Name
Abstract | ||
|---|---|---|
Because of the fast developing technologies in multimedia devices, we are able to receive huge amounts of images from daily life. Once these images have been stored, the next step is to figure out how to retrieve the desired pictures quickly and accurately from the database. In this paper, we intend to develop an efficient image retrieval algorithm. Using this algorithm, we can retrieve desired images by using similar input sample images. Our research images include vehicles, buildings, flowers and other natural scenes. First, we applied the edge and morphological filter on the grey scale images to refill and extract the largest interesting object from the image. Second, we developed an image retrieval algorithm called Region of Interest (ROI) Motif Co-occurrence Matrix (RMCM) to find the relation of the neighboring pixels on the image. In this algorithm, we need to generate a 2 × 2 pattern called a motif. The main idea of this algorithm is to quickly and accurately find the characteristic values about motif. Finally, we can compare the Euclidean distance of the characteristic values from the motif to locate the most similar image from database. In our develop algorithm we combine the partly area motif and characteristic area center location methods to raise the accuracy and speed of recognition. Using our proposed algorithm RMCM, the mean processing time is about 0.82 seconds per image. This value is faster than using Motif Co-occurrence Matrix (MCM) by about 2.57 times. The accurate recognition rates are about 95% and 87% as related to vehicles and buildings. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/ISPACS.2012.6473494 | ISPACS |
Keywords | Field | DocType |
peano scan,rmcm,color histogram,vehicle,motif co-occurrence matrix,flower,content based retrieval,matrix algebra,multimedia device,building,edge filter,roi,grey scale image,region-of-interest motif cooccurence matrix,image retrieval,morphological filter,natural scenes,filtering theory,euclidean distance,characteristic area center location method,image colour analysis,texture recognition | Computer vision,Automatic image annotation,Computer science,Image texture,Euclidean distance,Image retrieval,Image processing,Pixel,Artificial intelligence,Digital image processing,Visual Word | Conference |
ISBN | Citations | PageRank |
978-1-4673-5081-5 | 0 | 0.34 |
References | Authors | |
3 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yen-Shin Lee | 1 | 0 | 0.34 |
| Shu-Sheng Hao | 2 | 0 | 0.34 |
| Shu-Wei Lin | 3 | 0 | 0.34 |
| Sheng-Yi Li | 4 | 17 | 7.33 |