Use Your Content > Improve > Image Analysis > Object Detection

Object Detection

Image Server can recognize and detect rigid two-dimensional objects in images. Example applications are:

All these examples consist of rigid objects that have a fixed geometry. The image of the object might vary in appearance owing to, for example, camera pose, lighting, partial occlusion, noise or compression artifacts, but the object itself retains the same geometry. In the example of the advert in a newspaper, for example, the page should be flat or nearly flat for object detection to function reliably.

Image Server returns the identity and location of each detected object.

For Image Server to detect an object, it must have a representative model of the object in a database. You create these models by sending Image Server example images. The accuracy of object detection is affected by the quality of both the training images and also the target images in which to search for the objects. You can also configure object detection to maximize accuracy.

You can use the Models page in the Control section of IDOL Admin to create your object detection models.

Note: Many companies have multiple versions of their logos; for example, Twitter has several subtly different versions of its logo. Logos consisting of text and graphics might have versions where the size and position of the text varies. Image Server recognizes only the version of the logo that it is trained on. If you want to detect several versions of the same logo, you must train each version as a separate logo.


_HP_HTML5_bannerTitle.htm