Dissertation > Excellent graduate degree dissertation topics show

Research and Application of Multi-granularity Based CBIR in Fabric

Author: HuangHaiQuan
Tutor: QiuTaoRong
School: Nanchang University
Course: Applied Computer Technology
Keywords: fabric card image retrieval granular computing compatible relationgranularity texture energy meature main color weight histogram
CLC: TP391.41
Type: Master's thesis
Year: 2013
Downloads: 2
Quote: 0
Read: Download Dissertation

Abstract


In traditional.the factories use the artificial way to do the material’s purchasing, testing and processing in the field of fabric’s goods.Material’s purchasing, testing and processing is influenced by people’s experience.mood and perceptions. Furthermore, the artificial way wastes massive time and manpow.The technology of image retrieval is increasingly applied in our life with the development in the field of computer, pattern recognition and artificial intelligence. This paper uses the Content-based image retrieval(CBIR) method to develop the image retrieval system.The key technique of CBIR is to extract the image’s visual feature and to choose the similarity’s meature method.As the fabric material has marked color feature and texture feature.this paper choose color featurea and texture feature as the visual feature. This paper use the improved color histogram(Main Color Weight Method:MCWM) which is based on traditional histogram and HSV color space to describe the image’s color feature.Meanwhile.this paper inroduces a new method to improve the color’s quantization.As the fabric’s texture is artificial texture.this paper uses K.Laws’texture energy meature to extract the texture feature.The traditional similarity’s meature method is calculating the distance between unqueried image and the image in the library.Generally speaking.the trational similarity’s meature method has high error rate.Moreover it is not appropriate for all of the visual feature.The granularity in the granular computing is a good way to classify the objects according to the different granularity.The different granularity and the granularity’s scale will affect the classification’s result and accuracy.This paper classifies the fabric images according to the domain knowledge and the images’color feature and texture feature with the granular computing’s concept. Compatible relation granularity is also built by the granular computing.The following paper uses the standard criterion along with the query-stability and order-stability put forward in the paper to do the test in the testing data(Brodaz Texture Set and Fabric Image Set etc).The different feature and different meature have the different result and effect.The method combining with MCWM and K.Laws is more effective than classical color histogram,accumulate histogram and color volume method.The method combined with the compatible relation granularity to do the classification is more effective than the method without compatible relation granularity.At last,this paper uses the Java Swing to develop the fabric images retrieval system.This system is based on the MVC architecture.This system sets the scanning parameter including the scanning size,scanning resolution and saving format in the system with the TWAIN rather than using the scanners’software.The system use the new algorithm to extract the image’s feature and the granular computing method to get the matched images with the unqueried image.The system also provides the way to set the retrieving parameters to get the retrieval result.

Related Dissertations

  1. Research on Facial Feature Extraction and Matching Algorithms for Image Retrieval,TP391.41
  2. The Research and Implemention of Image Retrieval Based on User Interested Feature,TP391.41
  3. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  4. Research and Implementation on Content-Based Clothing Image Retrieval,TP391.41
  5. The Discovery of User Concept Region Based on Multiple Instance Learning,TP391.41
  6. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  7. Research and Application of Diverse Density Learning Algorithm,TP181
  8. Research on Theory of Granular Computing and Its Application on Image Retrieval,TP18
  9. Content-Based Thangka Image Retrieval Technology Research,TP391.41
  10. Study on Extraction Methods of Image Interesting Regions,TP391.41
  11. Research and System Implementation of Image Retrieval Method Based on Fuzzy Clustering,TP391.41
  12. Research on Classification of Texture Images,TP391.41
  13. The Granules of Formal Concept,TP18
  14. Granular Computing Based Neuro-Fuzzy System Modeling for Forecast of Operator Functional State,TP18
  15. Study on Integration and Retrieval for Lunar Spatial Data,P184.5
  16. Traffic Flow Simulation Base on Granular Computing and Three-tier Structure,U491.112
  17. The Research and Application of Fuzzy Control Based on Granular Computing,TP273.4
  18. Research on Content Based Image Retrieval Methods,TP391.41
  19. Research on Semantic-Based Image Classification and Retrieval,TP391.41
  20. Granular Space and Granular Computing of Information Systems Based on Binary Relation,O159
  21. The Research of Data Fusion Algorithm in Sensor Network,TP202

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