scholarly journals A Detection Method for Apple Fruits Based on Color and Shape Features

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 67923-67933 ◽  
Author(s):  
Xiaoyang Liu ◽  
Dean Zhao ◽  
Weikuan Jia ◽  
Wei Ji ◽  
Yueping Sun
Keyword(s):  
Detection Method ◽  
Shape Features ◽  
Apple Fruits

SHAPE-BASED ADULT IMAGE DETECTION

2006 ◽  
Vol 06 (01) ◽  
pp. 115-124 ◽  
Author(s):  
QING-FANG ZHENG ◽  
WEI ZENG ◽  
WEI-QIANG WANG ◽  
WEN GAO
Keyword(s):  
Skin Color ◽  
Detection Method ◽  
Skin Detection ◽  
Shape Descriptors ◽  
Shape Features ◽  
Image Detection ◽  
Classification Schemes ◽  
Skin Color Detection ◽  
Color Detection ◽  
Boosted Classifiers

This paper investigates adult images detection based on the shape features of skin regions. In order to accurately detect skin regions, we propose a skin detection method using multi-Bayes classifiers in the paper. Based on skin color detection results, shape features are extracted and fed into a boosted classifier to decide whether or not the skin regions represent a nude. We evaluate adult image detection performance using different boosted classifiers and different shape descriptors. Experimental results show that classification using boosted C4.5 classifier and combination of different shape descriptors outperforms other classification schemes.

On Vision-Based Orientation Detection Analysis of Industrial Object with Circular-Shape Features

2012 ◽  
Vol 190-191 ◽  
pp. 710-714
Author(s):  
Feng Lian Niu ◽  
Xin Hua Yi
Keyword(s):  
Detection Method ◽  
Robot Manipulator ◽  
Monocular Vision ◽  
Work Piece ◽  
Shape Features ◽  
Detection Analysis ◽  
Industrial Object ◽  
Orientation Detection ◽  
Assembly Precision ◽  
Experiment Analysis

For the need of accuracy orientation location about work piece with circle features in vision-based automatic assemble industry, a kind of orientation detection method about work piece based on monocular vision was presented to locate the work piece and then adjust the orientation of assembly parts to guarantee the assembly precision. Ellipse parameters and center point of contours about holes was solved by extracting the center and edge about given the work piece with four holes in the experiment, orientation and location about surface of work piece can be derived. And then Automatic assemble was implemented by orientation of work piece feeding back to robot manipulator to adjust the orientation of assembling part. Experiment analysis has demonstrated that the uncertain of position is less than 8 um and the uncertain of orientation is less than 5 degree.

Research on Pedestrian Detection Method with Motion and Shape Features

2016 ◽  
Vol 13 (9) ◽  
pp. 5788-5793 ◽  
Author(s):  
Xiaolan Wang ◽  
Xintian Liu ◽  
Hui Guo ◽  
Qiang Guo ◽  
Ningning Liu
Keyword(s):  
Detection Method ◽  
Pedestrian Detection ◽  
Shape Features

A Person Detection Method Using 3D Laser Scanner – Proposal of Efficient Grouping Method of Point Cloud Data –

2015 ◽  
Vol 27 (4) ◽  
pp. 374-381 ◽  
Author(s):  
Kento Hosaka ◽  
◽  
Tetsuo Tomizawa
Keyword(s):  
Point Cloud ◽  
Detection Method ◽  
Laser Scanner ◽  
Experimental Results ◽  
Point Cloud Data ◽  
Shape Features ◽  
Person Detection ◽  
Cloud Data ◽  
Grouping Method ◽  
Individual Objects

<div class=""abs_img""> <img src=""[disp_template_path]/JRM/abst-image/00270004/07.jpg"" width=""300"" /> Our proposed method</div> The purpose of this study is to develop a system for detecting target persons using a 3D laser scanner. The system consists of two parts -- one for grouping and one for determining targets. The grouping part effectively segments individual objects by using two-step grouping. The target part determines target persons for grouping results using shape features. Experimental results showed that our proposed system detects targets as well as existing methods do and that our proposed method performs more quickly than existing methods do. </span>

Shape Features Detection Based on Hough Transform in Images

2014 ◽  
Vol 644-650 ◽  
pp. 1104-1106 ◽  
Author(s):  
Guang Li Chu ◽  
Yan Jie Wang
Keyword(s):  
Hough Transform ◽  
Template Matching ◽  
Traditional Method ◽  
Detection Method ◽  
Feature Points ◽  
Shape Features ◽  
Line Segments ◽  
Definition Of ◽  
Straight Lines ◽  
And Storage

Hough transform as an effective graphics target detection method can detect straight lines, circles, ellipses, parabolas and many other analytical graphics. The discretization of space, as well as the calculation of the process make Hough transform have some limitations, such as poor detection results because of high-intensity noise, a large amount of calculation, large demand of storage resources and so on. This paper analyzes the Hough Transform voting process and points out that the accumulation with 1 in the method is unreasonable. The paper proposed a Hough transform based on template matching via the modification of the definition of the traditional method. In this method, each parameter unit identifies a template in image space. The feature points according with the conditions can be searched by the template actively. The method takes the number of feature points as the value of parameter unit and takes the record of the coordinates of line segment endpoints. So line segments can be detected and storage resources can be saved.

scholarly journals Research on Pedestrian’s Detection Based on the Integration of AdaBoost Algorithm and Shape Features

2011 ◽  
Vol 2-3 ◽  
pp. 433-438
Author(s):  
Ying Yang ◽  
Yu Gang Ma ◽  
Xiao Dong Guo ◽  
Kun Jiao
Keyword(s):  
Detection Method ◽  
Pedestrian Detection ◽  
Morphological Characteristics ◽  
Vertical Axis ◽  
Adaptive Threshold ◽  
Candidate Region ◽  
Vertical Edge ◽  
Shape Features ◽  
Adaboost Algorithm ◽  
Axis Of Symmetry

In this Paper, Propose a Pedestrian Detection Method that Based on Adaboost Algorithm and Pedestrian Shape Features Integration. First According to the Collected Pedestrian True, False Sample, Selected the Characteristics of the Extended Class Haar, Adopt Adaboost Algorithm Training Get Pedestrian Classifier to Split the Initial Candidate Region of All Pedestrians in the Image. in this Paper, Propose an Adaptive Threshold Weight Update Method, Significantly Reduced the Number of the Characteristics of Strong Classifier, Optimize the Classifier Structure, Reduce the Complexity of the Algorithm; Meanwhile, the Online Update Detector, Improving the Reliability of the Detector. Pedestrian Leg Have Strong Vertical Edge Symmetry Characteristic so that Extracted the Vertical Edge Detection in the Initial Candidate Region, According to the Symmetry Determine the Vertical Axis of Symmetry, Combined with the Morphological Characteristics of Pedestrians to Determine the Width and Height Characteristics of the Pedestrian, to Determine the Pedestrian Candidate Region, Finally, Put a Further Validation to the Pedestrian Candidate Region.

The Purity Detection Method of Gem Material Based on the Echo Reflection

2014 ◽  
Vol 644-650 ◽  
pp. 1046-1049
Author(s):  
Hong Yu Qin
Keyword(s):  
Reflection Spectrum ◽  
Detection Method ◽  
Detection System ◽  
Characteristic Parameter ◽  
Shape Features ◽  
Accuracy Rate ◽  
Splitting Algorithm ◽  
Spectrum Splitting ◽  
Spectrum Characteristic

In traditional purity detecting system, the purity of gem is determined by depending on the obtained shape of the reflection spectrum and the different shape features. Once gem is mixed, the system cannot accurately identify the aliasing and deformation reflection spectrum, and the accuracy rate of detection is low. A detection system for the purity of gem based on aliasing spectrum splitting algorithm is proposed. By extracting the detection spectrum characteristic parameter of the gem, the superposition and correlation for spectrum characteristic parameter is calculated; aliasing spectrum information is made splitting to classified achieve the purity detection of gem. Experiments show that this method improve the accuracy rate of the purity detection, and achieves satisfactory results.

scholarly journals S-CNN-BASED SHIP DETECTION FROM HIGH-RESOLUTION REMOTE SENSING IMAGES

2016 ◽  
Vol XLI-B7 ◽  
pp. 423-430 ◽  
Author(s):  
Ruiqian Zhang ◽  
Jian Yao ◽  
Kao Zhang ◽  
Chen Feng ◽  
Jiadong Zhang
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Detection Method ◽  
Saliency Detection ◽  
Head Model ◽  
Shape Features ◽  
Remote Sensing Images ◽  
Line Segments ◽  
Ship Detection ◽  
Efficient Detection

Reliable ship detection plays an important role in both military and civil fields. However, it makes the task difficult with high-resolution remote sensing images with complex background and various types of ships with different poses, shapes and scales. Related works mostly used gray and shape features to detect ships, which obtain results with poor robustness and efficiency. To detect ships more automatically and robustly, we propose a novel ship detection method based on the convolutional neural networks (CNNs), called SCNN, fed with specifically designed proposals extracted from the ship model combined with an improved saliency detection method. Firstly we creatively propose two ship models, the “V” ship head model and the “||” ship body one, to localize the ship proposals from the line segments extracted from a test image. Next, for offshore ships with relatively small sizes, which cannot be efficiently picked out by the ship models due to the lack of reliable line segments, we propose an improved saliency detection method to find these proposals. Therefore, these two kinds of ship proposals are fed to the trained CNN for robust and efficient detection. Experimental results on a large amount of representative remote sensing images with different kinds of ships with varied poses, shapes and scales demonstrate the efficiency and robustness of our proposed S-CNN-Based ship detector.

Sign in / Sign up

Export Citation Format

Share Document