riview paper on content based image indexing rerival
- 1. Review paper on Content Based Image Indexing and Retrieval BY Ermias Geremew
- 2. Introduction • As in internet era most difficult task is to retrieve the relevant information in response to a query. • There was no interaction in between the user and the search engine i.e. after obtaining search result user have no option to provide feedback regarding whether the result is relevant or not.
- 3. Cont.. • Content-based image retrieval (CBIR), also known as query by image content (QBIC) and content- based visual information retrieval (CBVIR) is the application of computer vision to the image retrieval problem, that is, the problem of searching for digital image in large databases. “ • The term 'content' in this context might refer to colors, shapes, textures, or any other information that can be derived from the image itself.
- 4. FEATURE EXTRACTION ALGORITHMS • The researcher discuss various features that can be extracted from digital images for indexing and retrieval. • Color Feature: A digital image may be considered as a two dimensional array where the array cells correspond to the image pixels and the values stored in the cells to the values of color-intensity, in case of a grey scale (single-color) image
- 5. Cont.. • Texture Feature :Texture is another important property of images. Various texture representations have been investigated in pattern recognition and computer vision. • Texture representation methods can be classified into two categories: structural and statistical.
- 6. Cont… • Edge Feature :Edge detection is useful for locating the boundaries of objects within an image. Any abrupt change in image frequency over a relatively small area within an image is defined as an edge • . Image edges usually occur at the boundaries of objects within an image, where the amplitude of the object abruptly changes to the amplitude of the background or another object
- 7. SHAPE-BASED IMAGE RETRIEVAL Shape extraction remains a challenge to feature- oriented approaches. Several methods have been developed for detecting shapes indirectly. Whereas it tends to be extremely difficult to perform semantically meaningful segmentation, many reasonably reliable algorithms for low-level feature extraction have been developed. These will be used to provide the spatial information that is lacking in color histograms.
- 8. SIMILARITY MEASUREMENT • Histogram Euclidean distance Let h and g represent two color histograms. The Euclidean distance between the color histograms h and g can be computed as:
- 9. Histogram Intersection Distance • The color histogram intersection was proposed for color image retrieval. The intersection of histograms h and g is given by:
- 10. conclussion We have presented a comprehensive survey highlighting popular methods and algorithms for evaluation relevant to the young and exciting field of image retrieval. With ease of bandwidth, memory and computational power, we believe that the field will experience a paradigm shift in the future, with the focus being more on applicationoriented, generating considerable impact in day- to-day life. With explosive growth of social media, image search options being provided by most search engine has contributed in quality and quantity of images being uploaded in recent times.