R. Chopra and R. K. Srihari, Control Structures for Incorporating Picture-Specific Context in Image Interpretation, IJCAI '95 (1995).  Home/Search   Document Details and Download   Summary   Related Articles   Check

.... and others have studied the nature of the image database query task [1315 ] The model we build on is developed in [16] Others also argue for statistical models of data for image retrieval [17] Finally, in the area of using associated text for image understanding the work of Srihari and others [18 22] bears mentioning. For the image retrieval component of this work we insisted that browsing was well supported. This is in contrast with many existing systems where the main access to the images is through query. This puts the burden on the user to pose the correct question, and the system to ....

R. Chopra and R. K. Srihari, "Control Structures for Incorporating Picture-Specific Context in Image Interpretation," Proc. IJCAI '95, Montreal, Canada, 1995.

.... size face) Face recognition may follow face detection when faces are large enough and in a semi frontal position, using a method we developed and described in [16] When detected faces are recognized and associated automatically with textual information like in the systems Name it [33] or Piction [6], potential applications such as news video viewer providing description of the displayed faces, news text browser giving facial information, or automated video annotation generators for faces are possible. Although face detection is closely related to face recognition as a preliminary required ....

K. Chopra and R. K. Srihari, "Control structures for incorporating picture-specific context in image interpretation," in Proc. Int. Joint Conf. Artificial Intell., 1995.

....and comparison, camera motion analysis, motion segmentation, etc. are employed. Although videos can be parsed, i.e. the structure of videos can be analyzed, these methods do not provide content information such as object identification or topic classification in news videos. Piction system [8] identifies faces within given captioned photos, typically in newspapers. The system extracts faces from a photo and analyzes captions to obtain geometric constraints among faces which will appear in the photo, then labels each face with each name. The system works fine due to the fact that ....

R. Chopra and R. K. Srihari, Control structures for incorporating picture --- specific context in image interpretation, in Proceedings, International Joint Conference on Artificial Intelligence, 1995.

....eigenvector based method for face similarity matching [4] It is noteworthy that Photobook applied their method to more than 7,500 images of about 3,000 people and got successful results. The results reveal that eigenvector based face similarity matching works well to some extent. Piction system [5] identifies faces within given captioned photos, typically of newspapers. The system extracts faces from a photo and analyzes captions to get geometric constraints among faces which will appear in the photo, then label each face as each name. As far as integrating image processing and text ....

R. Chopra and R. K. Srihari, "Control structures for incorporating picture --- specific context in image interpretation," in Proceedings of IJCAI '95, 1995.

....domain, one would typically augment the semantic model with domain specific concepts and relations that are specializations of the ones provided here. We have demonstrated the applicability of these structures and the benefits of the associated control algorithm in two implemented systems Piction[Chopra and Srihari, 1995; Srihari, 1995c ] and Show Tell. Domain Independent Model The scene hypothesis consists of descriptions of entities of the domain world (instances of specializations of the concept world entity) their visual properties and spatial relations between the entities. The concept conceptual graph ....

....1988] Consistency algorithms for finite domains assume that constraints are enumerated as explicit relations with little or no cost, and that verifying the existence of a tuple in a relation is a unit cost operation. However, there are applications of CSP, in domains such as computer vision [Chopra and Srihari, 1995] , where enumerating the complete extension of a constraint relation is neither inexpensive nor necessary. When dealing with expensive constraints, reducing the domains of the relation s nodes prior to computing the relation s extension seems an obvious improvement over computing the extension ....

[Article contains additional citation context not shown here]

Rajiv Chopra and Rohini Srihari. Control Structures for Incorporating Picture-Specific Context in Image Interpretation. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI95), pages 50--55, Montreal,Canada, August 1995. Morgan Kaufmann.

....domain, one would typically augment the semantic model with domain specific concepts and relations that are specializations of the ones provided here. We have demonstrated the applicability of these structures and the benefits of the associated control algorithm in two implemented systems Piction[Chopra and Srihari, 1995; Srihari, 1995c ] and Show Tell. Domain Independent Model The scene hypothesis consists of descriptions of entities of the domain world (instances of specializations of the concept world entity) their visual properties and spatial relations between the entities. The concept conceptual graph ....

....1988] Consistency algorithms for finite domains assume that constraints are enumerated as explicit relations with little or no cost, and that verifying the existence of a tuple in a relation is a unit cost operation. However, there are applications of CSP, in domains such as computer vision [Chopra and Srihari, 1995] , where enumerating the complete extension of a constraint relation is neither inexpensive nor necessary. When dealing with expensive constraints, reducing the domains of the relation s nodes prior to computing the relation s extension seems an obvious improvement over computing the extension ....

[Article contains additional citation context not shown here]

Rajiv Chopra and Rohini Srihari. Control Structures for Incorporating Picture-Specific Context in Image Interpretation. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI95), pages 50--55, Montreal,Canada, August 1995. Morgan Kaufmann.

....Primitives Semantic analysis II refers to the process of mapping simple spatial expressions and objects onto the set of spatial primitives. These spatial primitives are then expressed as a set of constraints: assertions in PICTION are represented as sets of constraints on a spatial scene [ Chopra and Srihari, 1995 ] First, objects are associated with picture objects and are mapped to in picture constraints, which assert the existence of an object in the accompanying photograph. Next, spatial relations are mapped onto spatial primitives. For example, beside and next to are used to indicate proximity in ....

Rajiv Chopra and Rohini Srihari. Control structures for incorporating picturespecific context in image interpretation. In IJCAI-95, Montreal,Canada, August 1995. Morgan Kaufmann.

....1988 ] Consistency algorithms for finite domains assume that constraints are enumerated as explicit relations with little or no cost, and that verifying the existence of a tuple in a relation is a unit cost operation. However, there are applications of CSP, in domains such as computer vision [ Chopra and Srihari, 1995 ] where enumerating the complete extension of a constraint relation is neither inexpensive nor necessary. When dealing with expensive constraints, reducing the domains of the relation s nodes prior to computing the relation s extension seems an obvious improvement over computing the extension ....

....arity. These unary constraints need not be enforced in scenarios where non unary constraints are much cheaper to evaluate and achieve substantial problem reduction. 7 Application The algorithm has been prototyped in Allegro Common Lisp and used for an application in high level computer vision [ Chopra and Srihari, 1995; Srihari et al. 1994 ] The nodes are people names, the labels are rectangular sub images denoting human faces. The constraints are extracted from a caption accompanying the image [ Srihari and Burhans, 1994 ] Most of the constraints are binary spatial and visual relations but some are also ....

Rajiv Chopra and Rohini Srihari. Control structures for incorporating picture-specific context in image interpretation. In Proceedings of IJCAI-95, Montreal,Canada, August 1995. Morgan Kaufmann.

No context found.

R. Chopra and R. K. Srihari, Control Structures for Incorporating Picture-Specific Context in Image Interpretation, IJCAI '95 (1995).

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC