Academia.eduAcademia.edu

Figure 5 – uploaded by Harsha Bhute

See full PDFdownloadDownload figure
International Journal of Computer Applications (0975 — 8887) Volume 58— No.3, November 2012 Video segmentation is first step towards the content based video retrieval aiming to segment moving objects in video sequences. Video segmentation initially segments the first image frame as the Iimage frame into some moving objects and then it tracks the evolution of the moving objects in the subsequent image frames. After segmenting objects in each image frame, these segmented objects have many applications, such as surveillance, object manipulation, scene composition, and video retrieval[10]. Video is created by taking a set of shots and composing them together using specified composition operators. To support communication over the Internet, the data should compress well and be suitable for heterogeneous environment with a variety of the user platforms and viewing devices, large scatter of the user's machine power, and changing viewing conditions. The CBIR systems are not aware usually of the difference in original, encoded, and perceived colors, e.g., differences between the colorimetric and device color data.

Table 5 International Journal of Computer Applications (0975 — 8887) Volume 58— No.3, November 2012 Video segmentation is first step towards the content based video retrieval aiming to segment moving objects in video sequences. Video segmentation initially segments the first image frame as the Iimage frame into some moving objects and then it tracks the evolution of the moving objects in the subsequent image frames. After segmenting objects in each image frame, these segmented objects have many applications, such as surveillance, object manipulation, scene composition, and video retrieval[10]. Video is created by taking a set of shots and composing them together using specified composition operators. To support communication over the Internet, the data should compress well and be suitable for heterogeneous environment with a variety of the user platforms and viewing devices, large scatter of the user's machine power, and changing viewing conditions. The CBIR systems are not aware usually of the difference in original, encoded, and perceived colors, e.g., differences between the colorimetric and device color data.

Related Figures (7)

system should then allow the user to provide relevance feedback to the system. The system uses this information to modify query, query representation, and/or document representations. Another retrieval is done based on the modified query and document representations. If necessary, the retrieval-feedback process is iterated a few times. Note that not all IR systems support the user relevance feedback process. Following Table 1 briefly review various retrieval approaches with its advantages and limitations.
system should then allow the user to provide relevance feedback to the system. The system uses this information to modify query, query representation, and/or document representations. Another retrieval is done based on the modified query and document representations. If necessary, the retrieval-feedback process is iterated a few times. Note that not all IR systems support the user relevance feedback process. Following Table 1 briefly review various retrieval approaches with its advantages and limitations.
Table 1. Comparison of Text Indexing and retrieval Approaches The basic document retrieval process is shown in Figure 1. As shown on the right side of the figure, the documents are processed off-line to obtain document representations. These representations are stored together with documents themselves. During retrieval (left side of the figure), the user issues a query that is processed (online) to obtain its representation. Then the query representation is compared with the document representations. Documents deemed relevant by the system are retrieved and presented to the user, who evaluates the returned documents and decides which ones are actually relevant to the information need. A good IR
Table 1. Comparison of Text Indexing and retrieval Approaches The basic document retrieval process is shown in Figure 1. As shown on the right side of the figure, the documents are processed off-line to obtain document representations. These representations are stored together with documents themselves. During retrieval (left side of the figure), the user issues a query that is processed (online) to obtain its representation. Then the query representation is compared with the document representations. Documents deemed relevant by the system are retrieved and presented to the user, who evaluates the returned documents and decides which ones are actually relevant to the information need. A good IR
Table 2. Comparison of Image Indexing and Retrieval Approaches This section briefly describes seven main approaches, which are based on structured attributes, object-recognition, text, and low-level image features. The first approach, attribute-based, uses traditional database management systems for image indexing and retrieval. The second approach color and third based on shape are not mature yet as it relies on automatic object recognition. Text-based image retrieval uses traditional IR for image indexing and retrieval. The low-level content- based approach to image indexing and retrieval requires the extraction of low level image features. The common features used are color, object shape, and texture. As most images are stored in compressed form, it would be advantageous if we could derive image features directly from compressed image data. Table 2 looks into a number of image indexing and retrieval techniques based on compressed image data. An individual feature will not be able to describe an image adequately. For example, it is not possible to distinguish a red car from a red apple based on color alone. Therefore, a combination of features is required for effective image indexing and retrieval. 3. IMAGE INDEXING & RETRIEVAL
Table 2. Comparison of Image Indexing and Retrieval Approaches This section briefly describes seven main approaches, which are based on structured attributes, object-recognition, text, and low-level image features. The first approach, attribute-based, uses traditional database management systems for image indexing and retrieval. The second approach color and third based on shape are not mature yet as it relies on automatic object recognition. Text-based image retrieval uses traditional IR for image indexing and retrieval. The low-level content- based approach to image indexing and retrieval requires the extraction of low level image features. The common features used are color, object shape, and texture. As most images are stored in compressed form, it would be advantageous if we could derive image features directly from compressed image data. Table 2 looks into a number of image indexing and retrieval techniques based on compressed image data. An individual feature will not be able to describe an image adequately. For example, it is not possible to distinguish a red car from a red apple based on color alone. Therefore, a combination of features is required for effective image indexing and retrieval. 3. IMAGE INDEXING & RETRIEVAL
Table 3. Comparison of Audio Indexing and Retrieval Approaches
Table 3. Comparison of Audio Indexing and Retrieval Approaches
5. VIDEO INDEXING & RETRIEVAL 4. AUDIO INDEXING & RETRIEVAL International Journal of Computer Applications (0975 — 8887) Volume 58— No.3, November 2012
5. VIDEO INDEXING & RETRIEVAL 4. AUDIO INDEXING & RETRIEVAL International Journal of Computer Applications (0975 — 8887) Volume 58— No.3, November 2012
Table 4. Comparison of Video Indexing and Retrieval Approaches Following Table 4 summarizes the video indexing and retrieval methods.
Table 4. Comparison of Video Indexing and Retrieval Approaches Following Table 4 summarizes the video indexing and retrieval methods.
International Journal of Computer Applications (0975 — 8887) Volume 58— No.3, November 2012 6. CONCLUSION
International Journal of Computer Applications (0975 — 8887) Volume 58— No.3, November 2012 6. CONCLUSION
Related topics:
Image ProcessingContent-Based Video Retrieval
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved