His image features on a 1997 Japanese postage stamp.

Simple classifiers built based on some image feature of the object tend to be weak in categorization performance.

The effect of the choice of image features on the control law is discussed with respect to just the depth axis.

For each set of image features, all possible matching sets of model features must be considered.

Thus, the image features indicate points at which dislocations intercept the sample surface.

A notable example is an image feature consisting of a single line, such as the letter "l".

Outliers can now be removed by checking for agreement between each image feature and the model, given the parameter solution.

The detection and description of local image features can help in object recognition.

Certain image features in example images may override the concept that the user is really focusing on.

This allows for a greater number of model parts and image features to be used in training.