Dissertation > Excellent graduate degree dissertation topics show
Research on the Technologies of Special Content-Based Erotic Image Filtering
Author: WangYingFang
Tutor: ChenLiWei
School: Harbin Engineering University
Course: Signal and Information Processing
Keywords: Skin color detection model Texture detection model Edge Detection Gabor wavelet transform Sensitive image filtering
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 94
Quote: 0
Read: Download Dissertation
Abstract
|
Technological advances make the network along with the rapid development of the Internet is like a double-edged sword , people are still rejoicing in the power of the web when many immoral people also took the opportunity to channeling in they upload many obscene , pornographic pictures serious pollution of cyberspace . Many researchers blocked pornographic websites , text message with the word sensitive filtering and other methods to control the spread of pornography on the network , but the control of these pornographic images are not very effective , so sensitive image content-based filtering technology came into being. In this paper, based on the specific content of the sensitive image filtering technology , the contents are as follows . Sensitive image filtering module skin detection module, the the texture detection module , feature extraction module and classification module . Skin detection module , through experiments compare our proposed method of combining color space models and statistical histogram model for skin detection , experimental results show that relative to traditional color space model , Gaussian mixture model , histogram model than the detection rate increased to 2.32 ( frames / sec ) . Texture detection module , five common texture algorithm , on this basis, an edge detection method based on the Particle Swarm fuzzy clustering algorithm and the Gabor function combination skin texture detection achieved good experimental results . This can be seen by comparison with the DCT transform method on the accurate detection rate of 16% , the false detection rate has dropped by 22% , the experimental results are very satisfactory . This selection of the decision tree classifier selection as the classifier . The experimental results show that the filtering of sensitive images have a significant effect, be able to distinguish the normal image and the normal image .
|
Related Dissertations
- Feature Extraction, Selection and Combination in Lipreading,TP391.41
- Research on Detecting Optical Fiber Geometric Parameter Based on Machine Vision,TN253
- Research on Image Segmentation Method Based on Measure of Medium Truth Degree,TP391.41
- High-speed detection and bayonet vehicle license identification information,TP391.41
- Image intensifier and a screen resolution of defect detection technology,TN144
- Based on structural similarity with the MTF image quality evaluation method,TP391.41
- Pattern recognition method based weather radar monitoring and analysis of digital products,TN959.4
- The Research of Image Matching Technology Based on Feature Detection,TP391.41
- Research and Implementation of K- means clustering of remote sensing images and watershed segmentation algorithm,TP751
- Research on Cutting Tool Wear Detection Based on Computer Vision,TP274
- The Research of Denoising and Edge Detection Method in Image Measurement,TP391.41
- Line Extraction and Matching Based on Hough Transformation,TP751
- Morphological Image Edge Detection by Using Multi-structuring Elements and Multi-scale Structure Elements,TP391.41
- The Research of Automatic Recognition of Cotton’s Top,TP391.41
- The Research of Face Detection and Recognition Technology Based on the Second Generation I.D. Card,TP391.41
- Research on Image Detection Technology for the Profile of Revolving Body,TP391.41
- Face Recognition by Improved Elastic Matching,TP391.41
- Research on Sensitive Image Filtering Algorithms Based on Content Analysis,TP391.41
- Detection Technology Research of Earthquake Change in Remote Sensing Image,P315.7
- Strip surface defect detection key technology research,TP274.4
CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net Mobile
|