A Background Subtraction Method for Defect Detection of Printed Image

2013 ◽  
Vol 462-463 ◽  
pp. 421-427
Author(s):  
Jian Hua Ding ◽  
Yao Lu ◽  
Wei Huang ◽  
Ming Qin
Keyword(s):  
Defect Detection ◽  
Background Subtraction ◽  
Moving Objects ◽  
Texture Feature ◽  
Background Modeling ◽  
Experimental Results ◽  
Subtraction Method ◽  
Moving Objects Detection ◽  
Hsv Histogram ◽  
Objects Detection

Background subtraction is often used to detect the moving objects from static cameras. The difficult of defect detecting of printing matter is how to detect the unknown flaws in complicate background effectively. Inspired by the background modeling approach for moving objects detection, a background modeling method in defect detection of printed image is suggested in this paper. Those pixels without defects are regarded as background, while the flaw pixels are defined as foreground. Firstly, we select LBP histogram as texture feature and HSV histogram as color feature to model the background respectively. Then, lots of printed images in which there are no defects are used to update these two models. Finally, we utilize the models to detect defects of printing images. Experimental results show that this background model works well in our defect detection.

scholarly journals Background Subtraction (BS) Using Instant Pixel Histogram

2019 ◽  
Vol 54 (5) ◽  
Author(s):  
Narjis Mezaal Shati ◽  
Sundos Abdulameer Alazawi ◽  
Huda Abdulaali Abdulbaqi
Keyword(s):  
Computer Vision ◽  
False Alarm ◽  
False Alarm Rate ◽  
Background Subtraction ◽  
Detection Rate ◽  
Moving Objects ◽  
Moving Objects Detection ◽  
Computer Vision Applications ◽  
Objects Detection ◽  
Published Research

Video computer vision applications require moving objects detection as a first phase of their operation. Therefore, background subtraction (BS), an investigate branch in computer vision with intensive published research, is applied to obtain the “background” and the “foreground.” Our study proposes a new BS model that utilizes instant pixel histogram, which is implemented to extract foreground objects from two datasets, the first Visor (different human actions) and the second Anomaly Detection Dataset UCSD (Peds2). The model when using the Visor dataset gives 100% detection rate with 8% false alarm rate, whereas, when using UCSD (Peds2), it achieves a detection rate and false alarm rate of 77% and 34% respectively.

Study of Moving Objects Detection Method for Examination Room Surveillance Based on Background Subtraction

2013 ◽  
Vol 718-720 ◽  
pp. 385-388
Author(s):  
Yong Zheng Lin ◽  
Pei Hua Liu
Keyword(s):  
Background Subtraction ◽  
Surveillance System ◽  
Moving Objects ◽  
Detection Method ◽  
Detection Algorithm ◽  
System Stability ◽  
Moving Objects Detection ◽  
System A ◽  
Objects Detection ◽  
Examination Room

Detection of moving objects is one of the primary factors to influence the examination surveillance system. A new moving objects detection algorithm based on background subtraction is presented after the introduction various of existing methods. Dynamic threshold conception is put forward while defining threshold. Practices show that this method can successfully overcome lighting variations and the system stability is improved.

Moving Object Detection and Tracking in outside Environments

2011 ◽  
Vol 130-134 ◽  
pp. 3862-3865
Author(s):  
Yi Ding Wang ◽  
Da Qian Li
Keyword(s):  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Background Subtraction ◽  
Moving Objects ◽  
Gaussian Mixture ◽  
Middle Ground ◽  
Moving Objects Detection ◽  
Detection And Tracking ◽  
Objects Detection ◽  
Typical Method

Background subtraction is a typical method for moving objects detection. The Gaussian mixture model is one of widely used method to model the background. However, in challenge environments, quick lighting changes, noises and shake of background can influence the detection of moving objects significantly. To solve this problem, an improved Gaussian Mixture Model is proposed in this paper. In the proposed algorithm, Objects are divided into three categories, foreground, background and middle-ground. The proposed algorithm is a segmented process. Moving objects including foreground and middle-ground are extracted firstly; then foreground is segmented from middle-ground. In this way almost middle-ground are filtered, so we can obtain a clear foreground objects. Experimental results show that the proposed algorithm can detect moving objects much more precisely, and it is robust to lighting changes and shadows.

A Real Implementation of Dangerous Objects Capturing in Surveillance Web

2013 ◽  
Vol 278-280 ◽  
pp. 1032-1035
Author(s):  
Yun Cheng ◽  
Hai Tao Lang ◽  
Peng Yao ◽  
Rui Guo ◽  
Jian Ying Hu ◽  
...  
Keyword(s):  
Background Subtraction ◽  
Moving Objects ◽  
Texture Feature ◽  
Multiple Scale ◽  
Experimental Results ◽  
Phase Method ◽  
Two Phase ◽  
Surveillance Camera ◽  
Object Learning ◽  
Classification Framework

The main focus of our research is capturing dangerous objects when they appear under the surveillance camera again, while have performed a dangerous activities in other places. Our solution is a two-phase method, including object learning and capturing under the classification framework. The samples of objects and non-objects are collected to train a classifier with libSVM in object learning phase. In object capturing phase, all moving objects are detected by background subtraction, then are classified into dangerous or non-dangerous. To obtain a robust objects representation to illumination, scale, rotation etc. we fuse HSV space based color feature and multiple scale texture feature. The experimental results with real surveillance data validated the proposed method.

Sign in / Sign up

Export Citation Format

Share Document