Dissertation > Excellent graduate degree dissertation topics show
Research on Off-line Handwritten Signature Recognition Based on Improved KNN
Author: LiZuo
Tutor: SunHuaZhi
School: Tianjin Normal University
Course: Applied Computer Technology
Keywords: Line signature recognition Image preprocessing Feature Extraction VPKNN LMKNN
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 25
Quote: 0
Read: Download Dissertation
Abstract
|
The signature verification is an emerging biometric - based identification technology , because of its convenient , reliable , and invasion of privacy information is not extracted from the handwriting was widely accepted in many areas of business , financial , legal , insurance and other widely the application , so the in - depth study using computer offline handwritten signature identification has important theoretical significance and of great practical value . This paper first introduces the research background and significance , and brief overview of the signature verification technology , summarizes the research progress and achievements at home and abroad in the field , and analyzed off - line signature verification study the problems , and then the signature image delve into line signature recognition preprocessing, feature extraction and selection , and classification and identification technology . Smooth signature image , binary , refinement, remove the blank edge , contour extraction pre-processing operations , and extract the signature shape characteristics and pseudo- dynamic characteristics of 56 -dimensional feature . Shape features include the signature geometric features and moments feature ; pseudo - dynamic feature extraction of high-density area , the group of 41 -dimensional feature grayscale histogram , gray , center of gravity , signature skeleton direction grayscale and stroke width histogram . In recognition technology using a weighted Euclidean distance and k-nearest neighbor (KNN) classification method to identify the specimen signatures . KNN algorithm , we study the impact on the quality of the classification results of the selection of the k value . The KNN algorithm insufficient , the paper proposed two improved the KNN signature classification algorithms : projection feature vectors the KNN (VPKNN) , and based on the learning model KNN ( LMKNN ) . VPKNN can quickly and accurately select a small set of training samples , greatly improving the efficiency of the algorithm . The algorithm of LMKNN overcomes the the basic KNN algorithm inert learning and k values ??dependent defects . The experimental results show that both improved KNN classification algorithm to ensure the correct recognition rate and false rejection rate (FRR) improve recognition efficiency of KNN .
|
Related Dissertations
- Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
- ISAR Imaging Simulation of Space Targets and Target Recognition Based on ISAR Images,TN957.52
- Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
- Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
- Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
- Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
- Research on Visual Measurement for Spacecraft Rendezvous and Approach,TP391.41
- Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
- Feature Extraction, Selection and Combination in Lipreading,TP391.41
- Multi-currency Notes Technology Research and Implementation,TP391.41
- The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
- Pavement Distress Recognition Based on Image,TP391.41
- Research on Visual Detection and Tracking of Mobile Robots,TP242.62
- Research on Fusion Algorithm of Hyper Spectral and High Spatial Resolution Remote Sensing Image,TP751
- An Approach for Identifying a Plant Resistance Gene Based on the Random Forest,Q943
- Tobacco Diseases Auto-Recognition Research Based on Image Processing Technology,S435.72
- Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
- Research on Identification System of Cashmere and Wool Fiber,TS101.921
- Research for Infrared Image Target Identification and Tracking Technology,TP391.41
- The Compression and Fusion Technique Research of Underwater Target Feature,TN911.7
- Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
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
|