An Intelligent Multi-resolution and Co-occuring local pattern generator for Image Retrieval
Content-based image retrieval (CBIR) is a methodology used to search indistinguishable images across any vast repository. Texture, Color and Shape are among the most prominent features of any CBIR system. Two texture descriptors namely Gray level Co-occurence matrix (GLCM) and Discrete wavelet trans...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
European Alliance for Innovation (EAI)
2019-07-01
|
| Series: | EAI Endorsed Transactions on Scalable Information Systems |
| Subjects: | |
| Online Access: | https://eudl.eu/pdf/10.4108/eai.10-6-2019.159344 |
| _version_ | 1811338199053631488 |
|---|---|
| author | Shikha Bhardwaj Gitanjali Pandove Pawan Kumar Dahiya |
| author_facet | Shikha Bhardwaj Gitanjali Pandove Pawan Kumar Dahiya |
| author_sort | Shikha Bhardwaj |
| collection | DOAJ |
| description | Content-based image retrieval (CBIR) is a methodology used to search indistinguishable images across any vast repository. Texture, Color and Shape are among the most prominent features of any CBIR system. Two texture descriptors namely Gray level Co-occurence matrix (GLCM) and Discrete wavelet transform (DWT) have been utilized here for the formation of a hybrid texture descriptor, denoted as (Co-DGLCM). To enhance the retrieval accuracy of the proposed system, a framework of an Extreme learning machine (ELM) with Relevance feedback (RF) has also been used. This technique provides simultaneously spatial relationship and information related to frequency in co-occuring local patterns of an image. Two benchmark texture databases namely Brodatz and MIT-Vistex have been tested and results are obtained in terms of accuracy, total average recall and total average precision which is 96.35% and 97.34% respectively on the two databases. |
| first_indexed | 2024-04-13T18:07:14Z |
| format | Article |
| id | doaj.art-6981d27037344e7cbd6a4593222b3075 |
| institution | Directory Open Access Journal |
| issn | 2032-9407 |
| language | English |
| last_indexed | 2024-04-13T18:07:14Z |
| publishDate | 2019-07-01 |
| publisher | European Alliance for Innovation (EAI) |
| record_format | Article |
| series | EAI Endorsed Transactions on Scalable Information Systems |
| spelling | doaj.art-6981d27037344e7cbd6a4593222b30752022-12-22T02:36:02ZengEuropean Alliance for Innovation (EAI)EAI Endorsed Transactions on Scalable Information Systems2032-94072019-07-0162210.4108/eai.10-6-2019.159344An Intelligent Multi-resolution and Co-occuring local pattern generator for Image RetrievalShikha Bhardwaj0Gitanjali Pandove1Pawan Kumar Dahiya2Department of Electronics and Communication, DCRUST, Murthal, Sonepat, India and UIET, Kurukshetra University, Kurukshetra, IndiaDepartment of Electronics and Communication, DCRUST, Murthal, Sonepat, IndiaDepartment of Electronics and Communication, DCRUST, Murthal, Sonepat, IndiaContent-based image retrieval (CBIR) is a methodology used to search indistinguishable images across any vast repository. Texture, Color and Shape are among the most prominent features of any CBIR system. Two texture descriptors namely Gray level Co-occurence matrix (GLCM) and Discrete wavelet transform (DWT) have been utilized here for the formation of a hybrid texture descriptor, denoted as (Co-DGLCM). To enhance the retrieval accuracy of the proposed system, a framework of an Extreme learning machine (ELM) with Relevance feedback (RF) has also been used. This technique provides simultaneously spatial relationship and information related to frequency in co-occuring local patterns of an image. Two benchmark texture databases namely Brodatz and MIT-Vistex have been tested and results are obtained in terms of accuracy, total average recall and total average precision which is 96.35% and 97.34% respectively on the two databases.https://eudl.eu/pdf/10.4108/eai.10-6-2019.159344Gray level co-occurence matrixDiscrete wavelet transformContent-based Image retrievalExtreme learning machineRelevance feedbackBrodatz datasetMIT-Vistex Dataset |
| spellingShingle | Shikha Bhardwaj Gitanjali Pandove Pawan Kumar Dahiya An Intelligent Multi-resolution and Co-occuring local pattern generator for Image Retrieval EAI Endorsed Transactions on Scalable Information Systems Gray level co-occurence matrix Discrete wavelet transform Content-based Image retrieval Extreme learning machine Relevance feedback Brodatz dataset MIT-Vistex Dataset |
| title | An Intelligent Multi-resolution and Co-occuring local pattern generator for Image Retrieval |
| title_full | An Intelligent Multi-resolution and Co-occuring local pattern generator for Image Retrieval |
| title_fullStr | An Intelligent Multi-resolution and Co-occuring local pattern generator for Image Retrieval |
| title_full_unstemmed | An Intelligent Multi-resolution and Co-occuring local pattern generator for Image Retrieval |
| title_short | An Intelligent Multi-resolution and Co-occuring local pattern generator for Image Retrieval |
| title_sort | intelligent multi resolution and co occuring local pattern generator for image retrieval |
| topic | Gray level co-occurence matrix Discrete wavelet transform Content-based Image retrieval Extreme learning machine Relevance feedback Brodatz dataset MIT-Vistex Dataset |
| url | https://eudl.eu/pdf/10.4108/eai.10-6-2019.159344 |
| work_keys_str_mv | AT shikhabhardwaj anintelligentmultiresolutionandcooccuringlocalpatterngeneratorforimageretrieval AT gitanjalipandove anintelligentmultiresolutionandcooccuringlocalpatterngeneratorforimageretrieval AT pawankumardahiya anintelligentmultiresolutionandcooccuringlocalpatterngeneratorforimageretrieval AT shikhabhardwaj intelligentmultiresolutionandcooccuringlocalpatterngeneratorforimageretrieval AT gitanjalipandove intelligentmultiresolutionandcooccuringlocalpatterngeneratorforimageretrieval AT pawankumardahiya intelligentmultiresolutionandcooccuringlocalpatterngeneratorforimageretrieval |