◽  
Vol 2020 (15) ◽  
pp. 350-1-350-10
Author(s):  
Yin Wang ◽  
Baekdu Choi ◽  
Davi He ◽  
Zillion Lin ◽  
George Chiu ◽  
...  
Keyword(s):  
Image Processing ◽  
Low Cost ◽  
Experimental Results ◽  
Color Management ◽  
Finger Nail ◽  
Inkjet Printer ◽  
Rgb Image ◽  
Novel Algorithm

In this paper, we will introduce a novel low-cost, small size, portable nail printer. The usage of this system is to print any desired pattern on a finger nail in just a few minutes. The detailed pre-processing procedures will be described in this paper. These include image processing to find the correct printing zone, and color management to match the patterns’ color. In each phase, a novel algorithm will be introduced to refine the result. The paper will state the mathematical principles behind each phase, and show the experimental results, which illustrate the algorithms’ capabilities to handle the task.

Ensemble Visual Content based Search and Retrieval for Natural Scene Images

2019 ◽  
Vol 12 ◽  
Author(s):  
Pushpendra Singh ◽  
P.N. Hrisheekesha ◽  
Vinai Kumar Singh
Keyword(s):  
Template Matching ◽  
Feature Descriptor ◽  
Natural Scene ◽  
Visual Content ◽  
Other Information ◽  
Similar Images ◽  
State Of Art ◽  
Natural Scene Images ◽  
Hybrid Methodology ◽  
Search And Retrieval

Content based image retrieval (CBIR) is one of the field for information retrieval where similar images are retrieved from database based on the various image descriptive parameters. The image descriptor vector is used by machine learning based systems to store, learn and template matching. These feature descriptor vectors locally or globally demonstrate the visual content present in an image using texture, color, shape, and other information. In past, several algorithms were proposed to fetch the variety of contents from an image based on which the image is retrieved from database. But, the literature suggests that the precision and recall for the gained results using single content descriptor is not significant. The main vision of this paper is to categorize and evaluate those algorithms, which were proposed in the interval of last 10 years. In addition, experiment is performed using a hybrid content descriptors methodology that helps to gain the significant results as compared with state-of-art algorithms. The hybrid methodology decreases the error rate and improves the precision and recall for large natural scene images dataset having more than 20 classes.

scholarly journals OFCOD: On the Fly Clustering Based Outlier Detection Framework

Data ◽  
2020 ◽  
Vol 6 (1) ◽  
pp. 1
Author(s):  
Ahmed Elmogy ◽  
Hamada Rizk ◽  
Amany M. Sarhan
Keyword(s):  
Data Mining ◽  
Image Processing ◽  
Intrusion Detection ◽  
Real Time ◽  
Outlier Detection ◽  
Real World ◽  
Medical Data ◽  
Experimental Results ◽  
Real Time Applications ◽  
Real World Datasets

In data mining, outlier detection is a major challenge as it has an important role in many applications such as medical data, image processing, fraud detection, intrusion detection, and so forth. An extensive variety of clustering based approaches have been developed to detect outliers. However they are by nature time consuming which restrict their utilization with real-time applications. Furthermore, outlier detection requests are handled one at a time, which means that each request is initiated individually with a particular set of parameters. In this paper, the first clustering based outlier detection framework, (On the Fly Clustering Based Outlier Detection (OFCOD)) is presented. OFCOD enables analysts to effectively find out outliers on time with request even within huge datasets. The proposed framework has been tested and evaluated using two real world datasets with different features and applications; one with 699 records, and another with five millions records. The experimental results show that the performance of the proposed framework outperforms other existing approaches while considering several evaluation metrics.

Sign in / Sign up

Export Citation Format

Share Document